摘要
全景智能化视频中存在多种近似的目标干扰项,且在动态活动条件下容易丢失监测目标,影响监测方法对设定目标的抓取效果,针对这一问题以人机交互为基础,设计全新的全景智能化视频目标自动监测方法。该方法以投影变换矩阵为前提,标定与配准摄像机安装节点;利用示性函数判断图像是否为背景图像,根据方向梯度公式排除近似目标干扰项;基于人机交互设置目标模板区域,通过均值偏移过程检测方法追踪监测目标所在位置,并自动恢复丢失目标,实现对全景智能化视频目标的自动监测。结果表明,对照其他3组自动监测方法,基于人机交互的自动监测,从第1帧图像开始匹配目标,抓取概率一直维持在0.9以上,监测效果远优于对照的3组方法。
There are many similar target interference items in panoramic intelligent video,and it is easy to lose the monitoring target under the condition of dynamic activity,which affects the grasping effect of the monitoring method on the set target.Aiming at solving this problem,a new panoramic intelligent video target automatic monitoring method was designed based on human-computer interaction.Based on the projection transformation matrix,the camera installation nodes were calibrated and registered;The indication function was used to judge whether the image is a background image,and the approximate target interference term was eliminated according to the directional gradient formula;Set the target template area based on human-computer interaction,tracked the location of the monitoring target through the mean shift process detection method,and automatically recovered the lost target,so as to realize the automatic monitoring of panoramic intelligent video target.The experimental results showed that compared with the other three groups of automatic monitoring methods,the automatic monitoring based on human-computer interaction matched the target from the first frame image,and the capture probability remained above 0.9,while the monitoring effect is much better than the three groups of methods..
作者
李蓉
LI Rong(Lu'an vocational and Technical College,Changzhi 046000,Shanxi China)
出处
《粘接》
CAS
2022年第1期111-115,共5页
Adhesion
关键词
人机交互
全景视频
摄像机标定
干扰目标
背景判别
自动监测
human computer interaction
Panoramic video
camera calibration
jamming target
background discrimination
automatic monitoring