Resolving occlusion and segmentation errors in multiple video object tracking

Hsu-Yung Cheng; Jenq-Neng Hwang

doi:10.1117/12.814418

2 February 2009 Resolving occlusion and segmentation errors in multiple video object tracking

Hsu-Yung Cheng, Jenq-Neng Hwang

Proceedings Volume 7246, Computational Imaging VII; 72460J (2009) https://doi.org/10.1117/12.814418
Event: IS&T/SPIE Electronic Imaging, 2009, San Jose, California, United States

Abstract

In this work, we propose a method to integrate the Kalman filter and adaptive particle sampling for multiple video object tracking. The proposed framework is able to detect occlusion and segmentation error cases and perform adaptive particle sampling for accurate measurement selection. Compared with traditional particle filter based tracking methods, the proposed method generates particles only when necessary. With the concept of adaptive particle sampling, we can avoid degeneracy problem because the sampling position and range are dynamically determined by parameters that are updated by Kalman filters. There is no need to spend time on processing particles with very small weights. The adaptive appearance for the occluded object refers to the prediction results of Kalman filters to determine the region that should be updated and avoids the problem of using inadequate information to update the appearance under occlusion cases. The experimental results have shown that a small number of particles are sufficient to achieve high positioning and scaling accuracy. Also, the employment of adaptive appearance substantially improves the positioning and scaling accuracy on the tracking results.

Citation Download Citation

Hsu-Yung Cheng and Jenq-Neng Hwang "Resolving occlusion and segmentation errors in multiple video object tracking", Proc. SPIE 7246, Computational Imaging VII, 72460J (2 February 2009); https://doi.org/10.1117/12.814418

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available