Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Using Optical Flow and HoG for Nighttime PDS

야간 PDS를 위한 광학 흐름과 기울기 방향 히스토그램 이용 방법

  • 조휘택 (전남대학교 문화사회과학대학원) ;
  • 유현중 (상명대학교 정보통신공학과) ;
  • 김형석 (전북대학교 전기전자컴퓨터학부) ;
  • 황젱넹 (워싱턴대학교 전기및컴퓨터공학과)
  • Published : 2009.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

The death rate of pedestrian in car accidents in Korea is 2.5 times higher than the average of OECD countries'. If a system that can detect pedestrians and send alarm to drivers is built and reduces the rate, it is worth developing such a pedestrian detection system (PDS). Since the accident rate in which pedestrians are involved is higher at nighttime than in daytime, the adoption of nighttime PDS is being standardized by big auto companies. However, they are usually using night visions or multiple sensors, which are usually expensive. In this paper we suggest a method for nighttime PDS using single wide dynamic range (WDR) monochrome camera in visible spectrum band. In our experiments, pedestrians were accurately detected if only most edges of pedestrians could be obtained.

자동차 주요 생산국인 우리나라 보행자의 교통사고 사망률은 인구 10만 명 당 5.28명으로서 OECD 평균의 약 2.5배에 달한다. 보행자를 감지하고 운전자에게 경보를 보내주는 시스템이 개발되어 보행자 교통사고를 조금이라도 줄일 수 있다면, 그 자체만으로도 보행자 감지 시스템의 가치는 충분하기 때문에 PDS에 대한 관심이 높아지고 있다. 보행자 교통사고율은 야간에 더 높기 때문에, 야간 보행자 감지 시스템에 주요 자동차 회사들이 관심을 두고 있으나, 그들은 일반적으로 고가의 나이트비젼 또는 복합적 센서를 사용하는 장비를 채택하고 있다. 본 논문에서는 PDS에서 나이트비젼 대신에, 넓은 동적 범위를 갖는 가시 스펙트럼 대역 흑백 카메라 한 대만을 사용하는 야간 보행자 감지 기법을 제안한다. 서로 다른 환경에서 촬영된 야간 동영상들에 대해 실험한 결과, 제안 알고리듬이 에지가 어느 정도 정확하게 검출되는 상황이라면 정확한 보행자 검출 성능을 보였다.

Keywords

References

  1. NHTSA, Traffic safety facts 2003: Pedestrians, Technical report, 2003.
  2. M. Bertozzi, A. Broggi, M. Felisa, G. Vezzoni and M. Del Rose, "Low‐level Pedestrian Detection by means of Visible and Far Infrared Tetra‐vision," Proc. of IEEE Intelligent Vehicles Symposium, Tokyo, Japan, pp. 231-236, 2006. https://doi.org/10.1109/IVS.2006.1689633
  3. D. Gavrila, "Sensor‐based pedestrian protection," IEEE Intelligent Systems, vol. 16:6, pp. 77–81, 2001. https://doi.org/10.1109/5254.972097
  4. M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, "Pedestrian detection using wavelet templates," Proc. of the Conf. on Computer Vision and Pattern Recognition, pp. 193-199, 1997. https://doi.org/10.1109/CVPR.1997.609319
  5. C. Papageorgiou, Evgeniou X, and T. Poggio, "A trainable pedestrian detection system," IEEE Intelligent Vehicles Symposium, pp. 241-246, 1998.
  6. C. Papageorgiou and T. Poggio, "Trainable pedestrian detection," IEEE Int'l Conf. on Image Processing, vol. 4, pp. 35-39, 1999. https://doi.org/10.1109/ICIP.1999.819462
  7. C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, C. Bruckhoff, T. Bergener, and W. von Seelen, "Walking pedestrian detection and classification," Proc. of the DAGM‐Symposium Mustererkennung, pp. 78-85, 1999.
  8. L. Zhao and C. Thorpe, "Stereo‐ and Neural Network ‐Based Pedestrian Detection," IEEE Trans. Intelligent Transportation Systems, vol. 1, pp. 148‐154, 2000. https://doi.org/10.1109/6979.892151
  9. D. Gavrila and S. Munder, "Multi‐cue Pedestrian Detection and Tracking from a Moving Vehicle", International Journal of Computer Vision, vol. 73, pp. 41–59, 2007. https://doi.org/10.1007/s11263-006-9038-7
  10. G. Grubb, 3D Vision Sensing for Improved Pedestrian Safety, Master's thesis, Australian National University, 2004.
  11. P. Lombardi, Survey on Pedestrian Detection for Autonomous Driving Systems, Technical report, University of Pavia, 2001.
  12. G. Ma, A. Kummert, S.‐B. Park, S. Muller‐ Schneiders, and A. Loffe, A Symmetry Search and Filtering Algorithm for Vision Based Pedestrian Detection System, SAE TECHNICAL PAPER SERIES 2008‐01‐1252, 2008.
  13. Q. Tian, Y. Luo, and D. Hu, "Pedestrian detection in nighttime driving," Proceedings of the Third International Conference on Image and Graphics, 2004.
  14. G. Grubb, A. Zelinsky, L. Nilsson, and M. Rilbe, "3D vision sensing for improved pedestrian safety," Proc. of IEEE Intelligent Vehicles Symposium, pp. 19-24, 2004. https://doi.org/10.1109/IVS.2004.1336349
  15. H. Elzein, S. Laksmanan, and P. Watta, "A motion and shape‐based pedestrian detection algorithm," IEEE Intelligent Vehicle Symposium, pp. 500‐504, 2003. https://doi.org/10.1109/IVS.2003.1212962
  16. F. Xu, X. Liu, and K. Fujimura, "Pedestrian detection and tracking with night vision," IEEE Intelligent Transportaion Systems, vol. 6, pp. 63‐71, 2005. https://doi.org/10.1109/TITS.2004.838222
  17. Y. Franke, D. Gavrila, S. Gorzig, F. Lindner, F. Paetzold, and C. Wohler, "Autonomous driving goes downtown," IEEE Intelligent Systems, vol. 13, pp. 40-48, 1998. https://doi.org/10.1109/5254.736001
  18. D. Gavrila, "Detection from a moving vehicle," European Conference on Computer Vision (ECCV), vol. 2, pp. 37-49, 2000.
  19. T. Tsuji, H. Hattori, M. Watanabe, and N. Nagaoka, "Development of nightvision system," IEEE Transactions on Intelligent Transportation Systems, vol. 3:3, pp. 203‐209, 2002. https://doi.org/10.1109/TITS.2002.802927
  20. H. Nanda and L. Davis. "Probabilistic template based pedestrian detection in infrared videos," IEEE Intelligent Vehicle Symposium, vol. 1, pp. 15-20. https://doi.org/10.1109/IVS.2002.1187921
  21. D. Gavrila and V. Philomen, "Real‐time object detection for smart vehicles," CVPR, Fort Collins, Colorado, USA, pp. 87-93, 1999.
  22. D. Gavrila, J. Giebel, and S. Munder, "Vision‐based pedestrian detection: the protector+ system," Proc. Of the IEEE Intelligent Vehicles Symposium, Parma, Italy, 2004.
  23. N. Dalal, and B. Triggs, "Histograms of oriented gradients for human detection," International Conference on Computer Vision and Pattern Recognition, June 2005.
  24. P. Viola and M. Jones, "Robust Real‐time Object Detection," 2nd International Workshop on Statistical and computational theories of vision‐modeling, learning, computing and sampling, Vancouver, Canada, July 13, 2001.