Particle filter based visual tracking with multi-cue adaptive fusion  

作　　者：李安平 敬忠良 胡士强 

机构地区：[1]Institute of Aerospace Information and Control School of Electronic,Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200030

出　　处：《Chinese Optics Letters》2005年第6期326-329,共4页中国光学快报（英文版）

基　　金：This work was jointly supported by the National Natural Science Foundation of China (No. 60375008)China PH.D Discipline Special Foundation (No. 20020248029)China Aviation Science Foundation (No. 02D57003)Aerospace Supporting Technology Foundation (No.2003-1.3 02), EXPO Technologies Special Project of National Key Technologies R&D Programme (No. 004BA908B07)Shanghai Key Technologies Preresearch Project (No. 035115009).

摘　　要：To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel tracking method based on adaptive fusion and particle filter is proposed in this paper. In this method, the image color and shape cues are adaptively fused to represent the target observation; fuzzy logic is applied to dynamically adjust each cue weight according to its associated reliability in the past frame; particle filter is adopted to deal with non-linear and non-Gaussian problems in visual tracking. The method is demonstrated to be robust to illumination changes, pose variations, partial occlusions, cluttered backgrounds and camera motion for a test image sequence.To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel tracking method based on adaptive fusion and particle filter is proposed in this paper. In this method, the image color and shape cues are adaptively fused to represent the target observation; fuzzy logic is applied to dynamically adjust each cue weight according to its associated reliability in the past frame; particle filter is adopted to deal with non-linear and non-Gaussian problems in visual tracking. The method is demonstrated to be robust to illumination changes, pose variations, partial occlusions, cluttered backgrounds and camera motion for a test image sequence.

关 键 词：Adaptive algorithms Computer vision Fuzzy sets Robustness (control systems) Sensor data fusion Signal filtering and prediction Tracking (position) 

分 类 号：TN713[电子电信—电路与系统]