A Parallel Processing System for Visual Media Applications

시각매체를 위한 병렬처리 시스템

  • 이형 (대전보건대학 방송제작기술과) ;
  • 박종원 (충남대학교 정보통신공학과)
  • Published : 2002.01.01

Abstract

Visual media(image, graphic, and video) processing poses challenge from several perpectives, specifically from the point of view of real-time implementation and scalability. There have been several approaches to obtain speedups to meet the computing demands in multimedia processing ranging from media processors to special purpose implementations. A variety of parallel processing strategies are adopted in these implementations in order to achieve the required speedups. We have investigated a parallel processing system for improving the processing speed o f visual media related applications. The parallel processing system we proposed is similar to a pipelined memory stystem(MAMS). The multi-access memory system is made up of m memory modules and a memory controller to perform parallel memory access with a variety of combinations of 1${\times}$pq, pq${\times}$1, and p${\times}$q subarray, which improves both cost and complexity of control. Facial recognition, Phong shading, and automatic segmentation of moving object in image sequences are some that have been applied to the parallel processing system and resulted in faithful processing speed. This paper describes the parallel processing systems for the speedup and its utilization to three time-consuming applications.

영상과 그래픽 및 비디오와 같은 시각 매체들을 실시간으로 처리하기 위한 구현 기술과 그에 따른 확정성 측면에서 많은 연구들이 진행되고 있는데, 이러한 연구들은 영상처리 전용 프로세서 구현부터 다양한 매체들을 함께 처리할 수 있는 프로세서 구현을 포함하는 범주까지 진행되고 있다. 또한, 다양한 병렬처리 기법들이 실시간 처리를 위한 프로세서의 구현에 적용되고 있다. 본 논문은 이러한 시각매체들을 실시간으로 처리하기 위하여 메모리 시스템과 다수개의 처리기로 구성된 pipelined SIMD 구조를 갖는 병렬처리시스템을 제안한다. 메모리시스템은 m개의 메모리 모듈과 메모리 제어기로 구성되어 있는 다중접근 기억장치로써, m개의 메모리 모듈에서 병렬로 n(=p${\times}$q)개의 데이터에 접근하기 위한 다양한 형태, 즉, 행(1${\times}$pq)과 열(pq${\times}$1) 및 블록 (p${\times}$q) 접근을 제공한다. 제안한 병렬처리시스템에 얼굴인식과 퐁 음영 및 동영상에서의 자동영상분할을 적용하여 시스템 성능을 분석하였다.

Keywords

References

  1. Sethuraman Panchanathan, 'Architecture Appr-caches for Multimedia Processing,' 4th ACPC'99 Satiburg, Austria, Feb. 1999
  2. Edwige Pissaloux, 'On Parallel Reconfigurable Architecture for Image Processing,' 4th ACPC'99 SaIzburg, Autstia, Feb. 1999
  3. M. Duff, 'Parallel Processors for Digital Image Processing,' Advances in Digitat Image Proce- ssing, pp. 265-279, 1979
  4. K. E. Batcher, 'Design a massively parallelprocessor,' IEEE Trans. Comput. Vol. C-29,pp. 836-840, Sep. 1980 https://doi.org/10.1109/TC.1980.1675684
  5. S. Wilson, 'The Pixie-SOOO -A Systolic An-ayProcessor,' in Proc, 1EEE Comput. Soc.WorkshoP, APAIDM, pp. 477-483, Nov, 1985
  6. M. J. Kimmel, et al.,'MITE:Morphic Image Transform Engine, an architecture for recon-figurable pipelines of neighborhood proce-ssors,' in Proc, IEEE Comput. Soc. Workshop, APAIDM, pp 493-500, Nov. 1985
  7. E. W. Kent, et al., 'Hierarchical Cell Logic and the PIPE processor: structural and func-tional correspondence,' in Proc, 1EEE Comput. Soc. Workshop.APAIDM, pp.311-319,Nov. 1985
  8. R. M. Laugheed, et al., 'Cytocomputer: Architecture for parallel image processing,' in Proc, of the workshop on Picture Data Description Management, pp. 281-286, Aug. 1980
  9. J. W. Park, 'An Efficient Memory System for Image Processing,' 1EEE trans. Comput. Vol. C-35, No. 7, pp. 33-39, 1986
  10. J.W.Park and D.T.Harper III, 'An Efficient Memoiy System for SIMD Construction of a Gaussian Pyramid,' IEEE Trans. on Parallel and Dist. Vol. 7, No. 7, July 1996
  11. Philippe Salembier, 'Morphological multiscale segmentation for image coding,' Signat Pro-cessing Vol. 38, pp. 359-386, 1994 https://doi.org/10.1016/0165-1684(94)90155-4
  12. Lic Vincent, 'Morphological Grayscale Re-construction in image analysis: applications and efficient algorithm,' IEEE Trans. on Image Processing, Vo1.2, No.2, pp. 176-201, Apr. 1993 https://doi.org/10.1109/83.217222
  13. 'IQ80960RM/RN Evaluation Platform Board Manual,' Feb. 1999
  14. H. Lee, K. A. Moon, J.W.Park, 'Design of parallel processing system for facila image retrieval', 4th ACPC'99 Sahburg, Feb. 1999
  15. http://www.pt.hk-r.se/$^\sim{pt93mm}$/thesis/ technique-s/fast_Phong/siggraph86.html
  16. Munchurl Kim, et al., 'A VOP Generation Tool: Automatic Segmentation of Moving Objects in Image Sequences Based on Spa-tio-Temporal Information,' 1EEE Trans. on CSVT, Vo1.9, No.8, pp.1216-1226, Nov. 1999
  17. L. Vincent and P. Soille, 'Watershed in digital spaces: An Efficient algorithm based on immersion simulations,' IEEE Trans. on PAMI, Vo1.13, No.6, pp.583-598, Jun. 1991