DOI QR코드

DOI QR Code

Performance Improvement of Traffic Signal Lights Recognition Based on Adaptive Morphological Analysis

적응적 형태학적 분석에 기초한 신호등 인식률 성능 개선

  • Kim, Jae-Gon (School of Electronics, Telecom. & Computer Engineering, Korea Aerospace University) ;
  • Kim, Jin-soo (Department of Information and Communication Engineering, Hanbat National University)
  • Received : 2015.06.29
  • Accepted : 2015.08.04
  • Published : 2015.08.20

Abstract

Lots of research and development works have been actively focused on the self-driving vehicles, locally and globally. In order to implement the self-driving vehicles, lots of fundamental core technologies need to be successfully developed and, specially, it is noted that traffic lights detection and recognition system is an essential part of the computer vision technologies in the self-driving vehicles. Up to nowadays, most conventional algorithm for detecting and recognizing traffic lights are mainly based on the color signal analysis, but these approaches have limits on the performance improvements that can be achieved due to the color signal noises and environmental situations. In order to overcome the performance limits, this paper introduces the morphological analysis for the traffic lights recognition. That is, by considering the color component analysis and the shape analysis such as rectangles and circles simultaneously, the efficiency of the traffic lights recognitions can be greatly increased. Through several simulations, it is shown that the proposed method can highly improve the recognition rate as well as the mis-recognition rate.

국내외적으로 무인자동차에 대한 연구와 개발이 활발히 진행되고 있다. 무인자동차를 성공적으로 구현하기 위해서는 매우 많은 요소 기술들을 필요로 한다. 특히 교통신호등의 검출과 인식 시스템은 무인자동차에서 컴퓨터 비전 기술의 핵심적인 요소기술로 주목 받고 있다. 최근까지 제안된 대부분의 교통 신호등 인식 방식들은 잡음과 환경적인 요소에 따라 의존적인 색깔 성분 분석 방법을 사용함으로써 인식률 개선에 있어 제한적인 성능 특성을 갖고 있다. 본 논문에서는 이러한 기존의 방식의 한계를 극복하기 위해 교통신호등이 갖는 형태학적인 특성을 최대한 고려한 방법을 제안한다. 제안한 방식은 색깔 성분과 사각형 특성, 원형 특성과 같은 형태학적 특성을 동시에 고려함으로써 인식 효율을 크게 증대시킨다. 다양한 모의실험을 통하여 제안한 방식은 교통신호등 인식률뿐만 아니라 오인식률 성능을 크게 개선시킬 수 있음을 보인다.

Keywords

References

  1. M. Mathias, R. Timofte, R. Benenson, and L.V.Gool, "Traffic Sign Recognition - How Far are We from the Solution," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2013.
  2. A. Lorsakul and J. Suthakorn, "Traffic Sign Recognition for Intelligent Vehicle/Driver Assistance System Using Neural Network on OpenCV", The 4th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI 2007), 2007. p. 22-24.
  3. R. Charette and F. Nashasibi, "Real Time Visual Traffic Lights Recognition Based on Spot Light Detection and Adaptive Traffic Lights Templates," Intelligent Vehicles Symposium, 2009 IEEE. IEEE, 2009.
  4. Y. Jie, C. Xiamin, G. Pengfei, and X. Zhonglong, "A New Traffic Light Detection and Recognition Algorithm for Electronic Travel Aid," 2013-4th International Conference on Intelligent Control and Information Processing (ICICIP), June 9-11, 2013.
  5. S. Kim, Y. Baek, and S. Moon, "Development of Traffic Light Automatic Discrimination System Using Digital Image Processing Technology", IEEK Signal Processing Society, Vol. 46, No.2, March 2009. pp.93-99
  6. Y. Kim, K. Lee, S. Cho, J. Park, and K. Choi, "Real-time Identification of Traffic Light and Road Sign for the Next Generation Video-Based Navigation System," journal of Korea Spatial Information System Society, Vol. 10, No. 2, June 2008, pp. 13-24
  7. M. Kim, J.H. Nam and J.W. Jang, "Implementation of Smart Car Infotainment System Including Black Box and Self-diagnosis Function," International Journal of Software Engineering and Its Applications, Vol.8, No.1, 2014, pp.267-274 https://doi.org/10.14257/ijseia.2014.8.1.23
  8. J. Jeong and D.Rho, "Real Time Detection and Recognition of Traffic Lights Using Component Subtraction and Detection Masks," IEEK Signal Processing Society, Vol. 43, No.2, March 2006. pp.65-72
  9. J. Ryu and J. Kim, "Road Distance Estimation Based on Pinhole Model for a Vehicle-attached Black Box Camera", IPIU2015, Jeju, Feb. 2015.
  10. J. Kim, "Effective Road Distance Estimation Using a Vehicle-attached Black Box Camera," Journal of Korea Institute of Info. and Comm. Eng., Vol.19, No.3, Mar 2015, pp.651-658. https://doi.org/10.6109/jkiice.2015.19.3.651

Cited by

  1. 명도와 채도 기반의 점등영역 검출 및 모델 검증에 의한 교통신호등 판별 vol.20, pp.11, 2015, https://doi.org/10.9717/kmms.2017.20.11.1729
  2. 야간 영상에서의 빛 번짐 현상을 이용한 교통신호등 인식 vol.20, pp.12, 2017, https://doi.org/10.9717/kmms.2017.20.12.1901