基于多源图像融合的收获目标准确定位研究
|
摘要
在充分了解国内外果实采摘自动化研究成果的基础上,针对果实收获机器人研究中存在的不足,以番茄采摘为研究对象,着眼于解决自然环境下成熟期果实与背景的颜色差异不大,且整个果实表面色彩不一致的果实目标识别与定位问题,将图像处理技术、多光谱技术、图像配准技术、信息融合技术和定位技术等有机结合起来,构建了多源传感视觉识别定位系统。
(1)采集了不同环境下番茄可见光图像和近红外图像作为图像分析的主要数据,并对图像进行了去噪、光照不均校正、图像增强和图像分割等前期预处理。针对生长状态为相互分离的番茄图像,在分割算法上,提出了一种新的基于互信息最佳阈值迭代优化分割方法。该算法在原理上充分考虑了图像的灰度信息、空间信息和分割后图像与原图像的内在联系,分割后的图像具有目标信息准确、特征保留完整、目标边缘连续等优点。对表面色彩一致且与背景有色差的成熟番茄分割完整率达到了90%以上,对成熟期果实与背景的颜色差异不大或表面色彩不一致的番茄可见光图像,MI-OPT分割方法的分割完整率达到了70%以上,对其多源融合图像,MI-OPT分割方法的分割完整率达到了90%左右;针对复杂生长状态的番茄图像,基于形态学重构的图像分水岭分割方法对多果相连图像具有良好的分割效果。
(2)建立了基于2D圆控制点的摄像机标定试验系统,对多源传感器视觉系统的摄像机,采用张正友等人提出的基于2D平面靶标摄像机标定方法进行了标定试验,得到了多源传感器视觉系统的摄像机内外参数,并对标定结果进行了精度和误差分析,得出视觉系统在X方向误差均值为3.39 mm,Y方向误差均值为0.43 mm,Z方向误差均值为1.52 mm,可以满足多源传感器视觉系统的定位要求。
(3)在多源传感视觉系统中,利用摄像机的几何特性进行多源图像的粗配准,对得到的粗配准图像采用基于点特征的配准方法进行了精配准,并采用图像之问的均方根误差、图像配准运算时间和鲁棒性等参数作为图像配准效果的评价。经配准实验表明:基于传感器参数和SIFT特征点的图像配准方法具有较强的噪声抑制能力,且其多源图像间的配准均方根误差均值为0.94,配准精度达到了像素级水平,可完全满足图像融合要求。
(4)以多源传感器图像融合为背景,讨论了像素级多源图像的融合问题。针对番茄可见光图像和近红外图像的特点,提出了基于主分量分析和提升小波变换的多源图像快速融合算法(PCA-LWT)。在融合原理上考虑了多源图像的成像机理,兼顾了图像的空频分布情况,在融合操作时根据融合目的引入多源图像的细节信息,从而表现出更强的针对性和实用性。实验结果表明PCA-LWT融合算法得到的融合图像自然,符合人类视觉特性,融合结果有利于对图像作进一步分析、理解和识别。
(5)在自然生长状态下,存在果实与背景的颜色差异不大,且整个果实表面色彩不一致的成熟番茄,针对这种目标物和其它生物体用颜色阈值难以分割或分割出的目标轮廓缺失严重的情况,利用近红外光谱和可见光谱各自有效的生物信息,采用多光谱图像融合技术使收获目标的轮廓特征信息得到修正和补全。就成熟番茄的选择性收获而言,选取园形度、凹度、面积比等形状特征和均匀度纹理特征等特征量对番茄进行识别和生长状态判别。
(6)在目标定位上,提出了双目彩色图像信息和近红外图像信息融合的三维定位方法,解决了多目标图像特征匹配的不确定问题。即从双目定位的几何模型出发,在双目匹配搜索中,提取多源传感融合图像的番茄凸壳有效形心点,采用极线约束、唯一性约束进行立体视觉图像的特征点及其邻域灰度相关的双向匹配,利用体视原理获取唯一被测目标的空间坐标。
(7)研究了收获目标空间定位误差的补偿方法。将双目立体视觉技术恢复出来的成熟番茄空间坐标与该成熟番茄的实际空间坐标进行比较,在定位误差分析的基础上,采用遗传和神经网络算法(GA-BP)修正成像过程中的测距误差,对测试样本进行仿真试验,结果表明收获目标空间定位的绝对误差X和Y值均可控制在(0-5)mm之间,Z坐标值可以控制在(0-7)mm之间,达到了番茄收获机器人的定位精度要求。
(8)设计了基于多源图像融合收获目标准确定位的处理流程。
The domestic and overseas research productions are firstly enough known for intelligent fruit-harvesting robot and existing key technology issues are proposed in Automatic recognition and three-dimensional localization of fruit. For these issues, it takes mature tomato as research object with a view to solve automatic recognition and localization by binocular stereo vision issues on little color difference between mature fruit and background and the entire fruit surface color inconsistent under natural environment. It is expected that quick and stable algorithms could be proposed by using the computer vision technology, the multi-spectrum technology, the multi-sensors image registration technology, the multi-sensors image information fusion technology and the localization technology. The multi-sensors vision recognition and positioning system has been constructed successfully.
(1) RGB tomato images and the near-infrared tomato images were collected by using multi-sensors under various environment conditions and taken main data of image analysis. The image pretreatments, such as the image de-noising, the illumination uneven adjustment, the image intensification and the image segment, are made. In view of the tomato images under the separating growth condition, a new image automatic optimization segment algorithm (MI-OPT) is proposed based on the mutual information and the best threshold iteration. This algorithm had considered fully the gradation information and spatial information of the tomato image and the inner link between the original image and the segmented image on the segment principle. The segmented image has the merits such as the accurate target information, the characteristic retains, the continual goal edge and so on. The segment complete ratio of the fruit edge achieves above 90% from the mature tomato RGB image, which has the consistent superficial color and the chromatic aberration between the tomato and the background. With the tomato RGB image of the inconsistent superficial color and little color difference between mature fruit and background, it achieves above 70%.It is above 80% to the multi-sensors fusing image of the tomato using MI-OPT algorithm. The multi-fruit connected tomato image is better segmented based on the morphology restructuring watershed segmentation (MREW).
(2) Camera calibration model based on 2D circular control point is established and calibration test of the multi-sensor vision system is carried out. The camera calibration method is based on the 2D plane target's camera calibration method that is proposed by Zhang Zheng-you et al. Intrinsic and extrinsic parameters of fixed-focus camera are obtained and the precision and the error analysis of Camera calibration are done. The multi-sensor vision system errors are obtained. The error average value is 3.39 mm in X lateral, 0.43 mm in Y lateral, and 1.52 mm in Z laterals. The precision might satisfy the multi-sensor vision system's localization request.
(3) The goal position and intensity have difference between the visible light image and the near-infrared image because of their image formation mechanism, resolution and field of view differences. To satisfy the timeliness and, accurate request of the image fusion, based on the analysis of the imaging process of optoelectronic imaging sensor and based on the characteristic related matching algorithm's research, two automatic registration algorithms are proposed. A kind registration algorithm is based on sensor parameters and the Harris corner point support intensity matching method, another is based on the sensor parameter and the SIFT characteristic matching method. The result of the registration experiments indicate that the image registration method based on the sensor parameter and the SIFT characteristic point has strong noise abatement ability, the matching deviation is smaller than another method in the noise variance increases, and the mean value of the matching root-mean-square error between its multi-sensor image is 0.94, the matching precision has achieved the image pixel level. The precision may completely satisfy the image fusion request.
(4) The multi-sensor images fusion issues are discussed. In view of the tomato RGB image and the near-infrared image's characteristic, a novel fast image fusion scheme (PCA-LWT) based on principal component analysis and lifting wavelet transform is proposed. The multi-sensor mages formation mechanisms and the image spatial frequency distributed situation are considered in this fusion algorithm principle. According to the fusion goal, the multi-sensor mages detail information is expressed in fusion rules. This fusion algorithm displays stronger the pointed and the usability. The experimental results indicate that the obtained image based on PCA-LWT fusion algorithm comforts to human vision feature. The fusion image contains the more information and the stronger spatial detail performance. The merged image is more advantageous to be further analyzed, understood and recognized.
(5) Sometimes, the surface color of the mature tomato has little difference with the background color or the entire fruit surface color has inconsistent under the nature growth condition. This fruit image segmentation is very difficulty with the color threshold or the segmentation result is the serious error of the goal outline. According to the near-infrared spectrum and the obvious spectrum respectively effective biology information, the revision and the complement of the harvesting goal outline can been obtained by using the multi-sensor image fusion technology. Taken harvesting tomato into account as an example, the shape feature (circle shape, concavity, area ratio) and texture feature (uniformity) are extracted respectively on the basis of morphological process of binary image. And flow of tomato recognition and its growth states' distinguish are determined according to selected feature quantities.
(6) There is the characteristic match indefinite problem with geometric model of localization of binocular stereo vision in multi-objective image. A novel three-dimensional localization method is proposed. Firstly, the tomato effective centric spots are obtained from the left multi-sensor fusion image and the right multi-sensor fusion image. Then, being looked as symmetries, image pairs other point to point correspondences are searched from two directions by pixel neighbor area correlation values by using the polar line restraint, the unique restraint and the disparity gradient restraint. The goal space coordinates can be gained with the stereoscope principle.
(7) The causes of errors existing in the measurement of three-dimensional coordinates of the tomato with the help of binocular vision technology are analyzed. Then it is pointed out that the errors can be amended by means of building the genetic and the neural network algorithm (GA-BP) and a corresponding training system. A simulation experiment is also carried out on the test sample. The experiment indicates that the errors can be controlled in the range of 0-10 mm, the precision meets the requirement for positioning of harvesting fruits robot.
(8) The overall frame of harvest goal accurate localization is given based on the multi-sensor images fusion.
(1)采集了不同环境下番茄可见光图像和近红外图像作为图像分析的主要数据,并对图像进行了去噪、光照不均校正、图像增强和图像分割等前期预处理。针对生长状态为相互分离的番茄图像,在分割算法上,提出了一种新的基于互信息最佳阈值迭代优化分割方法。该算法在原理上充分考虑了图像的灰度信息、空间信息和分割后图像与原图像的内在联系,分割后的图像具有目标信息准确、特征保留完整、目标边缘连续等优点。对表面色彩一致且与背景有色差的成熟番茄分割完整率达到了90%以上,对成熟期果实与背景的颜色差异不大或表面色彩不一致的番茄可见光图像,MI-OPT分割方法的分割完整率达到了70%以上,对其多源融合图像,MI-OPT分割方法的分割完整率达到了90%左右;针对复杂生长状态的番茄图像,基于形态学重构的图像分水岭分割方法对多果相连图像具有良好的分割效果。
(2)建立了基于2D圆控制点的摄像机标定试验系统,对多源传感器视觉系统的摄像机,采用张正友等人提出的基于2D平面靶标摄像机标定方法进行了标定试验,得到了多源传感器视觉系统的摄像机内外参数,并对标定结果进行了精度和误差分析,得出视觉系统在X方向误差均值为3.39 mm,Y方向误差均值为0.43 mm,Z方向误差均值为1.52 mm,可以满足多源传感器视觉系统的定位要求。
(3)在多源传感视觉系统中,利用摄像机的几何特性进行多源图像的粗配准,对得到的粗配准图像采用基于点特征的配准方法进行了精配准,并采用图像之问的均方根误差、图像配准运算时间和鲁棒性等参数作为图像配准效果的评价。经配准实验表明:基于传感器参数和SIFT特征点的图像配准方法具有较强的噪声抑制能力,且其多源图像间的配准均方根误差均值为0.94,配准精度达到了像素级水平,可完全满足图像融合要求。
(4)以多源传感器图像融合为背景,讨论了像素级多源图像的融合问题。针对番茄可见光图像和近红外图像的特点,提出了基于主分量分析和提升小波变换的多源图像快速融合算法(PCA-LWT)。在融合原理上考虑了多源图像的成像机理,兼顾了图像的空频分布情况,在融合操作时根据融合目的引入多源图像的细节信息,从而表现出更强的针对性和实用性。实验结果表明PCA-LWT融合算法得到的融合图像自然,符合人类视觉特性,融合结果有利于对图像作进一步分析、理解和识别。
(5)在自然生长状态下,存在果实与背景的颜色差异不大,且整个果实表面色彩不一致的成熟番茄,针对这种目标物和其它生物体用颜色阈值难以分割或分割出的目标轮廓缺失严重的情况,利用近红外光谱和可见光谱各自有效的生物信息,采用多光谱图像融合技术使收获目标的轮廓特征信息得到修正和补全。就成熟番茄的选择性收获而言,选取园形度、凹度、面积比等形状特征和均匀度纹理特征等特征量对番茄进行识别和生长状态判别。
(6)在目标定位上,提出了双目彩色图像信息和近红外图像信息融合的三维定位方法,解决了多目标图像特征匹配的不确定问题。即从双目定位的几何模型出发,在双目匹配搜索中,提取多源传感融合图像的番茄凸壳有效形心点,采用极线约束、唯一性约束进行立体视觉图像的特征点及其邻域灰度相关的双向匹配,利用体视原理获取唯一被测目标的空间坐标。
(7)研究了收获目标空间定位误差的补偿方法。将双目立体视觉技术恢复出来的成熟番茄空间坐标与该成熟番茄的实际空间坐标进行比较,在定位误差分析的基础上,采用遗传和神经网络算法(GA-BP)修正成像过程中的测距误差,对测试样本进行仿真试验,结果表明收获目标空间定位的绝对误差X和Y值均可控制在(0-5)mm之间,Z坐标值可以控制在(0-7)mm之间,达到了番茄收获机器人的定位精度要求。
(8)设计了基于多源图像融合收获目标准确定位的处理流程。
The domestic and overseas research productions are firstly enough known for intelligent fruit-harvesting robot and existing key technology issues are proposed in Automatic recognition and three-dimensional localization of fruit. For these issues, it takes mature tomato as research object with a view to solve automatic recognition and localization by binocular stereo vision issues on little color difference between mature fruit and background and the entire fruit surface color inconsistent under natural environment. It is expected that quick and stable algorithms could be proposed by using the computer vision technology, the multi-spectrum technology, the multi-sensors image registration technology, the multi-sensors image information fusion technology and the localization technology. The multi-sensors vision recognition and positioning system has been constructed successfully.
(1) RGB tomato images and the near-infrared tomato images were collected by using multi-sensors under various environment conditions and taken main data of image analysis. The image pretreatments, such as the image de-noising, the illumination uneven adjustment, the image intensification and the image segment, are made. In view of the tomato images under the separating growth condition, a new image automatic optimization segment algorithm (MI-OPT) is proposed based on the mutual information and the best threshold iteration. This algorithm had considered fully the gradation information and spatial information of the tomato image and the inner link between the original image and the segmented image on the segment principle. The segmented image has the merits such as the accurate target information, the characteristic retains, the continual goal edge and so on. The segment complete ratio of the fruit edge achieves above 90% from the mature tomato RGB image, which has the consistent superficial color and the chromatic aberration between the tomato and the background. With the tomato RGB image of the inconsistent superficial color and little color difference between mature fruit and background, it achieves above 70%.It is above 80% to the multi-sensors fusing image of the tomato using MI-OPT algorithm. The multi-fruit connected tomato image is better segmented based on the morphology restructuring watershed segmentation (MREW).
(2) Camera calibration model based on 2D circular control point is established and calibration test of the multi-sensor vision system is carried out. The camera calibration method is based on the 2D plane target's camera calibration method that is proposed by Zhang Zheng-you et al. Intrinsic and extrinsic parameters of fixed-focus camera are obtained and the precision and the error analysis of Camera calibration are done. The multi-sensor vision system errors are obtained. The error average value is 3.39 mm in X lateral, 0.43 mm in Y lateral, and 1.52 mm in Z laterals. The precision might satisfy the multi-sensor vision system's localization request.
(3) The goal position and intensity have difference between the visible light image and the near-infrared image because of their image formation mechanism, resolution and field of view differences. To satisfy the timeliness and, accurate request of the image fusion, based on the analysis of the imaging process of optoelectronic imaging sensor and based on the characteristic related matching algorithm's research, two automatic registration algorithms are proposed. A kind registration algorithm is based on sensor parameters and the Harris corner point support intensity matching method, another is based on the sensor parameter and the SIFT characteristic matching method. The result of the registration experiments indicate that the image registration method based on the sensor parameter and the SIFT characteristic point has strong noise abatement ability, the matching deviation is smaller than another method in the noise variance increases, and the mean value of the matching root-mean-square error between its multi-sensor image is 0.94, the matching precision has achieved the image pixel level. The precision may completely satisfy the image fusion request.
(4) The multi-sensor images fusion issues are discussed. In view of the tomato RGB image and the near-infrared image's characteristic, a novel fast image fusion scheme (PCA-LWT) based on principal component analysis and lifting wavelet transform is proposed. The multi-sensor mages formation mechanisms and the image spatial frequency distributed situation are considered in this fusion algorithm principle. According to the fusion goal, the multi-sensor mages detail information is expressed in fusion rules. This fusion algorithm displays stronger the pointed and the usability. The experimental results indicate that the obtained image based on PCA-LWT fusion algorithm comforts to human vision feature. The fusion image contains the more information and the stronger spatial detail performance. The merged image is more advantageous to be further analyzed, understood and recognized.
(5) Sometimes, the surface color of the mature tomato has little difference with the background color or the entire fruit surface color has inconsistent under the nature growth condition. This fruit image segmentation is very difficulty with the color threshold or the segmentation result is the serious error of the goal outline. According to the near-infrared spectrum and the obvious spectrum respectively effective biology information, the revision and the complement of the harvesting goal outline can been obtained by using the multi-sensor image fusion technology. Taken harvesting tomato into account as an example, the shape feature (circle shape, concavity, area ratio) and texture feature (uniformity) are extracted respectively on the basis of morphological process of binary image. And flow of tomato recognition and its growth states' distinguish are determined according to selected feature quantities.
(6) There is the characteristic match indefinite problem with geometric model of localization of binocular stereo vision in multi-objective image. A novel three-dimensional localization method is proposed. Firstly, the tomato effective centric spots are obtained from the left multi-sensor fusion image and the right multi-sensor fusion image. Then, being looked as symmetries, image pairs other point to point correspondences are searched from two directions by pixel neighbor area correlation values by using the polar line restraint, the unique restraint and the disparity gradient restraint. The goal space coordinates can be gained with the stereoscope principle.
(7) The causes of errors existing in the measurement of three-dimensional coordinates of the tomato with the help of binocular vision technology are analyzed. Then it is pointed out that the errors can be amended by means of building the genetic and the neural network algorithm (GA-BP) and a corresponding training system. A simulation experiment is also carried out on the test sample. The experiment indicates that the errors can be controlled in the range of 0-10 mm, the precision meets the requirement for positioning of harvesting fruits robot.
(8) The overall frame of harvest goal accurate localization is given based on the multi-sensor images fusion.
引文
[1]Scherta,C E,Brown G K.Basic considerations in mechanizing citrus harvest [J].Transactions of the ASAE,1968,11(2):343-346.
[2]Parrish,E,Goksel A K.Pictorial pattern recognition applied to fruit harvesting [J].Transactions of the ASAE,1977,20(5):822-827.
[3]D'Esnon,A G,Rabatel G,Pellenc R.A self-propelled robot to pick apples [J].Transactions of the ASAE,1987,87:1032-1037
[4]Rabatel,G..,A vision system for Magalia,the fruit picking robot[C].Agricultural Engineering,Paris,London,U.K.Paper 88293,AGENG88, International Conference:Ministry of Agriculture,Fisheries and Food 1988.
[5]Slaughter,D.C,and Harrell R.C.Color vision in robotic fruit harvesting[J].Transactions of the ASAE,1987,30(4):1144-1148.
[6]Slaughter,D.C and Harrell R C.Discriminating fruit for robotic harvest using color in natural outdoor scenes[J].Transactions of the ASAE,1989,32(2):757-763
[7]Harrell R.C.,Slaughter D.C.etc.A fruit-tracking system for robotic harvesting[J].Machine Vision & Application,1989(2):69-80.
[8]Whittaker A D,Miles G E,Mitchell 0 R etc.Fruit location in a partially occluded image[J].Transactions of the ASAE,1987,30(3):591-596.
[9]Illingworth,J.,and J,Kitten.A survey of the Hough transforms[J].Computer Vision,Graph.& Image Proc.,1988,44:87-116.
[10]Sites P W,Delwiche M J.Computer vision to locate fruit on a tree[J].Transactions of the ASAE,1988,31(1):257-263.
[11]#12
[12]#12
[13]#12
[14]#12
[15]#12
[16]周增产,J.Bontsema,L.Van Kollenburg-Crisan。荷兰黄瓜收获机器人的研究开发[J].农业工程学报,2001,1(6):77-80
[17]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Bontsema J.Collision-free Motion Planning for a Cucumber Picking Robot[J].Bio-systems engineering,2003,86(2):135-144
[18]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Meuleman J,Bontsema J,Van OsEA.Field Test of an Autonomous Cucumber Picking Robot[J]。Bios stems engineering,2003,86(3):305-313
[19]Dnhrousin,Y.,and Y.Edan.,Real-time image processing for robotic melon harvesting[C].ASAE Paper No.92-3515,1992
[20]Hayashi,S.,Ganno,K.& Ishii,Y.Machine vision algorithm of eggplant recognition for robotic harvesting[J].J.SHITA,2000,12(1):38-46
[21]Hayashi,S.,Ganno,K.and Ishii,Y.Visual feedback guidance of manipulator for eggplant harvesting using fuzzy logic[J].J.SHITA,2002,12(2):83-92
[22]Hayashi S.,Ganno K.,Ishii Y.and Tanaka I.Robotic Harvesting System for Eggplants[J].JARO,2006,36(3):163-168
[23]张铁中,林宝龙,高锐.水果采摘机器人视觉系统的目标提取[J].中国农业大学学报,2004,9(2):68-72
[24]徐丽明,张铁中.果蔬果实收获机器人的研究现状及关键问题和对策[J].农业工程学报,2004,(05).
[25]谢志勇,张铁中.基于RGB彩色模型的草莓图像色调分割算法[J].中国农业大学学报,2006,11(1):84-86
[26]张铁中,周天娟.草莓采摘机器人的研究:I.基于BP神经网络的草莓图像分割[J].中国农业大学学报,2004,9(4):65-68
[27]应义斌,饶秀勤,马俊福.柑橘成熟度机器视觉无损检测方法研究[J].农业工程学报,2004,20(2):144-147
[28]徐惠荣,叶尊忠,应义斌.基于彩色信息的树上柑橘识别研究[J].农业工程学报,2005,21(5):98-101
[29]徐惠荣,应义斌.红外热成像在树上柑桔识别中的应用研究[J].红外与毫米波学报,2004,23(5):353-356
[30]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D],江苏大学博士学位论文,2006。
[31]Kassay.L.Hungarian robotic apple harvester[C].ASAE,1992,92-7042:1-14.
[32]Dnhrousin,Y.,and Y.Edan.Real-time image processing for robotic melon harvesting[C].ASAE Paper No.92-3515,1992
[33]Grasso,G..and M.Recce,Scene analysis for an orange picking robot[C].In Proc.Int.Congress for Computer Technology in Agriculture(ICCTA'96),1996
[34]#12
[35]#12
[36]Cao Q,Nagata M,Gejima Y,Shrestha B.P.,Hiyoshi K.Basic study on strawberry harvesting robot(Part Ⅰ)- algorithm for locating and feature extracting of strawberry fruits.Bio-Robotics,Information Technology and Intelligent Control for Bio-production System 2000
[37]Fujiura,T.,J.Yamasjita,and N.Kondo,Agricultural robots(1),Vision sensing system[J],ASAE,1992,92-3517
[38]Fujiura,T.,S.Nakao,N.Kondo etc,Dichromatic 3-D vision sensor for the agricultural robot[J].J.Jpn.Soc.Agric.Technol.Manage,1995,2(1):59-64
[39]Arima,S.,N.Kondo,etc,Study on cucumber harvesting robot(Part 1)[J].J.Jpn.Soc.Agric.Mach,1994,56(1):45-53
[40]Arima,S.,N.Kondo,etc,Study on cucumber harvesting robot(Part 2)[J].J.Jpn.Soc.Agric.Mach,1994,56(6):69-76
[41]Kondo N,Nishitsuji Y,Ling P Petal.Visual feedback guided robotic cherry tomato harvesting[J].Transactions of the ASAE,1996,39(6):2331-2338
[42]周云山,李强 计算机视觉在蘑菇采摘视器人上的应用[J],农业工程学报,1995.11(4):27-31。
[43]张瑞合 姬长英 沈明霞 曹坤.计算机视觉技术在番茄收获中的应用[J],农业机械学报2001.9 32(5):50-52。
[44]郑小东 赵杰文等.基于双目立体视觉的番茄识别与定位技术[J],计算机工程,2004.30(22):155-171。
[45]仲琴.基于机器视觉的番茄收获机器人目标定位技术研究,江苏大学硕士论文,2005。
[46]蔡健荣,赵杰文.自然场景下成熟水果的计算机视觉识别[J].农业机械学报,2005,36(2)61-64[
47]蔡健荣.基于立体视觉的成熟水果识别定位及机器人路径规划[D].江苏大学博土学位论文,2005
[1]王章野.地面目标的红外成像仿真与多光谱成像真实感融合研究[D].杭州:浙江大学博士学位论文,2002.
[2]A_R.Jimenez,R.Ceres,J.L.Pons.A vision system based on a laser range-finder applied to robotic fruit harvesting[J].Machine Vision and Applications,2002,11:321-329.
[3]林伟明,毛罕平,王新忠等.多光谱视觉技术在收获机器人中的应用[J].农业装备技术,2004,(06).
[4]Subrata et al.3_Dvision sensor for cherry tomato harvesting robot[J].Proceedings of International Symposium of Automation and Robotics on bio-production and processing,1:13-20.
[5]项震.基于CCD器件特征的图像噪声消除[J].光电工程,2001,28(6):66-68.
[6]刘延武,何友金,陆斌等.舰船目标红外图像预处理[J].红外技术,2003,25(3):9-12.
[7]汪鲁才,王辉南,毛六平.基于小波变换和中值滤波的InSAR干涉图像滤波方法[J].测绘学报,2005,34(2):108-112.
[8]J.H.Bosworth,S.T.Acton.Morphological scale-space in image processing [J].Digital Signal Processing,2003,13(2):338-367.
[9]A.Castratos,I.Andreadis.Soft mathematical morphology:extensions,algorithms and implementations[J].Advances in Imaging and Electron Physics,1999,110(1),63-99.
[10]J.H.Bosworth,S.T.Acton.Morphological scale-space in image processing [J].Digital Signal Processing,2003,13(2):338-367.
[11]P.Soille.Beyond self-duality in morphological image analysis[J].Image and Vision Computing,2005,23(2):249-257.
[12]Y.Grau,M.A.Raga,C.Monserrat.Hierarchical image segmentation using a correspondence with a tree model[J].Pattern Recognition,2004,37(1):47-59.
[13]王小鹏,郑玉甫.一种图像噪声的形态学多尺度去除方法[J].计算机工程,2006,32(4):208-210.
[14]游安清,程义民,赵平等.红外图像去噪中形态学结构元素的选取[J].应用科学学报,2004,22(4):483-486.
[15]赵健,宋祖勋,俞卞章.基于多重分形分析的SAR图像消噪增强研究[J].西北工业大学学报,2003,21(1):30-33.
[16]蒋定定,许兆林,李开端.基于改进分形技术的红外图像噪声抑制研究[J].测绘工程,2004,13(4):32-34.
[17]李明喜,毛罕平.基于数学形态学和多重分形的图像消噪算法研究[J].仪器仪表学报,2007.8
[18]李明喜,毛罕平,张艳诚.基于提升小波变换和中值滤波的图像去噪方法研究[J].激光与红外,2007(5)
[19]李明喜,吴鸿霞.基于小波变换和中值滤波的图像去噪方法研究[J].黄石理工学院学报,2007(2)
[20]李明喜,毛罕平,张艳诚.近红外图像消噪方法的对比实验研究[J].红外技术,2007,11
[21]G.Fan,X-G Xia.Image De-noising Using Local Contextual Hidden Markov Model in the Wavelet Domain[J].IEEE Signal Processing Letter,8(5),May 2001,125-128.
[22]R.Kimmel,M.Elad,D.Shaked,R.Keshet(Kresch),I.Sobel,"A variation framework for Retinex",Int.J.Comput.Vision,2003,Vol.52:7-23
[23]T.Iketani,N.Unagmi,M.Suwa,M.Kimachi,"Human Detection System using stereovision sensor," 2004,04:231-234.
[24]Rafael C.Gonzalez等著.阮秋琦等译.数字图像处理(MATLAB版).北京:电子工业出版社,2005,9
[25]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006
[26]Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[27]Ahmed,Mohamed N.A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data[J],IEEE Transactions on Medical Imaging,2002,21(3):193-199.
[28]刘华军,任明武,杨静宇.一种改进的基于模糊聚类的图像分割方法[J].中国图象图形学报,2006,11(9):1312-1316
[29]马华,张永,庞长刚.一种改进的FCM在医学图像分割中的应用[J].电脑开发与应用,2006,19(4):10-11
[30]金立左,夏良正,杨世周.图象分割的白适应模糊阈值法[J].中国图象图形学报,2000,5A(5):390-395
[31]岳振军,邱望成,刘春林.一种自适应的多目标图像分割方法[J].中国图象图形学报,2004,9(6):674-678
[32]曹力,史忠科.基于最大熵原理的多阈值自动选取新方法[J].中国图象图形学报,2002,7(A版)No.5:461-465
[33]张红蕾,宋建社,翟晓颖.一种基于二维最大熵的SAR图像自适应阈值分割算法[J].电光与控制,2007,14(4):63-65
[34]Rigau J,Feixas M,Sbert M,et al.Medical Image Segmentation Based on Mutual Information Maximization[C]//Proceedings of MICCAI' 04,Saint-Malo,France 2004:135-142.
[35]Pluim J,Maintz J,Viergever M.Mutual information based registration of medical images:a survey[J].IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
[36]周小舟,张加万,孙济洲.基于互信息和Chan-Vese模型的图像分割方法[J].计算机工程,2007,33(22):220-222
[37]Shafarenko L,Petrou M,Kittlerd.Automatic watershed segmentation of randomly textured color images[J].IEEE Transactions on Image Processing 1997,6(11):1530-1544
[38]Vincent L.Morphological grayscale reconstruction in image analysis:applications and efficient algorithms[J].IEEE Transactions on Image Processing,1993,2(2),176-201.
[39]Gao Hal,Lin Weisi,Xue Ping,et al.Marker- based image segmentation relying on disjoint set union[J].Signal Processing:Image Communication,2006,21(2):100-112.
[40]Rodriguez R,Alarcon T E,Pacheco O.A new strategy to obtain robust markers for blood vessels segmentation by using the water-sheds method[J].Computers in Biology and Medicine,2005,35(8):665- 686.
[41]Jung C R.Combining wavelets and watersheds for robust multi-scale image segmentation[J].Image and Vision Computing,2007,25(1)' 24- 33.
[42]包振健,邸书灵.一种基于分水岭变换的细胞图像分割方法[J].计算机工程与应用,2008,44(4):230-232
[43]尹建军,毛罕平等.不同生长状态下多目标番茄图像的自动分割方法[J].农业工程学报.2006.22(10):149-152.
[1]吴文琪,孙增.机器视觉中的摄像机定标方法综述[J].计算机应用研究,2004,2:4-7
[2]Y I Abdel-Aziz,H M Karara.Direct Linear Transformation into Object Space Coordinates in Close-Range Photogrammetry[C].In:Proc.Symposium on Close-Range Photogrammetry,Urbana,University of Illinois,January 1971:1-18
[3]I Sobel.On Calibration Computer Controlled Cameras for Perceiving 3D Scenes [J].Artif.Intell.1974:5:185-198
[4]Tsai R Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J].IEEE Journal of Robotics and Automation,1987,3(4):323-344
[5]Martins H A,Birk J R,Kelley R B.Camera models based on data from two calibration planes[J].Computer Graphics Image Processing,1981,17(2):173-180
[6]Malik M,Mudar S,Florent C.Automatic camera calibration based on robot calibration[C].IEEE Instrumentation and Measurement Technology Conference.1992,2:1278-1282
[7]Zhang Z.A flexible new technique for camera calibration.Microsoft Corporation:Technical Report MSR-TR-98-71,2002
[8]孙长库,张效栋.CCD摄像机参数标定实验设计[J].光电子技术与信息,2000,18(2):43-46
[9]蔡健荣,赵杰文.双目立体视觉系统摄像机标定[J].江苏大学学报,2007,27(1):6-9
[10]J.More.The Levenberg-marquardt algorithm,implementation and theory[M].In G.A.Watson,editor,Numerical Analysis,Lecture Notes in Mathematics 630.Springer-Verlag,1977
[1]金剑秋.多光谱图像的融合与配准[D]。杭州:浙江大学博士学位论文,2005
[2]OWN H S,HASSANIEN A E.Multi-resolution image registration algorithm in wavelet transform domain[A].IEEE 14~(th) International Conference on Digital Signal Processing[C].Santorini,Greece:IEEE,2002,2:889-892
[3]HAIKEL Salem Alhichri,MOHAMED Kamel.Image registration using virtual circles and edge direction[A].IEEE 16~(th) International Conference on Pattern Recognition[C].Quebec,CANADA:IEEE,2002,2:969-972
[4]LISA Gottesfeld Brown.A survey of image registration techniques[J].ACM Computing Surveys,1992,24(4):325-376
[5]XIE Zhi-yong.Image registration using hierarchical B-Splines[D].USA:Arizona state university,2002
[6]Barnea D I,Silverman H F.A class of algorithms for fast digital registration [J]IEEE Trans.Computer,1972,(21):179-186
[7]KUGLIN C D,HINES D C.The phase correlation image alignment method[A].Proceedings of 1975 IEEE International Conference on Cybernetics and Society[C].New York,USA:IEEE,1975.163-165
[8]张二虎,卞正中.基于最大嫡和和互信息最人化的特征点配准算法[J].计算机研究与发 展,2004,7(3)
[9]王小睿,吴信才,李军.模拟退火算法的改进策略在模板匹配上的应用[J].小型微型计算机系统,1997,18(8):32-37
[10]AVERBUCH A,KELLER Y.FFT based image registration[A].Proceedings of 2002IEEE International Conference on Acoustics,Speech and Signal Processing[C].Orlando,USA:IEEE,2002,4.3608-3611
[11]VIOLA P A,WELLS III W M.Alignment by maximization of mutual information [C].Proc.5th Int.Conf.Computer Vision,Boston,MA,1995:16-23
[12]COLLIGNON A,MAES F,DELAERE D.Automated multi-modality image registration based on information theory[C].Proc.of the Information Processing in Medical Imaging Conference,Norwell,MA:Kluwer,1995:263-274
[13]THEVENAZ P,RUTTIMANNU E,UNSER M.A pyramid approach to sub pixel registration based on intensity[J].IEEE Trans.Image Processing,1998(7):27-41
[14]STEFAN H,MAHNKEO,POTTS D,et al.Fast computation of mutual information in a variation image registration approach[C].CEUR Workshop Proceedings,2004:448-452
[15]JEFFREY P K.Reliable band-to-band registration of multi-spectral thermal imager data using multivariate mutual information and cyclic consistency [C].Proceedings of SPIE,2004,5558:57-68
[16]WACHOWIAKM P,RENATA S,GEORGIA D,et al.Generalized mutual information similarity metrics for multimodal biomedical image registration [C].Proceedings of the Second Joint EMBS/BMES Conference,2002:1005-1006
[17]MARTIN S,MORISON G,NAILON W,et al.Fast and accurate image registration using tallish entropy and simultaneous perturbation stochastic approximation[J].Electronics Letters,2004,40(10):595-597
[18]Yao Jianchao.Image registration based on both feature and intensity matching [A].Proceedings of 2001 IEEE International Conference on Acoustics,Speech and Signal Processing[C].Kauai,Hawaii,USA:IEEE,2001,3.1693-1696
[19]Jun-Wei Hsieh.Image registration using a new edge-based approach[J].Computer Vision and Image Understanding,1997,67(2):112-130
[20]钮永胜.可见光与热红外图像配准技术研究[博士后出站报告][R].北京:北京理工大学,1999.
[21]张迁,刘政凯,庞彦伟等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250
[22]周鹏,谭勇,徐守时.基于角点检测图像配准的一种新算法[J].中国科学技术大学学报,2002,32(4):455-461
[23]Kyun Jung,Lacroix S.A robust interest points matching algorithm[A].Proceedings of Eighth IEEE International Conference on Computer Vision[C].Vancouver,BC,Canada:IEEE,2001,2.538 -543
[24]HUI Li,MANJUNATH B S A contour-based approach to multi-sensor image registration[J].IEEE Transactions on Image Processing,1995,4(3):320-334.
[25]TON J,JAIN A K.Registering Land sat images by point matching[J].IEEE Transactions on Geosciences and Remote Sensing,1989,27(5):642-651
[26]COX G S,JAGER G De.A survey of point matching techniques and a new approach to point pattern recognition[A].Pro.of 1992 South African Symposium on Communications and Signal Processing[C].Cape Town,South African:IEEE,1992.243-248
[27]Corvi M,Nicchiotti G.Multi-resolution image registration[C].1995International Conference on Image Processing,Washington,D.C.,Oct 23-26,1995
[28]Moigne J L.The use of wavelets for remote sensing image registration and fusion [J].SPIE,1996(2762):535
[29]Kaymaz Emre,et al.Registration of satellite imagery utilizing the low-low components of the wavelet transforms[J].SPIE,1997(2962):45-54
[30]Hao Wu,Yongmin Kim.Fast wavelet-based Multi-resolution image registration on a multi-processing digital signal processor[C].International Journal of Imaging System and Technology,1998,(9):29-37
[31]Zhengwei Yang,Fernand S Cohen.Image registration and object recognition using affine invariants and convex hulls[J].IEEE Trans.Image Processing,1998(7):934-946
[32]A Goshtasby.A symbolically-assisted approach to digital image registration with application in computer vision[D].Michigan:Dept.of Computer Science,Michigan State University,1983
[33]J Flusser,T Suk.A moment-based approach to registration of images with affine geometric distortion[J].IEEE Trans on geosciences and remote sensing,1994,32(2):382-387
[34]CHEN C S C,EVENSM W,ARMATO S G.Performance evaluation of image registration[C].Proceedings of the 22~(th) Annual EMBS International Conference, Chicago IL,2000:3140 - 3143
[35]WALL I KC.Automated multi-sensor image registration[C].Proceedings of applied imagery Pattern Recognition Workshop,2003:103-107
[36]LE M J,COLE - RHODES A,Eastman R.A study of the sensitivity of automatic image registration algorithms to initial conditions[C].Proceedings of IEEE,2004:1390-1393
[37]席志红,刘利彬.SUSAN角点检测算法改进[J].应用科技.2006,33(9):29-32
[38]周骥 石教英.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报.2002,14(8):754-758
[39]刘松涛,王学伟,周晓东等.基于传感器参数和目标轮廓中心的自动配准算法研究[J].光学精密工程,2005,13(3):354-363
[40]SCHMID C,MOHR R.Local gray value invariants for image retrieval[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1997,19(5):530- 534
[41]LOWE D G.Object recognition from local scale invariant features [C]//International Conference on Computer Vision,1999:1150- 1157
[42]Lowe D G.Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110
[43]STEPHEN S,LOWED G,LITTLE J J.Vision based global localization and mapping for mobile robots[J].IEEE Transactions on Robotics,2005,21(3):364- 375.
[44]HELMER S,LOWED G.Object recognition with many local features[C]//Workshop on Generative Model Based Vision 2004(GMBV),2004
[45]LINDEBERG T.Scale space theory:A basic tool for analyzing structures at different scales[J].Journal of Applied Statistics,1994,21:224- 270
[46]Mikolajczyk K,Schmid C.Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[47]Mikolajczyk K,et al.Local features for object class recognition[A].Proc.ICCV' 05[C],Beijing,China,2005,Vol.2:1792-1799
[48]骞森,朱剑英.基于改进的SIFT特征的图像双向匹配算法[J].机械科学与技术,2007,26(9):1179-1182
[49]张强,郝向阳,刘松林等.一种用于机器视觉检测的图像配准快速算法[J].测绘学院学报,2005,22(1):33-35
[50]袁贞明,吴飞,庄越挺.基于视觉特征的多传感器图像配准[J].中国图像图形学报,2005,10(6):767-772
[51]曹闻,李弼强,邓子建.一种基于小波变换的图像配准方法[J].测绘通 报,2004,(2):16-19
[52]刘卫光,崔江涛,周利华.多源图像实时配准融合系统[J].系统工程与电子技术,2005,27(1):185-188
[53]ASTR ID F,CARLSEN I C,KABUS S,et a1.Modular toolbox for derivative-based medical image registration[C].SPIE,2005,5747:1222-1233
[54]陈煜,田裕鹏.图像融合中的图像配准方法研究[J].激光与红外,2004,34(1):34-36
[1]刘松涛.面向目标识别的图像融合技术研究[D].烟台:海军航空工程学院博士学位论文,2006
[2]Lallier E,Farooq M.A Real Time Pixel-level Based Image Fusion via Adaptive Weight Averaging[C].Proceedings of International Conference on Information Fusion,2000,3-13
[3]罗彩莲.基于Brovey融合的卫星影像土地覆盖变化检测[J].佳木斯大学学报,2005,23(1):1-5
[4]陆冬华,赵英俊.基于改进型Brovey算法的高光谱数据融合技术[J].世界核地质科学,2006,23(3):177-1780
[5]Leprieur C,Kerr Y H,Mastorchio S,et al.Monitoring vegetation cover across semi-arid regions:comparison of remote observations from various scales[J].International Journal of Remote Sensing,2000,21(2):281-300
[6]A lvarez R.Multi-emporia land-cover classification of Mexico using land-sat MSS imagery[J].International Journal of Remote Sensing,2003,24(12):2 501-514
[7]Jia Y.H.Fusion of Land-sat TM and SAR Images Based on Principal Component Analysis[J].Remote Sensing Technology and Application,1998,13(1):46-49
[8]Yang Jian,Zhang David,Yang Jing-yu.Two-dimensional PCA:a new approach to appearance- based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):131-137
[9]Chen Fu- bing,Chen Xiu- hong,Zhang Sheng- liang,et al.A human face recognition method based on modular 2DPCA[J].Journal of Image and Graphics,2006(4).
[10]Han Ke,Zhu Xiuchang.Research on face recognition based on IMED and 2DPCA [J].Journal of Electronics,2006,23(5):786- 790
[11]魏旭,陶冰洁.基于2DPCA的特征融合方法及其应用[J].计算机工程与应用,2008,44(5):70-72
[12]A.Toet,J.Walraven.New false color mapping for image fusion[J].Optical Engineering,1996,35(3):650-658
[13]吴连喜,王茂新.一种基于IHS变换的改进型图像融合的算法[J].农业工程学报.2003.19(6):163-166
[14]魏俊,李弼程.基于IHS变换、小波变换与高通滤波的遥感影像融合[J].信息工程大学学报.2003.4(2):46-50
[15]李弼程,魏俊,彭天强.基于IHS变换与小波变换的遥感图像融合[J].数据采集与 处理.2003.18(3):268-272
[16]曹闻,张勇.基于小波包变换与IHS变换的遥感图像融合[J].测绘学院学报.2004.21(2):114-117
[17]王仁礼,戚铭尧,王慧.用于图像融合的IHS变换方法的比较[J].测绘学院学报.2000.17(4):269-272
[18]Smith S,Scarff L A.Combining visual and IR images for sensor fusion - two approaches[J].SPIE,1992,1668,1102 - 1112
[19]Toet A.Hierarchical image fusion[J].Machine Vision and Applications,1990,3(1):1-11
[20]蒲恬.应用于图像融合中的多尺度对比度调制法[J].北京理工大学学报,2000,120(2)
[21]蒲恬,方庆韶,倪国强.基于对比度的多分辨率图像融合[[J].电子学报,2002,28(12):116-118
[22]Fechner T,Godlewski G.Optimal fusion of TV and infrared images using artificial neural networks:SPIE:On Application and Science of Artificial Neural Networks [C].Washington,USA:SPIE Press,1995:919-925
[23]P.J.Burt and E.H.Adelson.The Laplacian pyramid as a compact image code [J].IEEE Trans.Communications,1983,31(4):532 -540
[24]P.J.Burr.The pyramid as structure for efficient computation[J].Multiresolution Image Processing and Analysis,1984:6 - 35
[25]P.J.Burt and E.H.Adelson.Merging images through pattern decomposition [J].Applications of Digital Image Processing Ⅷ,A.G.Tescher,ed.,Proc.SPIE 575,173-181,1985
[26]A.Toet,J.J.Ruyven,J.M.Valeton.Merging thermal and visual images by a contrast pyramid[J].Optical Engineering,28(1989) 789-792
[27]Toet A.Morphological pyramidal image decomposition[J].Pattern recognition letters,1989,9(4):255-261
[28]P.J.Burt,R.J.Kolczynski.Enhanced image capture through fusion[C].Proc.4th Int.Conf.on Computer Vision,1993.173-182
[29]H.Li,B.S.Manjunath,S.K.Mitra.Multi-sensor image fusions using the wavelet transform[J].Graphical Models and Image Process,1995,57(3):235-245
[30]L.J.Chipman,T.M.Orr,L.N.Graham.Wavelets and image fusion[C].Proc.Int.Conf.on Image Processing,1995,248-251
[31]Z.Zhang,R.S.Blum.A categorization of multi-scale decomposition based image fusion schemes with a performance study for a digital camera application[J].Proceedings of the IEEE,1999,87(8):1315-1326
[32]景娟娟,吕群波,周锦松等.图像融合效果评价方法研究[J].光子学报,2007(6):313-317
[33]胡良梅,高隽,何柯峰.图像融合质量评价方法的研究[J].电子学报,2004,32(12A):218-221
[34]李树涛,王耀南,张昌凡.多传感器图像融合的客观评价与分析[J].仪器仪表学报,2002,23(6):651-654
[35]阳方林,郭红阳,杨风暴.像素级图像融合效果的评价方法研究[J].测试技术学报,2002,6(4):276-279
[36]王海晖,彭嘉雄,吴巍.评价多传感器图像融合效果方法的比较[J].红外与激光工程,2004,33(2):189一193
[37]Woebbecke,DM,et.al.Color indices for weed identification under various soil,residue,and lighting conditions[J].Transactions of the ASAE,1995,38(1):259-269
[38]Zhang N,Chaisattapagon C.Effective criteria for weed identification in wheat fields using machine vision[J].Transactions of the ASAE,1995,38(3):965-974.
[39]吕俊伟,马成林,于永胜.利用多光谱图像融合提高作物和杂草灰度比值[J].农业机械学报,2005,21(11):99-102
[40]姜庆娟,谭景信.象素级图像融合方法与选择[J].计算机工程与应用,2003,25:116-120
[41]王志武,丁国清,颜国正等.自适应提升小波变换与图象去噪[J].红外与毫米波学报,2002,21(6):447-450
[42]李卫华,周军,周连文等.一种基于提升小波分解图像融合方法[J].计算机应用.2006.26(2):403-405
[43]W.Sweldens.The Lifting Scheme:A Construction of Second Generation Wavelets[J].SIAM Journal of Mathematical Analysis,1998,29(2):511-546
[44]W.Sweldens.The Lifting Scheme:A new Philosophy in Biorthogonal Wavelet Constructions[C].Proceedings of SPIE on Wavelet Applications in Signal and Image Processing Ⅲ,New York:SPIE,1995,2569:68-79
[45]Daubechies I,Sweldens W.Factoring wavelet transform into lifting steps[J].Journal of Fourier analysis and Applications,1998,4(3):245-267
[46]Honggang Li,Qiao Wang,and Lenan Wu.A Novel Design of Lifting Scheme from General Wavelet[J].IEEE Transactions on Signal Processing,2001,49(8):1714-1717
[47]A.Toet and E.M.Franken.Perceptual evaluation of different image fusion schemes[J].Displays,2003,24:25-37
[48]G.Piella and H.Heijmans.A new quality metric for image fusion[J].Proc.IEEE International Conference on Image Processing,2003,3:173-176
[49]刘贵喜,杨万海.一种像素级多算子红外与可见光图像融合方法[J].红外与毫米学报,2001,20(3):207-210
[1]赵杰文,杨国彬,刘木华.基于HIS颜色特征的田间成熟番茄识别技术[J].农业机械学报,2004,35(9):122-124,135
[2]李明喜,毛罕平,张艳诚.基于提升小波和分形的苹果树多源图像融合算法[J].农业机械学报,2007,38(10):91-93,121
[3]Wang H,Peng J,Wu W.Fusion algorithm for multi-sensor images based on discrete multi-wavelets transform[A].IEE Proceedings of Vision Image and Signal Processing[C].2002,149(5):283-289
[4]杨翔宇,孙惠.用数学形态学进行图像边缘检测的新方法[J].开发研究与设计技术,2007(2):501-502
[5]JING XIAO-JUN,MAYI-XIA,QU EN.Morphological filter based on genetic learning [J].Communication and Information Technology,2005,1(12 /14):749- 752
[6]EVANSA N,LIU X U.A morphological gradient approach to color edge detection [J].Image Processing,2006,15(6):1454- 1463
[7]SHIH F Y,CHENG S X.Adaptive mathematical morphology for edge linking[J].Information Sciences,2004,167(1/4):9- 21.
[8]张艳玲,刘桂雄,曹东等.数学形态学基本算法及在图像预处理中的应用[J].科学技术与工程,2007,7(3):356-359
[9]毛罕平,李明喜.基于多光谱图像融合和形态学重构的图像分割方法研究[J].农业工程学报,2008(6)
[10]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006
[11]仲琴.基于机器视觉的番茄收获机器人目标定位技术研究[D].镇江:江苏大学硕士论文,2005
[1]隋蜻,金伟其.双目立体视觉技术的实现及其进展[J].计算机应用,2004,10:4-12
[2]Jia B,Zhang Y J,Lin X G.Stereo matching using both orthogonal and multiple image pairs[J].In:Proceedings of International Conference on Acoustics,Speech,and Signal Processing,2000:2139-2142
[3]Lowe D G.Distinctive Image Features from Scale Invariant key points [J].International Journal of Computer Vision,2004,60(2):91 -110
[4]管业鹏,顾伟康.基于双目视觉的基准差梯度立体匹配法[J].传感技术学报,2004,1:74-77
[5]刘正东,杨静宇.自适应窗口的时间规整立体匹配算法[J].计算机辅助设计与图形学学报,2005,17(2):291-295
[6]向登宁,邓文怡,燕必希等.利用极线约束方法实现图像特征点的匹配[J].北京机械工业学院学报,2002,17(4):21-25
[7]周东翔,菜宣平,孙茂印.一种基于特征约束的立体匹配算法[J].中国图象图形学报,2001,6(7):653-656
[8]李德广,李科杰.一种快速立体视觉边缘匹配算法[J].计算机应用,2005,25(4):763-765
[9]周敬利,罗秋明,余胜生.使用视差一致性约束的立体匹配与遮掩检测[J].小型微型计算机系统,2003,24(10):1791-1795
[10]郝晓辰,刘爽,张强等.双目立体视觉测量模型与同名点匹配研究[J].仪器仪表学报,2005,8:11-13
[11]Luigi Di Stefano,Massimiliano Marchionni,Stefano Mattoccia.A fast area-based stereo matching algorithm[J].Image and Vision Computing,2004,22:983-1005
[12]廖素珍,杨华军.一种快速有效提取浓密视差图的方法[J].电子科技大学学报,2005,34(2):199-201
[13]李海滨,单文军,刘彬.双目立体视觉测距系统误差模型的研究[J].光学技术,2006,32(1):24-16
[14]洪露,马长山,谢宗安.基于遗传算法的神经网络权值优化[J].贵州工业大学学报,2003,32(6):48-51
[15]刘云霞.水下机器人运动系统的神经网络辨识[J].机械工程与自动化,2006,135(2):81-83
[16]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006
[2]Parrish,E,Goksel A K.Pictorial pattern recognition applied to fruit harvesting [J].Transactions of the ASAE,1977,20(5):822-827.
[3]D'Esnon,A G,Rabatel G,Pellenc R.A self-propelled robot to pick apples [J].Transactions of the ASAE,1987,87:1032-1037
[4]Rabatel,G..,A vision system for Magalia,the fruit picking robot[C].Agricultural Engineering,Paris,London,U.K.Paper 88293,AGENG88, International Conference:Ministry of Agriculture,Fisheries and Food 1988.
[5]Slaughter,D.C,and Harrell R.C.Color vision in robotic fruit harvesting[J].Transactions of the ASAE,1987,30(4):1144-1148.
[6]Slaughter,D.C and Harrell R C.Discriminating fruit for robotic harvest using color in natural outdoor scenes[J].Transactions of the ASAE,1989,32(2):757-763
[7]Harrell R.C.,Slaughter D.C.etc.A fruit-tracking system for robotic harvesting[J].Machine Vision & Application,1989(2):69-80.
[8]Whittaker A D,Miles G E,Mitchell 0 R etc.Fruit location in a partially occluded image[J].Transactions of the ASAE,1987,30(3):591-596.
[9]Illingworth,J.,and J,Kitten.A survey of the Hough transforms[J].Computer Vision,Graph.& Image Proc.,1988,44:87-116.
[10]Sites P W,Delwiche M J.Computer vision to locate fruit on a tree[J].Transactions of the ASAE,1988,31(1):257-263.
[11]#12
[12]#12
[13]#12
[14]#12
[15]#12
[16]周增产,J.Bontsema,L.Van Kollenburg-Crisan。荷兰黄瓜收获机器人的研究开发[J].农业工程学报,2001,1(6):77-80
[17]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Bontsema J.Collision-free Motion Planning for a Cucumber Picking Robot[J].Bio-systems engineering,2003,86(2):135-144
[18]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Meuleman J,Bontsema J,Van OsEA.Field Test of an Autonomous Cucumber Picking Robot[J]。Bios stems engineering,2003,86(3):305-313
[19]Dnhrousin,Y.,and Y.Edan.,Real-time image processing for robotic melon harvesting[C].ASAE Paper No.92-3515,1992
[20]Hayashi,S.,Ganno,K.& Ishii,Y.Machine vision algorithm of eggplant recognition for robotic harvesting[J].J.SHITA,2000,12(1):38-46
[21]Hayashi,S.,Ganno,K.and Ishii,Y.Visual feedback guidance of manipulator for eggplant harvesting using fuzzy logic[J].J.SHITA,2002,12(2):83-92
[22]Hayashi S.,Ganno K.,Ishii Y.and Tanaka I.Robotic Harvesting System for Eggplants[J].JARO,2006,36(3):163-168
[23]张铁中,林宝龙,高锐.水果采摘机器人视觉系统的目标提取[J].中国农业大学学报,2004,9(2):68-72
[24]徐丽明,张铁中.果蔬果实收获机器人的研究现状及关键问题和对策[J].农业工程学报,2004,(05).
[25]谢志勇,张铁中.基于RGB彩色模型的草莓图像色调分割算法[J].中国农业大学学报,2006,11(1):84-86
[26]张铁中,周天娟.草莓采摘机器人的研究:I.基于BP神经网络的草莓图像分割[J].中国农业大学学报,2004,9(4):65-68
[27]应义斌,饶秀勤,马俊福.柑橘成熟度机器视觉无损检测方法研究[J].农业工程学报,2004,20(2):144-147
[28]徐惠荣,叶尊忠,应义斌.基于彩色信息的树上柑橘识别研究[J].农业工程学报,2005,21(5):98-101
[29]徐惠荣,应义斌.红外热成像在树上柑桔识别中的应用研究[J].红外与毫米波学报,2004,23(5):353-356
[30]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D],江苏大学博士学位论文,2006。
[31]Kassay.L.Hungarian robotic apple harvester[C].ASAE,1992,92-7042:1-14.
[32]Dnhrousin,Y.,and Y.Edan.Real-time image processing for robotic melon harvesting[C].ASAE Paper No.92-3515,1992
[33]Grasso,G..and M.Recce,Scene analysis for an orange picking robot[C].In Proc.Int.Congress for Computer Technology in Agriculture(ICCTA'96),1996
[34]#12
[35]#12
[36]Cao Q,Nagata M,Gejima Y,Shrestha B.P.,Hiyoshi K.Basic study on strawberry harvesting robot(Part Ⅰ)- algorithm for locating and feature extracting of strawberry fruits.Bio-Robotics,Information Technology and Intelligent Control for Bio-production System 2000
[37]Fujiura,T.,J.Yamasjita,and N.Kondo,Agricultural robots(1),Vision sensing system[J],ASAE,1992,92-3517
[38]Fujiura,T.,S.Nakao,N.Kondo etc,Dichromatic 3-D vision sensor for the agricultural robot[J].J.Jpn.Soc.Agric.Technol.Manage,1995,2(1):59-64
[39]Arima,S.,N.Kondo,etc,Study on cucumber harvesting robot(Part 1)[J].J.Jpn.Soc.Agric.Mach,1994,56(1):45-53
[40]Arima,S.,N.Kondo,etc,Study on cucumber harvesting robot(Part 2)[J].J.Jpn.Soc.Agric.Mach,1994,56(6):69-76
[41]Kondo N,Nishitsuji Y,Ling P Petal.Visual feedback guided robotic cherry tomato harvesting[J].Transactions of the ASAE,1996,39(6):2331-2338
[42]周云山,李强 计算机视觉在蘑菇采摘视器人上的应用[J],农业工程学报,1995.11(4):27-31。
[43]张瑞合 姬长英 沈明霞 曹坤.计算机视觉技术在番茄收获中的应用[J],农业机械学报2001.9 32(5):50-52。
[44]郑小东 赵杰文等.基于双目立体视觉的番茄识别与定位技术[J],计算机工程,2004.30(22):155-171。
[45]仲琴.基于机器视觉的番茄收获机器人目标定位技术研究,江苏大学硕士论文,2005。
[46]蔡健荣,赵杰文.自然场景下成熟水果的计算机视觉识别[J].农业机械学报,2005,36(2)61-64[
47]蔡健荣.基于立体视觉的成熟水果识别定位及机器人路径规划[D].江苏大学博土学位论文,2005
[1]王章野.地面目标的红外成像仿真与多光谱成像真实感融合研究[D].杭州:浙江大学博士学位论文,2002.
[2]A_R.Jimenez,R.Ceres,J.L.Pons.A vision system based on a laser range-finder applied to robotic fruit harvesting[J].Machine Vision and Applications,2002,11:321-329.
[3]林伟明,毛罕平,王新忠等.多光谱视觉技术在收获机器人中的应用[J].农业装备技术,2004,(06).
[4]Subrata et al.3_Dvision sensor for cherry tomato harvesting robot[J].Proceedings of International Symposium of Automation and Robotics on bio-production and processing,1:13-20.
[5]项震.基于CCD器件特征的图像噪声消除[J].光电工程,2001,28(6):66-68.
[6]刘延武,何友金,陆斌等.舰船目标红外图像预处理[J].红外技术,2003,25(3):9-12.
[7]汪鲁才,王辉南,毛六平.基于小波变换和中值滤波的InSAR干涉图像滤波方法[J].测绘学报,2005,34(2):108-112.
[8]J.H.Bosworth,S.T.Acton.Morphological scale-space in image processing [J].Digital Signal Processing,2003,13(2):338-367.
[9]A.Castratos,I.Andreadis.Soft mathematical morphology:extensions,algorithms and implementations[J].Advances in Imaging and Electron Physics,1999,110(1),63-99.
[10]J.H.Bosworth,S.T.Acton.Morphological scale-space in image processing [J].Digital Signal Processing,2003,13(2):338-367.
[11]P.Soille.Beyond self-duality in morphological image analysis[J].Image and Vision Computing,2005,23(2):249-257.
[12]Y.Grau,M.A.Raga,C.Monserrat.Hierarchical image segmentation using a correspondence with a tree model[J].Pattern Recognition,2004,37(1):47-59.
[13]王小鹏,郑玉甫.一种图像噪声的形态学多尺度去除方法[J].计算机工程,2006,32(4):208-210.
[14]游安清,程义民,赵平等.红外图像去噪中形态学结构元素的选取[J].应用科学学报,2004,22(4):483-486.
[15]赵健,宋祖勋,俞卞章.基于多重分形分析的SAR图像消噪增强研究[J].西北工业大学学报,2003,21(1):30-33.
[16]蒋定定,许兆林,李开端.基于改进分形技术的红外图像噪声抑制研究[J].测绘工程,2004,13(4):32-34.
[17]李明喜,毛罕平.基于数学形态学和多重分形的图像消噪算法研究[J].仪器仪表学报,2007.8
[18]李明喜,毛罕平,张艳诚.基于提升小波变换和中值滤波的图像去噪方法研究[J].激光与红外,2007(5)
[19]李明喜,吴鸿霞.基于小波变换和中值滤波的图像去噪方法研究[J].黄石理工学院学报,2007(2)
[20]李明喜,毛罕平,张艳诚.近红外图像消噪方法的对比实验研究[J].红外技术,2007,11
[21]G.Fan,X-G Xia.Image De-noising Using Local Contextual Hidden Markov Model in the Wavelet Domain[J].IEEE Signal Processing Letter,8(5),May 2001,125-128.
[22]R.Kimmel,M.Elad,D.Shaked,R.Keshet(Kresch),I.Sobel,"A variation framework for Retinex",Int.J.Comput.Vision,2003,Vol.52:7-23
[23]T.Iketani,N.Unagmi,M.Suwa,M.Kimachi,"Human Detection System using stereovision sensor," 2004,04:231-234.
[24]Rafael C.Gonzalez等著.阮秋琦等译.数字图像处理(MATLAB版).北京:电子工业出版社,2005,9
[25]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006
[26]Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[27]Ahmed,Mohamed N.A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data[J],IEEE Transactions on Medical Imaging,2002,21(3):193-199.
[28]刘华军,任明武,杨静宇.一种改进的基于模糊聚类的图像分割方法[J].中国图象图形学报,2006,11(9):1312-1316
[29]马华,张永,庞长刚.一种改进的FCM在医学图像分割中的应用[J].电脑开发与应用,2006,19(4):10-11
[30]金立左,夏良正,杨世周.图象分割的白适应模糊阈值法[J].中国图象图形学报,2000,5A(5):390-395
[31]岳振军,邱望成,刘春林.一种自适应的多目标图像分割方法[J].中国图象图形学报,2004,9(6):674-678
[32]曹力,史忠科.基于最大熵原理的多阈值自动选取新方法[J].中国图象图形学报,2002,7(A版)No.5:461-465
[33]张红蕾,宋建社,翟晓颖.一种基于二维最大熵的SAR图像自适应阈值分割算法[J].电光与控制,2007,14(4):63-65
[34]Rigau J,Feixas M,Sbert M,et al.Medical Image Segmentation Based on Mutual Information Maximization[C]//Proceedings of MICCAI' 04,Saint-Malo,France 2004:135-142.
[35]Pluim J,Maintz J,Viergever M.Mutual information based registration of medical images:a survey[J].IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
[36]周小舟,张加万,孙济洲.基于互信息和Chan-Vese模型的图像分割方法[J].计算机工程,2007,33(22):220-222
[37]Shafarenko L,Petrou M,Kittlerd.Automatic watershed segmentation of randomly textured color images[J].IEEE Transactions on Image Processing 1997,6(11):1530-1544
[38]Vincent L.Morphological grayscale reconstruction in image analysis:applications and efficient algorithms[J].IEEE Transactions on Image Processing,1993,2(2),176-201.
[39]Gao Hal,Lin Weisi,Xue Ping,et al.Marker- based image segmentation relying on disjoint set union[J].Signal Processing:Image Communication,2006,21(2):100-112.
[40]Rodriguez R,Alarcon T E,Pacheco O.A new strategy to obtain robust markers for blood vessels segmentation by using the water-sheds method[J].Computers in Biology and Medicine,2005,35(8):665- 686.
[41]Jung C R.Combining wavelets and watersheds for robust multi-scale image segmentation[J].Image and Vision Computing,2007,25(1)' 24- 33.
[42]包振健,邸书灵.一种基于分水岭变换的细胞图像分割方法[J].计算机工程与应用,2008,44(4):230-232
[43]尹建军,毛罕平等.不同生长状态下多目标番茄图像的自动分割方法[J].农业工程学报.2006.22(10):149-152.
[1]吴文琪,孙增.机器视觉中的摄像机定标方法综述[J].计算机应用研究,2004,2:4-7
[2]Y I Abdel-Aziz,H M Karara.Direct Linear Transformation into Object Space Coordinates in Close-Range Photogrammetry[C].In:Proc.Symposium on Close-Range Photogrammetry,Urbana,University of Illinois,January 1971:1-18
[3]I Sobel.On Calibration Computer Controlled Cameras for Perceiving 3D Scenes [J].Artif.Intell.1974:5:185-198
[4]Tsai R Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J].IEEE Journal of Robotics and Automation,1987,3(4):323-344
[5]Martins H A,Birk J R,Kelley R B.Camera models based on data from two calibration planes[J].Computer Graphics Image Processing,1981,17(2):173-180
[6]Malik M,Mudar S,Florent C.Automatic camera calibration based on robot calibration[C].IEEE Instrumentation and Measurement Technology Conference.1992,2:1278-1282
[7]Zhang Z.A flexible new technique for camera calibration.Microsoft Corporation:Technical Report MSR-TR-98-71,2002
[8]孙长库,张效栋.CCD摄像机参数标定实验设计[J].光电子技术与信息,2000,18(2):43-46
[9]蔡健荣,赵杰文.双目立体视觉系统摄像机标定[J].江苏大学学报,2007,27(1):6-9
[10]J.More.The Levenberg-marquardt algorithm,implementation and theory[M].In G.A.Watson,editor,Numerical Analysis,Lecture Notes in Mathematics 630.Springer-Verlag,1977
[1]金剑秋.多光谱图像的融合与配准[D]。杭州:浙江大学博士学位论文,2005
[2]OWN H S,HASSANIEN A E.Multi-resolution image registration algorithm in wavelet transform domain[A].IEEE 14~(th) International Conference on Digital Signal Processing[C].Santorini,Greece:IEEE,2002,2:889-892
[3]HAIKEL Salem Alhichri,MOHAMED Kamel.Image registration using virtual circles and edge direction[A].IEEE 16~(th) International Conference on Pattern Recognition[C].Quebec,CANADA:IEEE,2002,2:969-972
[4]LISA Gottesfeld Brown.A survey of image registration techniques[J].ACM Computing Surveys,1992,24(4):325-376
[5]XIE Zhi-yong.Image registration using hierarchical B-Splines[D].USA:Arizona state university,2002
[6]Barnea D I,Silverman H F.A class of algorithms for fast digital registration [J]IEEE Trans.Computer,1972,(21):179-186
[7]KUGLIN C D,HINES D C.The phase correlation image alignment method[A].Proceedings of 1975 IEEE International Conference on Cybernetics and Society[C].New York,USA:IEEE,1975.163-165
[8]张二虎,卞正中.基于最大嫡和和互信息最人化的特征点配准算法[J].计算机研究与发 展,2004,7(3)
[9]王小睿,吴信才,李军.模拟退火算法的改进策略在模板匹配上的应用[J].小型微型计算机系统,1997,18(8):32-37
[10]AVERBUCH A,KELLER Y.FFT based image registration[A].Proceedings of 2002IEEE International Conference on Acoustics,Speech and Signal Processing[C].Orlando,USA:IEEE,2002,4.3608-3611
[11]VIOLA P A,WELLS III W M.Alignment by maximization of mutual information [C].Proc.5th Int.Conf.Computer Vision,Boston,MA,1995:16-23
[12]COLLIGNON A,MAES F,DELAERE D.Automated multi-modality image registration based on information theory[C].Proc.of the Information Processing in Medical Imaging Conference,Norwell,MA:Kluwer,1995:263-274
[13]THEVENAZ P,RUTTIMANNU E,UNSER M.A pyramid approach to sub pixel registration based on intensity[J].IEEE Trans.Image Processing,1998(7):27-41
[14]STEFAN H,MAHNKEO,POTTS D,et al.Fast computation of mutual information in a variation image registration approach[C].CEUR Workshop Proceedings,2004:448-452
[15]JEFFREY P K.Reliable band-to-band registration of multi-spectral thermal imager data using multivariate mutual information and cyclic consistency [C].Proceedings of SPIE,2004,5558:57-68
[16]WACHOWIAKM P,RENATA S,GEORGIA D,et al.Generalized mutual information similarity metrics for multimodal biomedical image registration [C].Proceedings of the Second Joint EMBS/BMES Conference,2002:1005-1006
[17]MARTIN S,MORISON G,NAILON W,et al.Fast and accurate image registration using tallish entropy and simultaneous perturbation stochastic approximation[J].Electronics Letters,2004,40(10):595-597
[18]Yao Jianchao.Image registration based on both feature and intensity matching [A].Proceedings of 2001 IEEE International Conference on Acoustics,Speech and Signal Processing[C].Kauai,Hawaii,USA:IEEE,2001,3.1693-1696
[19]Jun-Wei Hsieh.Image registration using a new edge-based approach[J].Computer Vision and Image Understanding,1997,67(2):112-130
[20]钮永胜.可见光与热红外图像配准技术研究[博士后出站报告][R].北京:北京理工大学,1999.
[21]张迁,刘政凯,庞彦伟等.基于SUSAN算法的航空影像的自动配准[J].测绘学报,2003,32(3):245-250
[22]周鹏,谭勇,徐守时.基于角点检测图像配准的一种新算法[J].中国科学技术大学学报,2002,32(4):455-461
[23]Kyun Jung,Lacroix S.A robust interest points matching algorithm[A].Proceedings of Eighth IEEE International Conference on Computer Vision[C].Vancouver,BC,Canada:IEEE,2001,2.538 -543
[24]HUI Li,MANJUNATH B S A contour-based approach to multi-sensor image registration[J].IEEE Transactions on Image Processing,1995,4(3):320-334.
[25]TON J,JAIN A K.Registering Land sat images by point matching[J].IEEE Transactions on Geosciences and Remote Sensing,1989,27(5):642-651
[26]COX G S,JAGER G De.A survey of point matching techniques and a new approach to point pattern recognition[A].Pro.of 1992 South African Symposium on Communications and Signal Processing[C].Cape Town,South African:IEEE,1992.243-248
[27]Corvi M,Nicchiotti G.Multi-resolution image registration[C].1995International Conference on Image Processing,Washington,D.C.,Oct 23-26,1995
[28]Moigne J L.The use of wavelets for remote sensing image registration and fusion [J].SPIE,1996(2762):535
[29]Kaymaz Emre,et al.Registration of satellite imagery utilizing the low-low components of the wavelet transforms[J].SPIE,1997(2962):45-54
[30]Hao Wu,Yongmin Kim.Fast wavelet-based Multi-resolution image registration on a multi-processing digital signal processor[C].International Journal of Imaging System and Technology,1998,(9):29-37
[31]Zhengwei Yang,Fernand S Cohen.Image registration and object recognition using affine invariants and convex hulls[J].IEEE Trans.Image Processing,1998(7):934-946
[32]A Goshtasby.A symbolically-assisted approach to digital image registration with application in computer vision[D].Michigan:Dept.of Computer Science,Michigan State University,1983
[33]J Flusser,T Suk.A moment-based approach to registration of images with affine geometric distortion[J].IEEE Trans on geosciences and remote sensing,1994,32(2):382-387
[34]CHEN C S C,EVENSM W,ARMATO S G.Performance evaluation of image registration[C].Proceedings of the 22~(th) Annual EMBS International Conference, Chicago IL,2000:3140 - 3143
[35]WALL I KC.Automated multi-sensor image registration[C].Proceedings of applied imagery Pattern Recognition Workshop,2003:103-107
[36]LE M J,COLE - RHODES A,Eastman R.A study of the sensitivity of automatic image registration algorithms to initial conditions[C].Proceedings of IEEE,2004:1390-1393
[37]席志红,刘利彬.SUSAN角点检测算法改进[J].应用科技.2006,33(9):29-32
[38]周骥 石教英.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报.2002,14(8):754-758
[39]刘松涛,王学伟,周晓东等.基于传感器参数和目标轮廓中心的自动配准算法研究[J].光学精密工程,2005,13(3):354-363
[40]SCHMID C,MOHR R.Local gray value invariants for image retrieval[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1997,19(5):530- 534
[41]LOWE D G.Object recognition from local scale invariant features [C]//International Conference on Computer Vision,1999:1150- 1157
[42]Lowe D G.Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110
[43]STEPHEN S,LOWED G,LITTLE J J.Vision based global localization and mapping for mobile robots[J].IEEE Transactions on Robotics,2005,21(3):364- 375.
[44]HELMER S,LOWED G.Object recognition with many local features[C]//Workshop on Generative Model Based Vision 2004(GMBV),2004
[45]LINDEBERG T.Scale space theory:A basic tool for analyzing structures at different scales[J].Journal of Applied Statistics,1994,21:224- 270
[46]Mikolajczyk K,Schmid C.Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86
[47]Mikolajczyk K,et al.Local features for object class recognition[A].Proc.ICCV' 05[C],Beijing,China,2005,Vol.2:1792-1799
[48]骞森,朱剑英.基于改进的SIFT特征的图像双向匹配算法[J].机械科学与技术,2007,26(9):1179-1182
[49]张强,郝向阳,刘松林等.一种用于机器视觉检测的图像配准快速算法[J].测绘学院学报,2005,22(1):33-35
[50]袁贞明,吴飞,庄越挺.基于视觉特征的多传感器图像配准[J].中国图像图形学报,2005,10(6):767-772
[51]曹闻,李弼强,邓子建.一种基于小波变换的图像配准方法[J].测绘通 报,2004,(2):16-19
[52]刘卫光,崔江涛,周利华.多源图像实时配准融合系统[J].系统工程与电子技术,2005,27(1):185-188
[53]ASTR ID F,CARLSEN I C,KABUS S,et a1.Modular toolbox for derivative-based medical image registration[C].SPIE,2005,5747:1222-1233
[54]陈煜,田裕鹏.图像融合中的图像配准方法研究[J].激光与红外,2004,34(1):34-36
[1]刘松涛.面向目标识别的图像融合技术研究[D].烟台:海军航空工程学院博士学位论文,2006
[2]Lallier E,Farooq M.A Real Time Pixel-level Based Image Fusion via Adaptive Weight Averaging[C].Proceedings of International Conference on Information Fusion,2000,3-13
[3]罗彩莲.基于Brovey融合的卫星影像土地覆盖变化检测[J].佳木斯大学学报,2005,23(1):1-5
[4]陆冬华,赵英俊.基于改进型Brovey算法的高光谱数据融合技术[J].世界核地质科学,2006,23(3):177-1780
[5]Leprieur C,Kerr Y H,Mastorchio S,et al.Monitoring vegetation cover across semi-arid regions:comparison of remote observations from various scales[J].International Journal of Remote Sensing,2000,21(2):281-300
[6]A lvarez R.Multi-emporia land-cover classification of Mexico using land-sat MSS imagery[J].International Journal of Remote Sensing,2003,24(12):2 501-514
[7]Jia Y.H.Fusion of Land-sat TM and SAR Images Based on Principal Component Analysis[J].Remote Sensing Technology and Application,1998,13(1):46-49
[8]Yang Jian,Zhang David,Yang Jing-yu.Two-dimensional PCA:a new approach to appearance- based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):131-137
[9]Chen Fu- bing,Chen Xiu- hong,Zhang Sheng- liang,et al.A human face recognition method based on modular 2DPCA[J].Journal of Image and Graphics,2006(4).
[10]Han Ke,Zhu Xiuchang.Research on face recognition based on IMED and 2DPCA [J].Journal of Electronics,2006,23(5):786- 790
[11]魏旭,陶冰洁.基于2DPCA的特征融合方法及其应用[J].计算机工程与应用,2008,44(5):70-72
[12]A.Toet,J.Walraven.New false color mapping for image fusion[J].Optical Engineering,1996,35(3):650-658
[13]吴连喜,王茂新.一种基于IHS变换的改进型图像融合的算法[J].农业工程学报.2003.19(6):163-166
[14]魏俊,李弼程.基于IHS变换、小波变换与高通滤波的遥感影像融合[J].信息工程大学学报.2003.4(2):46-50
[15]李弼程,魏俊,彭天强.基于IHS变换与小波变换的遥感图像融合[J].数据采集与 处理.2003.18(3):268-272
[16]曹闻,张勇.基于小波包变换与IHS变换的遥感图像融合[J].测绘学院学报.2004.21(2):114-117
[17]王仁礼,戚铭尧,王慧.用于图像融合的IHS变换方法的比较[J].测绘学院学报.2000.17(4):269-272
[18]Smith S,Scarff L A.Combining visual and IR images for sensor fusion - two approaches[J].SPIE,1992,1668,1102 - 1112
[19]Toet A.Hierarchical image fusion[J].Machine Vision and Applications,1990,3(1):1-11
[20]蒲恬.应用于图像融合中的多尺度对比度调制法[J].北京理工大学学报,2000,120(2)
[21]蒲恬,方庆韶,倪国强.基于对比度的多分辨率图像融合[[J].电子学报,2002,28(12):116-118
[22]Fechner T,Godlewski G.Optimal fusion of TV and infrared images using artificial neural networks:SPIE:On Application and Science of Artificial Neural Networks [C].Washington,USA:SPIE Press,1995:919-925
[23]P.J.Burt and E.H.Adelson.The Laplacian pyramid as a compact image code [J].IEEE Trans.Communications,1983,31(4):532 -540
[24]P.J.Burr.The pyramid as structure for efficient computation[J].Multiresolution Image Processing and Analysis,1984:6 - 35
[25]P.J.Burt and E.H.Adelson.Merging images through pattern decomposition [J].Applications of Digital Image Processing Ⅷ,A.G.Tescher,ed.,Proc.SPIE 575,173-181,1985
[26]A.Toet,J.J.Ruyven,J.M.Valeton.Merging thermal and visual images by a contrast pyramid[J].Optical Engineering,28(1989) 789-792
[27]Toet A.Morphological pyramidal image decomposition[J].Pattern recognition letters,1989,9(4):255-261
[28]P.J.Burt,R.J.Kolczynski.Enhanced image capture through fusion[C].Proc.4th Int.Conf.on Computer Vision,1993.173-182
[29]H.Li,B.S.Manjunath,S.K.Mitra.Multi-sensor image fusions using the wavelet transform[J].Graphical Models and Image Process,1995,57(3):235-245
[30]L.J.Chipman,T.M.Orr,L.N.Graham.Wavelets and image fusion[C].Proc.Int.Conf.on Image Processing,1995,248-251
[31]Z.Zhang,R.S.Blum.A categorization of multi-scale decomposition based image fusion schemes with a performance study for a digital camera application[J].Proceedings of the IEEE,1999,87(8):1315-1326
[32]景娟娟,吕群波,周锦松等.图像融合效果评价方法研究[J].光子学报,2007(6):313-317
[33]胡良梅,高隽,何柯峰.图像融合质量评价方法的研究[J].电子学报,2004,32(12A):218-221
[34]李树涛,王耀南,张昌凡.多传感器图像融合的客观评价与分析[J].仪器仪表学报,2002,23(6):651-654
[35]阳方林,郭红阳,杨风暴.像素级图像融合效果的评价方法研究[J].测试技术学报,2002,6(4):276-279
[36]王海晖,彭嘉雄,吴巍.评价多传感器图像融合效果方法的比较[J].红外与激光工程,2004,33(2):189一193
[37]Woebbecke,DM,et.al.Color indices for weed identification under various soil,residue,and lighting conditions[J].Transactions of the ASAE,1995,38(1):259-269
[38]Zhang N,Chaisattapagon C.Effective criteria for weed identification in wheat fields using machine vision[J].Transactions of the ASAE,1995,38(3):965-974.
[39]吕俊伟,马成林,于永胜.利用多光谱图像融合提高作物和杂草灰度比值[J].农业机械学报,2005,21(11):99-102
[40]姜庆娟,谭景信.象素级图像融合方法与选择[J].计算机工程与应用,2003,25:116-120
[41]王志武,丁国清,颜国正等.自适应提升小波变换与图象去噪[J].红外与毫米波学报,2002,21(6):447-450
[42]李卫华,周军,周连文等.一种基于提升小波分解图像融合方法[J].计算机应用.2006.26(2):403-405
[43]W.Sweldens.The Lifting Scheme:A Construction of Second Generation Wavelets[J].SIAM Journal of Mathematical Analysis,1998,29(2):511-546
[44]W.Sweldens.The Lifting Scheme:A new Philosophy in Biorthogonal Wavelet Constructions[C].Proceedings of SPIE on Wavelet Applications in Signal and Image Processing Ⅲ,New York:SPIE,1995,2569:68-79
[45]Daubechies I,Sweldens W.Factoring wavelet transform into lifting steps[J].Journal of Fourier analysis and Applications,1998,4(3):245-267
[46]Honggang Li,Qiao Wang,and Lenan Wu.A Novel Design of Lifting Scheme from General Wavelet[J].IEEE Transactions on Signal Processing,2001,49(8):1714-1717
[47]A.Toet and E.M.Franken.Perceptual evaluation of different image fusion schemes[J].Displays,2003,24:25-37
[48]G.Piella and H.Heijmans.A new quality metric for image fusion[J].Proc.IEEE International Conference on Image Processing,2003,3:173-176
[49]刘贵喜,杨万海.一种像素级多算子红外与可见光图像融合方法[J].红外与毫米学报,2001,20(3):207-210
[1]赵杰文,杨国彬,刘木华.基于HIS颜色特征的田间成熟番茄识别技术[J].农业机械学报,2004,35(9):122-124,135
[2]李明喜,毛罕平,张艳诚.基于提升小波和分形的苹果树多源图像融合算法[J].农业机械学报,2007,38(10):91-93,121
[3]Wang H,Peng J,Wu W.Fusion algorithm for multi-sensor images based on discrete multi-wavelets transform[A].IEE Proceedings of Vision Image and Signal Processing[C].2002,149(5):283-289
[4]杨翔宇,孙惠.用数学形态学进行图像边缘检测的新方法[J].开发研究与设计技术,2007(2):501-502
[5]JING XIAO-JUN,MAYI-XIA,QU EN.Morphological filter based on genetic learning [J].Communication and Information Technology,2005,1(12 /14):749- 752
[6]EVANSA N,LIU X U.A morphological gradient approach to color edge detection [J].Image Processing,2006,15(6):1454- 1463
[7]SHIH F Y,CHENG S X.Adaptive mathematical morphology for edge linking[J].Information Sciences,2004,167(1/4):9- 21.
[8]张艳玲,刘桂雄,曹东等.数学形态学基本算法及在图像预处理中的应用[J].科学技术与工程,2007,7(3):356-359
[9]毛罕平,李明喜.基于多光谱图像融合和形态学重构的图像分割方法研究[J].农业工程学报,2008(6)
[10]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006
[11]仲琴.基于机器视觉的番茄收获机器人目标定位技术研究[D].镇江:江苏大学硕士论文,2005
[1]隋蜻,金伟其.双目立体视觉技术的实现及其进展[J].计算机应用,2004,10:4-12
[2]Jia B,Zhang Y J,Lin X G.Stereo matching using both orthogonal and multiple image pairs[J].In:Proceedings of International Conference on Acoustics,Speech,and Signal Processing,2000:2139-2142
[3]Lowe D G.Distinctive Image Features from Scale Invariant key points [J].International Journal of Computer Vision,2004,60(2):91 -110
[4]管业鹏,顾伟康.基于双目视觉的基准差梯度立体匹配法[J].传感技术学报,2004,1:74-77
[5]刘正东,杨静宇.自适应窗口的时间规整立体匹配算法[J].计算机辅助设计与图形学学报,2005,17(2):291-295
[6]向登宁,邓文怡,燕必希等.利用极线约束方法实现图像特征点的匹配[J].北京机械工业学院学报,2002,17(4):21-25
[7]周东翔,菜宣平,孙茂印.一种基于特征约束的立体匹配算法[J].中国图象图形学报,2001,6(7):653-656
[8]李德广,李科杰.一种快速立体视觉边缘匹配算法[J].计算机应用,2005,25(4):763-765
[9]周敬利,罗秋明,余胜生.使用视差一致性约束的立体匹配与遮掩检测[J].小型微型计算机系统,2003,24(10):1791-1795
[10]郝晓辰,刘爽,张强等.双目立体视觉测量模型与同名点匹配研究[J].仪器仪表学报,2005,8:11-13
[11]Luigi Di Stefano,Massimiliano Marchionni,Stefano Mattoccia.A fast area-based stereo matching algorithm[J].Image and Vision Computing,2004,22:983-1005
[12]廖素珍,杨华军.一种快速有效提取浓密视差图的方法[J].电子科技大学学报,2005,34(2):199-201
[13]李海滨,单文军,刘彬.双目立体视觉测距系统误差模型的研究[J].光学技术,2006,32(1):24-16
[14]洪露,马长山,谢宗安.基于遗传算法的神经网络权值优化[J].贵州工业大学学报,2003,32(6):48-51
[15]刘云霞.水下机器人运动系统的神经网络辨识[J].机械工程与自动化,2006,135(2):81-83
[16]尹建军.基于颜色差异的果实自动识别方法与双目定位技术研究[D].镇江:江苏大学博士学位论文,2006