Real-time object tracking with relevance feedback

Currently there are many systems available that use relevance feedback for text and image retrieval. This query by example method has been shown to optimize the search strategy whilst keeping a fast response time, two important factors when querying large image databases. The use of relevance feedback in real time video object tracking and identification however is essentially unexplored. This paper discusses the ongoing project and current results towards integrating interactive relevance feedback within the context of video object tracking. We discuss the important limitations in real time video object tracking and we design a next generation video object tracking system which exploits interactive relevance feedback towards addressing the primary limitations.

[1]  Thomas S. Huang,et al.  Relevance Feedback Techniques in Image Retrieval , 2001, Principles of Visual Information Retrieval.

[2]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Stephen J. Maybank,et al.  Real-Time Tracking of Pedestrians and Vehicles , 2001 .

[4]  Hamid Aghajan,et al.  Video-based freeway-monitoring system using recursive vehicle tracking , 1995, Electronic Imaging.

[5]  Bohyung Han,et al.  Kernel-based Bayesian filtering for object tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[7]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[8]  Manuele Bicego,et al.  Integrated region- and pixel-based approach to background modelling , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[9]  Michael S. Lew,et al.  Principles of Visual Information Retrieval , 2001, Advances in Pattern Recognition.

[10]  Vittorio Murino,et al.  Segmentation and tracking of multiple objects in video sequences , 2004 .

[11]  C. Jaynes,et al.  Multi-resolution background modeling of dynamic scenes using weighted match filters , 2004, VSSN '04.

[12]  Qi Tian,et al.  Foreground object detection from videos containing complex background , 2003, MULTIMEDIA '03.

[13]  N. Funk.  A Study of the Kalman Filter applied to Visual Tracking , 2003 .

[14]  J. Malo,et al.  Perceptually weighted optical flow for motion-based segmentation in MPEG-4 paradigm , 2000 .