基于全视域GA-SVR模型的鱼类行为双目视觉观测系统标定
|
摘要
针对大视场水下环境鱼类行为视觉观测系统较难准确标定的问题,该文以双目立体测量系统为例,提出一种基于全视域GA-SVR(genetic algorithm-support vector regression)模型的鱼类行为三维观测系统标定方法。该方法选用具有圆点靶标的方形标定板为标定工具,通过设计具备前后左右移动能力的简易滑动轨道,实现了标定板的全视域空间定位。然后利用HALCON算子获取标定板靶点二维坐标,联立标定板空间位置,构建训练样本集。选取SVR模型对样本集进行训练,对比不同的寻优算法对支持向量回归模型的参数组合寻优结果,选用最优参数分别建立X,Y,Z轴标定模型。试验结果表明,利用遗传算法进行参数寻优构建的标定模型,其X、Y、Z轴测量均方误差分别为0.959、0.893和4.381 mm,互相关系数分别为0.999 988,0.999 998和0.998 356,优于差分进化算法和粒子群算法参数寻优的标定结果。与传统标定方法比较,该方法单点测量均方误差为1.861 mm,距离测量均方误差为0.706 mm,均低于空气中标定方法(单点均方误差27.75 mm;距离均方误差10.188 mm)和水下测量标定方法(单点均方误差8.215 mm;距离均方误差2.832 mm)的标定结果,有效的提高了鱼类行为视觉观测系统的定位精度。该研究可为鱼类行为量化方法研究和优化提供理论支持和技术参考。
For reducing the calibration error and improving the measurement accuracy of fish behavior observation system, a binocular calibration method based on genetic algorithm-support vector regression(GA-SVR) is proposed to solve the problem of image distortion and light refraction, and realize the indirect calibration of underwater large field of view. In this paper, a standard board with 49 uniformly arranged circular targets points developed by HALCON is chosen for calibration. The diameter of the target is 35.5 mm, the center distance of two targets is 70 mm, and the size of the calibration board is 600 mm×600 mm. Furthermore, in order to reduce the dependence on precision instruments for full-view sampling, a sliding track with bidirectional mobile positioning ability is designed, which is manufactured by the high precision CNC(computerized numerical control) tool with accuracy of 0.05 mm. And along the short axis of the track, 17 pairs of slots are machined at 50 mm intervals to locate the calibration board longitudinal moving distance. A transverse moving bar is erected in the slots, and on which 3 pairs of slots are machined at 400 mm intervals. According to the slot positions, the calibration board is moved along the long axis and the moving rod is moved along the short axis respectively. Sample images are acquired at each slot position, so that the image of the calibration board can cover the whole space of fish tank. The calibration board is used as the basis to collect parallax coordinates and world coordinates, and then the complete sample sets are established in the entire effective vision field of the binocular system. The parallax coordinates of the target points are acquired by Halcon operators, and the relative position information of the calibration board is acquired according to the position of sliding track. The samples of target point used in this study include 2 352 targets from all 49 sample images. The SVR is selected to train the sample set, and three decision function with mathematical expression are established with model parameters calculated by the genetic algorithm. In this article the differential evolution(DE) algorithm, particle swarm optimization(PSO) algorithm and genetic algorithm(GA) are chosen to optimize the SVR parameters, and establish the calibration models respectively. The root mean square error(RMSE), single point error and cross-correlation coefficient are used as evaluation indicators. Based on evaluation results the optimal parameters are selected to establish the position calibration model in X, Y, Z axis respectively. Experimental results show that the genetic algorithm has better optimization effect than the other two algorithms. The mean square errors acquired of X, Y and Z axis are 0.959, 0.893 and 4.381 mm, and the correlation coefficients are 0.999 988, 0.999 998 and 0.998 356, respectively. Compared with traditional calibration methods, the single-point mean square error and distance mean square error of proposed method are 1.861 and 0.706 mm, which are lower than that of calibration method in air(single-point mean square error of 27.75 mm; distance mean square error of 10.188 mm) and underwater calibration methods(single-point mean square error of 8.215 mm; distance mean square error of 2.832 mm). This study could provide reference for quantitative methods of fish behavior.
For reducing the calibration error and improving the measurement accuracy of fish behavior observation system, a binocular calibration method based on genetic algorithm-support vector regression(GA-SVR) is proposed to solve the problem of image distortion and light refraction, and realize the indirect calibration of underwater large field of view. In this paper, a standard board with 49 uniformly arranged circular targets points developed by HALCON is chosen for calibration. The diameter of the target is 35.5 mm, the center distance of two targets is 70 mm, and the size of the calibration board is 600 mm×600 mm. Furthermore, in order to reduce the dependence on precision instruments for full-view sampling, a sliding track with bidirectional mobile positioning ability is designed, which is manufactured by the high precision CNC(computerized numerical control) tool with accuracy of 0.05 mm. And along the short axis of the track, 17 pairs of slots are machined at 50 mm intervals to locate the calibration board longitudinal moving distance. A transverse moving bar is erected in the slots, and on which 3 pairs of slots are machined at 400 mm intervals. According to the slot positions, the calibration board is moved along the long axis and the moving rod is moved along the short axis respectively. Sample images are acquired at each slot position, so that the image of the calibration board can cover the whole space of fish tank. The calibration board is used as the basis to collect parallax coordinates and world coordinates, and then the complete sample sets are established in the entire effective vision field of the binocular system. The parallax coordinates of the target points are acquired by Halcon operators, and the relative position information of the calibration board is acquired according to the position of sliding track. The samples of target point used in this study include 2 352 targets from all 49 sample images. The SVR is selected to train the sample set, and three decision function with mathematical expression are established with model parameters calculated by the genetic algorithm. In this article the differential evolution(DE) algorithm, particle swarm optimization(PSO) algorithm and genetic algorithm(GA) are chosen to optimize the SVR parameters, and establish the calibration models respectively. The root mean square error(RMSE), single point error and cross-correlation coefficient are used as evaluation indicators. Based on evaluation results the optimal parameters are selected to establish the position calibration model in X, Y, Z axis respectively. Experimental results show that the genetic algorithm has better optimization effect than the other two algorithms. The mean square errors acquired of X, Y and Z axis are 0.959, 0.893 and 4.381 mm, and the correlation coefficients are 0.999 988, 0.999 998 and 0.998 356, respectively. Compared with traditional calibration methods, the single-point mean square error and distance mean square error of proposed method are 1.861 and 0.706 mm, which are lower than that of calibration method in air(single-point mean square error of 27.75 mm; distance mean square error of 10.188 mm) and underwater calibration methods(single-point mean square error of 8.215 mm; distance mean square error of 2.832 mm). This study could provide reference for quantitative methods of fish behavior.
引文
[1]Kuroda Toshikazu.A system for the real-time tracking of operant behavior as an application of 3D camera[J].Journal of the Experimental Analysis of Behavior,2018,110(3):1-23.
[2]周应祺,王军,钱卫国,等.鱼类集群行为的研究进展[J].上海海洋大学学报,2013,22(5):734-743.Zhou Yingqi,Wang Jun,Qian Weiguo,et al.Review of fish schooling behavior study[J].Journal of Shanghai Ocean University,2013,22(5):734-743.(in Chinese with English abstract)
[3]刘世晶,王帅,陈军,等.基于改进主成分分析和Ada Boost算法的运动虾苗识别方法[J].农业工程学报,2017,33(1):212-218.Liu Shijing,Wang Shuai,Chen Jun,et al.Moving larval shrimps recognition based on improved principal component analysis and AdaBoost[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(1):212-218.(in Chinese with English abstract)
[4]Matthew D Campbell,Joseph Salisbury,Ryan Caillouet,et al.Camera field-of-view and fish abundance estimation:Acomparison of individual-based model output and empirical data[J].Journal of Experimental Marine Biology and Ecology,2018,501:46-53.
[5]Laurel B J,Laurel C J,Brown J A,et al.A new technique to gather 3-D spatial information using a single camera[J].Journal of Fish Biology,2005,66(2):429-441.
[6]徐盼麟,韩军,童剑锋.基于单摄像机视频的鱼类三维自动跟踪方法初探[J].水产学报,2012,36(4):623-628.Xu Panlin,Han Jun,Tong Jianfeng.Preliminary studies on an automated 3D fish tracking method based on a single video camera[J].Journal of Fisheries of China,2012,36(4):623-628.(in Chinese with English abstract)
[7]Gilbert A,Bonifasius P S,Stevhen J,et al.A simple setup to serform 3D locomotion tracking in zebrafish by using a single camera[J].Inventions,2018,3(1):11-14
[8]Mao J F,Xiao G,Sheng W G,et al.A 3D occlusion tracking model of the underwater fish targets[C]//IEEE International Conference on Electro/information Technology,2015:82-86.
[9]Santana Garcon J,Newman S J,Harvey E S.Development and validation of a mid-water baited stereo-video technique for investigating pelagic fish assemblages[J].Journal of Experimental Marine Biology and Ecology,2014,452:82-90.
[10]Bond T,Partridge J C,Taylor M D,et al.Fish associated with a subsea pipeline and adjacent seafloor of the North West Shelf of Western Australia[J].Marine Environmental Research,2018,141:53-65.
[11]Viscido S V,Parrish J K,Grünbaum D.Individual behavior and emergent properties of fish schools:A comparison of observation and theory[J].Marine Ecology Progress Series,2004,273:239-249.
[12]李林波,陈从平,吴喆,等.基于双目视觉的鱼类游动三维轨迹跟踪[J].三峡大学学报:自然科学版,2018,40(2):95-99.Li Linbo,Chen Congping,Wu Zhe,et al.Three-dimensional trajectory tracking of fish swimming based on binocular vision[J].Journal of China Three Gorges University:Natural Science Edition,2018,40(2):95-99.(in Chinese with English abstract)
[13]Zhang Zhengyou.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[14]徐杰,王宗义,刘涛,等.水下图像的校正[J].黑龙江科技学院学报,2008,18(2):133-136.Xu Jie,Wang Zongyi,Liu Tao,et al.Correction for underwater image[J].Journal of Heilongjiang Institute of Science and Technology,2008,18(2):133-136.(in Chinese with English abstract)
[15]张文明,邓茜雪,张强,等.基于非平行系统的水下图像转化模型[J].光子学报,2015,44(2):158-162.Zhang Wenming,Deng Xixue,Zhang Qiang,et al.Non-parallel system underwater image transformation model[J].Acta Photonica Sinica,2015,44(2):158-162.(in Chinese with English abstract)
[16]张强,王鑫,李海滨.基于粒子群优化的水下成像系统标定[J].光子学报,2014,43(1):109-113.Zhang Qiang,Wang Xin,Li Haibin.Calibration algorithm of underwater imaging system based on PSO[J].Acta Photonica Sinica,2014,43(1):109-113.(in Chinese with English abstract)
[17]Tu Junchao,Zhang Liyan.Laser projection positioning of spatial contour curves via a galvanometric scanner[J].Multimedia Tools and Applications,2018,10696(25):17-121.
[18]延和,吴斌.基于改进型神经网络的双目摄像机标定[J].西南科技大学学报,2013,28(4):66-70.Yan He,Wu Bin.Improved neural network for binocular camera calibration[J].Journal of Southwest University of Science and Technology,2013,28(4):66-70.(in Chinese with English abstract)
[19]刘小娟,李学军,王文韫,等.基于神经网络的虚拟靶标大视场双目相机标定技术[J].光学技术,2017,43(4):314-318.Liu Xiaojuan,Li Xuejun,Wang Wenyun,et al.Large-scale binocular camera calibration combining neural network with virtual target[J].Optical Technique,2017,43(4):314-318.(in Chinese with English abstract)
[20]金伟龙,周美英.基于不同BP网络层数的双目立体视觉标定研究[J].光学技术,2015,41(1):72-76.Jin Weilong,Zhou Meiying.Study on calibration of binocular stereovision based on BP neural network with different layers[J].Optical Technique,2015,41(1):72-76.(in Chinese with English abstract)
[21]刘胜,傅荟璇,王宇超.基于分割区间LS-SVM的摄像机标定[J].计算机工程,2009,35(24):179-181.Liu Sheng,Fu Huixuan,Wang Yuchao.Camera calibration based on divided region LS-SVM[J].Computer Engineering,2009,35(24):179-181.(in Chinese with English abstract)
[22]张从鹏,刘重阳.基于机器视觉的UVW定位系统[J].机床与液压,2018,46(14):108-110,127.Zhang Congpeng,Liu Chongyang.UVW positioning system based on machine vision[J].Machine Tool and Hydraulics,2018,46(14):108-110,127.(in Chinese with English abstract)
[23]尹晓艮,张晓芳,张伟超,等.基于光场数字重聚焦的三维重建方法研究[J].光电子·激光,2015,26(5):986-991.Yin Xiaogen,Zhang Xiaofang,Zhang Weichao,et al.Study on 3D reconstruction based on light field digital refocusing[J].Journal of Optoelectronics·Laser,2015,26(5):986-991.(in Chinese with English abstract)
[24]崔东文.几种智能算法与支持向量机融合模型在中长期月径流预测中的应用[J].华北水利水电大学学报,2016(5):51-57.Cui Dongwen.Application of several intelligent algorithms and support vector machine fusion model in medium and long term runoff forecasting[J].North China Institute of Water Conservancy and Hydroelectric Power,2016(5):51-57.(in Chinese with English abstract)
[25]孙俊,莫云南,戴春霞,等.基于介电特性与IRIV-GWO-SVR算法的番茄叶片含水率检测[J].农业工程学报,2018,34(14):188-195.Sun Jun,Mo Yunnan,Dai Chunxia,et.al.Detection of moisture content of tomato leaves based on dielectric properties and IRIV-GWO-SVR algorithm[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2018,34(14):188-195.(in Chinese with English abstract)
[26]段青玲,张磊,魏芳芳,等.基于时间序列GA-SVR的水产品价格预测模型及验证[J].农业工程学报,2017,33(1):308-314.Duan Qingling,Zhang Lei,Wei Fangfang,et.al.Forecasting model and validation for aquatic product price based on time series GA-SVR[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(1):308-314.(in Chinese with English abstract)
[27]王海军,柳敏燕,高娟.利用遗传算法和支持向量机测算农用地理论单产和可实现单产[J].农业工程学报,2013,29(19):244-252.Wang Haijun,Liu Minyan,Gao Juan.Calculation of theoretical and accessible yields of agricultural land based on geneticalgorithm and support vector machine[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2013,29(19):244-252.(in Chinese with English abstract)
[28]孙俊,张国坤,毛罕平,等.基于介电特性与回归算法的玉米叶片含水率无损检测[J].农业机械学报,2016,47(4):257-264.Sun Jun,Zhang Guokun,Mao Hanping,et al.Nondestructive moisture content detection of corn leaves based on dielectric properties and regression algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(4):257-264.(in Chinese with English abstract)
[29]Foucard R,Essid S,Richard G,et al.Exploring new features for music classification[C]//IEEE Transportation on 201314th International Workshop on Image Analysis for Multimedia Interactive Services,2013:1-4.
[30]果佳良.基于计算机视觉的鱼类三维行为监测研究及应用[D].秦皇岛:燕山大学,2011.Guo Jialiang.Fish Behavior of Three-Dimensional monitoring Research and Application Based on Computer Vision[D].Qinhuangdao:Yanshan University,2011.(in Chinese with English abstract)
[31]高新浩,黄茹楠,杨育林.水下相机标定算法研究[J].燕山大学学报,2014,38(3):252-258.Gao Xinhao,Huang Runan,Yang Yulin.Study on underwater camera calibration algorithm[J].Journal of Yanshan University,2014,38(3):252-258.(in Chinese with English abstract)
[32]He Lei,Wang Guanghui,Hu Zhanyi.Learning depth from single images with deep neural network embedding focal length[J].IEEE permission On Image Processing,2018,27(9):4676-4689.
[33]黄小云,高峰,徐国艳,等.基于单幅立式标靶图像的单目深度信息提取[J].北京航空航天大学学报,2015,41(4):649-655.Huang Xiaoyun,Gao Feng,Xu Guoyan,et al.Depth Information extraction of on-board monocular vision based on a single vertical target image[J].Journal of Beijing University of Aeronautics and Astronautics,2015,41(4):649-655.(in Chinese with English abstract)
[2]周应祺,王军,钱卫国,等.鱼类集群行为的研究进展[J].上海海洋大学学报,2013,22(5):734-743.Zhou Yingqi,Wang Jun,Qian Weiguo,et al.Review of fish schooling behavior study[J].Journal of Shanghai Ocean University,2013,22(5):734-743.(in Chinese with English abstract)
[3]刘世晶,王帅,陈军,等.基于改进主成分分析和Ada Boost算法的运动虾苗识别方法[J].农业工程学报,2017,33(1):212-218.Liu Shijing,Wang Shuai,Chen Jun,et al.Moving larval shrimps recognition based on improved principal component analysis and AdaBoost[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(1):212-218.(in Chinese with English abstract)
[4]Matthew D Campbell,Joseph Salisbury,Ryan Caillouet,et al.Camera field-of-view and fish abundance estimation:Acomparison of individual-based model output and empirical data[J].Journal of Experimental Marine Biology and Ecology,2018,501:46-53.
[5]Laurel B J,Laurel C J,Brown J A,et al.A new technique to gather 3-D spatial information using a single camera[J].Journal of Fish Biology,2005,66(2):429-441.
[6]徐盼麟,韩军,童剑锋.基于单摄像机视频的鱼类三维自动跟踪方法初探[J].水产学报,2012,36(4):623-628.Xu Panlin,Han Jun,Tong Jianfeng.Preliminary studies on an automated 3D fish tracking method based on a single video camera[J].Journal of Fisheries of China,2012,36(4):623-628.(in Chinese with English abstract)
[7]Gilbert A,Bonifasius P S,Stevhen J,et al.A simple setup to serform 3D locomotion tracking in zebrafish by using a single camera[J].Inventions,2018,3(1):11-14
[8]Mao J F,Xiao G,Sheng W G,et al.A 3D occlusion tracking model of the underwater fish targets[C]//IEEE International Conference on Electro/information Technology,2015:82-86.
[9]Santana Garcon J,Newman S J,Harvey E S.Development and validation of a mid-water baited stereo-video technique for investigating pelagic fish assemblages[J].Journal of Experimental Marine Biology and Ecology,2014,452:82-90.
[10]Bond T,Partridge J C,Taylor M D,et al.Fish associated with a subsea pipeline and adjacent seafloor of the North West Shelf of Western Australia[J].Marine Environmental Research,2018,141:53-65.
[11]Viscido S V,Parrish J K,Grünbaum D.Individual behavior and emergent properties of fish schools:A comparison of observation and theory[J].Marine Ecology Progress Series,2004,273:239-249.
[12]李林波,陈从平,吴喆,等.基于双目视觉的鱼类游动三维轨迹跟踪[J].三峡大学学报:自然科学版,2018,40(2):95-99.Li Linbo,Chen Congping,Wu Zhe,et al.Three-dimensional trajectory tracking of fish swimming based on binocular vision[J].Journal of China Three Gorges University:Natural Science Edition,2018,40(2):95-99.(in Chinese with English abstract)
[13]Zhang Zhengyou.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[14]徐杰,王宗义,刘涛,等.水下图像的校正[J].黑龙江科技学院学报,2008,18(2):133-136.Xu Jie,Wang Zongyi,Liu Tao,et al.Correction for underwater image[J].Journal of Heilongjiang Institute of Science and Technology,2008,18(2):133-136.(in Chinese with English abstract)
[15]张文明,邓茜雪,张强,等.基于非平行系统的水下图像转化模型[J].光子学报,2015,44(2):158-162.Zhang Wenming,Deng Xixue,Zhang Qiang,et al.Non-parallel system underwater image transformation model[J].Acta Photonica Sinica,2015,44(2):158-162.(in Chinese with English abstract)
[16]张强,王鑫,李海滨.基于粒子群优化的水下成像系统标定[J].光子学报,2014,43(1):109-113.Zhang Qiang,Wang Xin,Li Haibin.Calibration algorithm of underwater imaging system based on PSO[J].Acta Photonica Sinica,2014,43(1):109-113.(in Chinese with English abstract)
[17]Tu Junchao,Zhang Liyan.Laser projection positioning of spatial contour curves via a galvanometric scanner[J].Multimedia Tools and Applications,2018,10696(25):17-121.
[18]延和,吴斌.基于改进型神经网络的双目摄像机标定[J].西南科技大学学报,2013,28(4):66-70.Yan He,Wu Bin.Improved neural network for binocular camera calibration[J].Journal of Southwest University of Science and Technology,2013,28(4):66-70.(in Chinese with English abstract)
[19]刘小娟,李学军,王文韫,等.基于神经网络的虚拟靶标大视场双目相机标定技术[J].光学技术,2017,43(4):314-318.Liu Xiaojuan,Li Xuejun,Wang Wenyun,et al.Large-scale binocular camera calibration combining neural network with virtual target[J].Optical Technique,2017,43(4):314-318.(in Chinese with English abstract)
[20]金伟龙,周美英.基于不同BP网络层数的双目立体视觉标定研究[J].光学技术,2015,41(1):72-76.Jin Weilong,Zhou Meiying.Study on calibration of binocular stereovision based on BP neural network with different layers[J].Optical Technique,2015,41(1):72-76.(in Chinese with English abstract)
[21]刘胜,傅荟璇,王宇超.基于分割区间LS-SVM的摄像机标定[J].计算机工程,2009,35(24):179-181.Liu Sheng,Fu Huixuan,Wang Yuchao.Camera calibration based on divided region LS-SVM[J].Computer Engineering,2009,35(24):179-181.(in Chinese with English abstract)
[22]张从鹏,刘重阳.基于机器视觉的UVW定位系统[J].机床与液压,2018,46(14):108-110,127.Zhang Congpeng,Liu Chongyang.UVW positioning system based on machine vision[J].Machine Tool and Hydraulics,2018,46(14):108-110,127.(in Chinese with English abstract)
[23]尹晓艮,张晓芳,张伟超,等.基于光场数字重聚焦的三维重建方法研究[J].光电子·激光,2015,26(5):986-991.Yin Xiaogen,Zhang Xiaofang,Zhang Weichao,et al.Study on 3D reconstruction based on light field digital refocusing[J].Journal of Optoelectronics·Laser,2015,26(5):986-991.(in Chinese with English abstract)
[24]崔东文.几种智能算法与支持向量机融合模型在中长期月径流预测中的应用[J].华北水利水电大学学报,2016(5):51-57.Cui Dongwen.Application of several intelligent algorithms and support vector machine fusion model in medium and long term runoff forecasting[J].North China Institute of Water Conservancy and Hydroelectric Power,2016(5):51-57.(in Chinese with English abstract)
[25]孙俊,莫云南,戴春霞,等.基于介电特性与IRIV-GWO-SVR算法的番茄叶片含水率检测[J].农业工程学报,2018,34(14):188-195.Sun Jun,Mo Yunnan,Dai Chunxia,et.al.Detection of moisture content of tomato leaves based on dielectric properties and IRIV-GWO-SVR algorithm[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2018,34(14):188-195.(in Chinese with English abstract)
[26]段青玲,张磊,魏芳芳,等.基于时间序列GA-SVR的水产品价格预测模型及验证[J].农业工程学报,2017,33(1):308-314.Duan Qingling,Zhang Lei,Wei Fangfang,et.al.Forecasting model and validation for aquatic product price based on time series GA-SVR[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(1):308-314.(in Chinese with English abstract)
[27]王海军,柳敏燕,高娟.利用遗传算法和支持向量机测算农用地理论单产和可实现单产[J].农业工程学报,2013,29(19):244-252.Wang Haijun,Liu Minyan,Gao Juan.Calculation of theoretical and accessible yields of agricultural land based on geneticalgorithm and support vector machine[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2013,29(19):244-252.(in Chinese with English abstract)
[28]孙俊,张国坤,毛罕平,等.基于介电特性与回归算法的玉米叶片含水率无损检测[J].农业机械学报,2016,47(4):257-264.Sun Jun,Zhang Guokun,Mao Hanping,et al.Nondestructive moisture content detection of corn leaves based on dielectric properties and regression algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(4):257-264.(in Chinese with English abstract)
[29]Foucard R,Essid S,Richard G,et al.Exploring new features for music classification[C]//IEEE Transportation on 201314th International Workshop on Image Analysis for Multimedia Interactive Services,2013:1-4.
[30]果佳良.基于计算机视觉的鱼类三维行为监测研究及应用[D].秦皇岛:燕山大学,2011.Guo Jialiang.Fish Behavior of Three-Dimensional monitoring Research and Application Based on Computer Vision[D].Qinhuangdao:Yanshan University,2011.(in Chinese with English abstract)
[31]高新浩,黄茹楠,杨育林.水下相机标定算法研究[J].燕山大学学报,2014,38(3):252-258.Gao Xinhao,Huang Runan,Yang Yulin.Study on underwater camera calibration algorithm[J].Journal of Yanshan University,2014,38(3):252-258.(in Chinese with English abstract)
[32]He Lei,Wang Guanghui,Hu Zhanyi.Learning depth from single images with deep neural network embedding focal length[J].IEEE permission On Image Processing,2018,27(9):4676-4689.
[33]黄小云,高峰,徐国艳,等.基于单幅立式标靶图像的单目深度信息提取[J].北京航空航天大学学报,2015,41(4):649-655.Huang Xiaoyun,Gao Feng,Xu Guoyan,et al.Depth Information extraction of on-board monocular vision based on a single vertical target image[J].Journal of Beijing University of Aeronautics and Astronautics,2015,41(4):649-655.(in Chinese with English abstract)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |