Control Charts Approach for Scenario Recognition in Video Sequences

A new approach, based on control charts, is presented for the task of recognition of events and scenarios in video image sequences. For each image in the sequence, low level image processing and feature extraction steps result in feature descriptors for objects of interest detected in the images. Control charts analysis is then explored to classify the nature of the activity depicted by the temporal changes in these features over the image sequence. Scenario recognition with higher accuracy is achieved using this simple approach.

Control Charts Approach for Scenario Recognition in Video Sequences

A new approach, based on control charts, is presented for the task of recognition of events and scenarios in video image sequences. For each image in the sequence, low level image processing and feature extraction steps result in feature descriptors for objects of interest detected in the images. Control charts analysis is then explored to classify the nature of the activity depicted by the temporal changes in these features over the image sequence. Scenario recognition with higher accuracy is achieved using this simple approach.

___

  • S. Hongeng and R. Nevatia,“Multi-agent event recognition,” IEEE International Conference on Computer Vision, July 2001.
  • S. Hongeng, F. Bremond and R. Nevatia, “Representation and optimal recognition of human activities,” IEEE Computer Vision and Pattern Recognition, June 2000.
  • S. Hongeng, F. Bremond and R. Nevatia, “Bayesian framework for video surveillance application,” International Conference on Pattern Recognition, September 2000.
  • M. Hamid, “ARGMode – Activity recognition using graphical models,” Computer Vision and Pattern Recogni- tion, June 2003.
  • J. Yamato, S. Kurakakae, A. Tomono, and K. Ishii, “Human action recognition using HMM with category sepa- rated vector quantization,” Transaction of Institute of Electronics, Information, and Communication Engineers, A. R. Chowdhury and R. Chellappa, “A factorization approach for activity recognition,” Computer Vision and Pattern Recognition, June 2003.
  • A. Amer, “A computational framework for simultaneous real-time high-level video representation,” Multisensor Surveillance Systems, pp 149-182, July 2003.
  • J. W. Davis and A. Tyagi, “A reliable inference framework for recognition of human actions,” IEEE Conference on Advanced Video and Signal Based Surveillance, July 2003.
  • T. Moeslund and E. Granum, “A survey of computer-based human motion capture,” Computer Vision and Image Understanding, vol 81, March 2001.
  • R. T. Collins, A. J. Lipton and T. Kanade, “A system for video surveillance and monitoring” Proc. American Nuclear Society (ANS ), Eighth International Topical Meeting Robotic and Remote Systems, 1999.
  • L. M. Fuentes and S. A. Velastin, “People tracking in surveillance applications,” Proceedings 2nd IEEE Inter- national Workshop on PETS, Kauai, Hawaii, USA, December 9, 2001.
  • J. R. Quinlan, “C5.0: An informal tutorial,” Rilequest Research, http://www.rulequest.com/see5-unix.html, A. Lipton, H. Fujiyoshi, and R. Patil, “Moving target detection and classification from real-time video,” IEEE Workshop on applications of Computer Vision, October 1998.
  • D. C. Montgomery, “Introduction to Statistical Quality Control’, John Wiley & Sons; 3rd edition (August, ). D. T. Pham and A. B. Chan, “Unsupervised neural networks for control chart pattern recognition,” CIRP International seminar on Intelligent computation in Manufacturing Engineering, 1998.