Hybrid Morphology Processing Unit Architecture for Moving Object Segmentation Systems

  • Authors:

  • Shao-Yi Chien;Bing-Yu Hsieh;Yu-Wen Huang;Shyh-Yih Ma;Liang-Gee Chen

  • Affiliations:

  • DSP/IC Design Lab, Graduate Institute of Electronics Engineering and Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan 106;Media Tek, Inc., Hsinchu, Taiwan 300;Media Tek, Inc., Hsinchu, Taiwan 300;Vivotek, Inc., Taipei, Taiwan 235;DSP/IC Design Lab, Graduate Institute of Electronics Engineering and Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan 106

  • Venue:
  • Journal of VLSI Signal Processing Systems
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Video segmentation is a key operation in MPEG-4 content-based coding systems. For real-time applications, hardware implementation of video segmentation is inevitable. In this paper, we propose a hybrid morphology processing unit architecture for real-time moving object segmentation systems, where a prior effective moving object segmentation algorithm is implemented. The algorithm is first mapped to pixel-based operations and morphological operations, which makes the hardware implementation feasible. Then the high computation load, which is more than 4.2 GOPS, can be overcome with a dedicated morphology engine and a programmable morphology PE array. In addition, the hardware cost, memory size, and memory bandwidth can be reduced with the partial-result-reuse concept. This chip is designed with TSMC 0.35 驴m 1P4M technology, and can achieve the processing speed of 30 QCIF frames or 7,680 morphological operations per second at 26 MHz. Simulation shows that the proposed hardware architecture is efficient in both hardware complexity and memory organization. It can be integrated into any content-based video processing and encoding systems.