改进的自适应颜色属性目标跟踪算法  

Improved adaptive color attributes target tracking algorithm

作　　者：覃为广 宋鸿陟[1] 彭红星[1] 司国东[1] 

机构地区：[1]华南农业大学信息学院人机交互研究中心,广东广州510642

出　　处：《计算机工程与设计》2016年第3期803-808,共6页Computer Engineering and Design

基　　金：国家自然科学基金项目(60875045)

摘　　要：针对自适应颜色属性实时视觉跟踪(ACAT)算法仅对目标颜色特征进行跟踪,仅根据当前帧的目标中心位置确定后一帧目标搜索范围和目标分类情况的不足,提出一种改进的ACAT目标跟踪算法。采用ACAT中的颜色特征,结合基于拉普拉斯算子的边缘特征提取方法,融入惯性漂移思想。实验结果表明,该算法优于近年一些跟踪效果较好的目标跟踪算法,有更高的跟踪精度,平均跟踪速度达到了标准视频的要求。To overcome disadvantages of the adaptive color attributes for real-time visual tracking（ACAT）algorithm which only uses color feature to track the target and only uses the target center of the current frame to confirm the search scope and the classification of the target of the next frame,an improved ACAT target tracking algorithm was presented.The color characteristics in ACAT were used,and the edge feature extraction method based on Laplacian was combined,and the inertial drift thought was blended.Experimental results show that the algorithm is better than some target tracking algorithms which are good at tracking in recent years and it has higher tracking precision.In addition,its mean tracking speed meets the standard requirement for the video.

关 键 词：目标跟踪 颜色特征 边缘特征 自适应 惯性漂移 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]