Video Shot Boundary Detection for Low Complexity HEVC Encoders

This paper proposes a new preprocessing phase in High Efficiency Video Coding of high resolution video: a module for shot boundary detection and a complementary decision of ad-hoc intra frame encoding. The data processing involves only the chroma subsampled components, thus delivering faster results with less computations. Experiments using the HM (HEVC test Model) reference encoder from ITV show the method's efficiency and increasing detection accuracy, while conveniently introducing infrequently intra coded frames that improve the SNR (Signal to Noise Ratio) quality measure for the following inter-predicted frames.

[1]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Qingxin Zhu,et al.  A Video Shot Boundary Detection Approach Based on CNN Feature , 2017, 2017 IEEE International Symposium on Multimedia (ISM).

[3]  Gary J. Sullivan,et al.  High Efficiency Video Coding (HEVC), Algorithms and Architectures , 2014, Integrated Circuits and Systems.