TY - GEN
T1 - A nonparametric treatment for location/segmentation based visual tracking
AU - Lu, Le
AU - Hager, Gregory D.
PY - 2007
Y1 - 2007
N2 - In this paper, we address two closely related visual tracking problems: 1) localizing a target's position in low or moderate resolution videos and 2) segmenting a target's image support in moderate to high resolution videos. Both tasks are treated as an online binary classification problem using dynamic foreground/background appearance models. Our major contribution is a novel nonparametric approach that successfully maintains a temporally changing appearance model for both foreground and background. The appearance models are formulated as "bags of image patches" that approximate the true two-class appearance distributions. They are maintained using a temporaladaptive importance resampling procedure that is based on simple nonparametric statistics of the appearance patch bags. The overall framework is independent of an specific foreground/background classification process and thus offers the freedom to use different classifiers. We demonstrate the effectiveness of our approach with extensive comparative experimental results on sequences from previous visual tracking [1, 12] and video matting [4] work as well as our own data.
AB - In this paper, we address two closely related visual tracking problems: 1) localizing a target's position in low or moderate resolution videos and 2) segmenting a target's image support in moderate to high resolution videos. Both tasks are treated as an online binary classification problem using dynamic foreground/background appearance models. Our major contribution is a novel nonparametric approach that successfully maintains a temporally changing appearance model for both foreground and background. The appearance models are formulated as "bags of image patches" that approximate the true two-class appearance distributions. They are maintained using a temporaladaptive importance resampling procedure that is based on simple nonparametric statistics of the appearance patch bags. The overall framework is independent of an specific foreground/background classification process and thus offers the freedom to use different classifiers. We demonstrate the effectiveness of our approach with extensive comparative experimental results on sequences from previous visual tracking [1, 12] and video matting [4] work as well as our own data.
UR - http://www.scopus.com/inward/record.url?scp=34948892116&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34948892116&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2007.382976
DO - 10.1109/CVPR.2007.382976
M3 - Conference contribution
AN - SCOPUS:34948892116
SN - 1424411807
SN - 9781424411801
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
BT - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
T2 - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
Y2 - 17 June 2007 through 22 June 2007
ER -