摘要
提出了一种利用随机图的地理视频流解析方法,用于对地理视频中的运动要素进行相关性分析。利用运动要素在时空上的相关性和连续性,得到一种反映视频流中运动要素空间关联的时序结构,提供了一个将语义信息与运动信息有效整合的思路。实验证明,该方法不仅能够动态、直观地描述地理视频流中运动要素的空间关系,而且为地理视频场景的语义描述提供了新的思路。
Decomposition of a Geo-video stream presents the expression of video from spatial feature set. Although it has been studied widely, spatial relations underlying a scenario are not well understood. Here we use a method which takes advantage of random graph theory to investigate the semantic knowledge in Geo-video, leading to correlation analysis of the target motion elements in a Geo-video stream. We used the connections of target motion elements, both correlation and continuity, to lead to a structure in time series that reveals clues to the event development of the video stream. Furthermore, it provides a method for the effective integration of semantic and campaign information. Ultimately, experimental results show that the method offers a better description of video elements than can be achieved with existing schemes. In addition, the proposed method offers a new way of thinking about the semantic description of the geographic video scenarios.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2014年第2期206-209,共4页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金资助项目(41101432
41201378)
重庆市自然科学基金资助项目(2010BB2416)~~
