The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)

Korea Information Electronic Communication Technology (한국정보전자통신기술학회)
권호 표지
DOI QR코드

DOI QR Code

Image Filter Optimization Method based on common sub-expression elimination for Low Power Image Feature Extraction Hardware Design

저전력 영상 특징 추출 하드웨어 설계를 위한 공통 부분식 제거 기법 기반 이미지 필터 하드웨어 최적화

  • Kim, WooSuk (Electrical, Electronic, and Control Engineering, HanKyong University) ;
  • Lee, Juseong (Center of Human-centered Interaction for Coexistence) ;
  • An, Ho-Myoung (Department of Electronics, Osan University) ;
  • Kim, Byungcheul (Department of Electronic Engineering, Gyeongnam National University of Science and Technology)
  • Received : 2017.01.12
  • Accepted : 2017.04.25
  • Published : 2017.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, image filter optimization method based on common sub-expression elimination is proposed for low-power image feature extraction hardware design. Low power and high performance object recognition hardware is essential for industrial robot which is used for factory automation. However, low area Gaussian gradient filter hardware design is required for object recognition hardware. For the hardware complexity reduction, we adopt the symmetric characteristic of the filter coefficients using the transposed form FIR filter hardware architecture. The proposed hardware architecture can be implemented without degradation of the edge detection data quality since the proposed hardware is implemented with original Gaussian gradient filtering algorithm. The expremental result shows the 50% of multiplier savings compared with previous work.

본 논문은 저전력 영상 특징 추출 하드웨어 설계를 위한 공통 부분식 제거 기법 기반 이미지 필터 하드웨어 최적화 기법을 제안한다. 저전력 및 고성능 물체인식 하드웨어는 공장 자동화를 위한 산업용 로봇에 필수 모듈로 채택되고 있다. 따라서 물체인식 하드웨어의 영상 특징 추출 알고리즘에 다양하게 적용되는 Gaussian gradient 필터 하드웨어의 저면적 설계가 필수적이다. Gaussian gradient 필터의 하드웨어 복잡도를 줄이기 위해 필터에 사용되는 계수의 Symmetric한 특징과 Transposed form FIR 필터 하드웨어 구조를 이용했다. 제안된 이미지 필터의 하드웨어 구조는 알고리즘에 적용된 계수의 변형 없이 구현되었기 때문에 윤곽선 검출 알고리즘에 적용했을 때 검출 데이터의 열화 없이 구현될 수 있다. 제안된 이미지 필터 하드웨어 구조는 기존 구조와 비교했을 때 곱셈기의 수를 50% 절감할 수 있음을 확인했다.

Keywords

References

  1. A. Alaghi, C. Li and J. P. Hayes, "Stochastic circuits for real-time image processing applications", in Proc. ACM/EDAC/ IEEE Design Automation Conference (DAC) , pp. 136:1-6, Jun. 2013.
  2. S. Na, W. Lee, and K. Yoo, "Edge-based fast mode decision algorithm for intra prediction in HEVC," in Proc. IEEE Int. Conf. Consum. Electron. (ICCE) , Jan. 2014, pp. 11-14.
  3. Y. Lee, S. Chen, J. Hwang, and Y. Hung, "An Ensemble of Invariant Features for Person Reidentification," IEEE Transaction on Circuits and Systems for Video Technology, vol. 27, no. 3, pp. 470-483, Mar. 2017. https://doi.org/10.1109/TCSVT.2016.2637818
  4. K. Pauwels, L. Rubio, and E. Ros, "Real-Time Pose Detection and Tracking of Hundreds of Objects," IEEE Transaction on Circuits and Systems for Video Technology, vol. 26, no. 12, pp. 2200-2214, Dec. 2016. https://doi.org/10.1109/TCSVT.2015.2430652
  5. M. Nixon and A. Aguado, "Low-level feature extraction", in Feature Extraction & Image Processing for Computer Vision, 3rd ed., Academic Press, Sep. 2012.
  6. R. Deriche, "Using Canny's criteria to derive a recursively implemented optimal edge detector", Int. J . Comput. Vision, vol. 1, no. 2, pp. 167-187, Jun. 1987. https://doi.org/10.1007/BF00123164
  7. Q. Xu, S. Varadarajan, C. Chakrabarti, and L. J. Karam, "A Distributed Canny Edge Detector: Algorithm and FPGA Implementation", IEEE Transaction on Image Processing, vol. 23, no. 7, pp. 2944-2960, Jul. 2014. https://doi.org/10.1109/TIP.2014.2311656
  8. Keshab K. Parhi, "VLSI Digital Signal Processing Systems: Design and Implementation", John Wiley, Indian Reprint, 2007.

Cited by

  1. A performance optimization strategy based on degree of parallelism and allocation fitness vol.2018, pp.1, 2018, https://doi.org/10.1186/s13638-018-1254-7