期刊名称：International Journal of Advanced Robotic Systems
印刷版ISSN：1729-8806
电子版ISSN：1729-8814
出版年度：2014
卷号：11
DOI：10.5772/58430
语种：English
出版社：SAGE Publications
摘要：The appearance model has been shown to be essential for robust visual tracking since it is the basic criterion to locating targets in video sequences. Though existing tracking-by-detection algorithms have shown to be greatly promising, they still suffer from the drift problem, which is caused by updating appearance models. In this paper, we propose a new appearance model composed of ranking middle-level patches to capture more object distinctiveness than traditional tracking-by-detection models. Targets and backgrounds are represented by both low-level bottom-up features and high-level top-down patches, which can compensate each other. Bottom-up features are defined at the pixel level, and each feature gets its discrimination score through selective feature attention mechanism.In top-down feature extraction, rectangular patches are ranked according to their bottom-up discrimination scores, by which all of them are clustered into irregular patches, named ranking middle-level patches. In addition, at the stage of classifier training, the online random forests algorithm is specially refined to reduce drifting problems. Experiments on challenging public datasets and our test videos demonstrate that our approach can effectively prevent the tracker drifting problem and obtain competitive performance in visual tracking.
关键词：Middle-level Patches; Selective Feature Attention; Random Forests; Tracking-by-detection
