Analytical distortion aware video coding for computer based video analysis
| Autor: | Ce Zhu, Fangliang Song, Yuyang Liu, Frederic Dufaux, Xiang Zhang, Mao Min |
|---|---|
| Přispěvatelé: | University of Electronic Science and Technology of China (UESTC), Laboratoire des signaux et systèmes (L2S), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS) |
| Rok vydání: | 2017 |
| Předmět: |
HEVC
Mean squared error Computer science media_common.quotation_subject Real-time computing ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Fidelity 02 engineering and technology 03 medical and health sciences 0302 clinical medicine [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing video analysis 0202 electrical engineering electronic engineering information engineering media_common Computer based 030229 sport sciences Object detection [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] rate-analytical- distortion optimization Bit rate 020201 artificial intelligence & image processing Algorithm design Video coding [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Labor cost Coding (social sciences) |
| Zdroj: | MMSP 19th International Workshop on Multimedia Signal Processing (MMSP) 19th International Workshop on Multimedia Signal Processing (MMSP), Oct 2017, London-Luton, United Kingdom. ⟨10.1109/mmsp.2017.8122253⟩ Web of Science |
| DOI: | 10.1109/mmsp.2017.8122253 |
| Popis: | International audience; With the development of artificial intelligence, more and more multimedia applications for various tasks have emerged in our daily life. Meanwhile, as one of the main information sources of the applications, a huge amount of video data has been being generated by portable or mounted cameras in daily basis for varying purposes including surveillance, in which case we may need computers to "watch" videos to save labor cost. However, most video coding standards are designed for the highest human perceptual quality given a bit rate by minimizing a fidelity cost function (e.g., mean squared error, MSE), assuming the content will be consumed by human beings. In view of the above considerations, this paper proposes a new rate-analytical-distortion optimization method (RADO) for video analysis. Specifically, we consider moving object detection as the analysis task. Accordingly, we develop a novel rate analytical distortion (RAD) model for video coding, where the analytical distortion is related to the object detection performance expressed in terms of F-measure. As shown in the experimental results, the performance of the video analysis task can be significantly improved (up to 40% reduction of analytical distortion) with a slight bit rate increase. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|