A Quick Moving Target Detection Method based on Real-time Airborne Videos

摘要：

In this paper,a fast method of moving target detection from real-time airborne videos is presented.We explore the motion relationship in the airborne videos,employ the global motion estimation to evaluate the background movement,and utilize binocular interpolation for motion compensation.Thus,the moving target detection in dynamic airborne videos is converted into detection in static backgrounds.We multiply the difference of the symmetrical images among three adjacent frames to enhance moving target and enlarge the difference between the target and background noises.Region growth and morphological image processing techniques are employed finally to segment the target.Experimental results demonstrate the effectiveness and robustness of the proposed approach.

关键词： airborne video global motion estimation target detection motion compensation

作者: Hong-bin Deng Yuan-yuan He Zhen-yong Guo Fa-wang Liu

作者单位: Beijing Laboratory of Intelligent Information Technology,School of Computer Science and Technology,B School of Aerospace Science and Engineering,Beijing Institute of Technology,Beijing,China,100081 Institute of Electronics,Chinese Academy of Sciences,China,100081

会议类型: 国际会议

会议名称: International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)

会议地点: 上海

会议语种:英文

在线出版日期: 2008-06-29（万方平台首次上网日期，不代表论文的发表时间）