计算机与数字工程2017，Vol.45Issue(8)：1533-1538,6.DOI:10.3969/j.issn.1672-9722.2017.08.016
基于多特征融合和反向投影的均值漂移改进跟踪算法
An Improved Meanshift Tracking Algorithm Based on Multi-feature Fusion and Back Projection
摘要
Abstract
The traditional MeanShift tracking algorithm is easy to fail due to its single colorfeature,also since its tracking win-dow size is fixed,it is unable to track size changed object successfully. Thus,a modified scale-adaptive MeanShift tracking algo-rithm based on multi-feature fusion and back projection is proposed. First,texture feature is fused with the original color feature to describe the object. Then,in order to reduce the interference of the background,background-weighted algorithm is introduced to our method. Finally,adaptive tracking window is realized by back projection and similarity comparison. The experimental results show that the improved algorithm achieves better tracking results than the traditional algorithm.关键词
目标跟踪/自适应跟踪窗口/纹理特征/反向投影Key words
object tracking/adaptive tracking window/texture feature/back projection分类
信息技术与安全科学引用本文复制引用
沈梦舟,黎宁,徐斌,曹蔡旻,顾晓蓉..基于多特征融合和反向投影的均值漂移改进跟踪算法[J].计算机与数字工程,2017,45(8):1533-1538,6.基金项目
中国民航总局科技基金项目(编号:1004-14000202) （编号:1004-14000202）
南京航空航天大学理工融合项目(编号:1008-56XZA15009)资助. （编号:1008-56XZA15009）
