DOI QR코드

DOI QR Code

Performance Improvement of Pedestrian Detection using a GM-PHD Filter

GM-PHD 필터를 이용한 보행자 탐지 성능 향상 방법

  • Lee, Yeon-Jun (Dept. of Electrical and Computer Engineering, INMC, Seoul National University) ;
  • Seo, Seung-Woo (Dept. of Electrical and Computer Engineering, INMC, Seoul National University)
  • 이연준 (서울대학교 전기정보공학부 및 뉴미디어통신공동연구소) ;
  • 서승우 (서울대학교 전기정보공학부 및 뉴미디어통신공동연구소)
  • Received : 2015.10.19
  • Accepted : 2015.11.19
  • Published : 2015.12.25

Abstract

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.

보행자 인식은 차량자율주행 및 사고방지를 위해 중요한 요소기술로서 많이 연구되고 있다. 이 기술들은 크게 카메라기반과 LIDAR 기반, 두 가지로 구별할 수 있다. 카메라 기반 방법과 대비되어 LIDAR 기반 방법은 화각이 넓고 조도환경에 영향을 받지 않는다는 강점이 있다. 하지만 LIDAR 기반 방법은 먼 물체를 인식하기엔 센서 해상도가 낮고, 복잡한 환경에서는 분할 오류나 폐색 등의 원인으로 인식률이 낮아진다는 문제점이 있다. 본 논문에서는 3차원 LIDAR 기반 보행자 탐지 알고리즘의 낮은 인식률을 개선시키기 위해 다중객체추적 기법의 하나인 GM-PHD 필터를 이용한 두 가지 성능 향상 방법을 제안한다. 첫 번째 방법은 GM-PHD 필터를 이용해 이전 프레임의 포인트를 현재 프레임의 물체에 자동으로 누적하여 물체 해상도 및 보행자 분류 성능을 향상시킨다. 두 번째 방법은 인식 성능이 낮은 상황에 맞춰 개선된 GM-PHD 필터를 분류된 다중객체에 적용하여 탐지 성능을 더욱 강화시킨다. 직접 취득한 도로 주행 데이터에 두 방법을 적용하여 제안한 방법이 기존의 보행자 탐지 알고리즘 성능을 대폭 향상시키는 것을 정량적으로 증명하였다.

Keywords

References

  1. 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, Shenzhen, China, June 2011.
  2. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Computer Vision and Pattern Recognition, San Diego, CA, USA, June 2005.
  3. D. Prokhorov, "A Convolutional Learning System for Object Classification in 3-D Lidar Data," IEEE Trans. Neural Networks, Vol. 21, No. 5, pp. 858-863, May 2010. https://doi.org/10.1109/TNN.2010.2044802
  4. S. Awan, M. Muhamad, K.Kusevic, P. Mrstik and M. Greenspan, "Object Class Recognition in Mobile Urban Lidar Data Using Global Shape Descriptors," 2013 International Conference on 3D Vision, Seattle, WA, USA, June 2013.
  5. C. Premebida, O. Ludwig and U. Nunes, "Exploiting LIDAR-based Features on Pedestrian Detection in Urban Scenarios," 12th International IEEE Conference on Intelligent Transportation Systems, St. Louis, MO, USA, Oct. 2009.
  6. L. E. Navarro-Serment, C. Mertz, and M. Hebert, "Pedestrian Detection and Tracking Using Three-Dimensional LADAR Data," International Conference on Field and Service Robotics, 2009.
  7. A. Teichman, J. Levinson and S. Thrun, "Towards 3D Object Recognition via Classification of Arbitrary Object Tracks," International Conference on Robotics and Automation, Shanghai, China, May 2011.
  8. H. Himmelsbach, Felix v. Hundelshausen and H.-J. Wuensche, "Fast Segmentation of 3D Point Clouds for Ground Vehicles," Intelligent Vehicles Symposium, San Diego, CA, USA, June 2010.
  9. K. Kidono, T. Miyasaka, A. Watanabe, T. Naito and J.Miura, "Pedestrian Recognition Using High-definition LIDAR," Intelligent Vehicles Symposium, Baden-Baden, Germany, June 2011.
  10. B. Vo and W. Ma, "The Gaussian Mixture Probability Hypothesis Density Filter," IEEE Trans. Signal Processing, Vol. 54, no. 11, pp. 4091-4104, Nov. 2006. https://doi.org/10.1109/TSP.2006.881190
  11. K. Panta, D. E. Clark and B. Vo, "Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter," IEEE Trans. Aerospace and Electronic Systems, Vol. 45, no. 3, pp. 1003-1016, July 2009. https://doi.org/10.1109/TAES.2009.5259179

Cited by

  1. Autonomous Campus Mobility Services Using Driverless Taxi vol.18, pp.12, 2017, https://doi.org/10.1109/TITS.2017.2739127