Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Design and Implementation of the Stop line and Crosswalk Recognition Algorithm for Autonomous UGV

자율 주행 UGV를 위한 정지선과 횡단보도 인식 알고리즘 설계 및 구현

  • Lee, Jae Hwan (School of Computer Engineering, National Defense University) ;
  • Yoon, Heebyung (School of Computer Engineering, National Defense University)
  • 이재환 (국방대학교 컴퓨터공학과) ;
  • 윤희병 (국방대학교 컴퓨터공학과)
  • Received : 2014.01.15
  • Accepted : 2014.03.27
  • Published : 2014.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

In spite of that stop line and crosswalk should be aware of the most basic objects in transportation system, its features extracted are very limited. In addition to image-based recognition technology, laser and RF, GPS/INS recognition technology, it is difficult to recognize. For this reason, the limited research in this area has been done. In this paper, the algorithm to recognize the stop line and crosswalk is designed and implemented using image-based recognition technology with the images input through a vision sensor. This algorithm consists of three functions.; One is to select the area, in advance, needed for feature extraction in order to speed up the data processing, 'Region of Interest', another is to process the images only that white color is detected more than a certain proportion in order to remove the unnecessary operation, 'Color Pattern Inspection', the other is 'Feature Extraction and Recognition', which is to extract the edge features and compare this to the previously-modeled one to identify the stop line and crosswalk. For this, especially by using case based feature comparison algorithm, it can identify either both stop line and crosswalk exist or just one exists. Also the proposed algorithm is to develop existing researches by comparing and analysing effect of in-vehicle camera installation and changes in recognition rate of distance estimation and various constraints such as backlight and shadow.

정지선과 횡단보도는 자율 주행에서 가장 기본적으로 인식해야 하는 인식대상임에도 불구하고 추출할 수 있는 특징이 매우 제한적이고 영상기반의 인식기술을 제외한 레이저나 RF, GPS/INS 인식기술로는 인식이 어려운 분야다. 이러한 이유로 이 분야에 대한 연구는 매우 제한적으로 수행되어왔다. 본 논문에서는 비전센서를 통해 입력된 정지선과 횡단보도 영상을 영상기반으로 인식할 수 있는 알고리즘을 설계하고 구현한다. 제안한 알고리즘은 3개 부분으로 구성된다. 즉 특징추출에 필요한 영역을 사전에 선정하여 처리속도를 향상시키는 관심영역 설정 부분, 일정비율 이상의 백색이 검출된 영상만 인식되도록 하여 불필요한 연산을 제거하는 색상패턴 검사 부분, 에지특징을 추출하고 추출된 에지특징을 사전에 모델링한 특징모델과 비교하여 정지선과 횡단보도 여부를 식별하는 특징 추출과 인식 부분이다. 특징추출과 인식 부분에는 유형별 특징비교 알고리즘을 적용하여 정지선과 횡단보도가 병행하여 존재하거나 각각 존재하는 경우에 대해 모두 식별되도록 한다. 또한 제안한 알고리즘은 기존연구를 발전시키기 위해 카메라의 차량내부 설치의 효과, 역광 및 그림자와 같은 다양한 제약조건에 대한 인식률 변화와 거리에 따른 적정 인식률 평가를 비교 분석하였다.

Keywords

References

  1. J. W. Lee and U. K. Yi, "A lane-departure identification based in LBPE, Hough transform, and linear regression," CVIU, vol 99, no.3, pp.359-383, 2005
  2. Jeon HwangSoo, "Unmanned Vehicle Technology and Development Trends," National IT Industry Promotion Agency, 2012.
  3. D. Xu, Y. F. Li, M. Tan, and Y. Shen, "A New Active Visual System for Humanoid Robots," IEEE Trans. on Sys. Man and Cyber, vol. 38, no. 2, 99. 320-330, 2008. https://doi.org/10.1109/TSMCB.2007.912082
  4. Lee JunWoong, "Coloring-based blob detection crosswalk and stop line," J ournal of Institute of Control, Robotics and Systems, 2011. https://doi.org/10.5302/J.ICROS.2011.17.8.799
  5. Park TaeJun, Cho TaeHoon, "Pedestrian Crossing and Stop Line Recognition System for Unmanned Autonomous Vehicle," Journal of Korean Institute of Intelligent Systems, Vol.22, No. 2, pp. 154-160, 2012. https://doi.org/10.5391/JKIIS.2012.22.2.154
  6. Coughlan J, Shen H, "A fast algorithm for finding crosswalks using figure-ground segmentation," Proc. 2nd Workshop on Applications of Computer Vision, in conjunction with ECCV 2006.
  7. H. K Swant, H. D. Magar, "Crosswalk Detection System Using Mobile Phone," Journal of Information, Knowledge and Research In Computer Engineering, Vol 01. Issue 02, pp. 38-42. 2008.
  8. National Police Agency(Transportation Planning), Enforcement Rules of the Road Traffic Act, 312 (2012. 9. 12 Revision)
  9. National Police Agency(Transportation Planning), "Traffic Road Marking Installation Administration Manual", National Police Agency, 2005.
  10. Park HyeYeong, Lee GwanYong, "Pattern Recognition and Maching Learning(From Basis to Application)," EhanMedia, 2011
  11. R. M. Haralick and L. G. Shapiro, "Computer and Robot Vision," Addison-Wesley Pulishing Company, 1992
  12. Peter A. Lachenbrucha, Cheryl Sneeringerb, Lawrence T. Revoc, "Robustness of the linear and quadratic discriminant function to certain types of non-normality," Communications in Statistics, vol. 1, issue. 1, pp. 39-56, 1973.
  13. Kim WonJun, Kim ChangIk, "Interest and Case Detection Technology," The Institute of Electronics and Information Engineers Vol.39, February, pp. 20-28, 2012.
  14. M. J. Magee and J. K. Aggarwal, "Determining vanishing points from perspective images," Computer Vision Graphics and Image Procesing, vol. 26, pp. 256-267, 1984. https://doi.org/10.1016/0734-189X(84)90188-9
  15. Rules and Facilities of the road structure, Ministry of Land, Infrastructure and Transport(2012.4.15)
  16. Lee HeungKyu, "Digital Image Processing Theory and Implementation," SciTech Media, 2007
  17. Ha YeongHo, Nam JaeYeol, Lee Eung, Lee CheolHui, "Digital Image Processing 2nd Edition," Green Press, 2005
  18. Mark Nixon & Alberto Aguado, "Feature Extraction & Image Processing Second edition," AP, 2012
  19. Xiaoxiao zhou, "Study of image Edge detection techiques," Advanced materials Research, Vol 505, pp. 393-396, April. 2012. https://doi.org/10.4028/www.scientific.net/AMR.505.393

Cited by

  1. Infrared Image Segmentation by Extracting and Merging Region of Interest vol.26, pp.6, 2016, https://doi.org/10.5391/JKIIS.2016.26.6.493