This paper studies the relative entropy and its square root as distance measures ofneighboring video frames for video key frame extraction. We develop a novel approach handlingboth common and wavelet video sequences, in which the extreme Studentized deviate test isexploited to identify shot boundaries for segmenting a video sequence into shots. Then, video shotscan be divided into different sub-shots, according to whether the video content change is large ornot, and key frames are extracted from sub-shots. The proposed technique is general, effective andefficient to deal with video sequences of any kind. Our new approach can offer optional additionalmultiscale summarizations of video data, achieving a balance between having more details andmaintaining less redundancy. Extensive experimental results show that the new scheme obtainsvery encouraging results in video key frame extraction, in terms of both objective evaluation metricsand subjective visual perception
展开▼
