Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Pedestrian Detection Algorithm Using Feature Data in Multiple Pedestrian Tracking Process

다수의 보행자 추적과정에서 특징정보를 이용한 보행자 검출 알고리즘 설계

  • Han, Myung-ho (Department of Information and Communication Engineering, Chosun University) ;
  • Ryu, Chang-ju (Department of Information and Communication Engineering, Chosun University) ;
  • Lee, Sang-duck (Department of Information and Communication Engineering, Chosun University) ;
  • Han, Seung-jo (Department of Information and Communication Engineering, Chosun University)
  • Received : 2017.12.08
  • Accepted : 2018.03.28
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, CCTV, which provides video information for multiple purposes, has been transformed into an intelligent, and the range of automation applications increased using the computer vision. A highly reliable detection method must be performed for accurate recognition of pedestrians and vehicles and various methods are being studied for this purpose. In such an object detection system. In this paper, we propose a method to detect a large number of pedestrians by acquiring three characteristic information that features of color information using HSI, motion vector information and shaping information using HOG feature information of a pedestrian in a situation where a large number of pedestrians are moving. The proposed method distinguishes each pedestrian while minimizing the failure or confusion of pedestrian detection and tracking. Also when pedestrians approach or overlap, pedestrians are identified and detected using stored frame feature data.

최근 여러 목적으로 영상 정보를 제공하는 CCTV는 지능형으로 변화하고 있으며, 컴퓨터 비전을 이용한 자동화 응용 범위가 증가하고 있다. 보행자 및 차량 등의 정확한 인식을 위해 신뢰성이 높은 검출방법을 수행하여야 하며 이를 위해 다양한 방법들이 연구되고 있다. 본 논문에서는 다수의 보행자가 움직이는 상황에서 보행자의 세 가지 특징 정보를 획득하여 다수의 보행자들을 검출하는 방법을 제안한다. 제안하는 방법은 보행자 검출 및 추적에 실패하거나 혼동되는 상황을 최소화 하면서 각각의 보행자를 구별한다. 보행자들끼리 근접하거나 겹치는 경우 미리 저장된 프레임 특징 정보를 이용하여 보행자를 구별 및 검출한다.

Keywords

References

  1. P. H. Jeon, C. J. Park, J. Y. Kim, S. K. Oh, "Design of Pedestrian Detection and Tracking System Using HOG-PCA and Object Tracking Algorithm," The Transactions of the Korean Institute of Electrical Engineers, vol. 66, no. 4, pp. 682-691, Apr. 2017. https://doi.org/10.5370/KIEE.2017.66.4.682
  2. B. Wu and R. Nevatia, "Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors," in 10th IEEE International Conference on Computer Vision, vol.1, pp. 90-97, Oct. 2005.
  3. 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 System vol. 19, no.11, pp.1017-1021, Nov. 2013. https://doi.org/10.5302/J.ICROS.2013.13.1858
  4. A. Alahi, Y. Boursier, L. Jacques, and P. Vandergheynst, "A Sparsity Constrained Inverse Problem to Locate People in a Network of Cameras," in 16th International Conference on Digital Signal Processing, pp. 1-7, Jul. 2009.
  5. N. H. Cho and H. S. Jung, "A Study on the Model Generative Algorithm for Pedestrian Detection," Journal of Korean Institute of Information Technology vol.11, no.1, pp.63-69, Jan. 2013.
  6. M. Szarvas, A. Yoshizawa, M. Yamamoto, and J. Ogata, "Pedestrian Detection with Convolutional Neural Networks," Proceeding IEEE Intelligent Vehicles Symposium, pp. 223-228, Jun. 2005.
  7. M. Mahlisch, M. Oberlader, O. Lolein, D. Gavrila, and W. Ritter, "A Multiple Detector approach to low-resolution for Pedestrian Recognition," Proceeding of the IEEE Intelligent Vehicles Symposium, pp. 23-28, Jun. 2005.
  8. S. Lee and J. S. Cho, "Tracking and Recognition of vehicle and pedestrian for intelligent multi-visual surveillance systems," Journal of the Korea Institute of Information and Communication Engineering vol.19, no.2, pp.435-442, Feb. 2015. https://doi.org/10.6109/jkiice.2015.19.2.435
  9. S. Y. Lee, "OpenCV-based Object Tracking System," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol.6, no.5, pp. 29-37, May 2016.