DOI QR코드

DOI QR Code

Pedestrian Traffic Counting Using HoG Feature-Based Person Detection and Multi-Level Match Tracking

HoG 특징 기반 사람 탐지와 멀티레벨 매칭 추적을 이용한 보행자 통행량 측정 알고리즘

  • Received : 2016.01.14
  • Accepted : 2016.04.18
  • Published : 2016.08.31

Abstract

Market analysis for a business plain is required for the success in the modern world. Most important part in this analysis is pedestrian traffic counting. A traditional way for this is counting it in person. However, it causes high labor costs and mistakes. This paper proposes an automatic algorithm to measure the pedestrian traffic count using images with webcam. The proposed algorithm is composed of two parts: pedestrian area detection and movement tracking. In pedestrian area detection, moving blobs are extracted and pedestrian areas are detected using HoG features and Adaboost algorithm. In movement tracking, multi-level matching and false positive removal are applied to track pedestrian areas and count the pedestrian traffic. Multi-level matching is composed of 3 steps: (1) the similarity calculation between HoG area, (2) the similarity calculation of the estimated position with Kalman filtering, and (3) the similarity calculation of moving blobs in the pedestrian area detection. False positive removal is to remove invalid pedestrian area. To analyze the performance of the proposed algorithm, a comparison is performed with the previous human area detection and tracking algorithm. The proposed algorithm achieves 83.6% accuracy in the pedestrian traffic counting, which is better than the previous algorithm over 11%.

현대 사회에서 상업적 성공을 위해서는 상권 분석이 필요하며, 상권 분석의 요소 중에서 핵심적인 부분은 통행량이다. 통행량을 측정하기 위해서 사람이 직접 측정하는 방법이 많이 사용되고 있으나 높은 인건비와 측정 실수를 유발할 가능성이 높다. 본 논문에서는 웹캠을 통해 촬영한 이미지를 이용하여 보행자의 통행량을 측정할 수 있는 알고리즘을 제안한다. 제안하는 알고리즘은 사람 영역 탐지와 움직임 추적으로 구성되어 있다. 사람 영역 탐지에서는 움직임 영역을 추출하고 HoG 특징과 Adaboost 분류기를 이용하여 사람 영역을 탐지한다. 움직임 추적에는 멀티 레벨 매칭과 거짓 양성 제거를 이용하여 추적 및 통행량을 측정한다. 멀티 레벨 매칭은 HoG 영역에 대해 유사도 계수를 구하여 판별하는 과정, 칼만 필터를 이용하여 추정한 위치의 이미지 유사도를 계산 과정, 사람 영역 탐지에서 추출한 움직임 영역을 이용해 유사도를 계산하는 3단계 과정으로 구성되어 있다. 거짓 양성 제거는 사람 영역 탐지에서 잘못된 탐지 영역을 제거한다. 제안한 알고리즘의 성능을 분석하기 위하여 기존의 사람 영역 탐지 및 추적하는 방법과 비교 실험을 수행하였다. 그 결과 제안하는 방법은 사람 통행량 측정에서 83.6% 정확도를 보였으며, 기존 알고리즘에 비하여 11% 높은 성능을 달성하였다.

Keywords

References

  1. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vol.2, pp.886-893, 2005.
  2. N. Dalal, "Finding People in Images and Videos," Institut National Polytechnique de Grenoble, 2006.
  3. Y. Freund and R. E. Schapire, "A Short Introduction to Boosting," Journal of Japanese Society for Artificial Intelligence, Vol.14, No.5, pp.771-780, 1999.
  4. P. Dollar, C. Wojek, B. Schiele, and P. Perona, "Pedestrian Detection: An Evaluation of the State of the Art," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.34, No.4, pp.743-761, 2011. https://doi.org/10.1109/TPAMI.2011.155
  5. C.-J. Seo and H.-I. Ji, "Pedestrian Detection using HOG Feature and Multi-Frame Operation," Journal of Korean Institute of Electrical Engineers (in Korean), Vol.64P, No.3, pp.193-198, 2015.
  6. S.-M. Yang and K.-H. Jo, "HOG based Pedestrian Detection and Behavior Pattern Recognition for Traffic Signal Control," Journal of Institute of Control, Robotics and Systems (in Korean), Vol.19, No.11, pp.1017-1021, 2013. https://doi.org/10.5302/J.ICROS.2013.13.1858
  7. P. Viola, M. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," International Journal of Computer Vision, Vol.63, No.2, pp.153-161, 2005. https://doi.org/10.1007/s11263-005-6644-8
  8. K.-K. Kong and K.-S. Hong, "Design of coupled strong classifiers in AdaBoost framework and its application to pedestrian detection," Pattern Recognition Letters, Vol.68, No.1, pp.63-69, 2015. https://doi.org/10.1016/j.patrec.2015.07.043
  9. B.-R. Lee, Q.-B. Truong, H.-S. Kim, and Y.-H. Bae, "A study on the pedestrian detection on the road using machine vision," Journal of Institute of Control, Robotics and Systems (in Korean), Vol.17, No.5, pp.490-498, 2011. https://doi.org/10.5302/J.ICROS.2011.17.5.490
  10. Z. Jiang, D. Q. Huynh, W. Moran, S. Challa, and N. Spadaccini, "Multiple Pedestrian Tracking Using Colour and Motion Models," Proceedings of International Conference on Digital Image Computing: Techniques and Applications, pp.328-334, 2010.
  11. X. Wang, "An HoG-LBP human detector with partial occlusion handling," Proceedings of International Conference on Computer Vision, pp.32-39, 2009.
  12. A. M. Elgammal and L. S. Davis, "Probabilistic Framework for Segmenting People under Occlusion," Proccedings of IEEE International Conference on Computer Vision, Vol.2, pp.145-152, 2001.
  13. Wikipedia, "Kalman filter" [Internet], http://en.wikipedia.org/wiki/kalman_filter.