Richard Chen

Real-time object segmentation and coding for selective-quality video communications

The MPEG-4 standard enables the representation of video as a collection of objects. This paper describes an automatic system that exploits such a representation. Our system consists of two parts: real-time content extraction algorithms and a real-time multi-object rate control method. We present two approaches to content extraction: foreground segmentation based on two cameras and face segmentation based on a single camera. The main contributions of this paper are: 1) under a stereo camera setup, we improve a disparity estimation algorithm to obtain crisp and smooth boundaries of foreground objects; 2) for a single camera scenario, we propose a novel algorithm for face detection and tracking, combining facial color and structure information; and 3) we develop a constant-quality variable bitrate (CQ-VBR) control algorithm that guarantees the quality specification for each object obtained from the two content extraction methods. Both segmentation algorithms run in real-time on a low-cost media processor, and have been tested extensively in various indoor environments. The CQ-VBR control algorithm is a useful tool for the evaluation of object-based coding. For low-bit-rate applications, we can achieve significant reduction in the overall bitrate, while maintaining the same visual quality of the foreground/face object as compared to conventional frame-based coding. Based on tests conducted on several sequences of different complexity levels, the bit-rate savings can be up to 48%. The satisfactory foreground segmentation (results presented) permits porting a live foreground object into arbitrary scenes to create composite video.

Wireless home entertainment networking using IEEE 802.11e QoS WLAN

We explore IEEE 802.11e enhanced distributed channel access (EDCA) to provide guaranteed delivery of high bit rate non-scalable high definition (HD) video and adaptive delivery of layered video to make efficient use of the remaining wireless bandwidth.

Complexity-adaptive streaming architecture for video multicasting to CE devices

The paper presents a layered streaming architecture for multicasting of scalable video to devices connected at various bandwidths and having different complexity-levels. The approach combines layered coding with a novel multi-channel streaming system that enables receiver-driven adaptation based on the experienced network conditions and device complexity.

Complexity-scalable MPEG-4 FGS streaming for UMA

This paper presents a systematic approach to establish the complexity scalability of MPEG-4 Fine-Granular-Scalability (FGS) to fulfill the requirements of Universal Multimedia Access (UMA). We also present receiver-driven streaming strategies using the proposed FGS-based system.

Industry track: adaptive wireless video streaming proxy for home entertainment networks

In this paper, we propose an adaptive wireless video streaming proxy (AWVSP) for distributing broadcast quality video coded using conventional non-scalable MPEG profiles. A fast Rate-Distortion optimized Data Partitioning (RDDP) algorithm is employed to dynamically adapt the data rate of the MPEG video in real-time to sporadically varying wireless channel. A rate-matching algorithm is used to determine the adaptive data rate based on transmission buffer-occupancy. Our simulation results indicate the superior performance of the proposed AWVSP in terms of perceived video quality measured in both PSNR and playback smoothness.