基于视频片段的视频检索

Video retrieval based on video clip

为提高视频检索的查询效率,提出一种基于视频片段的视频检索方法。该方法利用相邻帧之间的HIS(Hue,Saturation,Intensity)颜色信息特征将视频流分割成子片段,并采用高维索引结构Vector-Approximation Trie(VA-Trie)来组织视频子片段,然后,利用空间和纹理特征定义视频片段的相似度模型,在此基础上采用基于限定性滑动窗口的高效视频检索算法进行视频片段检索。研究结果表明:与其他检索方法相比,该方法能有效地提高视频检索的查全率和查询率,适合用于运动视频检索。

A video retrieval method based on video clip was presented to enhance the retrieval efficiency. The video stream was segmented into segments by HSI （Hue,Saturation,Intensity） color information between neighboring frames,and the high-dimensional index structure Vector-Approximation Trie （VA-Trie） was adopted to organize the segments. The new similarity model was defined using spatial and texture features,which can fully take into account the temporal order among video segments. Furthermore,the new query algorithm was used for video retrieval based on restricted sliding window to improve the retrieval accuracy. Experimental results indicate that the proposed approach can improve the recall ratio and precision ratio effectively,and suits the retrieval of sports videos.