Region-of-Interest Based Resource Allocation for Conversational Video Communication of H.264/AVC

Power-aware Regions-of-Interest Computational Resource Allocation for Mobile Sign Language Video Encoding

“…The hardware configuration of the laptop is as follows: CPU 2.13GHz, memory 2G DDR. Table 1 gives the details of performance for JM16.2, literature [6] and three operational levels of our encoder for two standard sign language test sequences. For Silent sequence compared to JM our Level1+ROI, Level2+ROI, Level3+ROI achieve encoding time reduction of 4.12%, 74.6%, 89.1% at the cost 2.29 dB, 2.46 dB, 2.85dB loss in average PSNR respectively, meanwhile, the PSNR in face increases 0.69 dB, 0.46 dB, 0.30dB, the PSNR in hands increases 0.42 dB, 0.17 dB, 0.09dB, increased bit rate of Level3+ROI is 4.9%.…”

“…This phenomenon gives a chance to code all MB unequally: ROI has higher priority which can be allocated more computational resource; non-ROI has lower priority which can be allocated less computational resource. Liu et al, [6] proposed a ROI based H.264 computational resource allocation scheme, in their scheme, several coding parameters including quantization parameter (QP), candidates for mode decision, number of reference frames (RF), accuracy of motion vectors and search range (SR) of motion estimation are adaptively adjusted at MB level according to the relative importance of each MB. It saves energy and guarantees fine quality in ROI.…”

Understanding User Experience of Mobile Video: Framework, Measurement, and Optimization

“…One is to allocate more of the limited encoding bits to the important areas than the background (Sun, Ahmad & Zhang, 2006). Many different bit allocation schemes for ROI-based video coding have been presented in (Ahmad, 2006a;Ahmad & Lee, 2008;Liu, Li & Soh, 2008;Lu et al, 2005;Shi, Yue & Yin, 2008;Sun et al, 2006;Yang, Zhang, Ma & Zhao, 2009). The other way is to crop and display the ROI area only on the small screen of a mobile device in order to zoom in the small objects, which has been examined for sports videos Seo & Kim, 2006;Shenghong, Yufu & Shenglong, 2010).…”

Subjective Quality Evaluation of Foveated Video Coding Using Audio-Visual Focus of Attention

“…Top-down attention has been more popularly employed because of its intuitiveness. Frequently used top-down cues include faces [20], [21], skin regions [22], [23], moving objects [3], [24], etc. Bottom-up and top-down attention models can be combined for more accurate attention modeling.…”