Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Mobile Advanced Driver Assistance System using OpenCL : Pedestrian Detection

OpenCL을 이용한 모바일 ADAS : 보행자 검출

  • Kim, Jong-Hee (School of Information and Communication Engineering, Inha University) ;
  • Lee, Chung-Su (School of Information and Communication Engineering, Inha University) ;
  • Kim, Hakil (School of Information and Communication Engineering, Inha University)
  • 김종희 (인하대학교 정보통신공학부) ;
  • 이충수 (인하대학교 정보통신공학부) ;
  • 김학일 (인하대학교 정보통신공학부)
  • Received : 2014.08.20
  • Accepted : 2014.10.06
  • Published : 2014.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a mobile-optimized pedestrian detection method using Cascade of HOG(Histograms of Oriented Gradients) for ADAS(Advanced Driver Assistance System) on smartphones. In order to use the limited resource of mobile platforms efficiently, the method is implemented by the OpenCL(Open Computing Language) library, and its processing time is reduced in the following two aspects. Firstly, the method sets a program build option specifically and adjusts work group sizes as variety of kernels in the host code. Secondly, it utilizes local memory and a LUT(Look-Up Table) in the kernel code to accelerate the program. For performance evaluation, the developed algorithm is compared with the mobile CPU-based OpenCV(Open Computer Vision) for Android function. The experimental results show that the processing speed is 25% faster than the OpenCV hogcascade.

본 논문에서는 상용 스마트폰에서의 첨단운전자보조시스템(ADAS)을 위해 모바일 플랫폼에 최적화된 cascade 방식의 HOG 특징을 이용한 보행자 검출 방법을 제안한다. 제한된 모바일 플랫폼 자원을 효율적으로 사용하기 위해 OpenCL 병렬처리 라이브러리를 이용하였고 크게 두 가지 방법으로 수행속도를 향상시켰다. 첫째, 호스트 코드에서 OpenCL 프로그램 빌드 옵션을 특정하고 작업 그룹 크기를 조절하였다. 둘째, 커널 코드에서 지역 메모리와 LUT 등을 사용하여 가속화하였다. 성능 평가를 위하여 널리 알려진 영상처리 라이브러리인 OpenCV for Android 함수의 모바일 CPU 수행 결과와 비교하였으며 실험 결과, OpenCV의 hogcascade 함수보다 25% 향상된 처리속도를 보였다.

Keywords

References

  1. International Data Corporation, http://www.idc.com/getdoc.jsp?containerId=prUS23982813
  2. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," Proc. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 886-893, San Diego, United States; 2005/6.
  3. P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, I-511-I-518, vol.1, Kauai, United States; 2001/12
  4. C. Cortes and V. Vapnik, "Support-vector networks," Mach Learn, vol. 20, no. 3, pp. 273-297, 1995.
  5. Y. Freund and R. E. Schapire, "A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting," J Comput Syst Sci, vol. 55, no. 1, pp. 119-139, 1997. https://doi.org/10.1006/jcss.1997.1504
  6. P. Geismann and G. Schneider, "A two-staged approach to vision-based pedestrian recognition using Haar and HOG features," Proc. Intelligent Vehicles Symposium, IEEE 554-559, Eindhoven, Netherlands; 2008/6.
  7. Q. Zhu, S. Avidan, M. C. Yeh, and K. T. Cheng, "Fast human detection using a cascade of histograms of oriented gradients," Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1491-1498, New York, United States; 2006/6.
  8. S. Kim, D. G. Yoo, and Y. H. Kim, "High Performance Pedestrian Detection System Using A Cascade Algorithm Structure," Proc. IEEK Conference on System-on-Chip, 91-94; 2011/4.
  9. J. Lee, S. H. Kang, M. H. Lee, S. Li, H. Kim, and I. K. Park, "Real-Time Parallel Image Processing Library using Mobile GPU," Journal of KIISE : Computing Practices and Letters, vol. 20, no. 2, pp. 96-100; 2014/2.
  10. H. Jia, Y. Zhang, W. Wang, and J. Xu, "Accelerating Viola-Jones facce detection algorithm on GPUs," Proc. the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012-9th IEEE International Conference on Embedded Software and Systems, ICESS-2012 396-403, Liverpool, United Kingdom; 2012/6.
  11. I. K. Park, M. H. Lee, and Y. K. Choi, "Technical Development Trend of Computer Vision on Embedded Platform," The Magazine of the IEEK, vol. 39, no. 2, pp. 85-92; 2012/2.