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

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Traffic Light Detection Using Color Based Saliency Map and Morphological Information

색상 기반 돌출맵 및 형태학 정보를 이용한 신호등 검출

  • Received : 2017.03.29
  • Accepted : 2017.07.26
  • Published : 2017.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic lights contain very important information for safety driving. So, the delivery of the information to drivers in real-time is a very critical issue for advanced driver assistance systems. However, traffic light detection is quite difficult because of the small sized traffic lights and the occlusion in real world. In this paper, a traffic light detection method using modified color based saliency map and morphological information is proposed. It shows 98.14% of precisions and 83.52% of recalls on computer simulations.

신호등은 운전자가 반드시 인지하고 조치를 취해야 할 교통 정보를 포함하고 있으며 이를 실시간으로 검출하여 운전자에게 알리는 것은 매우 중요하다. 그러나 신호등의 크기가 전체 영상에서 차지하는 비율이 낮고, 다른 객체에 의하여 가려지는 경우가 많아 실제 신호등 검출이 어려운 실정이다. 본 논문에서는 색상 기반 돌출맵과 형태학 정보를 이용한 신호등을 검출 방법을 제안한다. 돌출맵은 시각적 주의집중 영역을 검출하는데 사용되는데, 이를 개량한 색상 기반 돌출맵은 신호등의 색상과 형태를 검출 것에 적합함을 실험을 통하여 확인하였으며, 제안된 모델은 PC 환경에서 98.14%의 검출율과 83.52%의 재현율을 달성하였다.

Keywords

References

  1. Ministry of Land, Infrastructure and Transport, "National Indicator System - Automobile Registration Status," http://www.index.go.kr/potal/main/EachDtlPageDetail.do?idx_cd=1257.
  2. Korean National Police Agency, "Traffic accident statistics," 2016.
  3. C. Yu, C. Huang, and Y. Lang, "Traffic light detection during day and night conditions by a camera," in Prof. of IEEE Int. Conf. on Signal Processing, pp. 821-824, Beijing, China, Oct. 2010.
  4. M. Diaz-Cabrera, P. Cerri, and J. Sanchez-Medina, "Suspended traffic lights detection and distance estimation using color features," in Prof. of Int. IEEE Con. on Intelligent Transportation Systems, pp. 1315-1320, Anchorage, USA, Sep. 2012.
  5. M. Omachi and S. Omachi, "Traffic light detection with color and edge information," in Proc. of IEEE Int. Con. on Computer Science and Information Technology, pp. 284-287, Beijin, China, Sep. 2009.
  6. M. C. Jung, "Traffic Signal Detection and Recognition in an RGB Color Space," Journal of the Semiconductor & Display Technology, vol. 10, no. 3, pp. 53-59, Sep. 2011.
  7. J. Levinson, J. Askeland, J. Dolson, and S. Thrun, "Traffic light mapping, localization, and state detection for autonomous vehicles," in Prof. of IEEE Int. Conf. on Robotics and Automation, pp. 5784-5791, Shanghai, China, May 2011.
  8. Z. Cai, M. Gu, and Y, Li, "Real-time arrow traffic light recognition system for intelligent vehicle," in Proc. of World Congress in Computer Science, Computer Engineering, and Applied Computing, Jul. 2012.
  9. H.-K. Kim, J. H. Park, and H.-Y. Jung, "Effective traffic lights recognition method for real time driving assistance system in the daytime," Int. Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, Vol. 5, no. 11, pp. 1424-1427, 2011.
  10. A. Gomez, F. Alencar, P. Prado, F. Osorio, and D. Wolf, "Traffic lights detection and state estimation using hidden markov models," in Prof. of IEEE Intelligent Vehicles Symposium, Dearborn, USA, pp. 750-755, July 2014.
  11. R. Charette and F. Nashashibi, "Real time visual traffic light detection based on spot light detection and adaptive traffic lights templates," in Prof. of IEEE intelligent Vehicles symposium, Xian, China, pp.358-363, July 2009.
  12. J. Illingworth and J. Kittler, "The adaptive hough transform", IEEE Trans, on Pattern Analysis and Machine Intelligence, Vol. PAMI-9, no. 5, pp.690-698, Sep. 1987. https://doi.org/10.1109/TPAMI.1987.4767964
  13. C. Chiang, M. Ho and H. Liao, "Detecting and recognizing traffic lights by genetic approximate ellipse detection and spatial texture layouts," Int. Journal of Innovative Computing, Information and Control, Vol. 7, no. 12, pp. 6919-6934, Dec. 2011.
  14. R. Charette, and F. Nashashibi, "Traffic light recognition using image processing compared to learning processes", in Prof. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 333-338, St. Louis, USA, Oct. 2009.
  15. M. Philipsen, M. Jensen, M. Trivedi, and A. Mogelmose, "Traffic light detection at night: Comparison of a learning-based detector and three model-based detectors," in Proc. of Int. Symposium on Visual Computing, pp. 774-783, Las Vegas, USA, Dec. 2015.
  16. J. Kim, "Traffic Lights Detection Based on Visual Attention and Spot-Lights Regions Detection," Journal of The Institute of Electronics and Information Engineers, vol. 51, no. 6, pp. 1260-1270, Jun. 2014.
  17. L. Itti, C. Koch, E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 20, no. 11, pp. 1254-1259, Nov. 1998. https://doi.org/10.1109/34.730558
  18. Robotics Centre of Mines ParisTech., Traffic light recognition public benchmarks, http://www.lara.prd.fr/benchmarks/trafficlightsrecognition, 2015.
  19. G. Siogkas, E. Skodras, and E. Dermatas, "Traffic lights detection in adverse conditions using color, symmetry and spatiotemporal information.", in Proc. of the Int. Conf, on Computer Vision Theory and Applications, Rome, Italy, pp. 620-627, Feb. 2012.