摘要
在复杂的环境下,基于单一特征的视觉跟踪算法,往往不能满足实际环境的需要,对此文中提出了一种基于特征自动选取的跟踪方法。考虑到不同特征在不同场景下对目标与背景的区分能力的不同,重新定义了适合跟踪的背景区域,并在此基础上提出了特征自动选取的策略。基于此策略,利用目标的颜色特征和纹理特征,具体实现了特征自动选取的跟踪算法。实验结果证明了该策略的可行性。
In this paper,a scheme based on adaptive selection of proper features for visual tracking is proposed.The discriminability of each cue should be taken into account in the tracking process,the background region suitable for the tracking is re-defined,and a strategy for features selection is proposed.The color cue and the LBP cue are also employed to implement the tracking algorithm.The experiment result indicates that the proposed method is reliable and effective.
出处
《通信技术》
2010年第3期128-130,共3页
Communications Technology
关键词
视觉跟踪
均值偏移
特征选择
广义距离
visual tracking
mean shift
feature selection
generalized distance