计算机工程与应用2017，Vol.53Issue(9)：195-200,6.DOI:10.3778/j.issn.1002-8331.1511-0064
结合稀疏表示和均值偏移的运动目标跟踪算法
Moving objects tracking algorithm that combines sparse representation and Meanshift
摘要
Abstract
This paper proposes a robust method for visual tracking relying on Meanshift, sparse coding and spatial pyramids. Firstly, it extends the original Meanshift approach to handle orientation space and scale space and names this new method as mean transform. The mean transform method estimates the motion, including the location, orientation and scale, of the interested object window simultaneously and effectively. Secondly, a pixel-wise dense patch sampling technique and a region-wise trivial template designing scheme are introduced which enable this approach to run very accu-rately and efficiently. In addition, instead of using either holistic representation or local representation only, it applies spatial pyramids by combining these two representations into this approach to deal with partial occlusion problems robustly. Observed from the experimental results, this approach outperforms state-of-the-art methods in many benchmark sequences.关键词
均值漂移/尺度空间/稀疏编码/空间金字塔/部分遮挡Key words
Meanshift/scale space/sparse coding/spatial pyramids/partial occlusion分类
信息技术与安全科学引用本文复制引用
孙凯,谢林柏..结合稀疏表示和均值偏移的运动目标跟踪算法[J].计算机工程与应用,2017,53(9):195-200,6.基金项目
国家自然科学基金(No.61374047,No.60973095). （No.61374047,No.60973095）
