摘要
近年来,基于红外热成像的人体目标检测、跟踪与行为识别正逐渐成为智能视频监控、自动车辆辅助驾驶和高级人机接口等领域十分活跃的课题。与可见光图像相比,红外图像对于解决光照变化、阴影和夜间可视性等影响传统计算机视觉的问题提供了有力的支持,而且红外图像也具备较优的分割性能,但是目前存在的人体运动分析算法在红外图像中表现不佳;特别是红外图像本身固有的特点,如低对比度、低信噪比、无法校验的黑白极性反转以及人体周围易出现的光晕效应等,使得红外图像中人体目标的检测、跟踪和行为识别依然是一个极具挑战性的课题。本论文主要对红外热成像在智能视频监控领域中应用的关键技术进行研究,分析了红外热成像系统原理以及红外图像中人体目标成像的特点,研究内容涉及人体目标的检测、跟踪及其行为识别等方向。论文的主要研究成果如下:
①为了快速检测到序列红外图像中的人体目标,提出了一种基于复合分类特征的序列红外人体实时检测方法。该方法首先建立序列图像的时空域联合的概率分布模型,同时采用基于马尔科夫随机场的最大后验概率模型的前景检测方法,获取人体候选区域的可能位置,然后融合方向梯度直方图特征、形体特征和亮度分布惯性特征来提高描述人体候选区域特征的准确性,最后采用支持向量机对候选区域进行分类以检测出人体。实验表明,与单一形状特征或形状无关特征相比,提出的方法能够准确检测人体目标,同时提高了人体正确检测率,实现了序列红外人体目标的实时检测。
②为了获得更加精确的人体目标感兴趣区域的特征,提出了一种基于双密度双树复小波变换的小波熵特征的单帧红外人体鲁棒检测算法。该算法充分描述了红外图像中人体目标的多尺度分解频率空间的能量分布情况。其中,双密度双树复小波变换同时具有双树复小波变换和双密度小波变换的特性,如平移不变性、抗混叠性以及近似连续小波变换和良好的方向性;而小波熵能准确反映图像小波变换频率空间的能量分布信息,两者的结合使该算法能更好的描述图像特征。实验结果表明,本算法能够显著提高检测率和降低虚警率,是一种非常有效的红外人体检测方法。
③针对红外图像序列中人体目标鲁棒跟踪问题,提出了一种基于亮度-距离投影空间的红外人体跟踪算法。该算法结合红外图像中人体目标的亮度分布和形态特征,首先在以人体目标区域中心点为圆心的各个圆环域中统计其亮度信息,从而构建亮度-距离联合直方图对人体进行特征表达。然后将上述表达模型与粒子滤波相融合,设计了粒子滤波框架下的人体跟踪算法。实验结果表明,与传统的跟踪算法相比较,提出的算法具有更好的鲁棒性和可行性。
④为了克服红外图像中人体目标描述信息量不足的弱点,提出一种共生矩阵保局投影的红外人体跟踪方法。该方法的主要特点是构建了人体目标的共生矩阵保局投影子空间特征向量,并且融合了改进的均值漂移和粒子滤波跟踪框架。共生矩阵保局投影算法克服了红外图像中人体目标特征信息描述不足的缺点,同时具有保局投影算法所固有的线性映射的优点,而改进的均值漂移和粒子滤波框架则对非线性非高斯的系统有较好的适应性,从而使得系统能够实现鲁棒实时的人体目标跟踪。提出的方法在不同的红外视频序列中进行了充分的测试验证,理论分析和实验结果均表明所提出的方法是有效可行的,并且能够适应复杂的或有部分遮挡的场景。
⑤针对红外热成像中人体行为识别问题,构建了一个红外人体行为数据库,并且提出一种融合时空轮廓和局部尺度不变特征的识别方法。该方法首先使用高斯混合模型和背景减除算法提取红外图像序列中人体行为的时空轮廓,同时根据轮廓计算能量图。然后,基于三维角点检测算子和立方体梯度描述符获取红外图像人体行为的局部尺度不变特征。最后,融合时空轮廓能量图和局部尺度不变特征作为人体行为特征表征向量,使用最近邻分类实现行为识别。实验结果表明,提出的方法有机地融合了时空轮廓和局部不变特征的互补信息,取得了令人满意的识别效果。
上述研究成果主要针对智能视频监控领域的三个基本问题:人体目标检测、跟踪及其行为识别,并且按照它们在视频监控任务中所处的层次,由低到高有机连接,为红外热成像技术在智能视频监控领域的实用化提供了理论支持。
Recently,human detection, tracking and action recognition in thermal infrared imagery are very active in many fields, such as intelligent video surveillance, automatic vehicle driver assistance, and advanced human-machine interface. Compared with the visible light images, infrared images have almostly solved the problems of sudden illumination changes, shadows and poor night-time visibility in traditional computer vision fields, and furthermore have better performance on segmentation. However, the existing human motion analysis algorithms in infrared images have poor performance; especially the inherent characteristics of infrared images, such as the low contrast, low signal-to-noise ratio, uncalibrated white-black polarity changes, and the halo effect around the very hot or cold object, have made it a complex challenge for human detection, tracking and action recognition. In this paper, we aim at the study of key technology of thermal infrared imagery applied to the intelligent video surveillance systems. The principles of thermal infrared imagery and the characteristics of human target in infrared images are analyzed. Meanwhile, the human detection, tracking and action recognition algorithms are studied. The main contributions of the thesis can be concluded as follows.
①In order to rapidly detect human targets in infrared image sequences, a hybrid classification features-based human detection algorithm is proposed. First, it uses the MAP-MRF model to locate the regions of interest (ROI). Then the method combines the pedestrian’s shape-dependent and shape-independent features (including shape’s morphological feature, inertia-based feature and histograms of oriented gradients (HOG) feature) to describe the ROI in the round, and last uses support vector machine (SVM) to classify and detect the pedestrian region. Experimental results using several long-wave infrared image sequences show the proposed scheme can detect pedestrians accurately by combining hybrid classification features, and can be employed in real-time applications.
②In order to obtain more accurate target feature of human body in a single infrared image, a novel human detection algorithm based on double-density dual-tree complex wavelet transform (DD-DT CWT) of the wavelet entropy features is proposed. The DD-DT CWT combines the DT CWT and DD DWT and has the advantages of shift invariance, directional selectivity, freedom from aliasing, and a near-continuous wavelet transform. The proposed wavelet entropy properly reflects the energy distribution of the image in the frequency domain of the wavelet transform. The combination of DD-DT CWT and the wavelet entropy can thus describe the image features accurately. Experimental results have shown that our approach is very encouraging.
③According to the problem of robust human tracking in thermal infrared imagery, a novel algorithm based on the intensity-distance projection space is proposed. The algorithm combines the intensity distribution and morphological characteristics of the human target. The method constructs the ROI’s histogram representation in an intensity-distance projection space model. In addition, the tracking algorithm embeds the above mentioned representation model in the particle filter framework and updates the sample's representation model automatically. The experimental results show the proposed scheme performs more robust and stable than the classical tracking method.
④In order to overcome the weak object feature description ability of a single locality preserving projections (LPP) for pedestrian target in infrared images, a co-occurrence matrix locality preserving projections (COMLPP) method is proposed to improve the robust performance of real-time pedestrian tracking in infrared image sequences. The co-occurrence matrices of the training set are first generated, then the feature representation vector of the locality preserving projections subspaces is generated by applying the locality preserving projection method to the projected samples of the training set on the co-occurrence matrix subspaces. At last, the above mentioned pedestrian representation model in infrared images is embedded in an improved mean shift based particle filter framework. Experimental results using different infrared image sequences show the proposed scheme achieves success in real-time pedestrian tracking system. Meanwhile, the proposed method can be adapted to complex and occluding scenes.
⑤According to the problems of human action recognition in thermal infrared imagery, an infrared action database is constructed and a novel algorithm based on the fusion of human action silhouettes energy images and local scale-invariant features is proposed. The algorithm first makes use of the Gaussian mixture model and background subtraction to extract the human action silhouettes, while calculating the energy images for the action sequences. Then, the scale-invariant 3D Harris corner detector and brightness gradient cuboids descriptor are applied to obtain the local scale-invariant features from the action sequences. Finally, the human action is represented by fusing the energy images and local scale-invariant features, and recognized by using the nearest neighbor classifier. Experimental results show that the results of the proposed method are very promising.
The above creative works in the thesis, covering the main areas of intelligent video surveillance tasks which including human target detection, tracking and action recognition, from low level to high level technology, provide a theoretical support for the applications of thermal infrared imagery in video surveillance systems.
引文
[1] T. Moeslund, A. Hilton, V. Kruger. A survey of advances in vision-based human motion capture and analysis [J]. Computer Vision and Image Understanding, 2006, 104(2-3): 90-126.
[2] J. Davis, V. Sharma. Background-subtraction in thermal imagery using contour saliency [J]. International Journal of Computer Vision, 2007, 71(2): 161-181.
[3]明英,蒋晶珏.基于Cauchy分布的红外视频运动目标检测[J].红外与毫米波学报, 2008, 27(1): 65-71.
[4]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报, 2002, 25(3): 225-237.
[5] S. Avidan. Support vector tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8): 1064-1072.
[6] I. Laptev, P. Pérez. Retrieving actions in movies [C]. Proceedings of IEEE International Conference on Computer Vision, 2007.
[7] M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, T. Poggio. Pedestrian detection using wavelet templates [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997.
[8] A. El Maadi, X. Maldague. Outdoor infrared video surveillance: a novel dynamic technique for the subtraction of a changing background of IR images [J]. Infrared Physics & Technology, 2007, 49(3): 261-265.
[9] Y. Fang, K. Yamada, Y. Ninomiya, B. Horn, I. Masaki. A shape-independent method for pedestrian detection with far-infrared images [J]. IEEE Transactions on Vehicular Technology, 2004, 53(6): 1679-1697.
[10] J. Han, B. Bhanu. Human activity recognition in thermal infrared imagery [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[11] F. Xu, X. Liu, K. Fujimura. Pedestrian detection and tracking with night vision [J]. IEEE Transactions on Intelligent Transportation Systems, 2005, 6(1): 63-81.
[12] I. Haritaoglu, D. Harwood, L. Davis. W 4: real-time surveillance of people and theiractivities [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
[13] A. Mittal, N. Paragios. Motion-based background subtraction using adaptive kernel density estimation [C]. Proceedings of IEEE Computer Society Conference on Computer Visionand Pattern Recognition, 2004.
[14] N. Ohta. A statistical approach to background subtraction for surveillancesystems [C]. Proceedings of IEEE International Conference on Computer Vision, 2001.
[15] C. Stauffer, W. Grimson. Adaptive background mixture models for real-time tracking [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999.
[16] E. Stringa, C. Regazzoni. Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing, 2000, 9(1): 69-79.
[17] G. Foresti. Object recognition and tracking for remote video surveillance [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999, 9(7): 1045-1062.
[18] A. Lipton, H. Fujiyoshi, R. Patil. Moving target classification and tracking from real-time video [C]. Proceedings of IEEE Workshop on Applications of Compute Vision, 1998.
[19] F. Moscheni, S. Bhattacharjee, M. Kunt. Spatio-temporal segmentation based on region merging [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(9): 897-915.
[20] A. Neri, S. Colonnese, G. Russo, P. Talone. Automatic moving object and background separation [J]. Signal Processing, 1998, 66(2): 219-232.
[21] J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques [J]. International Journal of Computer Vision, 1994, 12(1): 43-77.
[22] A. Verri, S. Uras, E. DeMicheli. Motion Segmentation from optical flow [C]. Proceedings of the 5th Alvey Vision Conference, 1989.
[23] N. Friedman, S. Russell. Image segmentation in video sequences: a probabilistic approach [C]. Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence, 1997.
[24] G. McLachlan, T. Krishnan. The EM algorithm and extensions [M]. New York: Wiley, 1997.
[25] E. Stringa. Morphological change detection algorithms for surveillance applications [C]. Proceedings of British Machine Vision Conference, 2000.
[26] Y. Kuno, T. Watanabe, Y. Shimosakoda, S. Nakagawa. Automated detection of human for visual surveillance systemh [C]. Proceedings of IEEE International Conference on Pattern Recognition, 1996.
[27] R. Cutler, L. Davis. Robust real-time periodic motion detection, analysis, andapplications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 781-796.
[28] O. Javed, M. Shah. Tracking and Object Classification for Automated Surveillance [C]. Proceedings of European Conference on Computer Vision, 2002.
[29] T. Kanade, R. Collins, A. Lipton, P. Burt, L. Wixson. Advances in cooperative multi-sensor video surveillance [C]. Proceedings of DAPRA Image Understanding Workshop, 1998.
[30] A. Selinger, L. Wixson. Classifying moving objects as rigid or non-rigid without correspondences [C]. Proceedings of DAPRA Image Understanding Workshop, 1998.
[31] C. Stauffer. Automatic hierarchical classification using time-basedco-occurrences [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Rcognition, 1999.
[32]杨磊.复杂背景条件下的红外小目标检测与跟踪算法研究[D].上海交通大学: 2006.
[33]卓志敏.红外成像目标检测与跟踪技术研究[D].哈尔滨工程大学: 2007.
[34] V. Tom, T. Peli, M. Leung, J. Bondaryk. Morphology-based algorithm for point target detection in infrared backgrounds [C]. Proceedings of SPIE Signal and Data, 1993.
[35]熊辉,沈振康.低信噪比运动红外点目标的检测[J].电子学报, 1999, 27(12): 26-29.
[36]郑文龙,张涌,汤心溢,吴常泳.复杂背景下红外小目标实时识别方法研究[J].红外与毫米波学报, 2001, 20(6): 433-436.
[37]温佩芝,史泽林,于海斌.复杂海面背景红外小目标自动检测方法[J].红外与激光工程, 2003, 32(6): 590-593.
[38]杨磊,杨杰,郑忠龙.海空复杂背景中基于自适应局部能量阈值的红外小目标检测[J].红外与毫米波学报, 2006, 25(1): 41-45.
[39]刘涛,吕江北,王书宏,卢焕章.基于TDRNN的大气层外弹道式空间红外目标识别[J].电子与信息学报, 2010, 33(1): 80-85.
[40] H. Nanda, L. Davis. Probabilistic template based pedestrian detection in infrared videos [C]. Proceedings of IEEE Intelligent Vehicle Symposium, 2002.
[41] M. Bertozzi, A. Broggi, P. Grisleri, T. Graf, M. Meinecke. Pedestrian detection in infrared images [C]. Proceedings of IEEE Conference on Intelligent Transportation Systems, 2003.
[42] H. Sun, C. Hua, Y. Luo. A multi-stage classifier based algorithm of pedestrian detection in night with a near infrared camera in a moving car [C]. Proceedings of the Third International Conference on Image and Graphics, 2004.
[43] M. Leung, Y. Yang. First sight: a human body outline labeling system [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(4): 359-377.
[44] R. Polana, R. Nelson. Low level recognition of human motion [C]. Proceedings of IEEE Workshop on Motion of Non-Rigid and Articulated Objects, 1994.
[45] S. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, H. Wechsler. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[46] K. Pahlavan. Active robot vision and primary ocular processes [D]. Royal Institute ofTechnology: 1993.
[47] C. Wren, A. Azarbayejani, T. Darrell, A. Pentland. Pfinder: Real-time tracking of the human body [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785.
[48] J. Fan, J. Yu, G. Fujita, T. Onoye, L. Wu, I. Shirakawa. Spatiotemporal segmentation for compact video representation [J]. Signal Processing: Image Communication, 2001, 16(6): 553-566.
[49] I. Patras, E. Hendriks, R. Lagendijk. Video segmentation by MAP labeling of watershed segments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(3): 326-332.
[50] E. Steinbach, P. Eisert, B. Girod. Motion-based analysis and segmentation of image sequences using 3-D scene models [J]. Signal Processing, 1998, 66(2): 233-247.
[51] Y. Bar-Shalom. Tracking and data association [M]: Academic Press Professional, Inc. San Diego, CA, USA, 1987.
[52] Z. Zhang. Token tracking in a cluttered scene [J]. Image and Vision Computing, 1994, 12(2): 110-120.
[53] C. Hue, J. Le Cadre, P. Perez, R. IRISA. Sequential Monte Carlo methods for multiple target tracking anddata fusion [J]. IEEE Transactions on Signal Processing, 2002, 50(2): 309-325.
[54] M. Isard, A. Blake. Condensation-conditional density propagation for visual tracking [J]. International Journal of Computer Vision, 1998, 29(1): 5-28.
[55] M. Isard, A. Blake. ICONDENSATION: unifying low-level and high-level tracking in a stochastic framework [C]. Proceedings of European Conference on Computer Vision, 1998.
[56] M. Isard, J. MacCormick. BraMBLe: A Bayesian multiple-blob tracker [C]. Proceedings of IEEE International Conference on ComputerVision, 2001.
[57] J. MacCormick, A. Blake. A probabilistic exclusion principle for tracking multiple objects [J]. International Journal of Computer Vision, 2000, 39(1): 57-71.
[58] K. Nummiaro, E. Koller-Meier, L. Van Gool. Object tracking with an adaptive color-based particle filter [J]. Pattern Recognition, 2002: 353-360.
[59] P. Perez, C. Hue, J. Vermaak, M. Gangnet. Color-based probabilistic tracking [C]. Proceedings of European Conference on Computer Vision, 2002.
[60] D. Ponsa, A. L¨?pez. Variance reduction techniques in particle-based visual contour tracking [J]. Pattern Recognition, 2009, 42(11): 2372-2391.
[61] Y. Wu, T. Huang. Robust visual tracking by integrating multiple cues based on co-inferencelearning [J]. International Journal of Computer Vision, 2004, 58(1): 55-71.
[62]薛建儒.视频序列跟踪的统计计算方法[D].西安交通大学: 2003.
[63] P. Li, F. CHAUMETTE. Image cues fusion for object tracking based on particle filter [J]. Lecture Notes in Computer Science, 2004: 99-110.
[64] T. Wang, Q. Diao, Y. Zhang, G. Song, C. Lai, G. Bradski. A dynamic bayesian network approach to multi-cue based visual tracking [C]. Proceedings of International Conference on Pattern Recognition, 2004.
[65] M. Kass, A. Witkin, D. Terzopoulos. Snakes: active contour models [J]. International Journal of Computer Vision, 1988, 1(4): 321-331.
[66] N. Paragios, R. Deriche. Geodesic active contours and level sets for the detection andtracking of moving objects [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266-280.
[67] N. Peterfreund. Robust tracking of position and velocity with Kalman snakes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(6): 564-569.
[68] C. Xu, J. Prince. Snakes, shapes, and gradient vector flow [J]. IEEE Transactions on Image Processing, 1998, 7(3): 359-369.
[69] D. Freedman, T. Zhang. Active contours for tracking distributions [J]. IEEE Transactions on Image Processing, 2004, 13(4): 518-526.
[70]程建,周越,蔡念,杨杰.基于粒子滤波的红外目标跟踪[J].红外与毫米波学报, 2006, 25(2): 113-117.
[71]秦暄,章毓晋.一种基于曲线拟合预测的红外目标的跟踪算法[J].红外技术, 2003, 25(004): 23-25.
[72] U. Braga-Neto, M. Choudhary, J. Goutsias. Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators [J]. Journal of Electronic Imaging, 2004, 13: 802.
[73]李熙莹,倪国强.红外图像的光流计算[J].红外与激光工程, 2002, 31(003): 189-193.
[74] A. Yilmaz, K. Shafique, M. Shah. Target tracking in airborne forward looking infrared imagery [J]. Image and Vision Computing, 2003, 21(7): 623-635.
[75]崔宁周,谢维信.多传感器分布式推广卡尔曼滤波算法及其在雷达红外目标跟踪中的应用[J].电子科学学刊, 1997, 19(3): 289-294.
[76] E. Goubet, J. Katz, F. Porikli. Pedestrian tracking using thermal infrared imaging [R]. Mitsubishi Electric Research Laboratories: 2006.
[77] M. Yasuno, S. Ryousuke, N. Yasuda, M. Aoki. Pedestrian detection and tracking in far infrared images [C]. Proceedings of IEEE Conference on Intelligent TransportationSystems, 2005.
[78] C. Dai, Y. Zheng, X. Li. Layered representation for pedestrian detection and tracking in infrared imagery [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[79] C. Dai, Y. Zheng, X. Li. Pedestrian detection and tracking in infrared imagery using shape and appearance [J]. Computer Vision and Image Understanding, 2007, 106(2-3): 288-299.
[80] A. Treptow, G. Cielniak, T. Duckett. Real-time people tracking for mobile robots using thermal vision [J]. Robotics and Autonomous Systems, 2006, 54(9): 729-739.
[81]云廷进,郭永彩,高潮.基于粒子Mean Shift迁移的红外人体目标跟踪算法[J].计算机学报, 2009, 32(6): 1222-1228.
[82] A. Bobick, J. Davis. The recognition of human movement using temporal templates [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(3): 257-267.
[83] M. Bregonzio, S. Gong, T. Xiang. Recognising action as clouds of space-time interest points [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009.
[84] M. Escobar, G. Masson, T. Vieville, P. Kornprobst. Action recognition using a bio-inspired feedforward spiking network [J]. International Journal of Computer Vision, 2009, 82(3): 284-301.
[85] L. Gorelick, M. Blank, E. Shechtman, M. Irani, R. Basri. Actions as space-time shapes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2247-2253.
[86] A. Gupta, A. Kembhavi, L. Davis. Observing human-object interactions: using spatial and functional compatibility for recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10): 1775-1789.
[87] Y. Hu, L. Cao, F. Lv, S. Yan, Y. Gong, T. Huang. Action detection in complex scenes with spatial and temporal ambiguities [C]. Proceedings of IEEE International Conference on Computer Vision, 2009.
[88] N. Ikizler, P. Duygulu. Histogram of oriented rectangles: A new pose descriptor for human action recognition [J]. Image and Vision Computing, 2009, 27(10): 1515-1526.
[89] J. Niebles, H. Wang, L. Fei-Fei. Unsupervised learning of human action categories using spatial-temporal words [J]. International Journal of Computer Vision, 2008, 79(3): 299-318.
[90] M. Ryoo, J. Aggarwal. Semantic representation and recognition of continued and recursive human activities [J]. International Journal of Computer Vision, 2009, 82(1): 1-24.
[91] C. Sminchisescu, A. Kanaujia, D. Metaxas. Conditional models for contextual human motion recognition [J]. Computer Vision and Image Understanding, 2006, 104(2-3):210-220.
[92] P. Turaga, R. Chellappa, V. S. Subrahmanian, O. Udrea. Machine recognition of human activities: a survey [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(11): 1473-1488.
[93] A. Veeraraghavan, A. Roy-Chowdhury, R. Chellappa. Matching shape sequences in video with applications in human movement analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(12): 1896-1909.
[94] D. Weinland, R. Ronfard, E. Boyer. Free viewpoint action recognition using motion history volumes [J]. Computer Vision and Image Understanding, 2006, 104(2-3): 249-257.
[95] A. Efros, A. Berg, G. Mori, J. Malik. Recognizing action at a distance [C]. Proceedings of IEEE International Conference on Computer Vision, 2003.
[96] L. Gorelick, M. Galun, E. Sharon, R. Basri, A. Brandt. Shape representation and classification using the poisson equation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 1991-2005.
[97] M. Rodriguez, J. Ahmed, M. Shah. Action MACH: a spatio-temporal maximum average correlation height filter for action recognition [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[98] L. Wang, D. Suter. Learning and matching of dynamic shape manifolds for human action recognition [J]. IEEE Transactions on Image Processing, 2007, 16(6): 1646-1661.
[99] D. Weinland, E. Boyer, R. Ronfard. Action recognition from arbitrary views using 3d exemplars [C]. Proceedings of IEEE International Conference on Computer Vision, 2007.
[100] P. Dollar, V. Rabaud, G. Cottrell, S. Belongie. Behavior recognition via sparse spatio-temporal features [C]. Proceedings of IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005.
[101] I. Laptev, T. Lindeberg. Space-time Interest Points [C]. Proceedings of IEEE International Conference on Computer Vision, 2003.
[102] E. Shechtman, M. Irani. Space-time behavior-based correlation - OR - How to tell if two underlying motion fields are similar without computing them [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(11): 2045-2056.
[103] K. Mikolajczyk, H. Uemura. Action recognition with motion-appearance vocabulary forest [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[104] K. Jia, D. Yeung. Human action recognition using local spatio-temporal discriminant embedding [C]. Proceedings of IEEE Computer Society Conference on Computer Visionand Pattern Recognition, 2008.
[105] J. Yamato, J. Ohya, K. Ishii. Recognizing human action in time-sequential images using hidden markov model [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992.
[106] L. Wang, X. Geng, C. Leckie, R. Kotagiri. Moving shape dynamics: a signal processing perspective [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[107] C. Schuldt, I. Laptev, B. Caputo. Recognizing human actions: a local SVM approach [C]. Proceedings of International Conference on Pattern and Recognition, 2004.
[108] A. Fathi, G. Mori. Action recognition by learning mid-level motion features [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[109] S. Gong, T. Xiang. Scene events recognition without tracking [J]. Acta Automatica Sinica, 2003, 29(3): 321-321.
[110] P. Scovanner, S. Ali, M. Shah. A 3-dimensional sift descriptor and its application to action recognition [C]. Proceedings of International Conference on Multimedia, 2007.
[111] D. Lowe. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[112] K. Rapantzikos, Y. Avrithis, S. Kollias. Dense saliency-based spatiotemporal feature points for action recognition [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009.
[113] R. Collins, A. Lipton, T. Kanade. Introduction to the special section on video surveillance [J]. IEEE Transactions on pattern analysis and machine intelligence, 2000, 22(8): 745-746.
[114] R. Collins, A. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt. A system for video surveillance and monitoring (VSAM project final report) [R]. CMU Technical Report CMU-RI-TR-00: 2000.
[115] T. List, J. Bins, R. Fisher, D. Tweed, K. Thorisson. Two approaches to a plug-and-play vision architecture-CCAVIAR and Psyclone [C]. Proceedings of AAAI05 workshop on Modular Construction of Human-like Intelligence, 2005.
[116] P. Ribeiro, J. Santos-Victor, P. Lisboa. Human activity recognition from video: Modeling, feature selection and classification architecture [C]. Proceedings of Workshop on Human Activity Recognition and Modeling, 2005.
[117] D. Tweed, W. Feng, R. Fisher, J. Bins, T. List. Exploring techniques for behaviour recognition via the CAVIAR modular vision framework [C]. Proceedings of Workshop onHuman Activity Recognition and Modeling, 2005.
[118] E. Andrade, R. Fisher. Simulation of crowd problems for computer vision [C]. Proceedings of the First International Workshop on Crowd Simulation, 2005.
[119] S. Blunsden, R. Fisher, E. Andrade. Recognition of coordinated multi agent activities, the individual vs the group [C]. Proceedings of European Conference on Computer Vision, 2006.
[120] P. Remagnino, T. Tan, K. Baker. Multi-agent visual surveillance of dynamic scenes [J]. Image and Vision Computing, 1998, 16(8): 529-532.
[121] Microsoft Corporation. Microsoft surface [DB/OL]. 2010 [cited 2010.01.26]; Available rom: http://www.microsoft.com/surface/en/us/default.aspx.
[122] C. Maggioni, B. Kammerer. Gesture computer: history, design, and applications [M]. New York: Cambridge University Press, 1998.
[123] J. Aggarwal, Q. Cai. Human motion analysis: a review [J]. Computer Vision and Image Understanding, 1999, 73(3): 428-440.
[124] J. A. Garca, J. Fernández-Valdivia, X. R. Fernández-Vidal, R. Rodriguez-Sánchez. Information theoretic measure for visual target distinctness [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(4): 362-383.
[125] Y. Wu, T. Yu, G. Hua. A statistical field model for pedestrian detection [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[126] M. Bertozzi, A. Broggi, C. Caraffi, M. Del Rose, M. Felisa, G. Vezzoni. Pedestrian detection by means of far-infrared stereo vision [J]. Computer Vision and Image Understanding, 2007, 106(2-3): 194-204.
[127] F. Suard, A. Rakotomamonjy, A. Bensrhair, A. Broggi. Pedestrian detection using infrared images and histograms of oriented gradients [C]. Proceedings of IEEE Intelligent Vehicles Symposium, 2006.
[128]王江涛,杨静宇.红外图像中人体实时检测研究[J].系统仿真学报, 2007, 19(19): 4490-4494.
[129] Y. Sheikh, M. Shah. Bayesian modeling of dynamic scenes for object detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(11): 1778-1792.
[130] J. Besag. On the statistical analysis of dirty images [J]. Journal of Royal Statistics Society, 1986, 48: 259-302.
[131] S. Geman, D. Geman, K. Abend, T. Harley, L. Kanal. Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images [J]. Journal of Applied Statistics, 1993, 20(5): 25-62.
[132] V. Kolmogorov, R. Zabih. What energy functions can be minimized via graph cuts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 147.
[133] V. Vapnik. The nature of statistical learning theory [M]: Springer Verlag, 2000.
[134] A. Shashua, Y. Gdalyahu, G. Hayun. Pedestrian detection for driving assistance systems: Single-frame classification and system level performance [C]. Proceedings of IEEE Intelligent Vehicles Symposium, 2004.
[135] N. Dalal, B. Triggs. Histograms of oriented gradients for human detection [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[136]李伟红.基于支持向量机的人脸特征选择及识别研究[D].重庆大学: 2006.
[137] R. Miczianko. Terravic Research Infrared Database [DB/OL]. 2009 [cited 2009.02.06]; Available rom: http://www.terravic.com.
[138] N. Kingsbury. The dual-tree complex wavelet transform: a new efficient tool for image restoration and enhancement [C]. Proceedings of European Signal Processing Conference, 1998.
[139] N. Kingsbury. A dual-tree complex wavelet transform with improved orthogonalityand symmetry properties [C]. Proceedings of IEEE International Conference on Image Processing, 2000.
[140] N. Kingsbury. Complex wavelets for shift invariant analysis and filtering of signals [J]. Applied and Computational Harmonic Analysis, 2001, 10(3): 234-253.
[141] I. Selesnick, A. Abdelnour. Symmetric wavelet tight frames with two generators [J]. Applied and Computational Harmonic Analysis, 2004, 17(2): 211-225.
[142] I. Selesnick. The double-density dual-tree DWT [J]. IEEE Transactions on Signal Processing, 2004, 52(5): 1304-1314.
[143] I. Selesnick. Hilbert transform pairs of wavelet bases [J]. IEEE Signal Processing Letters, 2001, 8(6): 170-173.
[144] W. Ren, Z. Sun. Structural damage identification by using wavelet entropy [J]. Engineering Structures, 2008, 30(10): 2840-2849.
[145] J. Davis, M. Keck. A two-stage template approach to person detection in thermal imagery [C]. Proceedings of the Seventh IEEE Workshops on Application of Computer Vision, 2005.
[146] J. Davis, V. Sharma. Background-subtraction using contour-based fusion of thermal and visible imagery [J]. Computer Vision and Image Understanding, 2007, 106(2-3): 162-182.
[147] K. Nummiaro, E. Koller-Meier, L. Van Gool. An adaptive color-based particle filter [J].Image and Vision Computing, 2003, 21(1): 99-110.
[148] N. Gordon, D. Salmond, A. Smith. Novel approach to nonlinear/non-Gaussian Bayesian state estimation [C]. Proceedings of IEE Proceedings on Radar and Signal Processing, 1993.
[149] M. Isard, A. Blake. Contour tracking by stochastic propagation of conditional density [C]. Proceedings of European Conference on Computer Vision, 1996.
[150] J. Liu, R. Chen. Sequential Monte Carlo methods for dynamic systems [J]. Journal of the American statistical association, 1998, 93(443): 1032-1044.
[151] G. Kitagawa. Monte carlo filter and smoother for non-Gaussian nonlinear state space models [J]. Journal of Computational and Graphical Statistics, 1996: 1-25.
[152] T. Higuchi. Monte Carlo filter using the genetic algorithm operators [J]. Journal of Statistical Computation and Simulation, 1997, 59(1): 1-23.
[153] Y. Mo, D. Xiao. Hybrid system monitoring and diagnosing based on particle filter algorithm [J]. Acta Automatica Sinica, 2003, 29(3): 641-648.
[154] T. Tan, G. Sullivan, K. Baker. Model-based localisation and recognition of road vehicles [J]. International Journal of Computer Vision, 1998, 27(1): 5-25.
[155] H. Seung, D. Lee. The manifold ways of perception [J]. Science, 2000, 290(5500): 2268-2269.
[156] S. Roweis, L. Saul. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290(5500): 2323.
[157] J. Tenenbaum, V. Silva, J. Langford. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290(5500): 2319.
[158] M. Turk, A. Pentland. Eigenfaces for recognition [J]. Journal of Cognitive Neuroscience, 1991, 3(1): 71-86.
[159] P. Hespanha, D. Kriegman. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711.
[160] X. He, P. Niyogi. Locality preserving projections [C]. Proceedings of the Conference on Advances in Neural Information Processing System, 2003.
[161] K. Lu, X. He. Image retrieval based on incremental subspace learning [J]. Pattern Recognition, 2005, 38(11): 2047-2054.
[162] L. Yang, W. Gong, X. Gu, W. Li, Y. Liu. Bagging null space locality preserving discriminant classifiers for face recognition [J]. Pattern Recognition, 2009, 42(9): 1853-1858.
[163] W. Yu, X. Teng, C. Liu. Face recognition using discriminant locality preserving projections[J]. Image and Vision Computing, 2006, 24(3): 239-248.
[164]杨利平.保局子空间人脸特征提取及识别方法研究[D].重庆大学: 2008.
[165] M. Belkin, P. Niyogi. Laplacian eigenmaps and spectral techniques for embedding and clustering [C]. Proceedings of the Conference on Advances in Neural Information Processing system, 2002.
[166] R. Haralick, K. Shanmugam, I. Dinstein. Textural features for image classification [J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, 3(6): 610-621.
[167] J. F. Haddon, J. F. Boyce. Simultaneous region and edge segmentation of infrared images using non-maximal suppression for edge thinning [C]. Proceedings of the British Machine Vision Conference, 1990.
[168] B. Park, Y. Chen. Co-occurrence matrix texture features of multi-spectral images on poultry carcasses [J]. Journal of Agricultural Engineering Research, 2001, 78(2): 127-139.
[169]查宇飞,毕笃彦.一种基于粒子滤波的自适应运动目标跟踪方法[J].电子与信息学报, 2007, 29(1): 92-95.
[170]李龙,李俊山,叶霞.基于Mean Shift算法的运动平台下红外目标跟踪[J].红外与激光工程, 2007, 36(2): 229-232.
[171] B. Bhanu, J. Han. Kinematic-based human motion analysis in infrared sequences [C]. Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision, 2002.
[172] J. Liu, S. Ali, M. Shah. Recognizing human actions using multiple features [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008.
[173] M. Ahmad, S. Lee. Human action recognition using shape and CLG-motion flow from multi-view image sequences [J]. Pattern Recognition, 2008, 41(7): 2237-2252.
[174] M. Hu. Visual pattern recognition by moment invariants [J]. IRE Transactions on Information Theory, 1962, 8(2): 179-187.
[175] R. Prokop, A. Reeves. A survey of moment-based techniques for unoccluded object representation and recognition [J]. CVGIP: Graphical Models and Image Processing, 1992, 54(5): 438-460.
[176] S. Belkasim, M. Ahmadi, M. Shridhar. Efficient algorithm for fast computation of Zernike moments [J]. Journal of the Franklin Institute, 1996, 333(4): 577-581.
[177] I. Laptev. On space-time interest points [J]. International Journal of Computer Vision, 2005, 64(2): 107-123.
[178] C. Harris, M. Stephens. A combined corner and edge detector [C]. Proceedings of the Fourth Alvey Vision Conference, 1988.
[179] T. Lindeberg. On automatic selection of temporal scales in time-causal scale-space [J]. Algebraic Frames for the Perception-Action Cycle, 1997: 94-113.
[180] T. Lindeberg. Feature detection with automatic scale selection [J]. International Journal of Computer Vision, 1998, 30(2): 79-116.
[181] T. Lindeberg, L. Bretzner. Real-time scale selection in hybrid multi-scale representations [J]. Lecture Notes in Computer Science, 2003: 148-163.
