摘要
在视频监控方面,存在着运动目标的各种行为,针对这种情况,提出一种基于GMM与KLT算法的运动目标检测与跟踪方法。首先用基于GMM的背景减除法对运动目标进行检测,再通过形态学处理得到目标区域,然后对运动目标进行KLT特征点跟踪,最后根据特征点画出运动目标的运动轨迹。实验证明该算法有良好的检测结果与跟踪效果。
In video surveillance,there are various behaviors of moving objects. Aiming at this situation,this paper proposes a method of moving object detection and tracking based on GMM and KLT algorithm. Firstly,the background subtraction method based on GMM is used to detect the moving target and the target region is obtained by morphological processing. Then,the moving target is tracked by KLT feature point. Finally,the motion trajectory of the moving target is drawn according to the feature point.Experiments show that the algorithm has good detection result and tracking effect.
作者
梁硕
娄莉
张艳艳
HANG Shuo;LOU Li;ZHANG Yanyan(School of Computer, Xi＇an Shiyou University, Xi＇an 710065, China)
出处
《智能计算机与应用》
2018年第2期81-84,共4页
Intelligent Computer and Applications
基金
陕西省工业科技攻关项目(2015GY026)
陕西省工业科技攻关项目(2016GY123)
陕西省教育厅计算机科学与技术(学术学位)研究生教育综合改革项目(2015-S-ZH-015)
关键词
运动目标检测
背景减除法
运动目标跟踪
GMM
KLT
moving target detection
background subtraction method
moving target tracking
GMM
KLT
