융합신호처리학회논문지 (Journal of the Institute of Convergence Signal Processing)

한국융합신호처리학회 (The Korea Institute of Convergence Signal Processing)
권호 표지

이동 카메라 영상에서 움직임 정보와 Support Vector Machine을 이용한 다수 보행자 검출

Multiple Pedestrians Detection using Motion Information and Support Vector Machine from a Moving Camera Image

  • 투고 : 2011.07.30
  • 심사 : 2011.11.01
  • 발행 : 2011.10.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 이동 카메라 영상에서 움직임 정보와 SVM(Support Vector Machine)을 이용하여 다수의 보행자를 검출하는 방법을 제안하였다. 먼저 연속된 영상의 특징점을 이용하여 카메라 자체의 움직임 보상용 한 후 차 영상과 프로젝션 히스토그램을 통해 움직이는 보행자를 검출한다. 차 영상을 이용한 보행자 검출은 간단한 방법이지만 움직임이 없는 보행자는 검출하지 못하는 단점이 있다. 따라서 이러한 단점을 보완하기 위하여 SVM을 이용하여 움직이지 않는 보행자를 검출하였다. SVM은 보행자 검출과 같은 이진 분류 문제에 우수한 성능을 보이는 것으로 알려져 있다. 하지만 영상 내에 보행자가 서로 인접해 있거나 팔과 다리를 과도하게 움직이는 경우 검출하지 못하는 단점이 있다. 그러므로 본 논문에서는 움직임 정보와 SVM을 이용하여 움직임이 없는 보행자와 보행자가 서로 인접해 있거나 과도한 동작을 취하는 경우에도 강건하게 검출할 수 있는 방법을 제안하였다. 본 논문에서 제안된 방법의 성능을 평가하기 위하여 다양한 실세계 영상을 이용하여 수행하였으며, 그 결과 평균 검출률이 94%, FP(False Positive)가 2.8%로 제안된 방법의 우수성을 입증하였다.

In this paper, we proposed the method detecting multiple pedestrians using motion information and SVM(Support Vector Machine) from a moving camera image. First, we detect moving pedestrians from both the difference image and the projection histogram which is compensated for the camera ego-motion using corresponding feature sets. The difference image is simple method but it is not detected motionless pedestrians. Thus, to fix up this problem, we detect motionless pedestrians using SVM The SVM works well particularly in binary classification problem such as pedestrian detection. However, it is not detected in case that the pedestrians are adjacent or they move arms and legs excessively in the image. Therefore, in this paper, we proposed the method detecting motionless and adjacent pedestrians as well as people who take excessive action in the image using motion information and SVM The experimental results on our various test video sequences demonstrated the high efficiency of our approach as it had shown an average detection ratio of 94% and False Positive of 2.8%.

키워드

참고문헌

  1. L. Zhao and C. E. Thorpe, "Stereo- and neural network-based pedestrian detection," IEEE Trans. Intelligent Trans. Systems, Vol. 1, No. 3, pp. 148-154, 2000. https://doi.org/10.1109/6979.892151
  2. T. Darrell, G. Gordon, M. Harville, and J. Woodfill, "Integrated person tracking using stereo, color, and pattern detection," Proc. of the Conference on Computer Vision and Pattern Recognition, pp. 601-609, 1998.
  3. B. Leibe, E. Seemann, and B. Schiele, Pedestrian detection in crowded scenes," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 878-885, 2005.
  4. A. Censi, A. Fusiello, and V. Roberto, "Image stabilization by features tracking," Proc. of the International Conference on Image Analysis and Processing, pp. 665-667, 1999.
  5. S. Srinivasan and R. Chellappa, "Image stabilization and mosaicking using the overlapped basis optical flow field," Proc. of IEEE International Conference on Image Processing, pp. 420-425, 1997.
  6. M. Irani, B. Rousso, and S. Peleg, "Recovery of ego-motion using image stabilization," Proc. of the IEEE Computer Vision and Pattern Recognition, pp. 454-460, 1994.
  7. H. Inoue, T. Tachikawa, and M. Inaba, "Robot Vision System with a Correlation Chip for Real-time Tracking, Optical flow and Depth Map Generation," Proc. of the IEEE International Conference on Robotics and Automation, pp. 1621-1626, 1992.
  8. S. Yamamoto, Y. Mae, and Y. Shirai, "Real-time Multiple Object Tracking based on Optical Flows," Proc. of the Robotics and Automation, Vol. 3, pp. 2328-2333, 1995.
  9. A. Broggi, M. Bertozzi, and A. Fascioli, "Shape-based Pedestrian Detection," Proc. of the IEEE Intelligent Vehicles Symposium 2000, pp. 215-220, 2000.
  10. A. Mohan, C. Papageorgiou, and T. Poggio, "Example-based object detection in images by components," IEEE Trans. Pattern Anal. Mach Intell. Vol. 23, No. 4, pp. 156-177, 2001.
  11. P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," Proc. of IEEE International Conference on Computer Vision, pp. 734-741, 2003.
  12. H. Mori, N. M. Charkari, and T. Matsushita, "On-Line Vehicle and Pedestrian Detection based on Sign Pattern," IEEE Trans. on Industrial Electronics, Vol. 41, No. 4, pp. 384-391, 1994 . https://doi.org/10.1109/41.303788
  13. S. A. Niyogi and E. H. Adelson, "Analyzing and Recognizing Walking Figures in xyt," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 469-474, 1994.
  14. M. Yachida, M. Asada, and S. Tsuji, "Automatic Analysis of Moving Image," IEEE Trans. Pattern Anal. Mach. Intell, Vol. 3, No. 1, pp. 12-20, 1981.
  15. J. S. Lim and W. H. Kim, "Detection and tracking multiple pedestrians from a moving camera," Proc. of the 1st International Symposium on Visual Computing, pp. 527-534, 2005.
  16. C. Papageorgiou and T. Poggio, "A trainable system for object detection," Int. Journal of Computer Vision, Vol. 38, No. 1, pp. 15-33, 2000. https://doi.org/10.1023/A:1008162616689
  17. S. Paisitkriangkrai, C. Shen, and J. Zhang, "Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features," IEEE Trans. Circuit and System for Video Technology, Vol. 18, No. 8, pp. 1140-1151, 2008.
  18. N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, 2000.
  19. B. Wu and R. Nevatia, "Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors," Int. Journal of Computer Vision, Vol 75, No. 2, pp. 247-266, 2007. https://doi.org/10.1007/s11263-006-0027-7
  20. C. Harris and M. J. Stephens, "A combined corner and edge detector," Proc. of the 4th Alvey Vision Conference, pp. 147-152, 1998.
  21. J. Shi and C. Tomasi, "Good features to track," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 593-600, 1994.
  22. N. Dalal and B. Triggs "Histograms of Oriented Gradients for Human Detection," Int. Conference on Computer Vision and Pattern Recognition, pp. 886-893, 2005.