Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Method of Human Detection using Edge Symmetry and Feature Vector

에지 대칭과 특징 벡터를 이용한 사람 검출 방법

  • 변오성 (현대모비스 기술연구소)
  • Received : 2011.07.06
  • Accepted : 2011.07.25
  • Published : 2011.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, it is proposed for algorithm to detect human efficiently using a edge symmetry and gradient directional characteristics in realtime by the feature extraction in a single input image. Proposed algorithm is composed of three stages, preprocessing, region partition of human candidates, verification of candidate regions. Here, preprocessing stage is strong the image regardless of the intensity and brightness of surrounding environment, also detects a contour with characteristics of human as considering the shape features size and the condition of human for characteristic of human. And stage for region partition of human candidates has separated the region with edge symmetry for human and size in the detected contour, also divided 1st candidates region with applying the adaboost algorithm. Finally, the candidate region verification stage makes excellent the performance for the false detection by verifying the candidate region using feature vector of a gradient for divided local area and classifier. The results of the simulations, which is applying the proposed algorithm, the processing speed of the proposed algorithms is improved approximately 1.7 times, also, the FNR(False Negative Rate) is confirmed to be better 3% than the conventional algorithm which is a single structure algorithm.

본 논문에서는 단일 입력 영상에서 특징을 추출하여 실시간으로 에지 대칭과 기울기의 방향성 특징을 이용하여 효과적으로 사람을 검출하는 알고리즘을 제안한다. 제안된 알고리즘은 전처리, 사람 후보 영역 분할, 후보 영역 검증인 3단계로 구성되었다. 여기서 전처리 단계는 주변 조도 환경과 밝기에 강인하고, 사람의 특징인 모양 특징 크기, 사람의 조건을 고려한 사람의 특성을 가진 윤곽선을 검출한다. 그리고 사람 후보 영역 분할 단계는 검출된 윤곽선에서 사람의 에지 대칭성과 크기를 가지고 영역을 분리하고, 에이타부스트 알고리즘을 적용하여 1차 후보 영역을 분할한다. 마지막으로 후보 영역 검증 단계는 분할된 국소 영역에 대한 기울기의 특징 벡터 및 분류기를 이용하여 후보 영역을 검증하여 오검출의 성능을 우수하게 한다. 제안된 알고리즘을 적용하여 모의실험을 한 결과, 제안된 알고리즘은 단일 알고리즘을 적용한 기존 알고리즘 보다 처리 속도가 약 1.7배 정도 개선되었으며, FNR(False Negative Rate)은 3% 정도 우수함을 확인하였다.

Keywords

References

  1. W. H. Lee, H. J. Yoo, H. S. Kim and Y. B. Jang, "Detection Nighttime Pedestrians for PDS Using Camera in Visible Spectrum," Journal of KAIS, Vol. 10, No. 9, pp. 2280-2289, July, 2009.
  2. C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. V. Seelen, "Walking Pedestrian Recognition," IEEE Trans. on Intelligent Transportation Systems, Vol. 1, No. 3, pp. 155-163, Sept. 2000. https://doi.org/10.1109/6979.892152
  3. M. Gavrila and S. Munder, "Multi-cue Pedestrian Detection and Tracking fromaMoving Vehicle" International Journal of Computer Vision, Vol. 73, No. 1, pp. 41-59, June, 2007. https://doi.org/10.1007/s11263-006-9038-7
  4. 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, June, 2004.
  5. H. Elzein, S. Lakshmanan, and P. Watta, "Amotion and shape based pedestrian detection algorithm," Proc. of IEEE Intelligent Vehicle Symposium, pp. 500‐504, June, 2003.
  6. F. Xu, L. Xia and K. Fujimura, "Pedestrian detection and tracking with night vision," IEEE Trans. on Intelligent Transportation Systems, Vol. 6, No. 1, pp. 63‐71, Mar. 2005. https://doi.org/10.1109/TITS.2004.838222
  7. U. Franke, D. Gavrila, S. Gorzig, F. Lindner, F. Puet zold, and C. Wohler, "Autonomous driving goes downtown," IEEE Intelligent Systems and their Applications, Vol. 13, No. 6, pp. 40-48, Nov/Dec. 1998. https://doi.org/10.1109/5254.736001
  8. G. Ma, A. Kummert, S. B. Park, S. M. Schneiders, and A. Loffe, "A Symmetry Search and Filtering Algorithm for Vision Based Pedestrian Detection System," SAE TECHNICAL PAPER SERIES 2008-01-1252, 2008 World Congress, April, 2008.
  9. Q. M. Tian, Y. P. Luo and D. C. Hu, "Pedestrian dete ction in nighttime driving," Pro. of the Third International Conference on Image and Graphics, pp. 116-119, Dec. 2004.
  10. M. Enzweiler and D. M. Gavrila, "Monocular Pedest rian Detection: Survey and Experiments," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 12, pp. 2179-2195, Dec. 2009. https://doi.org/10.1109/TPAMI.2008.260
  11. T. Tsuji, H. Hattori, M. Watanabe, and N. Naga oka, "Development of night-vision system," IEEE Transactions on Intelligent Transportation Systems, Vol. 3, No. 3, pp. 203 ‐209, Sept. 2002. https://doi.org/10.1109/TITS.2002.802927
  12. H. Nanda and L. Davis. "Probabilistic template bas ed pedestrian detection in infrared videos," IEEE Intelligent Vehicle Symposium, Vol. 1, pp. 15‐20, June, 2002.
  13. M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, "Pedestrian detection using wavelet templates," Proc. of IEEE computer Society Conference on Computer Vision and Pattern Recognition, pp. 193-199, June, 1997.
  14. C. Papageorgiou and T. Poggio, "A trainable system for object detection," International Journal of Computer Vision, Vol. 38, No. 1, pp. 15-33, June, 2000. https://doi.org/10.1023/A:1008162616689
  15. L. Zhao and C. Thorpe, "Stereo and neural netwo rk-based pedestrian detection," IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems, pp. 298‐303, Oct. 1999.
  16. P. Viola, M. J. Jones and D. Snow, "Detecting pede strians using patterns of motion and appearance," Proc. Ninth IEEE International Conference on Computer Vision, Vol. 2, pp. 734-741, Oct. 2003.
  17. N. Dalal and B. Triggs, "Histograms of oriented gra dients for human detection," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 886-893, June, 2005.
  18. S. Paisitkriangkrai, C. Shen and J. Zhang, "Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features," IEEE Trans. on Circuits and Systems for Video Technology, Vol. 18, No. 8, pp. 1140-1151, Aug. 2008. https://doi.org/10.1109/TCSVT.2008.928213
  19. Y. H. Lee, J. Y. Ko, J. H. Suk, T. M. Roh, and J. C. Shim, "Pedestrian Recognition using Adaboost Algorithmbased on Cascade Method by Curvature and HOG," Journal of KIISE, Vol. 16, No. 6, pp. 654-662, June, 2010.
  20. Y. H. Hong, Y. J. Han and H. S. Hahn, "A Face Detection Method Based on Adaboost Algorithm using New Free Rectangle Feature," Journal of KSCI, Vol. 15, No. 2, pp. 55-64, Feb. 2010. https://doi.org/10.9708/jksci.2010.15.2.055
  21. H. G. Kim and G. B. Hung, "Real-time Face Detect ion Systemusing YCbCr Information and AdaBoost Algorithm," Journal of KSCI, Vol. 13, No. 5, pp. 19-26, Sept. 2008.
  22. http://cbcl.mit.edu/software-datasets/Pedestrian Data. html
  23. http://pascal.inrialpes.fr/data/human
  24. M. A. Sotelo, I. Parra, D. Fernandez, E. Naranjo, "Pedestrian Detection using SVM and Multi-feature Combination," In Proc. of the 2006. ITSC '06, IEEE Intelligence Trans., pp. 103-108, Sept. 2006.