Saliency-Based Fidelity Adaptation Preprocessing for Video Coding

• Published in: Journal of computer science and technology Vol. 26; no. 1; pp. 195 - 202
• Main Author: 卢少平 张松海
• Format: Journal Article
• Language: English
• Published: Boston Springer US 2011; Springer Nature B.V
• Subjects: Accuracy; Adaptation; Adjustment; Algorithms; Analysis; Artificial Intelligence; Blurring; Coding; Compression ratio; Computer Science; Data Structures and Information Theory; Digital video; Encoders; H.264; Image compression; Image processing systems; Information Systems Applications (incl.Internet); Mathematical models; Neurosciences; R&D; Research & development; Salience; Short Paper; Software Engineering; Studies; Theory of Computation; Video compression; Visual; Visual perception; 空间尺度; 编码方案; 视觉质量; 视频编码器; 计算技术; 预处理; 高斯模糊; region-of-interest; fidelity adjustment; visual saliency; encoder; bilateral filter
• ISSN: 1000-9000; 1860-4749; 1860-4749
• DOI: 10.1007/s11390-011-9426-5

In this paper, we present a video coding scheme which applies the technique of visual saliency computation to adjust image fidelity before compression. To extract visually salient features, we construct a spatio-temporal saliency map by analyzing the video using a combined bottom-up and top-down visual saliency model. We then use an extended bilateral filter, in which the local intensity and spatial scales are adjusted according to visual saliency, to adaptively alter the image fidelity. Our implementation is based on the H.264 video encoder JM12.0. Besides evaluating our scheme with the H.264 reference software, we also compare it to a more traditional foreground-background segmentation-based method and a foveation-based approach which employs Gaussian blurring. Our results show that the proposed algorithm can improve the compression ratio significantly while effectively preserving perceptual visual quality.