TY - GEN
T1 - Likelihood map fusion for visual object tracking
AU - Yin, Zhaozheng
AU - Porikli, Fatih
AU - Collins, Robert
PY - 2008
Y1 - 2008
N2 - Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.
AB - Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.
UR - http://www.scopus.com/inward/record.url?scp=50849138898&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=50849138898&partnerID=8YFLogxK
U2 - 10.1109/WACV.2008.4544036
DO - 10.1109/WACV.2008.4544036
M3 - Conference contribution
AN - SCOPUS:50849138898
SN - 1424419131
SN - 9781424419135
T3 - 2008 IEEE Workshop on Applications of Computer Vision, WACV
BT - 2008 IEEE Workshop on Applications of Computer Vision, WACV
T2 - 2008 IEEE Workshop on Applications of Computer Vision, WACV
Y2 - 7 January 2008 through 9 January 2008
ER -