Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

High-Performance Vision Engine for Intelligent Vehicles

지능형 자동차용 고성능 영상인식 엔진

  • Lyuh, Chun-Gi (Electronics and Telecommunications Research Institute, Mixed Signal Processing Research Section) ;
  • Chun, Ik-Jae (Electronics and Telecommunications Research Institute, Mixed Signal Processing Research Section) ;
  • Suk, Jung-Hee (Electronics and Telecommunications Research Institute, Mixed Signal Processing Research Section) ;
  • Roh, Tae Moon (Electronics and Telecommunications Research Institute, Mixed Signal Processing Research Section)
  • 여준기 (한국전자통신연구원 혼성신호처리연구실) ;
  • 천익재 (한국전자통신연구원 혼성신호처리연구실) ;
  • 석정희 (한국전자통신연구원 혼성신호처리연구실) ;
  • 노태문 (한국전자통신연구원 혼성신호처리연구실)
  • Received : 2013.05.13
  • Accepted : 2013.07.12
  • Published : 2013.07.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

본 논문에서는 고속 및 고인식률의 성능을 갖는 영상인식 엔진 구조를 제안한다. 본 엔진은 2단계의 특징점 추출 및 분류 알고리즘을 수행하여 자동차와 보행자를 인식할 수 있다. 엔진의 인식률을 높이기 위해 HOG 특징점 값과 LBP 특징점 값을 같이 사용하여 알고리즘을 구성하였으며, 처리 속도를 높이기 위해 병렬 구조를 개선하여 하드웨어를 설계하였다. 실험결과를 통해 설계한 엔진이 초당 90프레임의 인식 처리가 가능하며 FPPW $10^{-4}$ 하에서 97.7%의 보행자 인식률을 가짐을 보인다.

Keywords

References

  1. X. Wang, T.X. han, and S. Yan, "An HOG-LBP human detector with partial occlusion handling," International Conference on Computer Vision, 32-39, 2009.
  2. G. Gan and J. Cheng, "Pedestrian Detection Based on HOG-LBP Feature," International Conference on Computational Intelligence and Security, 1184-1187, 2011.
  3. C. Zeng, H. Ma, and A. Ming, "Fast human detection using mi-SVM and a cascade of HOG-LBP features," IEEE International Conference on Image Processing, 3845-3848, 2009.
  4. S.-H. Yoon, C.-G. Lyuh, I.-J. Chun, J.-H. Suk, and T. M. Roh, "A New Support Vector Compression Method Based on Singular Value Decomposition", ETRI Journal, vol. 33, no. 4, 652-655, Aug, 2011. https://doi.org/10.4218/etrij.11.0210.0349
  5. W.-J. Park, D.-H. Kim, S. Suryanto, C.-G. Lyuh, T. M. Roh, and S.-J. Ko, "Fast human detection using selective block-based HOG-LBP," IEEE International Conference on Image Processing, 601-604, 2012.
  6. H. Cho, P.E. Rybski, A. Bar-Hillel, and W. Zhang, "Real-time pedestrian detection with deformable part models," IEEE Intelligent Vehicles Symposium, 1035-1042, 2012.
  7. S. Lee, H. Son, J. C. Choi, and K. Min, "HOG feature extractor circuit for real-time human and vehicle detection," IEEE Region 10 Conference, 2012.
  8. S. Kim, S. Park, S. Lee, S. park, and K. Cho, "Design of high-performance pedestrian and vehicle detection circuit using Haar-like features," IEEE Region 10 Conference, 2012.
  9. http://www.mobileye.com
  10. http://www.nec.com
  11. C.-G. Lyuh, I.-J. Chun, J.-H. Suk, S.-H. Yoon, and T. M. Roh, "High-Speed Vision Engine for Intelligent Vehicles," Workshop on Image Prodessing and Image Understanding, 2012.
  12. P. Viola and M. J. Jones, "Robust Real-Time Face Detection,", International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, 2004. https://doi.org/10.1023/B:VISI.0000013087.49260.fb
  13. N. Dalal, "Finding People in Images and Videos," PhD thesis, Institut National Polytechnique de Grenoble, 2006.
  14. N. Dalal and B. Triggs, "Histogram of oriented gradient for human detection," IEEE Computer Vision and Pattern Recognition, 886-893, 2005.