智能交通系统中视频目标检测与识别的关键算法研究
|
摘要
视频目标的检测、识别是目前智能交通和计算机视觉领域中的一个重要研究方向。但是，由于检测和识别环境下存在背景复杂、光照变化、目标遮挡等原因，导致该应用仍面临着许多困难，检测和识别的鲁棒性及准确性都有待进一步提高。
本论文对视频目标检测和识别中的几个关键问题进行了研究，主要包括：复杂场景下目标与背景、阴影的准确分割；对提取的前景目标准确分类；复杂背景下的目标识别。针对这些问题，本论文提出了相应的解决方法。具体工作如下：
1.提出了一种基于自适应模糊估计的背景建模方法。该方法从函数估计的角度对背景进行建模，并采用TSK模糊系统作为估计函数。为了训练函数估计算子，分别使用粒子群优化（PSO）算法和递归最小二乘估计（RLSE）算法来优化模糊系统的前件参数和后件参数。为了有效估计背景，将前景像素看作背景像素的异常样例，并提出了异常样例的去除方法，然后用去除后的结果去训练模糊估计算子。该方法在动态背景、光照变化、摄像机振动等环境下都具有较高的运行效率和检测效果。
2.提出了一种基于模糊积分的运动阴影检测方法。在提取前景区域的基础上，选择颜色和纹理作为阴影检测的特征，并分别定义了这两种特征的相似性和重要性测度函数，然后通过Choquet模糊积分将这两种特征融合，实现阴影和前景目标的分类，最后通过后续处理，找到真正的阴影区域。
3.提出了一种基于JointBoost I2C距离度量的目标分类方法。针对经典I2C距离计算量大且易受噪声干扰等不足，首先提出了一种原型特征集的生成方法，该集合中的样本数量较少，但更具有代表性，计算测试图像到该原型特征集的距离花费较少时间；然后借助JointBoost算法的思想，联合多个I2C距离度量生成一个强分类器；最后还提出了一种将空间信息融合到强分类器的方法。实验证明，该方法在前景目标和图像分类实验中，具有更高的分类性能。
4.提出了基于特征码本树和能量最小化的目标识别方法。该方法考虑了特征的空间位置信息和特征之间的空间关系，集成了目标检测和目标识别。首先从目标图像提取的大量特征中过滤掉噪声特征；然后对单特征和空间上邻近的串联双特征分别使用层次k均值聚类算法构建特征码本树，利用树模型可以实现特征快速定位和分类；最后建立一个能量函数来融合单、双特征码本树的类别概率匹配结果，并通过在测试图像中寻找滑动窗口所在区域的能量最小化来确定所属类别目标的位置。
5.提出了基于优化Hough森林代价损失的目标识别方法。首先在充分利用训练图像中对象位置是已知的基础上,提出了改进的偏移量不确定性度量方法；其次借助Boosting算法的思想，学习图片块样本和目标对象样本的自适应权重分布，并分别优化用于构造随机树和Hough森林的代价损失函数；最后根据图片块样本的权重分布，提出了改进的类标志不确定性度量方法。基于Hough森林的代价损失函数，还提出了随机树权重的学习方法。
Visual object detection and recognition is an important research direction of theintelligent transportation and computer vision.However, complex background, illuminationchanges, object shielding and so on in practical detection and recognition environment is stillfacing many difficulties, so the robustness and accuracy of handling these proplems should befurther improved.
Some key issues of visual object and recognition are researched in this dissertation,which mainly include: accurate segmentation of background, objects and shadows undercomplex scene, accurate classification of the extracted foreground objects, object recognitionunder complex background.Motivated by these isssues, the corresponding solutions areproposed in this thesis.Specific studies as follows:
1. A new adaptive fuzzy estimate method for background modeling is proposed.Thismethod models background from the perspective of function estimation, and uses TSK fuzzysystem as the estimated function.In order to train the function estimator, the proposedapproach combines both the particle swarm optimization (PSO) and the recursive leastsquares estimator (RLSE) to optimze the parameters of the premise part and consequent partof the fuzzy system. In order to effectively estimate background, we interpret foregroundsamples as outliers relative to the background ones and so propose an outlier Separatormethod. After the outliers are removed, the obtained results are used to train the fuzzyestimator. This method has the high accuracy and effectiveness in dynamic background,illumination changes, camera vibration and so on.
2. A new shadow detection method based on choquet fuzzy integral is proposed. Afterthe foreground area is ectracted, this method chooses color and texture as detection features,and defines their similarity and feature importance degree measure functions. Then, thesemeasures are integrated by using the choquet integral in order to initially find shadow andforeground. Finally, the real the shadow areas is distinguished after the subsequent processingstep.
3. A new visual object classification method based on JointBoost I2C distance metric.Because the I2C distance has the expensive computation cost, and it is also easily affected bynoise features. At first, we propose to generate a prototype feature set, which has fewersamples, but more representative.The distance calculation of test image to this set can spendless time. And then, we adopt the idea of JointBoost algorithm, combine multiple I2C distance metric to generate a strong classifier, and also propose a spatial information fusion method.Experimental results show that the proposed method has higher classification performance inforeground object and image classification.
4. A new visual object recognition method based on feature vocabulary tree and energyminimization is proposed. This method takes into account the spatial position information oflocal features and the spatial relationships between local features, and combines objectdetection and classification. At first, a large number of features extracted from object imageare filtered. And then, the single feature and concatenated pairwise feaures are respectivelyused to build the vocabulary trees by using hierarchical k-means clustering algorithm, thetree-structure has the advantages of the fast lookup feature localization and calssification.wefinally built an energy function combing the matched class probability results of these twovocabulary trees, and then the visual object location and object type are known by minimizingthe energy function of the sliding window in test image.
5. A new visual object recognition method based on optimizing Hough forest cost lossfunction is proposed. At first, we propose an improved offset uncertainty measure, exploitingthe knowledge of the object locations in the training images. And then, we adopt the idea ofBoosting algorithm to learn the adaptive weight distribution over the image patch samples andobject image samples, and respectively optimize the cost loss function of constructing randomtree and Hough forest. At last, we propose an improved class uncertainty measure by usingthe weight distribution of the image patch samples, and also give a learning method ofrandom tree weight based on Hough forest cost loss function.
本论文对视频目标检测和识别中的几个关键问题进行了研究，主要包括：复杂场景下目标与背景、阴影的准确分割；对提取的前景目标准确分类；复杂背景下的目标识别。针对这些问题，本论文提出了相应的解决方法。具体工作如下：
1.提出了一种基于自适应模糊估计的背景建模方法。该方法从函数估计的角度对背景进行建模，并采用TSK模糊系统作为估计函数。为了训练函数估计算子，分别使用粒子群优化（PSO）算法和递归最小二乘估计（RLSE）算法来优化模糊系统的前件参数和后件参数。为了有效估计背景，将前景像素看作背景像素的异常样例，并提出了异常样例的去除方法，然后用去除后的结果去训练模糊估计算子。该方法在动态背景、光照变化、摄像机振动等环境下都具有较高的运行效率和检测效果。
2.提出了一种基于模糊积分的运动阴影检测方法。在提取前景区域的基础上，选择颜色和纹理作为阴影检测的特征，并分别定义了这两种特征的相似性和重要性测度函数，然后通过Choquet模糊积分将这两种特征融合，实现阴影和前景目标的分类，最后通过后续处理，找到真正的阴影区域。
3.提出了一种基于JointBoost I2C距离度量的目标分类方法。针对经典I2C距离计算量大且易受噪声干扰等不足，首先提出了一种原型特征集的生成方法，该集合中的样本数量较少，但更具有代表性，计算测试图像到该原型特征集的距离花费较少时间；然后借助JointBoost算法的思想，联合多个I2C距离度量生成一个强分类器；最后还提出了一种将空间信息融合到强分类器的方法。实验证明，该方法在前景目标和图像分类实验中，具有更高的分类性能。
4.提出了基于特征码本树和能量最小化的目标识别方法。该方法考虑了特征的空间位置信息和特征之间的空间关系，集成了目标检测和目标识别。首先从目标图像提取的大量特征中过滤掉噪声特征；然后对单特征和空间上邻近的串联双特征分别使用层次k均值聚类算法构建特征码本树，利用树模型可以实现特征快速定位和分类；最后建立一个能量函数来融合单、双特征码本树的类别概率匹配结果，并通过在测试图像中寻找滑动窗口所在区域的能量最小化来确定所属类别目标的位置。
5.提出了基于优化Hough森林代价损失的目标识别方法。首先在充分利用训练图像中对象位置是已知的基础上,提出了改进的偏移量不确定性度量方法；其次借助Boosting算法的思想，学习图片块样本和目标对象样本的自适应权重分布，并分别优化用于构造随机树和Hough森林的代价损失函数；最后根据图片块样本的权重分布，提出了改进的类标志不确定性度量方法。基于Hough森林的代价损失函数，还提出了随机树权重的学习方法。
Visual object detection and recognition is an important research direction of theintelligent transportation and computer vision.However, complex background, illuminationchanges, object shielding and so on in practical detection and recognition environment is stillfacing many difficulties, so the robustness and accuracy of handling these proplems should befurther improved.
Some key issues of visual object and recognition are researched in this dissertation,which mainly include: accurate segmentation of background, objects and shadows undercomplex scene, accurate classification of the extracted foreground objects, object recognitionunder complex background.Motivated by these isssues, the corresponding solutions areproposed in this thesis.Specific studies as follows:
1. A new adaptive fuzzy estimate method for background modeling is proposed.Thismethod models background from the perspective of function estimation, and uses TSK fuzzysystem as the estimated function.In order to train the function estimator, the proposedapproach combines both the particle swarm optimization (PSO) and the recursive leastsquares estimator (RLSE) to optimze the parameters of the premise part and consequent partof the fuzzy system. In order to effectively estimate background, we interpret foregroundsamples as outliers relative to the background ones and so propose an outlier Separatormethod. After the outliers are removed, the obtained results are used to train the fuzzyestimator. This method has the high accuracy and effectiveness in dynamic background,illumination changes, camera vibration and so on.
2. A new shadow detection method based on choquet fuzzy integral is proposed. Afterthe foreground area is ectracted, this method chooses color and texture as detection features,and defines their similarity and feature importance degree measure functions. Then, thesemeasures are integrated by using the choquet integral in order to initially find shadow andforeground. Finally, the real the shadow areas is distinguished after the subsequent processingstep.
3. A new visual object classification method based on JointBoost I2C distance metric.Because the I2C distance has the expensive computation cost, and it is also easily affected bynoise features. At first, we propose to generate a prototype feature set, which has fewersamples, but more representative.The distance calculation of test image to this set can spendless time. And then, we adopt the idea of JointBoost algorithm, combine multiple I2C distance metric to generate a strong classifier, and also propose a spatial information fusion method.Experimental results show that the proposed method has higher classification performance inforeground object and image classification.
4. A new visual object recognition method based on feature vocabulary tree and energyminimization is proposed. This method takes into account the spatial position information oflocal features and the spatial relationships between local features, and combines objectdetection and classification. At first, a large number of features extracted from object imageare filtered. And then, the single feature and concatenated pairwise feaures are respectivelyused to build the vocabulary trees by using hierarchical k-means clustering algorithm, thetree-structure has the advantages of the fast lookup feature localization and calssification.wefinally built an energy function combing the matched class probability results of these twovocabulary trees, and then the visual object location and object type are known by minimizingthe energy function of the sliding window in test image.
5. A new visual object recognition method based on optimizing Hough forest cost lossfunction is proposed. At first, we propose an improved offset uncertainty measure, exploitingthe knowledge of the object locations in the training images. And then, we adopt the idea ofBoosting algorithm to learn the adaptive weight distribution over the image patch samples andobject image samples, and respectively optimize the cost loss function of constructing randomtree and Hough forest. At last, we propose an improved class uncertainty measure by usingthe weight distribution of the image patch samples, and also give a learning method ofrandom tree weight based on Hough forest cost loss function.
引文
[1] Remagnino P，Tan T，Baker K．Multi-agent visual surveillance of dynamic scenes[J]．Image and Vision Computing，1998，16(8)：529-532
[2]凌志刚，赵春晖，梁彦，等．基于视觉的人行为理解综述[J]．计算机应用研究，2008，25(9)：2570-2578
[3] Zhu Z，Xu G，Yang B，et al．VISATRAM：A real-time vision system for automatic trafficmonitoring [J]．Image and Vision Computing，2000，18(10)：781-794
[4] Tai J，Tsang S，Lin C，et al．Real-time image tracking for automatic traffic monitoring andenforcement application [J]．Image and Vision Computing，2004，22(6)：485-501
[5] Li Q，Zheng N N，Cheng H．Springrobot：a prototype autonomous vehicle and itsalgorithms for lane detection[J]． IEEE Transactions on Intelligent TransportationSystems，2004，5(4)：300-308
[6]王智灵，周露平，陈宗海．针对不同信息特征的鲁棒背景建模技术分析[J]．模式识别与人工智能，2009，22(2)：240-245
[7] Sanin A，Sanderson C，Lovell B C．Shadow detection：A survey and comparativeevaluation of recent methods [J]．Pattern recognition，2012，45(4)：1684-1695
[8] Al Najdawi N，Bez H E，Singhai J，et al．A survey of cast shadow detection algorithms[J]．Pattern Recognition Letters，2012，33(6)：752-764
[9] Pooja Kamavisdar，Sonam Saluja，Sonu Agrawal．A Survey on Image Classification[J]．Internaltional Journal of Advanced Research in Computer and CommunicationEngineering，2013，2(1)：1005-1009
[10] Prasad D K．Survey of the problem of object detection in real images[J]．InternationalJournal of Image Processing，2012，6(6)：441-466
[11] Chu Y W，Liu T L．Co-occurrence random forests for object localization andclassification[C]//Asian Conference on Computer Vision，Xi’an，China，2009：621-632
[12] Liu Z，Xiong H．Object detection and localization using random forest[C]//InternationalConference on Intelligent System Design and Engineering Application， Sanya，China，2012：1074-1078
[13] Wang L，Hu W，Tan T．Recent developments in human motion analysis[J]． Patternrecognition，2003，36(3)：585-601
[14] Sen-Ching S C， Kamath C．Robust techniques for background subtraction in urbantraffic video[C]//International Society for Optics and Photonics Electronic Imaging，San Jose，CA，United States，2004：881-892
[15] Barron J L，Fleet D J，Beauchemin S S．Performance of optical flow techniques[J]．International journal of computer vision，1994，12(1)：43-77
[16]吴振杰．基于改进光流法的运动目标检测与跟踪系统[D]．河南：郑州大学，2012
[17]张泽旭，李金宗，李宁宁．基于光流场分割和Canny边缘提取融合算法的运动目标检测[J]．电子学报，2003，31(9)：1299-1302
[18]戴斌，方宇强，孙振平，王亮．基于光流技术的运动目标检测和跟踪方法研究[J]．科技导报2009,27(12)：55-60
[19]王静静，林明秀，魏颖．基于灰度相关的帧间差分和背景差分相融合的实时目标检测[J]．中南大学学报（自然科学版），2009，40(1)：142-148
[20]王小峰，王吉华，王远鹏，等．混合高斯模型和差分法相融合的运动目标检测[J]．小型微型计算机系统，2013，34(3)：685-688
[21]袁国庆，陈志强，龚健，等．一种结合光流法与三帧差分法的运动目标检测算法[J]．小微型计算机系统，2013，34(3)：668-671
[22]解晓萌．复杂背景下运动目标检测和识别关键技术研究[D]．广州：华南理工大学，2012
[23] Chu J，Miao J，Zhang G，et al．Edge and corner detection by color invariants[J]．Optics&Laser Technology，2013，45：756-762
[24]岑峰．视频监控系统中面向人的目标跟踪技术研究[D]．上海：上海交通大学，2002
[25] Gavrila D M，Munder S．Multi-cue pedestrian detection and tracking from a movingvehicle [J]．International Journal of Computer Vision，2007，73(1)：41-59
[26]陈国栋，孙立宁，杜志江，等．一种利用形状片段的物体检测方法[J]．自动化学报，2011，37(4)：427-439
[27] Lee H J， Hong K S．Class-Specifc Weighted Dominant Orientation Templates forObject Detection [C]//Asian Conference on Computer Vision，Daejeon， Korea，2012：97-108
[28] Crivelli T，Bouthemy P，Cernuschi-Frías B，et al．Simultaneous motion detection andbackground reconstruction with a conditional mixed-state markov randomfield[J]．International journal of computer vision，2011，94(3)：295-316
[29] Viola P，Jones M．Rapid object detection using a boosted cascade of simple features[C]//IEEE International Conference on Computer Vision and Pattern Recognition，Kauai，HI，USA，2001，1：511-518
[30]胡正平，杨建秀．HOG特征混合模型结合隐SVM的感兴趣目标检测定位算法[J]．信号处理，2011，27(8)：1206-1212
[31] Lowe D M．Distinctive image features from scale-invariant keypoints [J]．InternationalJournal of Computer Vision，2004，60(2)：91-110
[32] Ke Y， Sukthankar R．PCA-SIFT：A More Distinctive Representation for Local ImageDescriptors[C]//IEEE International Conference on Computer Vision and PatternRecognition，Washington，DC，USA，2004，2：506-513
[33] Zhu S． Statistical modeling and conceptualization of visual patterns[J]． IEEETransactions on Pattern Analysis and Machine Intelligence，2003，25(6)：691-712
[34] Bay H，Tuytelaars T，Van Gool L．Surf：Speeded up robust features[C]//EuropeanConference on Computer Vision，Graz，Austria，2006：404-417
[35] Dalal Navneet，Triggs Bill．Histograms of oriented gradients for human detection [C]//IEEE Conference on Computer Vision and Pattern Recognition，San Diego，CA，Unitedstates，2005：886-893
[36] Wang Xiaoyu，Han Tony X，Yan Shuicheng．An HOG-LBP Human Detector withPartial Occlusion Handling [C]//IEEE International Conference on Computer Vision，Kyoto，JAPAN，2009：32-39
[37] Yangwei Pang，Yuan Yuan，Xuelong Li，Jing Pan．Efficient HOG human detection[J]．Signal Processing，2011，91(4)：773-781
[38] Ojala T，Pietikainen M，Harwood D．Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions[C]//InternationalConference on Pattern Recognition，1994，1：582-585
[39] Ojala T，Pietikainen M，Maenpaa T．Multiresolution gray-scale and rotation-invarianttexture classification with local binary patterns[J]． IEEE Transactions on PatternAnalysis and Machine Intelligence，2002，24(7)：971-986
[40] Ahonen T，Hadid A，Pietik inen M．Face recognition with local binary patterns[C]//European Conference on Computer Vision，Prague，Czech，2004：469-481
[41] Pietik inen M．Image analysis with local binary patterns[J]．Image Analysis，2005，35(40)：115-118
[42] Lange M M，Novikov N A．Bayes classifier based on tree-structured Gaussian mixtures[J]．Pattern Recognition and Image Analysis，2012，22(1)：136-143
[43]李玲玲，金泰松，李翠华．基于局部特征和隐条件随机场的场景分类方法[J]．北京理工大学学报，2012，32(007)：720-724
[44] Qureshi I M， Jalil A． Object Recognition Using ANN with BackpropogationAlgorithm[J]． Pakistan Journal of Applied Sciences，2002，2(3)：281-287
[45] Park K，Shen C，Hao Z，et al．Efficiently learning a distance metric for large marginnearest neighbor classification[C]//Proceedings of the25th AAAI Conference onArtificial Intelligence，San Francisco，California， USA，2011：453-458
[46] Wang J，Neskovic P，Cooper L N．Improving nearest neighbor rule with a simpleadaptive distance measure[J]．Pattern Recognition Letters，2007，28(2)：207-213
[47] Noh Y K，Zhang B T，Lee D D．Generative local metric learning for nearest neighborclassification[J]．Advances in Neural Information Processing Systems,2010,18：417-424
[48] Wang Z，Hu Y，Chia L T．Improved learning of I2C distance and accelerating theneighborhood search for image classification[J]．Pattern Recognition，2011，44(10)：2384-2394
[49] Aci M， Avci M． K nearest neighbor reinforced expectation maximizationmethod[J]．Expert Systems with Applications，2011，38(10)：12585-12591
[50] Xu Y，Zhu Q，Fan Z，et al．Coarse to fine K nearest neighbor classifier[J]．PatternRecognition Letters，2013，34(9)：980-986
[51] Liu Z，Pan Q，Dezert J．A new belief-based K-nearest neighbor classificationmethod[J]．Pattern Recognition，2012，46(3)：834-844
[52] Felzenszwalb P F，Girshick R B，McAllester D，et al．Object detection withdiscriminatively trained part-based models[J]． Pattern Analysis and MachineIntelligence， IEEE Transactions on，2010，32(9)：1627-1645
[53] Zhu L，Chen Y，Yuille A，et al．Latent hierarchical structural learning for objectdetection[C]//IEEE Conference on Computer Vision and Pattern Recognition，SanFrancisco，CA，USA，2010：1062-1069
[54] Deselaers T，Heigold G，Ney H．Object classification by fusing SVMs and Gaussianmixtures[J]．Pattern Recognition，2010，43(7)：2476-2484
[55] Maji S，Berg A，Malik J．Efficient classification for additive kernel SVMs[J]．2013，35(1)：66-77
[56] Freund Y，Schapire R E．A decision-theoretic generalization of on-line learning and anapplication to boosting[J]．Journal of computer and system sciences，1997，55(1)：119-139
[57]李闯，丁晓青，吴佑寿．一种改进的AdaBoost算法—AD AdaBoost [J]．计算机学报，2007，30(1)：103–109
[58]李文辉，倪洪印．一种改进的Adaboost训练算法[J]．吉林大学学报(理学版)，2011，49(3)：498–504
[59] Mason L，Baxter J，Bartlett P，et al．Boosting algorithms as gradient descent in functionspace[C]．NIPS，Denver，Colorado，1999：512-518
[60] Torralba A，Murphy K P，Freeman W T．Sharing visual features for multiclass andmultiview object detection[J]． Pattern Analysis and Machine Intelligence， IEEETransactions on，2007，29(5)：854-869
[61] Huang Z F，Yang W，Wang Y，et al．Latent Boosting for Action Recognition[C]//BritishMachine Vision Conference，Dundee，2011：1-11
[62] Garcia C，Delakis M．Convolutional face finder: A neural architecture for fast and robustface detection[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence，2004，26(11)：1408-1423
[63] Jürgen Gall，Victor Lempitsky．Class-specific Hough forests for object detection [C]//IEEE Conference on Computer Vision and Pattern Recognition，Miami，FL， USA，2009：1022-1029
[64] Schwartz W R，Kembhavi A，Harwood D，et al．Human detection using partial leastsquares analysis[C]//IEEE International Conference on Computer Vision，Kyoto，Japan，2009：24-31
[65]代科学，李国辉，涂丹，等．监控视频运动目标检测减背景技术的研究现状和展望[J]．中国图象图形学报，2006，11(7)：919-927
[66] Cheng F C，Chen Y K．Effective background estimation for video backgroundgeneration[C]//IEEE Asia-Pacific Services Computing Conference，Yilan，Taiwan，2008：1315-1321
[67] Toral S，Vargas M，Barrero F，et al．Improved sigma-delta background estimation forvehicle detection[J]．Electronics Letter，2009，45(1)：32-34
[68] Koller D，Weber J，Huang T，et al．Towards robust automatic traffic scene analysis inreal-time[C]//Proceedings of the12th IAPR International Conference on PatternRecognition，Jerusalem，Israel，1994：126-131
[69] Stauffer C， Grimson W． Adaptive background mixture models for real-timetracking[C]//International Conference on computer Vision and Pattern Recognition，FtCollins，CO，USA，1999：246–252
[70] Chen J，Yang J，Zhou Y，et al．Flexible background mixture models for foregroundsegmentation[J]．Image and Vision Computing，2006，24(5)：473–482
[71] Kan J，Li K，Tang J，et al．Background Modeling Method Based on ImprovedMulti-Gaussian Distribution[C]//International Conference on Computer Application andSystem Modeling，Taiyuan，China，2010，2：214-218
[72]宋佳声，胡国清．基于时空熵分析的组合高斯背景建模方法[J]．华南理工大学学报，2012，40(9)：116-122
[73]张超，吴小培，周建英，等．基于改进高斯混合建模和短时稳定度的运动目标检测算法[J]．电子与信息学报，2012，34(10)：2402-2408
[74] Elgammal A，Duraiswami R，Harwood D，et al．Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance[J]．Proceedings ofthe IEEE，2002，90(7)：1151–1163
[75] Alireza T，Nicolescu M，George B，et al．Non-parametric statistical background modelingfor efficient foreground region detection[J]．Machine Vision and Applications，2008，20(6)：395-409
[76] Lee J，Park M．An Adaptive Background Subtraction Method Based on Kernel DensityEstimation[J]．Sensors，2012，12(9)：12279-12300
[77] Rittscher J，Kato J，Joga S，et al．A probabilistic background model for tracking[C]//the European Conference on Computer Vision，London，Britain，2000：336–350
[78] Vikas Reddy，Conrad Sanderson，Andres Sanin，et al．MRF-based BackgroundInitialisation for Improved Foreground Detection in Cluttered Surveillance Videos[C]//the Asian conference on Computer vision，Berlin，Germany，2010：547-559
[79] Culibrk D，Marques O，Socek D，et al．Neural network approach to background modelingfor video object segmentation[J]．IEEE Transactions on Neural Networks，2007，18(6)：1614-1627
[80] Maddalena L，Petrosino A．A self-organizing approach to background subtraction forvisual surveillance applications[J]．IEEE Transactions on Image Processing，2008，17(7)：1168-1177
[81]王志明，包宏，张丽．基于混合结构神经网络的自适应背景模型[J]．电子学报，2011，39(5)：1053-1058
[82] Sigari M H，Mozayani N，Pourreza H R．Fuzzy running average and fuzzy backgroundsubtraction：concepts and application[J]．International Journal of Computer Science andNetwork Security，2008，8(2)：138-143
[83] Shakeri M，Deldari H，Foroughi H，et al．A novel fuzzy background subtraction methodbased on cellular automata for urban traffic applications[C]//International Conference onSignal Processing，Leipzig，Germany，2008：899-902
[84] Chin Y B，Soong L W，Siong L H，et al．Extended fuzzy background modeling formoving vehicle detection using infrared vision[J]．IEICE Electronics Express，2011，8(6)：340-345
[85] Kim K，Chalidabhongse T H，Harwood D，et al．Real-time foreground-backgroundsegmentation using codebook model[J]．Real-Time Imaging，2005，11(3)：72–185
[86] Mingjun Wu，Xianrong Peng．Spatio-temporal context for codebook-based dynamicbackground subtraction[J]．International Journal of Electronics and Communications，2010，64(8)：739–747
[87] Jing Ming Guo，Yun Fu Liu，Chih Hsien Hsia，et al．Hierarchical Method for ForegroundDetection Using Codebook Model[J]．IEEE Transactions on Circuits and Systems forVideo Technology，2011，21(6)：804–815
[88]霍东海，杨丹，张小洪，洪明坚．一种基于主成分分析的Codebook背景建模算法[J]．自动化学报，2012，38(4)：591–600
[89] Lin C T，George Lee C S．Neural Fuzzy Systems：A Neuro-Fuzzy Synergism toIntelligent Systems[J]．IEEE Transactions on Neural Networks，1996，7(5)：40-43
[90] Feng H M． Particle Swarm Optimization Learning Fuzzy Systems Design[C]//International Conference on Information Technology and Applications，Taiwan China，2005，1：363-366
[91] Eberhart R C， Kennedy J． A new optimizer using particles swarm theory[C]//Proceedings of Sixth International Symposium on Micro Machine and Human Science，Nagoya，Japan，1995：39-43
[92] Astrom K J,Wittenmark B．Adaptive control[M]．Boston,MA,USA：Addison-WesleyLongman Publishing Co., Inc.1994：61-64
[93] Jang J S R, Sun C T, Mizutani E．Neuro-fuzzy and soft computing[M]．Prentice HallUpper Saddle River，1997：33-36
[94] Kim K, Chalidabhongse T H, Harwood D, et al．Real-time foreground-backgroundsegmentation using codebook model[J]．Real-Time Imaging,2005,11(3)：72–185
[95]汪海洋,潘德炉,夏德深.二维Otsu自适应阈值选取算法的快速实现[J].自动化学报,2007,33(9)：965-970
[96]岳峰,左旺孟,王宽全.基于分解的灰度图像二维阈值选取算法[J].自动化学报,2009,35(7)：1022-1027
[97] Li L, Huang W, Gu I Y H, et al. Statistical modeling of complex backgrounds forforeground object detection[J]. IEEE Transactions on Image Processing,2004,13(11)：1459-1472
[98] Zhao T, Nevada R．Tracking multiple humans in complex situations [J]．IEEETransactions on Pattern Analysis and Machine Intelligence,2004,26(9)：1208-1221
[99] Song K, Tai J．Image-based traffic monitoring with shadow suppression [J]．Proceedingsof the IEEE，2007，95(2)：413-426
[100] Jung C R．Efficient Background Subtraction and Shadow Removal for MonochromaticVideo Sequences[J]．IEEE Transactions on Multimedia，2009，11(3)：571–577
[101]彭祺，仲思东，屠礼芬，等．基于空间位置特征的运动阴影检测方法[J]．机器人，2012，34(5)：614-619
[102] Shoaib R，Dragon M，Ostermann J．Shadow Detection For Moving Humans UsingGradient-Based Background Subtraction [C]//International Conference on Acoustics,Speech and Signal Processing，Taipei, Taiwan,2009：773–776
[103] Spagnolo P，Mazzeo P L，Leo M，et al．Shadows Removal by Edges Matching[C]//Proceedings of the5th International Symposium on Advances in Visual Computing，Berlin, Heidelberg，2009：440-449
[104] Andres Sanin，Conrad Sanderson，Brian C Lovell．Improved Shadow Removal forRobust Person Tracking in Surveillance Scenarios[C]//International Conference onPattern Recognition，Istanbul，Turkey，2010：141-144
[105]姜柯，李艾华，苏延召．基于全局纹理和抽样推断的自适应阴影检测算法[J]．光电子.激光，2012，11：25-31
[106] Salvador E，Cavallaro A，Ebrahimi T．Cast shadow segmentation using invariant colorfeatures [J]．Computer Vision and Image Understanding，2004，95(2)：238-259
[107] Sun B，Li S．Moving cast shadow detection of vehicle using combined colormodels[C]//Chinese Conference on Pattern Recognition，Changsha，China，2010：1-5
[108] Ye J，Gao T，Zhang J．Moving object detection with background subtraction and shadowremoval[C]//9th International Conference on Fuzzy Systems and KnowledgeDiscovery，Tianjin，China，2012：1859-1863
[109]查宇飞，楚瀛，王勋，等．一种基于Boosting判别模型的运动阴影检测方法[J]．计算机学报，2007，30(8)：1295-1301
[110] Yang M T， Lo K H，Chiang C C，et al．Moving Cast Shadow Detection by ExploitingMultiple Cues [J]．IET Image Processing，2008，2(2)：95-104
[111]曹健，陈红倩，张凯，等．结合区域颜色和纹理的运动阴影检测方法[J]．机器人，2011，33(5)：628-633
[112] McFeely R，Glavin M，Jones E．Shadow identification for digital imagery using colourand texture cues[J]．IET Image Processing，2012，6(2)：148-159
[113] El Baf F, Bouwmans T, Vachon B. Foreground detection using the choquet integral[C]//Ninth International Workshop on Image Analysis for Multimedia Interactive Services，IEEE,2008:187-190
[114] Ojala T，Pietikainen M， Maenpaa T．Multiresolution gray-scale and rotation-invariant texture classification with local binary patterns[J]．IEEE Trans on PatternAnalysis，2002，24(7)：971-986
[115] Shu Liao，Albert C S Chung．Face Recognition with Salient Local Gradient OrientationBinary Patterns[C]//16th IEEE International Conference on Image Processing，Cairo，Egypt，2009：3317-3320
[116] Grabisch M，Murofushi T，Sugeno M．Fuzzy Measures and Integrals theory andApplications[M]．Germany：Physica Verlag,2000
[117] Bevilacqua A．Effective shadow detection in traffic monitoring applications [J]．JWinter School of Computer Graphics,2003,11(1)：57-64
[118] Martel-Brisson N, Zaccarin A．Kernel-based learning of cast shadows from a physicalmodel of light sources and surfaces for low-level segmentation[C]//IEEE Conferenceon Computer Vision and Pattern Recognition, Anchorgae, USA,2008：1-8
[119] JinMin Choi,Yung Jun Yoo,Jin Young Choi. Adaptive shadow estimator for removingshadow of moving object[J]．Computer Vision and Image Understanding,2010,114(9)：1017-1029
[120] Cucchiara R，Grana C，Piccardi M，et al．Detecting moving shadows: algorithms andevaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918-923
[121] Cucchiara R, Grana C, Piccardi M and Prati A. Detecting moving objects, ghosts, andshadows in video streams [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2003,25(10)：1337-1342
[122] Benedek C, Sziranyi T1. Markovian framework for foreground background shadowseparation of real world video scenes[C]//Proceedings of the7th Asian ConferenceComputer Vision, Daejeon, Korea,2006：898-907
[123] Zhang W, Fang X Z, Yang X K, et al. Moving cast shadows detection using ratioedge[J]. IEEE Transactions on Multimedia,2007,9(6):1202-1214
[124]Boiman O,Shechtman E,Irani M. Indefense of nearest-neighbor based imageclassification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,Alaska,USA,2008：1-8
[125] Wang Z, Hu Y, Chia L T. Learning instance-to-class distance for human actionrecognition[C]//16th IEEE International Conference on Image Processing,Cairo,Egypt2009：3545-3548
[126] Huang Y, Xu D, Cham T J.Face and human gait recognition using image-to-classdistance[J].IEEE Transactions on Circuits and Systems for Video Technology,2010,20(3)：431-438
[127]Wang Z, Hu Y,Chia L T. Image-to-class distance metric learning for imageclassification[C]//European Conference on Computer Vision, Crete,Greece,2010：709-719
[128] Behmo R,Marcombes P,Dalalyan A,Prinet V. Towards optimal naive Bayes nearestneighbor[C]//European Conference on Computer Vision, Crete,Greece,2010：171-184
[129] Wang Z, Hu Y, Chia L T. Improved learning of I2C distance and accelerating theneighborhood search for image classification[J].Pattern Recognition,2011,44：2384-2394
[130] Wang Z, Feng J, Yan S, et al. Linear Distance Coding for Image Classification[J].IEEEtransactions on image processing,2013,22(2)：537-548
[131] Galbiati J, Allende H and Becerra C. Dynamic Image Segmentation Method UsingHierarchical Clustering[C]//14th Iberoamerican Conference on Pattern Recognition：Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications,Guadalajara, Jalisco, Mexico,2009：177-184
[132] Li W, Zhang Z, and Liu Z. Expandable data-driven graphical modeling of humanactions based on salient postures[J].IEEE Trans. Circuits and Systems for VideoTechnology,2008,18(11)：1499-1510.
[133] Fei-Fei L, Perona P．A bayesian hierarchical model for learning natural scenecategories[C]//IEEE Computer Society Conference on Computer Vision and PatternRecognition, San Diego, CA, USA,2005,2：524-531
[134] Liang P, Li S, Wang C．A new image matching algorithm based on scale adaptedinterest point detection[C]//Proceedings of International Conference on Information andAutomation, Zhuhai, China,2009：330-335
[135]Bouchard G, Triggs．Hierarchical part-based visual object categorization[C]//IEEEComputer Society Conference on Computer Vision and Pattern Recognition, SanDiego, CA, USA,2005,1：710-715
[136] Ommer B, Buhmann J M．Learning the compositional nature of visual object categoriesfor recognition[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(3)：501-516
[137] Nister D, Stewenius H．Scalable recognition with a vocabulary tree[C]//IEEEComputer Society Conference on Computer Vision and Pattern Recognition, New York,NY, USA,2006,2：2161-2168
[138] Lin Z, Jiang Z, Davis L S．Recognizing actions by shape-motion prototype trees[C]//IEEE12th International Conference on Computer Vision, Kyoto, Japan,2009：444-451
[139] Reddy K K, Liu J, Shah M．Incremental action recognition using feature-tree[C]//IEEE12th International Conference on Computer Vision, Kyoto, Japan,2009：1010-1017
[140] Mikolajczyk K, Uemura H．Action recognition with motion-appearance vocabularyforest[C]//IEEE Conference on Computer Vision and Pattern Recognition, Anchorage,Alaska, USA,2008：1-8
[141] Moosmann F, Triggs B, Jurie F．Fast discriminative visual codebooks using randomizedclustering forests[J]．Advances in Neural Information Processing Systems,2007,19：985-992
[142] Morioka N, Satoh S．Building compact local pairwise codebook with joint feature spaceclustering[C]//European Conference on Computer Vision, Crete,Greece,2010：692-705
[143] C. Bishop．Pattern recognition and machine learning [M]．Spinger-Verlag,2006
[144] Agarwal S, Awan A, Roth D．Learning to detect objects in image via a sparse,part-based representation[J]．IEEE Transactions on Pattern Analysis and MachineIntelligence,2004,26(11)：1475-1490
[145] Fritz M, Leibe B, Caputo B, et al．Integrating representative and discriminant modelsfor object category detection[C]//Proceedings of International Conference on ComputerVision,Beijing,China,2005,(2)：1363-1370
[146] Pan H, Zhu Y P, Xia L Z, et al．Combining generic and class-specific codebooks forobject categorization and detection[C]//Proceedings of International Conference onAcoustic, Speech and Signal Processing,Prague,Czech,2011：2264-2267
[147] Lazebnik S, Schmid C, Ponce J. Beyond bags of features：Spatial pyramid matching forrecognizing natural scene categories[C]//IEEE Computer Society Conference onComputer Vision and Pattern Recognition, New York, NY, USA,2006,2：2169-2178
[148] Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding forimage classification[C]//IEEE Conference on Computer Vision and PatternRecognition, Miami, Florida, USA,2009：1794-1801
[149] Ren X, Ramanan D.Histograms of Sparse Codes for Object Detection[C]//IEEEConference on Computer Vision and Pattern Recognition, Portland, Oregon, USA,2013：1-8
[150] Liu Z, Xiong H. Object detection and localization using random forest[C]//SecondInternational Conference on Intelligent System Design and Engineering Application,Sanya, China,2012：1074-1078
[151] Moosmann F，Triggs B， Jurie F．Fast discriminative visual codebooks usingrandomized clustering forests[J]．Advances in Neural Information Processing Systems,2007,19：985-992
[152] Schroff F, Criminisi A, Zisserman A．Object class segmentation using randomforests[C]//The British Machine Vision Conference, Leeds, UK,2008：1-4
[153] Kohli P, Pelillo M, Bischof H． Context-Sensitive Decision Forests for ObjectDetection[J]．Advances in Neural Information Processing Systems,2012：440-448
[154] Gall J, Lempitsky V. Class-specific Hough forests for object detection [C]//IEEEConference on Computer Vision and Pattern Recognition, Miami, FL, USA,2009：1022-1029
[155] Fanelli G, Gall J, Van Gool L J. Hough transform-based mouth localization foraudio-visual speech recognition[C]//The British Machine Vision Conference, London,UK,2009：1-11
[156]Yao A, Gall J, Van Gool L．A hough transform-based voting framework for actionrecognition［C］//IEEE Computer Society Conference on Computer Vision and PatternRecognition. San Francisco, CA,2010：2061-2068
[157] Fanelli G, Yao A, Noel P L, et al. Hough Forest-based Facial Expression Recognitionfrom video sequences[C]//The European Conference on Computer Vision, Heraklion,Greece,2010：195-206
[158] Payet N, Todorovic S. Hough Forest Random Field for Object Recognition andSegmentation[J]．IEEE transactions on pattern analysis and machine intelligence,2012，35(5)：1066-1079
[159] Wohlhart P, Schulter S, K stinger M, et al. Discriminative Hough Forests for ObjectDetection[C]//The British Machine Vision Conference, Surrey,UK,2012：1-11
[160] Breiman L. Random Forests [J]．Machine learning,2001,45(1)：5-32
[161] Friedman J H．Greedy function approximation：a gradient boosting machine[J]．Annalsof Statistics,2001,29(5)：1189-1232
[162] Byrd R H, Lu P, Nocedal J, et al. A limited memory algorithm for bound constrainedoptimization[J]. SIAM Journal on Scientific Computing,1995,16(5)：1190-1208
[163] Leistner C,Saffari A, Santner J, et al. Semi-supervised random forests[C]//IEEEInternational Conference on Computer Vision, Miami, Florida, USA,2009：506-513
[164] Felzenszwalb P F, Girshick R B, McAllester D, et al． Object detection withdiscriminatively trained part-based models [J]． Pattern Analysis and MachineIntelligence, IEEE Transactions on,2010,32(9)：1627-1645
[165] Razavi N, Gall J, Kohli P, et al．Latent hough transform for object detection[C]//TheEuropean Conference on Computer Vision, Florence, Italy,2012：312-325
[166] Nima Razavi, Nima S. Alvar, Juergen Gall, et al．Sparsity Potentials for DetectingObjects with Hough Transform[C]//The British Machine Vision Conference, Surrey,UK,2012：11.1-11.10
[2]凌志刚，赵春晖，梁彦，等．基于视觉的人行为理解综述[J]．计算机应用研究，2008，25(9)：2570-2578
[3] Zhu Z，Xu G，Yang B，et al．VISATRAM：A real-time vision system for automatic trafficmonitoring [J]．Image and Vision Computing，2000，18(10)：781-794
[4] Tai J，Tsang S，Lin C，et al．Real-time image tracking for automatic traffic monitoring andenforcement application [J]．Image and Vision Computing，2004，22(6)：485-501
[5] Li Q，Zheng N N，Cheng H．Springrobot：a prototype autonomous vehicle and itsalgorithms for lane detection[J]． IEEE Transactions on Intelligent TransportationSystems，2004，5(4)：300-308
[6]王智灵，周露平，陈宗海．针对不同信息特征的鲁棒背景建模技术分析[J]．模式识别与人工智能，2009，22(2)：240-245
[7] Sanin A，Sanderson C，Lovell B C．Shadow detection：A survey and comparativeevaluation of recent methods [J]．Pattern recognition，2012，45(4)：1684-1695
[8] Al Najdawi N，Bez H E，Singhai J，et al．A survey of cast shadow detection algorithms[J]．Pattern Recognition Letters，2012，33(6)：752-764
[9] Pooja Kamavisdar，Sonam Saluja，Sonu Agrawal．A Survey on Image Classification[J]．Internaltional Journal of Advanced Research in Computer and CommunicationEngineering，2013，2(1)：1005-1009
[10] Prasad D K．Survey of the problem of object detection in real images[J]．InternationalJournal of Image Processing，2012，6(6)：441-466
[11] Chu Y W，Liu T L．Co-occurrence random forests for object localization andclassification[C]//Asian Conference on Computer Vision，Xi’an，China，2009：621-632
[12] Liu Z，Xiong H．Object detection and localization using random forest[C]//InternationalConference on Intelligent System Design and Engineering Application， Sanya，China，2012：1074-1078
[13] Wang L，Hu W，Tan T．Recent developments in human motion analysis[J]． Patternrecognition，2003，36(3)：585-601
[14] Sen-Ching S C， Kamath C．Robust techniques for background subtraction in urbantraffic video[C]//International Society for Optics and Photonics Electronic Imaging，San Jose，CA，United States，2004：881-892
[15] Barron J L，Fleet D J，Beauchemin S S．Performance of optical flow techniques[J]．International journal of computer vision，1994，12(1)：43-77
[16]吴振杰．基于改进光流法的运动目标检测与跟踪系统[D]．河南：郑州大学，2012
[17]张泽旭，李金宗，李宁宁．基于光流场分割和Canny边缘提取融合算法的运动目标检测[J]．电子学报，2003，31(9)：1299-1302
[18]戴斌，方宇强，孙振平，王亮．基于光流技术的运动目标检测和跟踪方法研究[J]．科技导报2009,27(12)：55-60
[19]王静静，林明秀，魏颖．基于灰度相关的帧间差分和背景差分相融合的实时目标检测[J]．中南大学学报（自然科学版），2009，40(1)：142-148
[20]王小峰，王吉华，王远鹏，等．混合高斯模型和差分法相融合的运动目标检测[J]．小型微型计算机系统，2013，34(3)：685-688
[21]袁国庆，陈志强，龚健，等．一种结合光流法与三帧差分法的运动目标检测算法[J]．小微型计算机系统，2013，34(3)：668-671
[22]解晓萌．复杂背景下运动目标检测和识别关键技术研究[D]．广州：华南理工大学，2012
[23] Chu J，Miao J，Zhang G，et al．Edge and corner detection by color invariants[J]．Optics&Laser Technology，2013，45：756-762
[24]岑峰．视频监控系统中面向人的目标跟踪技术研究[D]．上海：上海交通大学，2002
[25] Gavrila D M，Munder S．Multi-cue pedestrian detection and tracking from a movingvehicle [J]．International Journal of Computer Vision，2007，73(1)：41-59
[26]陈国栋，孙立宁，杜志江，等．一种利用形状片段的物体检测方法[J]．自动化学报，2011，37(4)：427-439
[27] Lee H J， Hong K S．Class-Specifc Weighted Dominant Orientation Templates forObject Detection [C]//Asian Conference on Computer Vision，Daejeon， Korea，2012：97-108
[28] Crivelli T，Bouthemy P，Cernuschi-Frías B，et al．Simultaneous motion detection andbackground reconstruction with a conditional mixed-state markov randomfield[J]．International journal of computer vision，2011，94(3)：295-316
[29] Viola P，Jones M．Rapid object detection using a boosted cascade of simple features[C]//IEEE International Conference on Computer Vision and Pattern Recognition，Kauai，HI，USA，2001，1：511-518
[30]胡正平，杨建秀．HOG特征混合模型结合隐SVM的感兴趣目标检测定位算法[J]．信号处理，2011，27(8)：1206-1212
[31] Lowe D M．Distinctive image features from scale-invariant keypoints [J]．InternationalJournal of Computer Vision，2004，60(2)：91-110
[32] Ke Y， Sukthankar R．PCA-SIFT：A More Distinctive Representation for Local ImageDescriptors[C]//IEEE International Conference on Computer Vision and PatternRecognition，Washington，DC，USA，2004，2：506-513
[33] Zhu S． Statistical modeling and conceptualization of visual patterns[J]． IEEETransactions on Pattern Analysis and Machine Intelligence，2003，25(6)：691-712
[34] Bay H，Tuytelaars T，Van Gool L．Surf：Speeded up robust features[C]//EuropeanConference on Computer Vision，Graz，Austria，2006：404-417
[35] Dalal Navneet，Triggs Bill．Histograms of oriented gradients for human detection [C]//IEEE Conference on Computer Vision and Pattern Recognition，San Diego，CA，Unitedstates，2005：886-893
[36] Wang Xiaoyu，Han Tony X，Yan Shuicheng．An HOG-LBP Human Detector withPartial Occlusion Handling [C]//IEEE International Conference on Computer Vision，Kyoto，JAPAN，2009：32-39
[37] Yangwei Pang，Yuan Yuan，Xuelong Li，Jing Pan．Efficient HOG human detection[J]．Signal Processing，2011，91(4)：773-781
[38] Ojala T，Pietikainen M，Harwood D．Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions[C]//InternationalConference on Pattern Recognition，1994，1：582-585
[39] Ojala T，Pietikainen M，Maenpaa T．Multiresolution gray-scale and rotation-invarianttexture classification with local binary patterns[J]． IEEE Transactions on PatternAnalysis and Machine Intelligence，2002，24(7)：971-986
[40] Ahonen T，Hadid A，Pietik inen M．Face recognition with local binary patterns[C]//European Conference on Computer Vision，Prague，Czech，2004：469-481
[41] Pietik inen M．Image analysis with local binary patterns[J]．Image Analysis，2005，35(40)：115-118
[42] Lange M M，Novikov N A．Bayes classifier based on tree-structured Gaussian mixtures[J]．Pattern Recognition and Image Analysis，2012，22(1)：136-143
[43]李玲玲，金泰松，李翠华．基于局部特征和隐条件随机场的场景分类方法[J]．北京理工大学学报，2012，32(007)：720-724
[44] Qureshi I M， Jalil A． Object Recognition Using ANN with BackpropogationAlgorithm[J]． Pakistan Journal of Applied Sciences，2002，2(3)：281-287
[45] Park K，Shen C，Hao Z，et al．Efficiently learning a distance metric for large marginnearest neighbor classification[C]//Proceedings of the25th AAAI Conference onArtificial Intelligence，San Francisco，California， USA，2011：453-458
[46] Wang J，Neskovic P，Cooper L N．Improving nearest neighbor rule with a simpleadaptive distance measure[J]．Pattern Recognition Letters，2007，28(2)：207-213
[47] Noh Y K，Zhang B T，Lee D D．Generative local metric learning for nearest neighborclassification[J]．Advances in Neural Information Processing Systems,2010,18：417-424
[48] Wang Z，Hu Y，Chia L T．Improved learning of I2C distance and accelerating theneighborhood search for image classification[J]．Pattern Recognition，2011，44(10)：2384-2394
[49] Aci M， Avci M． K nearest neighbor reinforced expectation maximizationmethod[J]．Expert Systems with Applications，2011，38(10)：12585-12591
[50] Xu Y，Zhu Q，Fan Z，et al．Coarse to fine K nearest neighbor classifier[J]．PatternRecognition Letters，2013，34(9)：980-986
[51] Liu Z，Pan Q，Dezert J．A new belief-based K-nearest neighbor classificationmethod[J]．Pattern Recognition，2012，46(3)：834-844
[52] Felzenszwalb P F，Girshick R B，McAllester D，et al．Object detection withdiscriminatively trained part-based models[J]． Pattern Analysis and MachineIntelligence， IEEE Transactions on，2010，32(9)：1627-1645
[53] Zhu L，Chen Y，Yuille A，et al．Latent hierarchical structural learning for objectdetection[C]//IEEE Conference on Computer Vision and Pattern Recognition，SanFrancisco，CA，USA，2010：1062-1069
[54] Deselaers T，Heigold G，Ney H．Object classification by fusing SVMs and Gaussianmixtures[J]．Pattern Recognition，2010，43(7)：2476-2484
[55] Maji S，Berg A，Malik J．Efficient classification for additive kernel SVMs[J]．2013，35(1)：66-77
[56] Freund Y，Schapire R E．A decision-theoretic generalization of on-line learning and anapplication to boosting[J]．Journal of computer and system sciences，1997，55(1)：119-139
[57]李闯，丁晓青，吴佑寿．一种改进的AdaBoost算法—AD AdaBoost [J]．计算机学报，2007，30(1)：103–109
[58]李文辉，倪洪印．一种改进的Adaboost训练算法[J]．吉林大学学报(理学版)，2011，49(3)：498–504
[59] Mason L，Baxter J，Bartlett P，et al．Boosting algorithms as gradient descent in functionspace[C]．NIPS，Denver，Colorado，1999：512-518
[60] Torralba A，Murphy K P，Freeman W T．Sharing visual features for multiclass andmultiview object detection[J]． Pattern Analysis and Machine Intelligence， IEEETransactions on，2007，29(5)：854-869
[61] Huang Z F，Yang W，Wang Y，et al．Latent Boosting for Action Recognition[C]//BritishMachine Vision Conference，Dundee，2011：1-11
[62] Garcia C，Delakis M．Convolutional face finder: A neural architecture for fast and robustface detection[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence，2004，26(11)：1408-1423
[63] Jürgen Gall，Victor Lempitsky．Class-specific Hough forests for object detection [C]//IEEE Conference on Computer Vision and Pattern Recognition，Miami，FL， USA，2009：1022-1029
[64] Schwartz W R，Kembhavi A，Harwood D，et al．Human detection using partial leastsquares analysis[C]//IEEE International Conference on Computer Vision，Kyoto，Japan，2009：24-31
[65]代科学，李国辉，涂丹，等．监控视频运动目标检测减背景技术的研究现状和展望[J]．中国图象图形学报，2006，11(7)：919-927
[66] Cheng F C，Chen Y K．Effective background estimation for video backgroundgeneration[C]//IEEE Asia-Pacific Services Computing Conference，Yilan，Taiwan，2008：1315-1321
[67] Toral S，Vargas M，Barrero F，et al．Improved sigma-delta background estimation forvehicle detection[J]．Electronics Letter，2009，45(1)：32-34
[68] Koller D，Weber J，Huang T，et al．Towards robust automatic traffic scene analysis inreal-time[C]//Proceedings of the12th IAPR International Conference on PatternRecognition，Jerusalem，Israel，1994：126-131
[69] Stauffer C， Grimson W． Adaptive background mixture models for real-timetracking[C]//International Conference on computer Vision and Pattern Recognition，FtCollins，CO，USA，1999：246–252
[70] Chen J，Yang J，Zhou Y，et al．Flexible background mixture models for foregroundsegmentation[J]．Image and Vision Computing，2006，24(5)：473–482
[71] Kan J，Li K，Tang J，et al．Background Modeling Method Based on ImprovedMulti-Gaussian Distribution[C]//International Conference on Computer Application andSystem Modeling，Taiyuan，China，2010，2：214-218
[72]宋佳声，胡国清．基于时空熵分析的组合高斯背景建模方法[J]．华南理工大学学报，2012，40(9)：116-122
[73]张超，吴小培，周建英，等．基于改进高斯混合建模和短时稳定度的运动目标检测算法[J]．电子与信息学报，2012，34(10)：2402-2408
[74] Elgammal A，Duraiswami R，Harwood D，et al．Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance[J]．Proceedings ofthe IEEE，2002，90(7)：1151–1163
[75] Alireza T，Nicolescu M，George B，et al．Non-parametric statistical background modelingfor efficient foreground region detection[J]．Machine Vision and Applications，2008，20(6)：395-409
[76] Lee J，Park M．An Adaptive Background Subtraction Method Based on Kernel DensityEstimation[J]．Sensors，2012，12(9)：12279-12300
[77] Rittscher J，Kato J，Joga S，et al．A probabilistic background model for tracking[C]//the European Conference on Computer Vision，London，Britain，2000：336–350
[78] Vikas Reddy，Conrad Sanderson，Andres Sanin，et al．MRF-based BackgroundInitialisation for Improved Foreground Detection in Cluttered Surveillance Videos[C]//the Asian conference on Computer vision，Berlin，Germany，2010：547-559
[79] Culibrk D，Marques O，Socek D，et al．Neural network approach to background modelingfor video object segmentation[J]．IEEE Transactions on Neural Networks，2007，18(6)：1614-1627
[80] Maddalena L，Petrosino A．A self-organizing approach to background subtraction forvisual surveillance applications[J]．IEEE Transactions on Image Processing，2008，17(7)：1168-1177
[81]王志明，包宏，张丽．基于混合结构神经网络的自适应背景模型[J]．电子学报，2011，39(5)：1053-1058
[82] Sigari M H，Mozayani N，Pourreza H R．Fuzzy running average and fuzzy backgroundsubtraction：concepts and application[J]．International Journal of Computer Science andNetwork Security，2008，8(2)：138-143
[83] Shakeri M，Deldari H，Foroughi H，et al．A novel fuzzy background subtraction methodbased on cellular automata for urban traffic applications[C]//International Conference onSignal Processing，Leipzig，Germany，2008：899-902
[84] Chin Y B，Soong L W，Siong L H，et al．Extended fuzzy background modeling formoving vehicle detection using infrared vision[J]．IEICE Electronics Express，2011，8(6)：340-345
[85] Kim K，Chalidabhongse T H，Harwood D，et al．Real-time foreground-backgroundsegmentation using codebook model[J]．Real-Time Imaging，2005，11(3)：72–185
[86] Mingjun Wu，Xianrong Peng．Spatio-temporal context for codebook-based dynamicbackground subtraction[J]．International Journal of Electronics and Communications，2010，64(8)：739–747
[87] Jing Ming Guo，Yun Fu Liu，Chih Hsien Hsia，et al．Hierarchical Method for ForegroundDetection Using Codebook Model[J]．IEEE Transactions on Circuits and Systems forVideo Technology，2011，21(6)：804–815
[88]霍东海，杨丹，张小洪，洪明坚．一种基于主成分分析的Codebook背景建模算法[J]．自动化学报，2012，38(4)：591–600
[89] Lin C T，George Lee C S．Neural Fuzzy Systems：A Neuro-Fuzzy Synergism toIntelligent Systems[J]．IEEE Transactions on Neural Networks，1996，7(5)：40-43
[90] Feng H M． Particle Swarm Optimization Learning Fuzzy Systems Design[C]//International Conference on Information Technology and Applications，Taiwan China，2005，1：363-366
[91] Eberhart R C， Kennedy J． A new optimizer using particles swarm theory[C]//Proceedings of Sixth International Symposium on Micro Machine and Human Science，Nagoya，Japan，1995：39-43
[92] Astrom K J,Wittenmark B．Adaptive control[M]．Boston,MA,USA：Addison-WesleyLongman Publishing Co., Inc.1994：61-64
[93] Jang J S R, Sun C T, Mizutani E．Neuro-fuzzy and soft computing[M]．Prentice HallUpper Saddle River，1997：33-36
[94] Kim K, Chalidabhongse T H, Harwood D, et al．Real-time foreground-backgroundsegmentation using codebook model[J]．Real-Time Imaging,2005,11(3)：72–185
[95]汪海洋,潘德炉,夏德深.二维Otsu自适应阈值选取算法的快速实现[J].自动化学报,2007,33(9)：965-970
[96]岳峰,左旺孟,王宽全.基于分解的灰度图像二维阈值选取算法[J].自动化学报,2009,35(7)：1022-1027
[97] Li L, Huang W, Gu I Y H, et al. Statistical modeling of complex backgrounds forforeground object detection[J]. IEEE Transactions on Image Processing,2004,13(11)：1459-1472
[98] Zhao T, Nevada R．Tracking multiple humans in complex situations [J]．IEEETransactions on Pattern Analysis and Machine Intelligence,2004,26(9)：1208-1221
[99] Song K, Tai J．Image-based traffic monitoring with shadow suppression [J]．Proceedingsof the IEEE，2007，95(2)：413-426
[100] Jung C R．Efficient Background Subtraction and Shadow Removal for MonochromaticVideo Sequences[J]．IEEE Transactions on Multimedia，2009，11(3)：571–577
[101]彭祺，仲思东，屠礼芬，等．基于空间位置特征的运动阴影检测方法[J]．机器人，2012，34(5)：614-619
[102] Shoaib R，Dragon M，Ostermann J．Shadow Detection For Moving Humans UsingGradient-Based Background Subtraction [C]//International Conference on Acoustics,Speech and Signal Processing，Taipei, Taiwan,2009：773–776
[103] Spagnolo P，Mazzeo P L，Leo M，et al．Shadows Removal by Edges Matching[C]//Proceedings of the5th International Symposium on Advances in Visual Computing，Berlin, Heidelberg，2009：440-449
[104] Andres Sanin，Conrad Sanderson，Brian C Lovell．Improved Shadow Removal forRobust Person Tracking in Surveillance Scenarios[C]//International Conference onPattern Recognition，Istanbul，Turkey，2010：141-144
[105]姜柯，李艾华，苏延召．基于全局纹理和抽样推断的自适应阴影检测算法[J]．光电子.激光，2012，11：25-31
[106] Salvador E，Cavallaro A，Ebrahimi T．Cast shadow segmentation using invariant colorfeatures [J]．Computer Vision and Image Understanding，2004，95(2)：238-259
[107] Sun B，Li S．Moving cast shadow detection of vehicle using combined colormodels[C]//Chinese Conference on Pattern Recognition，Changsha，China，2010：1-5
[108] Ye J，Gao T，Zhang J．Moving object detection with background subtraction and shadowremoval[C]//9th International Conference on Fuzzy Systems and KnowledgeDiscovery，Tianjin，China，2012：1859-1863
[109]查宇飞，楚瀛，王勋，等．一种基于Boosting判别模型的运动阴影检测方法[J]．计算机学报，2007，30(8)：1295-1301
[110] Yang M T， Lo K H，Chiang C C，et al．Moving Cast Shadow Detection by ExploitingMultiple Cues [J]．IET Image Processing，2008，2(2)：95-104
[111]曹健，陈红倩，张凯，等．结合区域颜色和纹理的运动阴影检测方法[J]．机器人，2011，33(5)：628-633
[112] McFeely R，Glavin M，Jones E．Shadow identification for digital imagery using colourand texture cues[J]．IET Image Processing，2012，6(2)：148-159
[113] El Baf F, Bouwmans T, Vachon B. Foreground detection using the choquet integral[C]//Ninth International Workshop on Image Analysis for Multimedia Interactive Services，IEEE,2008:187-190
[114] Ojala T，Pietikainen M， Maenpaa T．Multiresolution gray-scale and rotation-invariant texture classification with local binary patterns[J]．IEEE Trans on PatternAnalysis，2002，24(7)：971-986
[115] Shu Liao，Albert C S Chung．Face Recognition with Salient Local Gradient OrientationBinary Patterns[C]//16th IEEE International Conference on Image Processing，Cairo，Egypt，2009：3317-3320
[116] Grabisch M，Murofushi T，Sugeno M．Fuzzy Measures and Integrals theory andApplications[M]．Germany：Physica Verlag,2000
[117] Bevilacqua A．Effective shadow detection in traffic monitoring applications [J]．JWinter School of Computer Graphics,2003,11(1)：57-64
[118] Martel-Brisson N, Zaccarin A．Kernel-based learning of cast shadows from a physicalmodel of light sources and surfaces for low-level segmentation[C]//IEEE Conferenceon Computer Vision and Pattern Recognition, Anchorgae, USA,2008：1-8
[119] JinMin Choi,Yung Jun Yoo,Jin Young Choi. Adaptive shadow estimator for removingshadow of moving object[J]．Computer Vision and Image Understanding,2010,114(9)：1017-1029
[120] Cucchiara R，Grana C，Piccardi M，et al．Detecting moving shadows: algorithms andevaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918-923
[121] Cucchiara R, Grana C, Piccardi M and Prati A. Detecting moving objects, ghosts, andshadows in video streams [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2003,25(10)：1337-1342
[122] Benedek C, Sziranyi T1. Markovian framework for foreground background shadowseparation of real world video scenes[C]//Proceedings of the7th Asian ConferenceComputer Vision, Daejeon, Korea,2006：898-907
[123] Zhang W, Fang X Z, Yang X K, et al. Moving cast shadows detection using ratioedge[J]. IEEE Transactions on Multimedia,2007,9(6):1202-1214
[124]Boiman O,Shechtman E,Irani M. Indefense of nearest-neighbor based imageclassification[C]//IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,Alaska,USA,2008：1-8
[125] Wang Z, Hu Y, Chia L T. Learning instance-to-class distance for human actionrecognition[C]//16th IEEE International Conference on Image Processing,Cairo,Egypt2009：3545-3548
[126] Huang Y, Xu D, Cham T J.Face and human gait recognition using image-to-classdistance[J].IEEE Transactions on Circuits and Systems for Video Technology,2010,20(3)：431-438
[127]Wang Z, Hu Y,Chia L T. Image-to-class distance metric learning for imageclassification[C]//European Conference on Computer Vision, Crete,Greece,2010：709-719
[128] Behmo R,Marcombes P,Dalalyan A,Prinet V. Towards optimal naive Bayes nearestneighbor[C]//European Conference on Computer Vision, Crete,Greece,2010：171-184
[129] Wang Z, Hu Y, Chia L T. Improved learning of I2C distance and accelerating theneighborhood search for image classification[J].Pattern Recognition,2011,44：2384-2394
[130] Wang Z, Feng J, Yan S, et al. Linear Distance Coding for Image Classification[J].IEEEtransactions on image processing,2013,22(2)：537-548
[131] Galbiati J, Allende H and Becerra C. Dynamic Image Segmentation Method UsingHierarchical Clustering[C]//14th Iberoamerican Conference on Pattern Recognition：Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications,Guadalajara, Jalisco, Mexico,2009：177-184
[132] Li W, Zhang Z, and Liu Z. Expandable data-driven graphical modeling of humanactions based on salient postures[J].IEEE Trans. Circuits and Systems for VideoTechnology,2008,18(11)：1499-1510.
[133] Fei-Fei L, Perona P．A bayesian hierarchical model for learning natural scenecategories[C]//IEEE Computer Society Conference on Computer Vision and PatternRecognition, San Diego, CA, USA,2005,2：524-531
[134] Liang P, Li S, Wang C．A new image matching algorithm based on scale adaptedinterest point detection[C]//Proceedings of International Conference on Information andAutomation, Zhuhai, China,2009：330-335
[135]Bouchard G, Triggs．Hierarchical part-based visual object categorization[C]//IEEEComputer Society Conference on Computer Vision and Pattern Recognition, SanDiego, CA, USA,2005,1：710-715
[136] Ommer B, Buhmann J M．Learning the compositional nature of visual object categoriesfor recognition[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(3)：501-516
[137] Nister D, Stewenius H．Scalable recognition with a vocabulary tree[C]//IEEEComputer Society Conference on Computer Vision and Pattern Recognition, New York,NY, USA,2006,2：2161-2168
[138] Lin Z, Jiang Z, Davis L S．Recognizing actions by shape-motion prototype trees[C]//IEEE12th International Conference on Computer Vision, Kyoto, Japan,2009：444-451
[139] Reddy K K, Liu J, Shah M．Incremental action recognition using feature-tree[C]//IEEE12th International Conference on Computer Vision, Kyoto, Japan,2009：1010-1017
[140] Mikolajczyk K, Uemura H．Action recognition with motion-appearance vocabularyforest[C]//IEEE Conference on Computer Vision and Pattern Recognition, Anchorage,Alaska, USA,2008：1-8
[141] Moosmann F, Triggs B, Jurie F．Fast discriminative visual codebooks using randomizedclustering forests[J]．Advances in Neural Information Processing Systems,2007,19：985-992
[142] Morioka N, Satoh S．Building compact local pairwise codebook with joint feature spaceclustering[C]//European Conference on Computer Vision, Crete,Greece,2010：692-705
[143] C. Bishop．Pattern recognition and machine learning [M]．Spinger-Verlag,2006
[144] Agarwal S, Awan A, Roth D．Learning to detect objects in image via a sparse,part-based representation[J]．IEEE Transactions on Pattern Analysis and MachineIntelligence,2004,26(11)：1475-1490
[145] Fritz M, Leibe B, Caputo B, et al．Integrating representative and discriminant modelsfor object category detection[C]//Proceedings of International Conference on ComputerVision,Beijing,China,2005,(2)：1363-1370
[146] Pan H, Zhu Y P, Xia L Z, et al．Combining generic and class-specific codebooks forobject categorization and detection[C]//Proceedings of International Conference onAcoustic, Speech and Signal Processing,Prague,Czech,2011：2264-2267
[147] Lazebnik S, Schmid C, Ponce J. Beyond bags of features：Spatial pyramid matching forrecognizing natural scene categories[C]//IEEE Computer Society Conference onComputer Vision and Pattern Recognition, New York, NY, USA,2006,2：2169-2178
[148] Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding forimage classification[C]//IEEE Conference on Computer Vision and PatternRecognition, Miami, Florida, USA,2009：1794-1801
[149] Ren X, Ramanan D.Histograms of Sparse Codes for Object Detection[C]//IEEEConference on Computer Vision and Pattern Recognition, Portland, Oregon, USA,2013：1-8
[150] Liu Z, Xiong H. Object detection and localization using random forest[C]//SecondInternational Conference on Intelligent System Design and Engineering Application,Sanya, China,2012：1074-1078
[151] Moosmann F，Triggs B， Jurie F．Fast discriminative visual codebooks usingrandomized clustering forests[J]．Advances in Neural Information Processing Systems,2007,19：985-992
[152] Schroff F, Criminisi A, Zisserman A．Object class segmentation using randomforests[C]//The British Machine Vision Conference, Leeds, UK,2008：1-4
[153] Kohli P, Pelillo M, Bischof H． Context-Sensitive Decision Forests for ObjectDetection[J]．Advances in Neural Information Processing Systems,2012：440-448
[154] Gall J, Lempitsky V. Class-specific Hough forests for object detection [C]//IEEEConference on Computer Vision and Pattern Recognition, Miami, FL, USA,2009：1022-1029
[155] Fanelli G, Gall J, Van Gool L J. Hough transform-based mouth localization foraudio-visual speech recognition[C]//The British Machine Vision Conference, London,UK,2009：1-11
[156]Yao A, Gall J, Van Gool L．A hough transform-based voting framework for actionrecognition［C］//IEEE Computer Society Conference on Computer Vision and PatternRecognition. San Francisco, CA,2010：2061-2068
[157] Fanelli G, Yao A, Noel P L, et al. Hough Forest-based Facial Expression Recognitionfrom video sequences[C]//The European Conference on Computer Vision, Heraklion,Greece,2010：195-206
[158] Payet N, Todorovic S. Hough Forest Random Field for Object Recognition andSegmentation[J]．IEEE transactions on pattern analysis and machine intelligence,2012，35(5)：1066-1079
[159] Wohlhart P, Schulter S, K stinger M, et al. Discriminative Hough Forests for ObjectDetection[C]//The British Machine Vision Conference, Surrey,UK,2012：1-11
[160] Breiman L. Random Forests [J]．Machine learning,2001,45(1)：5-32
[161] Friedman J H．Greedy function approximation：a gradient boosting machine[J]．Annalsof Statistics,2001,29(5)：1189-1232
[162] Byrd R H, Lu P, Nocedal J, et al. A limited memory algorithm for bound constrainedoptimization[J]. SIAM Journal on Scientific Computing,1995,16(5)：1190-1208
[163] Leistner C,Saffari A, Santner J, et al. Semi-supervised random forests[C]//IEEEInternational Conference on Computer Vision, Miami, Florida, USA,2009：506-513
[164] Felzenszwalb P F, Girshick R B, McAllester D, et al． Object detection withdiscriminatively trained part-based models [J]． Pattern Analysis and MachineIntelligence, IEEE Transactions on,2010,32(9)：1627-1645
[165] Razavi N, Gall J, Kohli P, et al．Latent hough transform for object detection[C]//TheEuropean Conference on Computer Vision, Florence, Italy,2012：312-325
[166] Nima Razavi, Nima S. Alvar, Juergen Gall, et al．Sparsity Potentials for DetectingObjects with Hough Transform[C]//The British Machine Vision Conference, Surrey,UK,2012：11.1-11.10