Following the success of the audio video standard (AVS) for 2D video coding, in 2008, the China AVS workgroup started developing 3D video (3DV) coding techniques. In this paper, we discuss the background, technica...Following the success of the audio video standard (AVS) for 2D video coding, in 2008, the China AVS workgroup started developing 3D video (3DV) coding techniques. In this paper, we discuss the background, technical features, and applications of AVS 3DV coding technology. We introduce two core techniques used in AVS 3DV coding: inter-view prediction and enhanced stereo packing coding. We elaborate on these techniques, which are used in the AVS real-time 3DV encoder. An application of the AVS 3DV coding system is presented to show the great practical value of this system. Simulation results show that the advanced techniques used in AVS 3DV coding provide remarkable coding gain compared with techniques used in a simulcast scheme.展开更多
This paper presents a new implementation of a high-definition image-processing engine,which mainly targets the 3-dimensional(3D)visualization and stereo video stream display of binocular display equipment.The engine i...This paper presents a new implementation of a high-definition image-processing engine,which mainly targets the 3-dimensional(3D)visualization and stereo video stream display of binocular display equipment.The engine is compatible with the mainstream analog and digital stereo videos in component format and is able to receive stereo composite video broadcast signals using an integrated analog stereo video decoder.The four modules include a spatiotemporal scaling transform engine,a 2D–3D converter,an image animating engine,and a 2D scalar operating in pipeline architecture to implement the video format conversion and the stereo effect enhancement.Furthermore,the data access,hardware structure,and system-level configurations are optimized.Finally,the proposed architecture is realized by 0.18 lm CMOS technology.The application-specific integrated circuit verification results show that the engine can generate a strong feeling of 3D immersion and highdefinition image quality with minimal flicker.The chip has wide compatibility and an uppermost 1080P-processing capacity,which has approximately 3.5 million gates with about 43 mm2 die size.展开更多
基于图像的二维人脸识别技术日趋成熟,但仍受光照、姿态和表情等变化的影响。利用三维人脸模型提高人脸识别性能并将其应用于实际成为近几年学术界的研究趋势。本文提出了SWJTU-MF多模人脸数据库(SWJTU multimodal face database,SWJTU-...基于图像的二维人脸识别技术日趋成熟,但仍受光照、姿态和表情等变化的影响。利用三维人脸模型提高人脸识别性能并将其应用于实际成为近几年学术界的研究趋势。本文提出了SWJTU-MF多模人脸数据库(SWJTU multimodal face database,SWJTU-MF Database),包含200个中性表情中国人的4种人脸样本数据,包括可见光图像、二维视频序列、三维人脸(高精度)和立体视频序列。本文首先分类介绍现有的三维人脸识别算法,然后概述相关的多模人脸数据库,接着提出SWJTU-MF多模人脸数据库,并说明数据库的采集装置、采集环境、采集过程及数据内容,随后简要展示数据标准化过程。最后讨论本数据库面向的应用研究,并给出SWJTU-MF建议的评测协议。展开更多
文摘Following the success of the audio video standard (AVS) for 2D video coding, in 2008, the China AVS workgroup started developing 3D video (3DV) coding techniques. In this paper, we discuss the background, technical features, and applications of AVS 3DV coding technology. We introduce two core techniques used in AVS 3DV coding: inter-view prediction and enhanced stereo packing coding. We elaborate on these techniques, which are used in the AVS real-time 3DV encoder. An application of the AVS 3DV coding system is presented to show the great practical value of this system. Simulation results show that the advanced techniques used in AVS 3DV coding provide remarkable coding gain compared with techniques used in a simulcast scheme.
基金supported by the Important Specific Projects of National Science and Technology of China(2009ZX01033-001-010)
文摘This paper presents a new implementation of a high-definition image-processing engine,which mainly targets the 3-dimensional(3D)visualization and stereo video stream display of binocular display equipment.The engine is compatible with the mainstream analog and digital stereo videos in component format and is able to receive stereo composite video broadcast signals using an integrated analog stereo video decoder.The four modules include a spatiotemporal scaling transform engine,a 2D–3D converter,an image animating engine,and a 2D scalar operating in pipeline architecture to implement the video format conversion and the stereo effect enhancement.Furthermore,the data access,hardware structure,and system-level configurations are optimized.Finally,the proposed architecture is realized by 0.18 lm CMOS technology.The application-specific integrated circuit verification results show that the engine can generate a strong feeling of 3D immersion and highdefinition image quality with minimal flicker.The chip has wide compatibility and an uppermost 1080P-processing capacity,which has approximately 3.5 million gates with about 43 mm2 die size.
文摘基于图像的二维人脸识别技术日趋成熟,但仍受光照、姿态和表情等变化的影响。利用三维人脸模型提高人脸识别性能并将其应用于实际成为近几年学术界的研究趋势。本文提出了SWJTU-MF多模人脸数据库(SWJTU multimodal face database,SWJTU-MF Database),包含200个中性表情中国人的4种人脸样本数据,包括可见光图像、二维视频序列、三维人脸(高精度)和立体视频序列。本文首先分类介绍现有的三维人脸识别算法,然后概述相关的多模人脸数据库,接着提出SWJTU-MF多模人脸数据库,并说明数据库的采集装置、采集环境、采集过程及数据内容,随后简要展示数据标准化过程。最后讨论本数据库面向的应用研究,并给出SWJTU-MF建议的评测协议。