Item


Selecting Video Key Frames Based on Relative Entropy and the Extreme Studentized Deviate Test

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

This work has been funded by the Natural Science Foundation of China (61471261, 61179067, U1333110) and by Grants TIN2013-47276-C6-1-R from the Spanish Government and 2014-SGR-1232 from the Catalan Government (Spain)

MDPI (Multidisciplinary Digital Publishing Institute)

Author: Guo, Yuejun
Xu, Qing
Sun, Shihua
Luo, Xiaoxiao
Sbert, Mateu
Abstract: 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
This work has been funded by the Natural Science Foundation of China (61471261, 61179067, U1333110) and by Grants TIN2013-47276-C6-1-R from the Spanish Government and 2014-SGR-1232 from the Catalan Government (Spain)
Document access: http://hdl.handle.net/2072/267793
Language: eng
Publisher: MDPI (Multidisciplinary Digital Publishing Institute)
Rights: Attribution 4.0 Spain
Rights URI: http://creativecommons.org/licenses/by/4.0/es/
Subject: Imatge -- Segmentació
Imaging segmentation
Title: Selecting Video Key Frames Based on Relative Entropy and the Extreme Studentized Deviate Test
Type: info:eu-repo/semantics/article
Repository: Recercat

Subjects

Authors