摘要
对于镜头骤变检测 ,通过最小扩展树算法 (MST)提取保留了视频帧空间信息的颜色聚合向量直方图、引入了动态自适应阈值和时间阻尼 ,使得骤变检测效率高 ;对于渐变检测 ,通过分析其数学产生模型 ,根据模型特性实现渐变镜头检测 ;最后 。
The detection correctness of abrupt transition is improved by color coherence vector histogram using minimum spanning tree (MST) to keep video frames' spatial information, along with introducing adaptive threshold and time damping The detection of video gradual transition (fade and dissolve) is implemented based on the characteristics of production model Both the abrupt and gradual transitions are accomplished at the same time through a sound fusion strategy
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2003年第11期1386-1392,共7页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(60 2 72 0 3 1)
教育部博士点基金(2 0 0 10 3 3 5 0 49)
浙江省自然科学基金(ZD0 2 12 )
国家"十五"重大科技攻关项目(2 0 0 1BA10 1A0 7 0 3 )
浙江省科技计划重点科研项目(2 0 0 3C2 10 10 )资助
关键词
视频图像序列
镜头边缘检测融合算法
视频流
鲁棒性
图像识别
minimum spanning tree (MST)
color coherence vector (CCV)
adaptive threshold
production model
fusion shot detection
