检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]清华大学计算机科学与技术系,北京100084 [2]清华大学智能技术与系统国家重点实验室,北京100084
出 处:《软件学报》1999年第9期956-961,共6页Journal of Software
基 金:国家863高科技项目基金;国家"211"学科建设项目基金
摘 要:在电影、电视等观赏类视频信号中,情节的紧张程度一般都在镜头的切换频率上得以体现,而在对此类视频信号的检索中,用户往往希望能够根据情节紧张程度来进行检索.文章提出了对此类视频信号的镜头切换频率进行度量,并根据得到的镜头频度进行视频检索的方法,给出了视频流的镜头分割算法,以及为减小漏分/错分影响所采用的镜头频度度量——镜头平均帧数的鲁棒计算方法.文章还阐述了利用镜头频度进行视频检索的基本思想及算法细节。In the film, television and many other videos, exciting video sections are usually reflected by their frequent shot changes, and such sections are the most frequently objects in retrieval of this kind of video. In this paper, a method on retrieving videos according to their shot change frequencies is presented. Scene transition analysis has done on real videos, and video segmentation algorithm for both cut and dissolve are developed. To lessen the influence of error and missing shot segmentations, a robust calculation method of shot frequency on shot sequence acquired is proposed. Basic ideas and algorithm modules are given in detail, also with the experimental results on film video and analysis.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.3