Real time object detection and tracking: Histogram matching and Kalman filter approach

In this paper we present an approach to develop a real-time object tracking system using a static camera to grab the video frames and track an object. The work presents the concepts of histogram matching and absolute frame subtraction to implement a robust automated object tracking system. Once the object is detected it is tracked using discrete Kalman filter technique. The histogram matching algorithm proposed here helps to identify when the object enters the viewing range of the camera and the absolute frame subtraction gives better results even with low quality videos. Such a tracking system can be used in surveillance applications and proves to be cost effective.

[1]  Narendra Ahuja,et al.  Selecting objects with freehand sketches , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[2]  Fatih Porikli,et al.  Human Body Tracking by Adaptive Background Models and Mean-Shift Analysis , 2003 .

[3]  William A. Barrett,et al.  Toboggan-based intelligent scissors with a four-parameter edge model , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  William A. Barrett,et al.  Intelligent scissors for image composition , 1995, SIGGRAPH.

[5]  William A. Barrett,et al.  Interactive Segmentation with Intelligent Scissors , 1998, Graph. Model. Image Process..

[6]  Trista Pei-chun Chen,et al.  Computer Vision Workload Analysis: Case Study of Video Surveillance Systems , 2005 .

[7]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[8]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[9]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Nikos Paragios,et al.  Background modeling and subtraction of dynamic scenes , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

[12]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[13]  Montse Pardàs,et al.  Segmentation and tracking of static and moving objects in video surveillance scenarios , 2008, 2008 15th IEEE International Conference on Image Processing.

[14]  Jacques Verly,et al.  The State of the Art in Multiple Object Tracking Under Occlusion in Video Sequences , 2003 .