DOI QR코드

DOI QR Code

Traffic Sign Recognition using SVM and Decision Tree for Poor Driving Environment

SVM과 의사결정트리를 이용한 열악한 환경에서의 교통표지판 인식 알고리즘

  • Jo, Young-Bae (Dept. of Electronics and Communications Engineering, Kwangwoon University) ;
  • Na, Won-Seob (Dept. of Electronics and Communications Engineering, Kwangwoon University) ;
  • Eom, Sung-Je (Dept. of Electronics and Communications Engineering, Kwangwoon University) ;
  • Jeong, Yong-Jin (Dept. of Electronics and Communications Engineering, Kwangwoon University)
  • Received : 2014.10.06
  • Accepted : 2014.11.18
  • Published : 2014.12.31

Abstract

Traffic Sign Recognition(TSR) is an important element in an Advanced Driver Assistance System(ADAS). However, many studies related to TSR approaches only in normal daytime environment because a sign's unique color doesn't appear in poor environment such as night time, snow, rain or fog. In this paper, we propose a new TSR algorithm based on machine learning for daytime as well as poor environment. In poor environment, traditional methods which use RGB color region doesn't show good performance. So we extracted sign characteristics using HoG extraction, and detected signs using a Support Vector Machine(SVM). The detected sign is recognized by a decision tree based on 25 reference points in a Normalized RGB system. The detection rate of the proposed system is 96.4% and the recognition rate is 94% when applied in poor environment. The testing was performed on an Intel i5 processor at 3.4 GHz using Full HD resolution images. As a result, the proposed algorithm shows that machine learning based detection and recognition methods can efficiently be used for TSR algorithm even in poor driving environment.

교통 표지판 인식(TSR)은 운전자 보조 시스템(ADAS)의 중요한 부분 중의 하나이다. 하지만 일반적인 주간 상황이 아닌 야간, 눈, 비, 안개 등의 열악한 상황에 대한 연구는 주간 상황과 달리 표지판 고유의 색이 정확히 나타나지 않기 때문에 많이 이루어지지 않고 있다. 본 논문에서는, 주간 상황뿐 아니라 열악한 환경에서도 적용 가능한 기계학습 기반의 교통 표지판 인식 알고리즘을 제안한다. 열악한 환경에서는 일반적인 RGB 색 체계 정보를 이용한 방법은 좋은 성능을 보이지 못하므로 표지판의 형태적 특징을 이용하는 HoG 특징점 추출기를 이용하여 표지판의 형태적 특징을 추출하고 SVM 알고리즘을 이용하여 표지판을 검출하였다. 검출한 표지판의 인식에는 Normalized RGB 색 체계의 25개의 참조점을 통한 의사결정트리를 이용하였다. Intel i5 3.4GHz 환경에서 Full HD 해상도의 이미지에 대해 실험한 결과 안개 및 야간 등의 열악한 환경에서의 검출률은 96.4%, 인식률은 94%로 본 논문에서 제안하는 학습기반의 알고리즘이 열악한 환경에서의 표지판 검출 및 인식에 효율적으로 적용이 가능함을 알 수 있다.

Keywords

References

  1. Carrasco Pascual and Juan Pablo, "Advanced Driver Assistance System based on Computer Vision using Detection, Recognition and Tracking of Road Signs", Universidad Carlos III de Madrid. Departamento de Ingenieria de Sistemas y Automatica, 2009
  2. Mogelmose, Andreas, Mohan M. Trivedi, and Thomas B. Moeslund. "Vision-based traffic sign detection and analysis for intelligent driver assistance systems: Perspectives and survey." Intelligent Transportation Systems, IEEE Transactions on 13.4 (2012): 1484-1497. https://doi.org/10.1109/TITS.2012.2209421
  3. Jong-Beom Park, "A Study on the Revised Method using Normalized RGB Features in the Moving Object Detection by Background Subtraction," The Journal of The Korea Institute of Intelligent Transport Systems Vol. 12, No. 6, pp.108-115, Korea Intelligent Transport System, 2013 https://doi.org/10.12815/kits.2013.12.6.108
  4. Zaklouta, Fatin, and Bogdan Stanciulescu. "Real-time traffic-sign recognition using tree classifiers." Intelligent Transportation Systems, IEEE Transactions on 13.4 (2012): 1507-1514. https://doi.org/10.1109/TITS.2012.2225618
  5. Dalal, Navneet, and Bill Triggs. "Histograms of oriented gradients for human detection." Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, 2005.
  6. Mi-Jin Jun, Joon Jae Lee, "Image Histogram Equalization Based on Gaussian Mixture Model", Journal of Korea Multimedia Society Vol. 15 No. 6, pp.748-760, Korea Mutimedia Society, 2012 https://doi.org/10.9717/kmms.2012.15.6.748
  7. J. R. Quinlan.,"C4.5: programs for machine learning," San Mateo: Morgan Kaufmann Publishers, Burlington, Massachusetts, 1993
  8. Young-Sun Sohn, "A Recognition of Traffic Safty Signs Using Japanese Puzzle", J. Korean Inst. Intell. Syst. Vol. 18, No. 3, pp. 416-421, Korean Institute of Intelligent Systems, 2008 https://doi.org/10.5391/JKIIS.2008.18.3.416
  9. Min-Chul Shin, Sang-Il Na, Jung-Ho Lee, Jun-Ho Jeong, Dong-Seok Jeong, "Traffic Sign Recognition Using Color Information and Neural Networks", 32nd Fall Conference Vol. 32, No. 2, Korea Institute of Information Scientists and Engineers, 2005