提出一种新的用于视频点播系统的视频检索方法,用户提交单帧图片中的感兴趣部分作为查询输入,服务器据此查询对存储的视频摘要片断的数据帧进行分割,再判断帧数据与查询图片的相似性,并将结果返回给用户选择播放.用户查询的输入可以来自影片的海报宣传画、影片花絮镜头等等,由于仅对用户感兴趣的部分进行处理,所以对背景(非感兴趣区域)的色彩无须约束.实验结果表明本方法可以准确定位到用户期望的查询结果,可以有效应用于视频点播系统.
A novel type for video-on-demand (VOD) is presented. The user uses the interested part of single image as the query. The system server,which stores the video summary in the whole system,co-segments the frames in video summaries according to the query,and computes the distance between the image and the query. Furthermore,the server can localize and play the video that the user requested. The query can come from the poster or from the frame itself,since it only handles the region of interest (ROD,no constraints are required for the color of the background (out of ROD, Experiments show that it is a novel and effective style for video retrieval, and can be applied in the VOD system.