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

  • 제50권10호
  • /
  • Pages.162-170
  • /
  • 2013
  • /
  • 2287-5026(pISSN)
  • /
  • 2288-159X(eISSN)
대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지
DOI QR코드

DOI QR Code

PCA 복원과 HOG 특징 기술자 기반의 효율적인 보행자 인식 방법

An Efficient Pedestrian Recognition Method based on PCA Reconstruction and HOG Feature Descriptor

  • 투고 : 2013.06.18
  • 발행 : 2013.10.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 보행자의 교통안전 개선을 위한 목적으로 차량에 장착되는 보행자 보호 시스템(PPS, Pedestrian Protection System)에 대한 관심과 요구가 증가하고 있다. 본 연구에서는 보행자 검출 후보 윈도우 추출과 셀(cell) 단위 히스토그램 기반의 HOG 특징 계산 방법을 제안하였다. 보행자 검출 후보 윈도우 추출은 주변밝기 비율체크, 수직방향 에지투영, 에지펙터(edge factor), 그리고 PCA(Principal Component Analysis) 복원 영상을 이용하였다. Dalal 의 HOG 는 겹침 블록 상의 모든 픽셀에 대해 가우시안 가중치와 삼선형보간에 의한 히스토그램 계산이 필요한데 반하여 제안하는 방법은 단위 셀마다 가우시안 가중 및 히스토그램을 계산하고 그것들을 인접 셀과 결합하므로 연산 속도가 빠르다. 제안하는 PCA 복원 에러 기반의 보행자 검출 후보 윈도우 추출은 보행자의 머리와 어깨 영역과의 차이를 기준으로 배경을 효율적으로 분류한다. 제안하는 방법은 카메라 컬리브레이션이나 스테레오 카메라를 이용한 거리 정보 없이도 영상만으로 전통적인 HOG 에 비하여 연산속도가 크게 개선된다.

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

키워드

참고문헌

  1. D. Gavrila, J. Giebel, and S. Munder, "Vision-Based Pedestrian Detection: The PROTECTOR System", IEEE Intelligent Vehicles Symposium, pp. 13-18, 2004.
  2. P. Viola, M. Jones, and D. Snow, "Detecting Pedestrians Using Patterns of Motion and Appearance", IEEE International Conference on Computer Vision, pp. 153-161, 2005.
  3. G. Monteiro, P. Peixoto, and U. Nunes, "Vision-based pedestrian detection using Haar-like features", Robotica, pp. 16-20, 2006.
  4. P. Dollar and Z. Tu, P. Perona, S. Belongie, "Integral channel features", British Machine Vision Conference, pp. 1-11, 2009.
  5. Dalal, N and Triggs, B, "Histograms of oriented gradients for human detection". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 886-893, 2005.
  6. P. Dollar and S. Belongie, P. Perona, "The Fastest Pedestrian Detector in the West", British Machine Vision Conference, 2010.
  7. R. Benenson and M. Mathias, R. Timofte, L. Van Gool, "Pedestrian detection at 100 frames per second". Computer Vision and Pattern Recognition (CVPR), pp. 2903-2910, 2012.
  8. G. Xu, X. Wu, L. Liu, and Z. Wu, "Real-time Pedestrian Detection Based on Edge Factor and Histogram of Oriented Gradient", International Conference on Information and Automation (ICIA), pp. 384-389, 2011.
  9. W. Xing, Y. Zhao, R. Cheng, J. Xu, S. Lv, X. Wang, "Fast Pedestrian Detection Based on Haar Pre-Detection", International Journal of Computer and Communication Engineering, Vol. 1, pp. 207-209, 2012.
  10. A. Broggi, M. Bertozzi, A. Fascioli, and M. Sechi, "Shape-based Pedestrian Detection", IEEE Intelligent Vehicles Symposium 2000, pp. 215-220, 2000.
  11. T. Kancharla, P. Kharade, S. Gindi, K. Kutty, and V. Vaidya, "Edge based Segmentation for Pedestrian Detection using NIR Camera", 2011 International Conference on Image Information Processing, pp. 1-6, 2011.
  12. A. Mazoul, K. Zebbara, and M. Ansari, " Street crossing pedestrian detection based on edge curves motion", International Journal of Computer Applications, vol. 41, pp. 570-575, 2007.
  13. H. Kataoka, Y. Aoki, "Symmetrical Judgment and Improvement of CoHOG Feature Descriptor for Pedestrian Detection", MVA2011, pp. 13-15, 2011.
  14. Sang-Hun Kim, Dong-Gon Yoo, and Young- Hwan Kim, "High Performance Pedestrian Detection System Using A Cascade Algorithm Structure", IEEK SoC Conference, pp. 91-94, 2011.
  15. A. Cosma, R. Brehar, and S. Nedevschi, "Part-based pedestrian detection using HoG features and vertical symmetry", Intelligent Computer Communication and Processing (ICCP), pp. 229-236, 2012.
  16. G. Lie, W. Rongben, J. Lisheng, and Z. Mingheng, "STUDY ON PEDESTRIAN DETECTION AHEAD OF VEHICLE BASED ON MACHINE VISION", International Conference on Transportation Engineering ASCE, pp. 570-575, 2007.
  17. G. Lie, W. Rongben, J. Lisheng, L. Linhui, and Y. Lu, "Algorithm Study for Pedestrian Detection Based on Monocular Vision", Vehicular Electronics and Safety, pp. 83-87, 2006.
  18. D. Cheda, D. Ponsa, and M. Lopez, "Pedestrian candidates generation using monocular cues", Intelligent Vehicles Symposium(IV), pp. 7-12, 2012.
  19. Y. Fang, K. Yamada, Y. Ninomiya, K. Horn, and I. Masaki, "A Shape-independent method for pedestrian detection with far-infrared images", Vehicular Technology, pp. 1679-1697, 2004.
  20. Guilherme V. Carvalho, Lailson B. Moraes, "A weighted image reconstruction based on PCA for pedestrian Detection", Neural Networks (IJCNN), The 2011 International Joint Conference on, pp. 2005-2011, 2011.
  21. INRIA Person Dataset, http://pascal.inrialpes.fr/data/human/
  22. SVMlight, http://svmlight.joachims.org/
  23. CAVIAR Test Case Scenarios, http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/