Real-Time Hough Transform on 1-D SIMD Processors: Implementation and Architecture Exploration

  • Yifan He
  • Zoran Zivkovic
  • Richard Kleihorst
  • Alexander Danilin
  • Henk Corporaal
  • Bart Mesman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5259)

Abstract

In the first part of this paper, an improved slope-intercept like representation is proposed for implementation of Standard Hough Transform (SHT) on SIMD (Single-Instruction, Multiple-Data) architectures with no local indirect addressing support. The real-time implementation is realized with high accuracy on our Wireless Smart Camera (WiCa) platform. The processing time of this approach is independent of the number of edge points or the number of detected lines. In the second part, we focus on analyzing the differences between the SHT implementations on 1-D SIMD architectures with and without local indirect addressing. Three aspects are compared: total operation number, memory access/energy consumption, and memory area cost. When local indirect addressing is supported, the results show a considerable amount of reduction in total operations and energy consumption at the cost of extra chip area. The results also show that the focuses for further optimization of these two architectures are different.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hough, P.: Method and Means for Recognizing Complex Patterns. U.S. Patent No. 3, 069, 654 (1962)Google Scholar
  2. 2.
    Illingworth, J., Kittler, J.: A Survey of the Hough Transform. Computer Vision, Graphics, and Image Processing 44, 87–116 (1988)CrossRefGoogle Scholar
  3. 3.
    Duda, R., Hart, P.: Use of the Hough Transformation to Detect Lines and Curves in Pictures. Communications of the ACM 15, 11–15 (1972)CrossRefMATHGoogle Scholar
  4. 4.
    Kleihorst, R., Schueler, B., et al.: Architecture and Applications of Wireless Smart Cameras (Networks). In: IEEE Inter. Conf. on Acoustics, Speech and Signal Processing (2007)Google Scholar
  5. 5.
    Abbo, A., Kleihorst, R., et al.: Xetal-II: A 107 GOPS, 600mW Massively-Parallel Processor for Video Scene Analysis. In: International Solid-State Circuits Conference, pp. 192–201 (2008)Google Scholar
  6. 6.
    Canny, J.: A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 679–698 (1986)CrossRefGoogle Scholar
  7. 7.
    Li, Z., Tong, F., et al.: Parallel Algorithms for Line Detection on a 1xN Array Processor. In: International Conference on Robotics and Automation (1991)Google Scholar
  8. 8.
    Risse, T.: Hough Transform for Line Recognition: Complexity of Evidence Accumulation and Cluster Detection. Computer Vision, Graphics, and Image Processing 46, 327–345 (1989)CrossRefGoogle Scholar
  9. 9.
    He, Y., Zivkovic, Z., et al.: Real-Time Implementations of Hough Transform on SIMD Architecture. In: International Conference on Distributed Smart Cameras (2008)Google Scholar
  10. 10.
    Yamashita, N., Fujita, Y., et al.: An Integrated Memory Array Processor with a Synchronous-DRAM Interface for Real-Time Vision Applications. Pattern Recognition 4, 575–580 (1996)Google Scholar
  11. 11.
    Uh, G., Wang, Y., et al.: Effective Exploitation of a Zero Overhead Loop Buffer. In: ACM SIGPLAN workshop on Languages, compilers, and tools for embedded systems (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Yifan He
    • 1
    • 2
  • Zoran Zivkovic
    • 1
  • Richard Kleihorst
    • 1
  • Alexander Danilin
    • 1
  • Henk Corporaal
    • 2
  • Bart Mesman
    • 2
  1. 1.NXP Semiconductorsthe Netherlands
  2. 2.Technische Universiteit Eindhoventhe Netherlands

Personalised recommendations