DOI QR코드

DOI QR Code

Study of Traffic Sign Auto-Recognition

교통 표지판 자동 인식에 관한 연구

  • Kwon, Mann-Jun (Dept. of Automotive Engineering, Ajou Motor College)
  • 권만준 (아주자동차대학 자동차계열)
  • Received : 2014.06.12
  • Accepted : 2014.09.11
  • Published : 2014.09.30

Abstract

Because there are some mistakes by hand in processing electronic maps using a navigation terminal, this paper proposes an automatic offline recognition for traffic signs, which are considered ingredient navigation information. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which have been used widely in the field of 2D face recognition as computer vision and pattern recognition applications, was used to recognize traffic signs. First, using PCA, a high-dimensional 2D image data was projected to a low-dimensional feature vector. The LDA maximized the between scatter matrix and minimized the within scatter matrix using the low-dimensional feature vector obtained from PCA. The extracted traffic signs under a real-world road environment were recognized successfully with a 92.3% recognition rate using the 40 feature vectors created by the proposed algorithm.

내비게이션 단말기에 사용되는 전자지도 제작이 수작업으로 이루어지고 있어 오기가 발생할 수 있기 때문에, 본 논문에서는 내비게이션 정보의 요소로 다루어지는 교통 표지판에 대한 오프라인 자동 인식에 대해 제안하였다. 컴퓨터 비전과 패턴 인식 응용 분야로 2차원 얼굴 인식 분야에 널리 활용되고 있는 주성분분석기법(PCA)과 선형판별분석기법(LDA)을 이용하여 교통표지판을 인식하고자 한다. 먼저 PCA를 이용하여 높은 차원의 2차원 이미지 데이터를 저차원의 특징 벡터영역으로 투영을 시킨다. PCA로부터 구해진 저차원의 특징 벡터를 이용하여 LDA로 분산 매트릭스들 간에 최대가 되고 하고, 분산 매트릭스 내에서는 최소가 되도록 하였다. 실제 도로 환경에서 추출된 교통 신호판의 대부분을 제안된 알고리즘에 의해서 특징 벡터를 40개 이상 사용하였을 경우 92.3%이상의 높은 인식률을 보임을 확인하였다.

Keywords

References

  1. http://www.hyundai-mnsoft.com/, HYNDAI MnSOFT, SERVICE/Digital MAP DB.
  2. Guang-zhe Li, Song-jun Li, Chun-ri Fang, Sang-hyun Lee, "A Study on the Development of Automatic Manufactured Urban 3D Model by Using Numerical Map", Proceedings of the KAIS Fall Conference, pp. 279-282, 2007
  3. Jaehong Lee, Eunsoo Park, Hyoungrae Kim, Jonghwan Lee, Chungsu Lee, Jonghee Kim, Seungjun Lee, Hakil Kim, "Traffic Sign Recognition using Color Model and Color Edge Filter", The Korean Society of Automotive Engineers, Vol. 2013 No. 11, pp. 849-850, 2013
  4. Sangchul Kim, Jemin Lee, Daeyoung Kim, JongHo Nang, "Applying SIFT Feature to Occlusion, Damage and Rotation Invariant Traffic Sign Recognition", Korean Institute of Information Scientists and Engineers, Vol. 39 No. 1B, pp.351-353, 2012
  5. National Police Agency, "Traffic sign Installation.Management Manual" Road Traffic Authority(KoROAD), Dec.2011
  6. National Police Agency, "List of traffic signs" Road Traffic Authority(KoROAD), Dec. 2011
  7. M. Turk, A. Pentland, "Eigenfaces for Recognition", Journal of Cognitive Neuroscience, Vol 3, No. 1, pp. 71-86, 1991 DOI: http://dx.doi.org/10.1162/jocn.1991.3.1.71
  8. Juwei Lu, Plataniotis, K.N., Venetsanopoulos, A.N., "Face recognition using LDA-based algorithms", IEEE Transactions, Neural Networks, Vol.14, Issue. 1, pp. 195-200, Jan. 2003 DOI: http://dx.doi.org/10.1109/TNN.2002.806647
  9. P. Belhumeur, J. Hespanha, D. Kriegman, "Eigenfaces vs. fisherfaces: Recognition using class specific linear projection", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 711-720, 1997 DOI: http://dx.doi.org/10.1109/34.598228
  10. Marian Stewart Bartlett, Javier R. Movellan, Terrence J. Sejnowski, "Face recognition by Independent Component Analysis", IEEE Transactions on Neural Networks, Vol.13, No.6., pp. 1450-1464, 2002 DOI: http://dx.doi.org/10.1109/TNN.2002.804287
  11. Young-Jun Song, Young-Gil Kim, Jae-Hyeong Ahn, "A Performance Analysis of the Face Recognition Based on PCA/LDA on Distance Measures", Journal of the Korea Academia-Industrial Cooperation Society, Vol.6, No.3., pp. 249-254, 2005
  12. Alexis M. Martinez, Avinash C. Kak, "PCA versus LDA", IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.23, No.2, pp. 228-233, 2001 DOI: http://dx.doi.org/10.1109/34.908974