In this thesis, a fast real-time human detection system with low computing power is proposed.. The first part of our human detection system is to segment the moving object from the scenes. We use the background subtraction here to segment the moving blob. We provide a simple and fast function to calculate the binarization threshold for the varying environments and videos taken by different cameras. In second part of our system, we use simple trajectory tracking and condition judgment to provide some data for human detection algorithm and to decrease the false-alarm rate. The final part is human detection. Because of the requirement of low computing power, we choose the shape-based method, and the codebook by training to classify human being from the other objects. The people walking indoor are sometimes covered by furniture such as desks or chairs. To solve this kind of problem, we provide Deformable Codebook Matching, a human detection algorithm for first half body with different height/width ratio. With Deformable Codebook Matching, when someone’s bottom half body is covered, the system can still work. Further, we use Deformable Codebook Matching to implement the human detection for multiple people walking side by side.
The contribution of our thesis is listed below:
1. We realize the human detection on the DSP platform. It is easily to build up and the cost is cheaper.
2. The optimized threshold adjustment algorithm and novel usage of noise elimination filter make the system work in the scene with only infrared ray as light source, or in the scene with changeful luminance.
3. DCBM algorithm can provide the higher accurate in the scene that foreground object may be covered by some background object. And DCBM algorithm also makes the multiple-human detection passable.
Although the result of our system is fine, but there still some shortcomings need to be solved. The background subtraction method is not a good solution when light source is changeful, or the camera is against the light source. Although the optimized threshold adjustment algorithm and novel usage of noise elimination filter we present work, the nature shortcoming of the background subtraction method still exist. When the situation is over the capability of the system, it’s failed either. People in the training sample walk as front or lateral side. When people crawl or carry something which can cover him at all, this kind of situation can not be handle by the system.
Although we can add this kind of training samples into our system, the accuracy will be affected by lots of similar things, such as tree waving or dogs. In the multiple-occlusive human detection, the situation we can handle is when people walking shoulder by shoulder, but there are still lots of different situations for multiple-occlusive human walk into the scene. If we want to solve these questions, we must develop more complex algorithm to separate them.
References
[1] P. J. Burt, J. R. Bergen, R. Hingorani, R. Kolczynski, W. A. Lee, A. Leung, J.
Lubin,and H. Shvayster, “Object tracking with a moving camera,” in Proc. of the
IEEE Workshop on Visual Motion, March 1989, pp. 2-12.
[2] P. H. Batavia, D. E. Pomerleau, and C. E. Thorpe, “Overtaking vehicle detection using implicit optical flow,” IEEE Conference on Intelligent Transportation
System, Nov.1997, pp. 729-734.
[3] W. J. Gillner, “Motion based vehicle detection on motorways,” in Proc. of the
Intelligent Vehicles '95 Symposium, Sept. 1995, pp.483-487.
[4] L. Zhao and C. E. Thorpe, “Stereo- and neural network-based pedestrian detection,” IEEE Transactions on Intelligent Transportation Systems, vol. 1, no.
3, pp. 148-154, Sept.2000.
[5] C. E. Smith, C. A. Richards, S. A. Brandt, and N. P. Papanikolopoulos, “Visual tracking for intelligent vehicle-highway systems,” IEEE Transactions on
Vehicular Technology, vol. 45, no. 4, pp. 744-759, Nov. 1996.
[6] R. Polana and R. Nelson, “Detecting activities,” IEEE Computer Society
Conferenceon Computer Vision and Pattern Recognition, 1993, pp. 2-7.
[7] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. von Seelen, “Walking pedestrian recognition,” IEEE Transactions on Intelligent Transportation
Systems, vol. 1,no. 3, pp.155-163, Sept. 2000.
[8] C. Orrite-Uruñuela, J. Martínez del Rincón, J. Elías Herrero-Jaraba, G. Rogez,
“2D Silhouette and 3D Skeletal Models for Human Detection and Tracking,”
Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04), 2004.
[9] Z. L. Jlang, S. F. Li, D. F. Gao, “A Time Saving Method for Human Detection in Wide Angle Camera Images,” Proceedings of the Fifth International Conference
on Machine Learning and Cybernetics, Dalian, 13-16 August 2006.
[10] Y. L. Tian and A. Hampapur, “Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance,” Proceedings of the IEEE
Workshop on Motion and Video Computing (WACV/MOTION’05), August 2005.
[11] A. Elgammal, R. Duraiswami, D. Harwood, And L. S. Davis, “Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance,” Proceedings Of The IEEE, Vol. 90, No. 7, July 2002.
[12] K. Kim, T. H. Chalidabhongse, D. Hanuood, L. Davis, “Background Modeling And Subtraction By Codebook Construction,” 2004 International Conference on
Image Processing (ICIP), March 2004.
[13] L. Zhao and C. Thorpe, "Stereo- and Neural Network-Based Pedestrian Detection," Proceedings Of The IEEE, 1998.
[14] S. M. Yoon and H. Kim, “Real-time multiple people detection using skin color, motion and appearance information, ” Proceedings of the 2004 IEEE
International Workshop on Robot and Human Interactive Communication Kurashiki, Okayama Japan, September 20-22,2004.
[15] D. Tan, K. Huang, S. Yu, T. Tan, “Efficient Night Gait Recognition Based on Template Matching,” The 18th International Conference on Pattern Recognition
(ICPR'06), 2006.
[16] A. Gersho, “Asymptotically Optimal Block Quantization,” IEEE Transactions
On Information Theory,Vol.It-25,No.4,July 1979.
[17] J. Zhou and J. Hoang, “Real Time Robust Human Detection and Tracking System,” Proceedings of the 2005 IEEE Computer Society Conference on
Computer Vision and Pattern Recognition (CVPR’05) 2005.
[18] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. von Seelen, “Walking pedestrian recognition,” IEEE Trans. Intelligent Transportation Systems, vol. 1, issue 3, pp.155-163, Sept. 2000.
[19] H. Roh, S. Kang and S-W Lee, “Multiple People Tracking Using an Appearance Model Based on Temporal Color,” in 15th International Conference on Pattern
Recognition (ICPR'00) - Volume 4, 2000.
[20] D. Zhang and G. Lu, “A Comparative Study of Fourier Descriptors for Shape Representation and Retrieval,” the 5th
Asian Conference on Computer Vision, Jan.
2002.
[21] I. Haritaoglu, D. Harwood and S. Davis, “W4: Real-Time Surveillance of People and Their Activities,” IEEE Trans. On Pattern and Machine Intelligence, Vol.22,
No.8, Aug. 2000.
[22] I. Haritaoglu, D. Harwood and S. Davis, “Backpack: Detection of People Carrying Objects Using Silhouettes,” IEEE International Conference on
Computer Vision, pp. 102-107, 1999.
[23] I. Haritaoglu, D. Harwood and S. Davis, “Hydra: Multiple People Detection and Tracking Using Silhouettes,” In Second Workshop of Visual Surveillance at CVPR, pages 6-13, 1999.
[24] T. Zhao and R. Nevatia, “Tracking Multiple Human in Complex Situations,”
IEEE Trans. On Pattern and Machine Intelligence, vol. 26, No. 9, Sep, 2004.
[25] S. J. McKenna, S. Jabri, Z. Duric, H. Wechsler and A. Rosenfeld, “Tracking Groups of People,” Comput. Vision Image Understanding, no. 80, pp. 42--56,
2000.
[26] Y. Kuno, T. Watanabe, Y. Shimosakoda and S. Nakagawa, “Automated detection of Human for Visual Survillance System,” in IEEE Proceedings of ICPR, 1996.
[27] M. Riesenhuber and T. Poggio, “Models of Object Recognition,” in Nature
Neuroscience Supplement, vol. 3, Nov, 2000.
[28] I. Sekita, T. Kurita and N. Otsu, “Complex Autoregressive Model for Shape Recognition,” in IEEE Trans. On Pattern Analysis and Machine Intelligence, vol.
14, No4, Apr, 1992.
[29] H. Kauppinen, T. Seppanen and M. Pietikainen, “An Experimental Comparision of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification,” in
IEEE Tran. On Pattern Analysis and Machine Intelligence, Vol. 17, No. 2, Feb, 1995.
[30] L. Wang, T. Tan, W. Hu and H. Ning, “Automatic Gait Recognition Based on Statistical Shape Analysis,” in IEEE Trans. On Image Processing, vol. 12, No. 9,