A Real-Time Active Pedestrian Tracking System Inspired by the Human Visual System

详细信息    查看全文

• 作者：Yuxia Wang ; Qingjie Zhao ; Bo Wang ; Shixian Wang ; Yu Zhang ; Wei Guo…
• 关键词：Active tracking ; Pedestrian detection ; Coarse ; to ; fine pedestrian detection ; PTZ control model ; Human visual system
• 刊名：Cognitive Computation
• 出版年：2016
• 出版时间：February 2016
• 年：2016
• 卷：8
• 期：1
• 页码：39-51
• 全文大小：2,498 KB
• 参考文献：1.Li X, Hu W, Shen C, Zhang Z, Dick A, Hengel AVD. A survey of appearance models in visual object tracking. ACM Trans Intell Syst Technol. 2013;4(4):58.CrossRef
  2.Lu W, Li X, Gao X, et al. A video quality assessment metric based on human visual system. Cogn Comput. 2010;2(2):120–31.CrossRef
  3.Rapantzikos K, Avrithis Y, Kollias S. Spatiotemporal features for action recognition and salient event detection. Cogn Comput. 2011;3(1):167–84.CrossRef
  4.Tu Z, Zheng A, Yang E, et al. A biologically inspired vision-based approach for detecting multiple moving objects in complex outdoor scenes. Cogn Comput. 2015. doi:10.​1007/​s12559-015-9318-z .
  5.Gao F, Zhang Y, Wang J, et al. Visual attention model based vehicle target detection in synthetic aperture radar images: A novel approach. Cogn Comput. 2014. doi:10.​1007/​s12559-014-9312-x .
  6.Su Y, Zhao Q, Zhao L, et al. Abrupt motion tracking using a visual saliency embedded particle filter. Pattern Recogn. 2014;47(5):1826–34.CrossRef
  7.Murray D, Basu A. Motion tracking with an active camera. IEEE Trans Pattern Anal Mach Intel. 1994;16(5):449–59.CrossRef
  8.Daniilidis K, Krauss C, Hansen M, Sommer G. Real-time tracking of moving objects with an active camera. Real Time Imag. 1998;4(1):3–20.CrossRef
  9.Kang S, Paik JK, Koschan A, Abidi BR, Abidi MA. Real-time video tracking using PTZ cameras. Quality control by artificial vision. Int Soc Opt Photon. 2003;5132:103–111.
  10.Ribaric S, Adrinek G, Segvic S. Real-time active visual tracking system. In: Proceedings of 12th IEEE mediterranean electrotechnical conference, Dubrovnik, Croatia; 2004. vol 1, pp. 231–234.
  11.Zhang L, Xu K., Yu S, Fu R, Xu Y. An effective approach for active tracking with a PTZ camera. In: IEEE international conference on robotics and biomimetics (ROBIO), 2010. pp. 1768–1773.
  12.Salvagnini P, Cristani M, Del Bue A, Murino V. An experimental framework for evaluating ptz tracking algorithms. Computer vision systems. Berlin Heidelberg: Springer; 2011. p. 81–90.
  13.Szwoch G, Dalka P, Ciarkowski A, Szczuko P, Czyzewski A. Visual object tracking system employing fixed and PTZ cameras. Intel Decis Technol. 2011;5(2):177–88.
  14.Zhang R. Active target tracking using PTZ camera. Xi’an: XiDian University; 2009.
  15.Davis J, Chen X. Calibrating pan-tilt cameras in wide-area surveillance networks. In: Proceedings. Ninth IEEE international conference on computer vision, 2003. pp. 144–149.
  16.Park U, Choi HC, Jain AK, et al. Face tracking and recognition at a distance: A coaxial and concentric PTZ camera system. IEEE Trans Inf Forensics Secur. 2013;8(10):1665–77.CrossRef
  17.Morbidi F, Mariottini GL. Active target tracking and cooperative localization for teams of aerial vehicles. IEEE Trans Control Syst Technol. 2013;21(5):1694–707.CrossRef
  18.Doyle DD, Jennings AL, Black JT. Optical flow background estimation for real-time pan/tilt camera object tracking. Measurement. 2014;48:195–207.CrossRef
  19.Yildiz A, Takemura N, Iwai Y, et al. Tracking people with active cameras, human–computer interaction. Towards intelligent and implicit interaction. Berlin Heidelberg: Springer; 2013. p. 270–9.CrossRef
  20.Haque MA, Nasrollahi K, Moeslund TB. Real-time acquisition of high quality face sequences from an active pan-tilt-zoom camera. In: 10th IEEE international conference on advanced video and signal based surveillance (AVSS), 2013. pp 443–448.
  21.Cai Y, Medioni G, Dinh TB. Towards a practical PTZ face detection and tracking system. In: IEEE workshop on applications of computer vision (WACV), 2013. pp 31–38.
  22.Papageorgiou C, Poggio T. A trainable system for object detection. Int J Comput Vis. 2000;38(1):15–33.CrossRef
  23.Benenson R, Omran M, Hosang J, et al. Ten years of pedestrian detection, What have we learned?. arXiv preprint arXiv:1411.4304, 2014.
  24.Dollár P, Wojek C, Schiele B, Perona P. Pedestrian detection: an evaluation of the state of the art. PAMI, 2012.
  25.Dalal N, Triggs B. Histograms of oriented gradients for human detection. IEEE Comput Soc Conf Comput Vis Pattern Recogn. 2005;1:886–93.
  26.Pang Y, Yuan Y, Li X, Pan J. Efficient HOG human detection. Signal Process. 2011;91(4):773–81.CrossRef
  27.Dollár P, Tu Z, Perona P, et al. Integral channel features. BMVC. 2009;2(3):5.
  28.Luo P, Tian Y, Wang X, et al. Switchable deep network for pedestrian detection. In: IEEE conference on computer vision and pattern recognition (CVPR), 2014. pp. 899–906.
  29.Lim JJ, Zitnick CL, Dollár P. Sketch tokens: a learned mid-level representation for contour and object detection. In: IEEE conference on computer vision and pattern recognition (CVPR), 2013. pp. 3158–3165.
  30.Walk S, Majer N, Schindler K, et al. New features and insights for pedestrian detection. In: IEEE conference on computer vision and pattern recognition (CVPR), 2010. pp. 1030–1037.
  31.Wang X, Han TX, Yan S. An HOG-LBP human detector with partial occlusion handling. In: IEEE international conference on computer vision, 2009. pp. 32–39.
  32.Costea AD, Nedevschi S. Word channel based multiscale pedestrian detection without image resizing and using only one classifier. In: IEEE conference on computer vision and pattern recognition (CVPR), 2014. pp. 2393–2400.
  33.Paisitkriangkrai S, Shen C, Hengel A. Efficient pedestrian detection by directly optimize the partial area under the ROC curve. arXiv preprint arXiv:1310.0900, 2013.
  34.Maji S, Berg AC, Malik J. Classification using intersection kernel support vector machines is efficient. In: IEEE conference on computer vision and pattern recognition, 2008. pp. 1–8.
  35.Schapire RE, Singer Y. Improved boosting algorithms using confidence-rated predictions. Mach Learn. 1999;37(3):297–336.CrossRef
  36.Ouyang W, Wang X. Joint deep learning for pedestrian detection. In: IEEE international conference on computer vision (ICCV), 2013. pp. 2056–2063.
  37.Zong W. Research and implementation of moving object tracking algorithms based on PTZ camera. Boston: Northeastern University; 2011.
  38.Zhang Q, Bo LI, Zhang N. Research on automatic target tracking based on PTZ system. TELKOMNIKA Indones J Electr Eng. 2012;10(7):1582–7.
  39.Li H, Shen C, Shi Q. Real-time visual tracking using compressive sensing. In: IEEE conference on computer vision and pattern recognition, 2011. pp. 1305–1312.
  40.Zhang K, Zhang L, Yang MH. Real-time compressive tracking. Computer vision—ECCV. Berlin Heidelberg: Springer; 2012. p. 864–77.
  41.Boris B, Yang MH, Serge B. Robust object tracking with online multiple instance learning. IEEE Trans Pattern Anal Mach Intell. 2011;33(8):1619–32.CrossRef
  42.Xue M, Ling H. Robust visual tracking and vehicle classification via sparse representation. IEEE Trans Pattern Anal Mach Intell. 2011;33(11):2259–72.CrossRef
  43.Kalal Z, Krystian M, Jiri M. Tracking–learning–detection. IEEE Trans Pattern Anal Mach Intell. 2012;34(7):1409–22.CrossRef PubMed
  44.Stauffer C, Grimson WEL. Adaptive background mixture models for real-time tracking. In: IEEE computer society conference on computer vision and pattern recognition, 1999. p. 2.
  45.Chan YT, Allan GC. Hu, and J. B. Plant. A Kalman filter based tracking scheme with input estimation. IEEE Trans Aerosp Electron Syst. 1979;2:237–44.CrossRef
  
• 作者单位：Yuxia Wang (1)
  Qingjie Zhao (1) (2)
  Bo Wang (1)
  Shixian Wang (2)
  Yu Zhang (1)
  Wei Guo (1)
  Zhiquan Feng (2)
  
  1. Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, 100081, People’s Republic of China
  2. Provincial Key Laboratory for Network Based Intelligent Computing, University of Jinan, Jinan, 250022, People’s Republic of China
  
• 刊物主题：Neurosciences; Computation by Abstract Devices; Artificial Intelligence (incl. Robotics); Computational Biology/Bioinformatics;
• 出版者：Springer US
• ISSN：1866-9964

文摘

Pedestrian detection and tracking play a significant role in surveillance. Despite the numerous detection and tracking methods proposed in the literature, when the pedestrian is too small to recognize, which is a common case in modern surveillance systems, all methods fail. In order to deal with such case, we propose an active pedestrian tracking system inspired by the human visual system. A coarse-to-fine pedestrian detection algorithm is proposed for the small pedestrian detection by combining the Gaussian mixture model background subtraction with the histogram of oriented gradient detection. In addition, a three-dimensional pan–tilt–zoom control model is presented, which requires no calibration and is more accurate than other control models. In order to actively track a pedestrian in real time, we utilize an active control algorithm and a tracking–learning–detection tracker. Experimental results demonstrate that our active tracking system is both efficient and effective. Keywords Active tracking Pedestrian detection Coarse-to-fine pedestrian detection PTZ control model Human visual system