摘要
为了提高视频画面目标检测和跟踪的速度,缩短目标跟踪的时间,提出基于机器视觉技术的视频画面目标检测和跟踪方法。基于机器视觉技术的分析,将机器视觉技术引入到视频画面目标的检测和跟踪中,通过视频画面与前一帧视频画面做像素差分运算,得到了二值差分视频画面,并利用阈值的调整,完成视频画面目标的检测;最后依托Camshift跟踪算法流程,得到了视频画面目标的颜色概率分布图,完成了视频画面目标的跟踪。实验结果表明,提出的检测跟踪方法相比传统检测跟踪方法,跟踪时间缩短了5.3 ms。
In order to improve the detection and tracking speed of the objects on the video image,shorten the object tracking time,a method of machine vision technology based detection and tracking of the objects on the video image is proposed.The machine vision technology is analyzed and then introduced into the detection and tracking of the objects on the video image.The pixel difference operation is carried out between the video image and its front one to obtain a binary difference video image.The detection of the objects on the video image is completed by adjustment of threshold value.Finally,according to Camshift tracking algorithm flow,the color probability distribution map of the objects on the video image is obtained to complete the object tracking.Experimental results show that,in comparison with the traditional detection and tracking method,the tracking time of the proposed method is reduced by 5.3 ms.
作者
邹航菲
罗婷婷
ZOU Hangfei;LUO Tingting(Department of Human Resource,Jiangxi Police Institute,Nanchang 330103,China;Department of Scientific Research and Development Planning,Jiangxi Police Institute,Nanchang 330103,China)
出处
《现代电子技术》
2021年第5期94-97,共4页
Modern Electronics Technique
基金
江西省教育厅科学技术研究重点项目:视频监控中画面目标的测量技术研究(GJJ171057)。
关键词
目标检测
目标跟踪
机械视觉技术
视频画面
跟踪方法
仿真验证
object detection
object tracking
machine vision technology
video image
tracking method
simulation verification
