机构地区: 宁波大学
出 处: 《电子学报》 2003年第9期1426-1428,共3页
摘 要: 自动、快速的视频目标提取与跟踪是目标基视频编码中的一项关键技术 .本文提出一种运动目标提取与跟踪新算法 .首先 ,根据多帧运动信息和高阶统计检测方法得到二值运动掩模图像 ,然后提出一种改进分水岭算法对运动区域及其周围部分进行分割 .将二者所得结果进行投影运算 ,得到最终运动目标 .最后提出一种运动目标跟踪新算法 ,能对目标进行有效的跟踪 . Fast and automatic segmentation and tracking of video object is a key technology in object based video coding.A algorithm for extracting and tracking moving object is proposed.First,a binary motion image is achieved based on high order statistics detection and motion information of multiple frames.Then,an improved watershed algorithm is used to segment motion region and its surrounding areas.Thus the moving object with fine edges can be extracted with the spatial and temporal segmented results.Finally,a new algorithm is proposed to efficiently track moving object.Experimental results show that the proposed algorithm is efficient.
关 键 词: 视频目标分割 有限区域分割 改进分水岭算法 运动跟踪
领 域: [自动化与计算机技术] [自动化与计算机技术]