A Joint Object Tracking Framework with Incremental and Multiple Instance Learning
Chengjun Xie, Jieqing Tan, Linli Zhou, Lei He, Jie Zhang, Yingqiao Bu · 2012
When objects undergo large pose change, illumination variation or partial occlusion, most existed visual tracking algorithms tend to drift away from targets and even fail in tracking them. To address this issue, in this paper we propose an online algorithm by combining Incremental Learning (IL) and Multiple Instance Learning (MIL) based on local sparse representation for tracking an object in a video system. First, the target location is estimated using the online updated IL. Then, to decrease the visual drift due to the accumulation of errors while updating IL subspace with the first step results, a two-step object tracking method combining a static IL model with a dynamical MIL model is proposed. We utilize information of the static IL model involving the singular values, the Eigen template to avoid visual drift if there is no significant appearance change in the tracked objects. Otherwise, we use the dynamical MIL model to discriminate the target from the background when there is significant appearance change in the tracked objects. Experiments on some publicly available benchmarks of video sequences show that our proposed tracker is more robust and effective than others.