摘要
针对视觉运动目标的鲁棒跟踪问题,提出了一种基于局部分块和背景加权的跟踪算法。首先对目标的前景和背景区域进行分块采样,然后利用基于积分直方图的局部快速穷搜索算法计算每一个分块在当前帧中的后验概率图,最后对后验概率图确定的对应分块的搜索结果赋予不同的权值,进而计算出目标在当前帧中的位置。实验结果表明:基于局部分块加权的跟踪算法比单纯的背景加权跟踪和分块跟踪具有更高的跟踪精度和成功率,且算法复杂度较低。
In order to improve the robustness of visual moving object tracking, a tracking algorithm is pro- posed based on local patches and weighted background. Firstly, the local patches are sampled respectively from the foreground area and background area of the object. Secondly, the probability map of each patch to the frame image is calculated through the integral histogram based local exhaustive search. Finally, differ- ent weights are assigned to the searching results of patches by maximizing each probability map, and the final localization of the object in current frame is obtained by the weighted sum of the searching results of local patches. The experimental results indicate that weighted tracking and local patch based tracking in both sides, the proposed algorithm is not too complex. the proposed algorithm exceeds the background tracking precision and tracking successful rate. Besides, the proposed algorithm is not too complex.
出处
《空军工程大学学报(自然科学版)》
CSCD
北大核心
2014年第2期53-56,65,共5页
Journal of Air Force Engineering University(Natural Science Edition)
基金
国家自然科学基金资助项目(61175029)
陕西省自然科学基金资助项目(2011JM8015)
关键词
视觉跟踪
局部分块
背景加权
积分直方图
words, visual tracking
local patch
weighted background
integral histogram