中北大学学报（自然科学版）2016，Vol.37Issue(6)：633-637,665,6.DOI:10.3969/j.issn.1673-3193.2016.06.014
一种基于Meanshift算法的目标跟踪改进
An Improved Meanshift Algorithm for Target Tracking
摘要
Abstract
Aiming at the problem of occlusion and similar interference,a new improved algorithm based on the Meanshift algorithm was proposed.The algorithm effectively combined the Meanshift algorithm with the Kalman filtering algorithm to accurately determine the location of the target centroid.Accord-ing to the target centroid position and the front frame search window boundary,the current search win-dow boundary is adj usted adaptively to match the target position.In this way,the tracking results are more accurate and reliable,and the influence of the environment and other factors on the algorithm are also reduced.Through the experimental analysis,the improved algorithm which has good stability and adaptability can effectively solve the problem of large area occlusion and similar interference.关键词
目标跟踪/Meanshift算法/Kalman滤波算法Key words
target tracking/Meanshift algorithm/Kalman algorithm分类
信息技术与安全科学引用本文复制引用
朱钾,李化..一种基于Meanshift算法的目标跟踪改进[J].中北大学学报（自然科学版）,2016,37(6):633-637,665,6.基金项目
山西省自然科学基金资助项目(2014011019-1) （2014011019-1）
