智能监控系统中人体及其多种姿态的识别技术研究
|
摘要
智能视觉监控技术是计算机视觉领域一个新兴的应用方向和备受关注的前沿课题,监控的目的常常是对监控场景中的异常情况或监控对象的异常行为进行检测、分析,因此,对人的多种姿态进行识别有着十分重要的意义。本文针对户外智能监控中车辆、人体直立、哈腰、匍匐三种姿态的识别方法进行了研究。
首先,为了便于车辆及三种人体姿态识别的研究,建立了样本库,每种目标均采用了不同大小、多种方位的实物进行拍摄,每种样本的数量为200幅。为了进行多种目标识别方法的研究,提取了多种特征参数,如宽高比、惯性主轴角、矩形度、形状复杂度、离心率等,并研究了多种细化算法及轮廓提取算法,细化算法包括OPTA细化算法、Zhang细化算法、Rosenfeld细化算法、横井法细化算法,在对四种细化算法进行比较后发现横井法细化方法速度较快,细化效果较好,但存在细化不太彻底及细化不平滑的问题,因此,对其进行改进,改进后的算法细化效果更加彻底、平滑,利用细化后的目标及原目标二值图设计了双腿搜素算法及头部搜素算法,从而为后续决策树式识别方法的研究做好了准备。
其次,为了寻找到一种较好的识别方法,对一般常用的识别方法进行了研究,包括多种不变矩方法、RBF神经网络分类法及支持向量机分类法,实验表明多种不变矩方法不适于多种人体姿态的识别,而RBF神经网络及支持向量机方法的分类性能对运动目标特征量的依赖性较大,在初次尝试提取三种特征量进行分类后,发现正面哈腰人体与直立人体不能较好的区分。因此,提出了基于投影直方图的特征量提取方法,利用此特征量进行训练、分类,可得到较好的识别效果,平均识别率达到96%。此外,由于神经网络及支持向量机的内部结构较为复杂,设计实现时步骤较为繁琐,而且需要大量样本进行训练。因此,提出了一种结构简单、便于理解的识别方法研究,基于决策树式的识别研究。
最后,由于决策树具有把复杂分类问题分解为多个简单分类问题的特点,同时可以把人的经验知识加入其中,采取小样本就可设计实现,所以又进行了基于决策树的人体及其姿态的识别研究。识别原理为:首先利用矩形度与形状复杂度变化率将车辆与人体区分出来,然后使用宽高比粗略估计出人体目标,进一步搜素人体双腿或头部从而确定人体,最后利用头部与腿部位置的匹配判定人体姿态,系统通过多帧综合判别的结果最终确定了目标种类及人体姿态。考虑到监控系统中多目标同时出现的几率较大,因此在单目标识别的基础上,提出了多运动目标的识别方法,利用对各目标轮廓跟踪的方法将其标记,单独提取后进行识别分析,达到多目标中单目标提取、识别的目的。
利用样本库对决策树式识别方法进行测试,实验结果表明,该方法具有算法简单,识别率高,平均为96%,识别速度快,每帧识别时间平均为0.4322s,以及多方位人体姿态识别的特点。为智能监控系统中人体行为理解的任务做了基础研究工作。
Intelligent surveillance technology is a new application and hot research subject in computer vision area. The aim of surveillance system is detecting moving object and analysising abnormal situation or abnormal object in surveillance scene, so the recognition of various human posture is very important. This paper explores the means of recognition of cars and three human body postures, including standing body, stooping body and creeping body, in outdoor Intelligent surveillance system.
First, in order to make research on the recognition of cars and human body postures conveniently, we build a sample library for various size and orientation moving objects, every kind object has the number of 200 samples. Many character parameters have been extracted, such as the ratio of width and height of object, inertial spindle angular, rectangle degree, shape complexity degree, eccentricity, etc for the research of many recognition methods. And many thinning algorithms and two silhouette tracking algorithms have been introduced for the design of human head and legs searching algorithms, including OPTA thinning algorithm, Zhang’s thinning algorithm, Rosenfeld’s thinning algorithm, Hengjing thinning algorithm. After comparing the four thinning algorithms, we find the hengjing thinning algorithm has a good thinning performance and needs less execution time, but it also has a problem that it doesn’t have a complete and smoothing thinning effect. Having improved the hengjing thinning algorithm, the object can be thinned thoroughly and smoothly. The human’s head and legs searching algorithm prepares for recognition method research based on decision tree later.
Secondly, in order to develop a better recognition method, we make research on the common pattern recognition methods, including a variety of invariant moments method, RBF neural network classification method, SVM classification method. Experimental results demonstrate the first method is not very useful in presence of classification and the performance of the last two methods are obviously strictly related to the selected features. Having selected three features to test, we find a problem which is the misclassification between the front stooping human body and creeping human body posture. Therefore, we propose a method of choosing features based on the histograms of horizontal and vertical projections. The selected features have a large discriminatory capability and a good recognition ratio, which is up to 96%. Moreover, considering the complicated structure of the neural network and SVM, it is hard to design and needs lots of samples to train. So we present an approach with a simple structure, the decision tree system.
Finally, for the decision tree has advantages of making complex classification problem solved simply and adding the experiences of human to the decision, so the decision tree recognition system can be designed using a small number of samples. The recognition principle is distinguishing the car and human by rectangular degree and shape complexity degree firstly, and then recognizing the human object roughly using the ratio of width and height of the object, at last confirming the human body through the head and legs detecting algorithms and judging the human posture by location of human’s head and legs. The system using many frame recognition results as the system recognition results, which confirms the object class and the human posture. Considering the high ratio of multiple moving objects appearing, we present a multiple objects recognition methods based on the single object recognition method. Marking each object through tracking its silhouette, and recognizes it after extracting the single object. At last we realize the purpose of extracting single object and recognizing it in multiple objects appearing situation.
Testing the recognition system based on decision tree, experimental results show that, this approach has a simple algorithm, a good recognition ratio, which ups to 96%, a fast recognition speed, which is 0.4322s, and a advantage of many orientation of human body posture recognition. This paper provides a fundamental research for human body activity understanding task in intelligent surveillance system.
首先,为了便于车辆及三种人体姿态识别的研究,建立了样本库,每种目标均采用了不同大小、多种方位的实物进行拍摄,每种样本的数量为200幅。为了进行多种目标识别方法的研究,提取了多种特征参数,如宽高比、惯性主轴角、矩形度、形状复杂度、离心率等,并研究了多种细化算法及轮廓提取算法,细化算法包括OPTA细化算法、Zhang细化算法、Rosenfeld细化算法、横井法细化算法,在对四种细化算法进行比较后发现横井法细化方法速度较快,细化效果较好,但存在细化不太彻底及细化不平滑的问题,因此,对其进行改进,改进后的算法细化效果更加彻底、平滑,利用细化后的目标及原目标二值图设计了双腿搜素算法及头部搜素算法,从而为后续决策树式识别方法的研究做好了准备。
其次,为了寻找到一种较好的识别方法,对一般常用的识别方法进行了研究,包括多种不变矩方法、RBF神经网络分类法及支持向量机分类法,实验表明多种不变矩方法不适于多种人体姿态的识别,而RBF神经网络及支持向量机方法的分类性能对运动目标特征量的依赖性较大,在初次尝试提取三种特征量进行分类后,发现正面哈腰人体与直立人体不能较好的区分。因此,提出了基于投影直方图的特征量提取方法,利用此特征量进行训练、分类,可得到较好的识别效果,平均识别率达到96%。此外,由于神经网络及支持向量机的内部结构较为复杂,设计实现时步骤较为繁琐,而且需要大量样本进行训练。因此,提出了一种结构简单、便于理解的识别方法研究,基于决策树式的识别研究。
最后,由于决策树具有把复杂分类问题分解为多个简单分类问题的特点,同时可以把人的经验知识加入其中,采取小样本就可设计实现,所以又进行了基于决策树的人体及其姿态的识别研究。识别原理为:首先利用矩形度与形状复杂度变化率将车辆与人体区分出来,然后使用宽高比粗略估计出人体目标,进一步搜素人体双腿或头部从而确定人体,最后利用头部与腿部位置的匹配判定人体姿态,系统通过多帧综合判别的结果最终确定了目标种类及人体姿态。考虑到监控系统中多目标同时出现的几率较大,因此在单目标识别的基础上,提出了多运动目标的识别方法,利用对各目标轮廓跟踪的方法将其标记,单独提取后进行识别分析,达到多目标中单目标提取、识别的目的。
利用样本库对决策树式识别方法进行测试,实验结果表明,该方法具有算法简单,识别率高,平均为96%,识别速度快,每帧识别时间平均为0.4322s,以及多方位人体姿态识别的特点。为智能监控系统中人体行为理解的任务做了基础研究工作。
Intelligent surveillance technology is a new application and hot research subject in computer vision area. The aim of surveillance system is detecting moving object and analysising abnormal situation or abnormal object in surveillance scene, so the recognition of various human posture is very important. This paper explores the means of recognition of cars and three human body postures, including standing body, stooping body and creeping body, in outdoor Intelligent surveillance system.
First, in order to make research on the recognition of cars and human body postures conveniently, we build a sample library for various size and orientation moving objects, every kind object has the number of 200 samples. Many character parameters have been extracted, such as the ratio of width and height of object, inertial spindle angular, rectangle degree, shape complexity degree, eccentricity, etc for the research of many recognition methods. And many thinning algorithms and two silhouette tracking algorithms have been introduced for the design of human head and legs searching algorithms, including OPTA thinning algorithm, Zhang’s thinning algorithm, Rosenfeld’s thinning algorithm, Hengjing thinning algorithm. After comparing the four thinning algorithms, we find the hengjing thinning algorithm has a good thinning performance and needs less execution time, but it also has a problem that it doesn’t have a complete and smoothing thinning effect. Having improved the hengjing thinning algorithm, the object can be thinned thoroughly and smoothly. The human’s head and legs searching algorithm prepares for recognition method research based on decision tree later.
Secondly, in order to develop a better recognition method, we make research on the common pattern recognition methods, including a variety of invariant moments method, RBF neural network classification method, SVM classification method. Experimental results demonstrate the first method is not very useful in presence of classification and the performance of the last two methods are obviously strictly related to the selected features. Having selected three features to test, we find a problem which is the misclassification between the front stooping human body and creeping human body posture. Therefore, we propose a method of choosing features based on the histograms of horizontal and vertical projections. The selected features have a large discriminatory capability and a good recognition ratio, which is up to 96%. Moreover, considering the complicated structure of the neural network and SVM, it is hard to design and needs lots of samples to train. So we present an approach with a simple structure, the decision tree system.
Finally, for the decision tree has advantages of making complex classification problem solved simply and adding the experiences of human to the decision, so the decision tree recognition system can be designed using a small number of samples. The recognition principle is distinguishing the car and human by rectangular degree and shape complexity degree firstly, and then recognizing the human object roughly using the ratio of width and height of the object, at last confirming the human body through the head and legs detecting algorithms and judging the human posture by location of human’s head and legs. The system using many frame recognition results as the system recognition results, which confirms the object class and the human posture. Considering the high ratio of multiple moving objects appearing, we present a multiple objects recognition methods based on the single object recognition method. Marking each object through tracking its silhouette, and recognizes it after extracting the single object. At last we realize the purpose of extracting single object and recognizing it in multiple objects appearing situation.
Testing the recognition system based on decision tree, experimental results show that, this approach has a simple algorithm, a good recognition ratio, which ups to 96%, a fast recognition speed, which is 0.4322s, and a advantage of many orientation of human body posture recognition. This paper provides a fundamental research for human body activity understanding task in intelligent surveillance system.
引文
[1]黄琳.视频监控系统中的关键技术研究.西南交通大学硕士学位论文. 2006.04
[2] Robert T.Collins,Alan J.Lipton et al. A system for video surveillance and monitoring:VSAM final report. CMU-RI-TR-00-12, Robotic Institute Carnegie Mellon University, 2000.
[3] Haritaoglu I, Harwood D, Davis L. W4: Real-Time Surveillance of People and Their Activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000.
[4]Xinyu Wu, Yongsheng OU et al. A detection system for human abnormal behavior. Intelligent Robots and Systems,2005.(IROS 2005).2005 IEEE/RSJ International Conference on.
[5] Gregory Rogez et al. A spatio-temporal 2D-models framework for human pose recovery in monocular sequences. Pattern Recognition 41 (2008) 2926-2944.
[6] Buccolieri.F, Distante.C. Human posture recognition using active contours and radial basis function neural network. In Advanced Video and Signal Based Surveillance,2005.IEEE Conference.213-218.
[7] Tony Jan, Massimo Piccardi, Thomas Hintz. Neural network classifiers for automated video surveillance. In Proceedings of 2003 IEEE XIII Workshop on Neural Network for Signal Processing[C],Toulouse, France,2003:729-738.
[8] Leong lat-fai, Fang Jing-Jing. Automatic body feature extraction from a marker-less scanned human body. Computer-Aided Design 39.(2007.07)568-582.
[9] Remagnino P, Tan T, Baker K. Agent orientated Annotation in Model Based Visual Surveillance[A]. In Processings of IEEE International Conference on Computer Vision[C], Bombay India 1998 857-862.
[10] Ross Cutler, Larry S.Davis. Robust real-time periodic motion detection, analysis and applications[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2000.
[11]潘锋,王宣银等.智能监控中基于头肩特征的人体检测方法研究.浙江大学学报,2004年04期.397-401.
[12]刘菲,唐振民.基于不变矩的实时人形监测与识别系统.小型微型计算机系统,2003年09期.1665-1668.
[13]贾昔玲.复杂背景下基于序列图像的人体识别与跟踪.西化大学硕士学位论文.2007.04.32-44
[14]刘菲.运动人体行为分析系统及关键技术研究.西安电子科技大学硕士学位论文.2007.01.49-52
[15]倪福川,贺贵明,龙磊.基于不变矩的人形“头肩像”识别技术.计算机工程.2005年10期.
[16]唐勇,姜昱明.彩色图像序列中运动人体轮廓提取.计算机工程与设计,2006年20期.
[17]胡长勃,冯涛.基于主元分析法的行为识别.中国图象图形学报,2000年10.期.
[18] I Cohen,N, Sebe,A, et al. Facial expression recognition from video sequences.In Proc ICME,2002,121-124.
[19] Bernard Boulay,et al. Applying 3D human model in a posture recognition system. In Pattern Recognition 2006.11.1788-1796
[20] Yanxi Liu, S.Mitra. Human identification versus expression classification via bagging on facial asymmetry.tech.report CMU-RI-TR-03-08 ,Robotics Institute, Carnegie Mellon University,April,2003.
[21] Ahmed Bilal Ashraf et al. Learning patch correspondences for improved viewpoint invariant face recognition. In IEEE International Conference on Computer Vision and Pattern Recognition(CVPR),June,2008
[22]方帅.计算机智能视频监控系统关键技术研究,东北大学博士学位论文,2005.01.3-5.
[23]马宁.指纹图像的二值化与细化研究,南京理工大学硕士学位论文,2006.06.43-44.
[24] Chin R T, Wan H K, Stover D L. A one-pass thinning algorithm and its parallel implementation. Computer vision graphics image processing.1987(1):30-40.
[25] T.Y.Zhang, C.Y.Suen. A fast parallel algorithm for thinning digital patterns.Image processing and Computer Vision.1984.03.236-239.
[26] R.Stefanelli, A.Rosenfeld. Some parallel thinning algorithms for digital pictures. Journal of the ACM(JACM). 1971.04.255-264.
[27]方如明,蔡健荣等.《计算机图像处理技术及其在农业工程中的应用》.清华大学出版社.1999.
[28] Hu M K. Visual pattern recognition by moment invariants[J]. IEEE Trans On Information Theory.1962.02.179~187
[29] Flusser J,Suk T. Pattern recognition by affine moment invariants. Pattern Recognition. 1993.26(1):167~174
[30]穆云峰.RBF神经网络学习算法在模式分类中的应用研究.大连理工大学硕士学位论文.2006.12:8~10
[31]李盼池,肖红等.支持向量机在模式分类中的应用.大庆石油学院学报.2003年06期.59-61.
[32]杜树新,吴铁军.模式识别中的支持向量机方法.浙江大学学报(工学版).2003年09期.521-526.
[33]黄发良,钟智.用于分类的支持向量机.广西师范学院学报(自然科学版).2004年09期.75-78
[34]陈沛玲.决策树分类算法优化研究.中南大学硕士学位论文.2007年05期:17~20
[35]胡江洪.基于决策树的分类算法研究.武汉理工大学硕士学位论文.2006年04期:5~16
[36]卜亚杰.决策树分类算法的研究及应用.华北电力大学硕士学位论文.2007年12期:5~14
[37]杨淑莹,章慎锋等.一种特定问题多目标识别系统的设计.河北工业大学学报.2005年06期.102-105.
[38]陈忠碧,张启衡.一种适合于多目标检测的图像分割方法.光电工程.2004年05期.34-37.
[39]李娜,方卫宁.基于视频流的地铁人群目标识别.北京交通大学学报(自然科学版).2006年01期.96-99.
[40]张天序,刘进.目标不变矩的稳定性研究.红外与毫米波学报.2004年06期.197-200.
[41]徐学强,汪渤等.一种新型不变矩在图像识别中的应用.光学技术.2007年07期.580-583.
[42]李迎春,陈贺新等.基于仿射不变矩的神经网络目标识别.计算机工程.2004年01期.31-33.
[43]翟乃斌,苏建等.基于不变矩的机器视觉车辆类型识别技术.武汉理工大学学报.2007年04期7-10.
[44]刘亦书,杨力华,孙倩.轮廓矩不变量及其在物体形状识别中的应用.中国图象图形学报.2004年03期.308-311
[45]杨静,毛宗源.基于PCA和神经网络的识别方法研究.计算机工程与应用. 2007年25期.246-248.
[46]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报.2002.25卷,第3期.1-6.
[47]游素亚,徐光祐.立体视觉研究的现状与进展.中国图象图形学报.1997年01期.17-20.
[48]黄建强,陈祥献,汪乐宇.面向情景自觉计算的人体识别跟踪系统.仪器仪表学报.2002年10期.35-39.
[49]刘相滨,向坚持,王胜春.人行为识别与理解研究探讨.计算机与现代化.2004年12期.53-56.
[50]李华.矩方法及其在几何形状描述中的应用.中国科学院博士学位论文.2005年04期.
[51]程德胜,宣源等.红外图像模糊识别筛选方法.光电技术应用.2008年02期.86-89.
[52]刘晓冬,苏光大等.一种可视化智能户外监控系统.中国图象图形学报.2000年12期.1024-1028.
[53]胡正平,吴燕等.基于几何分析的支持向量机快速训练与分类算法.中国图象图形学报.2007年01期.82-86.
[54]左森,郭晓松等.多项式核函数SVM快速分类算法.计算机工程.2007年03期.27-29.
[55]郭勇,唐敏学,张桂菊.基于LVQ网络处理的多目标分类识别.2007年07期.55-59.
[56]袁蕴.基于行为分析的普适计算机智能监控系统.北京交通大学硕士学位论文.2006年12期
[2] Robert T.Collins,Alan J.Lipton et al. A system for video surveillance and monitoring:VSAM final report. CMU-RI-TR-00-12, Robotic Institute Carnegie Mellon University, 2000.
[3] Haritaoglu I, Harwood D, Davis L. W4: Real-Time Surveillance of People and Their Activities. IEEE Trans Pattern Analysis and Machine Intelligence, 2000.
[4]Xinyu Wu, Yongsheng OU et al. A detection system for human abnormal behavior. Intelligent Robots and Systems,2005.(IROS 2005).2005 IEEE/RSJ International Conference on.
[5] Gregory Rogez et al. A spatio-temporal 2D-models framework for human pose recovery in monocular sequences. Pattern Recognition 41 (2008) 2926-2944.
[6] Buccolieri.F, Distante.C. Human posture recognition using active contours and radial basis function neural network. In Advanced Video and Signal Based Surveillance,2005.IEEE Conference.213-218.
[7] Tony Jan, Massimo Piccardi, Thomas Hintz. Neural network classifiers for automated video surveillance. In Proceedings of 2003 IEEE XIII Workshop on Neural Network for Signal Processing[C],Toulouse, France,2003:729-738.
[8] Leong lat-fai, Fang Jing-Jing. Automatic body feature extraction from a marker-less scanned human body. Computer-Aided Design 39.(2007.07)568-582.
[9] Remagnino P, Tan T, Baker K. Agent orientated Annotation in Model Based Visual Surveillance[A]. In Processings of IEEE International Conference on Computer Vision[C], Bombay India 1998 857-862.
[10] Ross Cutler, Larry S.Davis. Robust real-time periodic motion detection, analysis and applications[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2000.
[11]潘锋,王宣银等.智能监控中基于头肩特征的人体检测方法研究.浙江大学学报,2004年04期.397-401.
[12]刘菲,唐振民.基于不变矩的实时人形监测与识别系统.小型微型计算机系统,2003年09期.1665-1668.
[13]贾昔玲.复杂背景下基于序列图像的人体识别与跟踪.西化大学硕士学位论文.2007.04.32-44
[14]刘菲.运动人体行为分析系统及关键技术研究.西安电子科技大学硕士学位论文.2007.01.49-52
[15]倪福川,贺贵明,龙磊.基于不变矩的人形“头肩像”识别技术.计算机工程.2005年10期.
[16]唐勇,姜昱明.彩色图像序列中运动人体轮廓提取.计算机工程与设计,2006年20期.
[17]胡长勃,冯涛.基于主元分析法的行为识别.中国图象图形学报,2000年10.期.
[18] I Cohen,N, Sebe,A, et al. Facial expression recognition from video sequences.In Proc ICME,2002,121-124.
[19] Bernard Boulay,et al. Applying 3D human model in a posture recognition system. In Pattern Recognition 2006.11.1788-1796
[20] Yanxi Liu, S.Mitra. Human identification versus expression classification via bagging on facial asymmetry.tech.report CMU-RI-TR-03-08 ,Robotics Institute, Carnegie Mellon University,April,2003.
[21] Ahmed Bilal Ashraf et al. Learning patch correspondences for improved viewpoint invariant face recognition. In IEEE International Conference on Computer Vision and Pattern Recognition(CVPR),June,2008
[22]方帅.计算机智能视频监控系统关键技术研究,东北大学博士学位论文,2005.01.3-5.
[23]马宁.指纹图像的二值化与细化研究,南京理工大学硕士学位论文,2006.06.43-44.
[24] Chin R T, Wan H K, Stover D L. A one-pass thinning algorithm and its parallel implementation. Computer vision graphics image processing.1987(1):30-40.
[25] T.Y.Zhang, C.Y.Suen. A fast parallel algorithm for thinning digital patterns.Image processing and Computer Vision.1984.03.236-239.
[26] R.Stefanelli, A.Rosenfeld. Some parallel thinning algorithms for digital pictures. Journal of the ACM(JACM). 1971.04.255-264.
[27]方如明,蔡健荣等.《计算机图像处理技术及其在农业工程中的应用》.清华大学出版社.1999.
[28] Hu M K. Visual pattern recognition by moment invariants[J]. IEEE Trans On Information Theory.1962.02.179~187
[29] Flusser J,Suk T. Pattern recognition by affine moment invariants. Pattern Recognition. 1993.26(1):167~174
[30]穆云峰.RBF神经网络学习算法在模式分类中的应用研究.大连理工大学硕士学位论文.2006.12:8~10
[31]李盼池,肖红等.支持向量机在模式分类中的应用.大庆石油学院学报.2003年06期.59-61.
[32]杜树新,吴铁军.模式识别中的支持向量机方法.浙江大学学报(工学版).2003年09期.521-526.
[33]黄发良,钟智.用于分类的支持向量机.广西师范学院学报(自然科学版).2004年09期.75-78
[34]陈沛玲.决策树分类算法优化研究.中南大学硕士学位论文.2007年05期:17~20
[35]胡江洪.基于决策树的分类算法研究.武汉理工大学硕士学位论文.2006年04期:5~16
[36]卜亚杰.决策树分类算法的研究及应用.华北电力大学硕士学位论文.2007年12期:5~14
[37]杨淑莹,章慎锋等.一种特定问题多目标识别系统的设计.河北工业大学学报.2005年06期.102-105.
[38]陈忠碧,张启衡.一种适合于多目标检测的图像分割方法.光电工程.2004年05期.34-37.
[39]李娜,方卫宁.基于视频流的地铁人群目标识别.北京交通大学学报(自然科学版).2006年01期.96-99.
[40]张天序,刘进.目标不变矩的稳定性研究.红外与毫米波学报.2004年06期.197-200.
[41]徐学强,汪渤等.一种新型不变矩在图像识别中的应用.光学技术.2007年07期.580-583.
[42]李迎春,陈贺新等.基于仿射不变矩的神经网络目标识别.计算机工程.2004年01期.31-33.
[43]翟乃斌,苏建等.基于不变矩的机器视觉车辆类型识别技术.武汉理工大学学报.2007年04期7-10.
[44]刘亦书,杨力华,孙倩.轮廓矩不变量及其在物体形状识别中的应用.中国图象图形学报.2004年03期.308-311
[45]杨静,毛宗源.基于PCA和神经网络的识别方法研究.计算机工程与应用. 2007年25期.246-248.
[46]王亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报.2002.25卷,第3期.1-6.
[47]游素亚,徐光祐.立体视觉研究的现状与进展.中国图象图形学报.1997年01期.17-20.
[48]黄建强,陈祥献,汪乐宇.面向情景自觉计算的人体识别跟踪系统.仪器仪表学报.2002年10期.35-39.
[49]刘相滨,向坚持,王胜春.人行为识别与理解研究探讨.计算机与现代化.2004年12期.53-56.
[50]李华.矩方法及其在几何形状描述中的应用.中国科学院博士学位论文.2005年04期.
[51]程德胜,宣源等.红外图像模糊识别筛选方法.光电技术应用.2008年02期.86-89.
[52]刘晓冬,苏光大等.一种可视化智能户外监控系统.中国图象图形学报.2000年12期.1024-1028.
[53]胡正平,吴燕等.基于几何分析的支持向量机快速训练与分类算法.中国图象图形学报.2007年01期.82-86.
[54]左森,郭晓松等.多项式核函数SVM快速分类算法.计算机工程.2007年03期.27-29.
[55]郭勇,唐敏学,张桂菊.基于LVQ网络处理的多目标分类识别.2007年07期.55-59.
[56]袁蕴.基于行为分析的普适计算机智能监控系统.北京交通大学硕士学位论文.2006年12期
© 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 |