基于视频的运动目标跟踪算法  

Algorithm of Moving Object Tracking Based on Video Images Sequence

作　　者：刘俊杰[1] 杨勇[1] 才华[2] 曲福恒[1] 李双鑫[3] 

机构地区：[1]长春理工大学计算机科学技术学院,长春130022 [2]长春理工大学电子信息工程学院,长春130022 [3]东北师范大学图书馆,长春130024

出　　处：《吉林大学学报（信息科学版）》2017年第3期347-353,共7页Journal of Jilin University（Information Science Edition）

基　　金：吉林省科技发展计划基金资助项目(20130101179JC)

摘　　要：为更加准确、快速地检测与跟踪到运动目标,将背景差分法和帧间差分法相融合对CAMSHIFT(Continuously Adaptive Mean-SHIFT)算法进行改进。首先,通过背景差分法和帧间差分法相融合确定目标所在区域,然后结合CAMSHIFT迭代算法实现目标跟踪。实验结果表明,该方法改变了传统CAMSHIFT算法需手动选定目标和跟踪窗容易发散的局限性,并提高了跟踪的准确性与稳定性。Moving target tracking in video is an important research direction in the field of computer vision. In order to detect and track the moving objects more accurately and quickly,we propose an improved CAMSHIFT（ Continuously Adaptive Mean-SHIFT） algorithm based on background subtraction and frame difference algorithm.First of all,the target area is determined by the background difference method and the frame difference method,then combining with the CAMSHIFT iterative algorithm the target tracking is realized. Experiments show that this method has changed the traditional CAMSHIFT algorithm which needs manually selecting the target,has overcome the limitations of diverging,and has improved the accuracy and stability of tracking.

关 键 词：CAMSHIFT算法 目标跟踪 背景差分法 帧间差分法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]