Fusion of cues for occlusion handling in tracking with particle filters

Xiaobo Chen; Xinting Pan; Wei Wang

doi:10.1117/12.832478

30 October 2009 Fusion of cues for occlusion handling in tracking with particle filters

Xiaobo Chen, Xinting Pan, Wei Wang

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749514 (2009) https://doi.org/10.1117/12.832478
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

In this paper, a new approach is presented for tracking object accurately and steadily when the target encountering occlusion in video sequences. First, we use Canny algorithm to extract the edges of the object. The edge pixels are classified as foreground/background for each frame using background subtraction. On the next stage, a set of cues including a motion model, an elliptical shape model, a spatial-color mixture of Gaussians appearance model, and an edge orientation histogram model is fused in a principled manner. All these cues could be modeled by a data likelihood function; Then, a particle filter algorithm is used for tracking and the particles are re-sampled based on the fusion of the cues. Result form simulations and experiments with real video sequences show the effectiveness of our approach for tracking people under occlusion conditions.

Citation Download Citation

Xiaobo Chen, Xinting Pan, and Wei Wang "Fusion of cues for occlusion handling in tracking with particle filters", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749514 (30 October 2009); https://doi.org/10.1117/12.832478

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