DOI QR코드

DOI QR Code

도로와 하늘 영역 추출을 위한 적응적 분할 방법

Adaptive Segmentation Approach to Extraction of Road and Sky Regions

  • 박경환 (군산대학교 컴퓨터정보공학과) ;
  • 남광우 (군산대학교 컴퓨터정보공학과) ;
  • 이양원 (군산대학교 컴퓨터정보공학과) ;
  • 이창우 (군산대학교 컴퓨터정보공학과)
  • Park, Kyoung-Hwan (Dept. of Computer Information Engineering, Kunsan National University) ;
  • Nam, Kwang-Woo (Dept. of Computer Information Engineering, Kunsan National University) ;
  • Rhee, Yang-Won (Dept. of Computer Information Engineering, Kunsan National University) ;
  • Lee, Chang-Woo (Dept. of Computer Information Engineering, Kunsan National University)
  • 투고 : 2011.03.11
  • 심사 : 2011.04.07
  • 발행 : 2011.07.31

초록

비젼기반 지능형교통정보시스템(ITS, Intelligent Transportation System) 환경에서 도로영역의 분할이 가장 기초적인 역할을 한다. 따라서 본 논문은 입력영상에서 도로 영역과 하늘 영역을 분할하기 위해 적응적 패턴 추출을 통한 영역분할 방법을 제안한다. 제안된 방법은 첫째, Mean Shift 알고리즘을 이용한 초기분할 단계, 둘째, 정적 패턴매칭 방법에 기반한 후보영역선별 단계, 셋째, 동적 패턴매칭 방법에 기반한 영역확장 단계로 구성된다. 제안된 방법은 적응적 패턴을 현 분할영역의 주변 영역으로부터 추출하여 영역병합에 사용함으로서 보다 신뢰성 높은 영역병합결과를 얻을 수 있다. 제안된 방법의 장점을 평가하기 위해 정적인(static) 패턴만을 사용해서 영역을 병합하는 방법과 비교하였다. 제안된 방법의 실험결과에서는 적응적인 패턴 추출방법을 사용하였을 때가 정적인 패턴 추출에 의한 영역병합 방법보다 8.12%의 성능이 향상됨을 보였다. 제안된 방법은 수시로 변화하는 도로환경에서 안정적으로 도로나 하늘영역을 추출할 수 있으며, 비전기반 지능형교통정보시스템의 핵심적인 역할을 할 것으로 기대한다.

In Vision-based Intelligent Transportation System(ITS) the segmentation of road region is a very basic functionality. Accordingly, in this paper, we propose a region segmentation method using adaptive pattern extraction technique to segment road regions and sky regions from original images. The proposed method consists of three steps; firstly we perform the initial segmentation using Mean Shift algorithm, the second step is the candidate region selection based on a static-pattern matching technique and the third is the region growing step based on a dynamic-pattern matching technique. The proposed method is able to get more reliable results than the classic region segmentation methods which are based on existing split and merge strategy. The reason for the better results is because we use adaptive patterns extracted from neighboring regions of the current segmented regions to measure the region homogeneity. To evaluate advantages of the proposed method, we compared our method with the classical pattern matching method using static-patterns. In the experiments, the proposed method was proved that the better performance of 8.12% was achieved when we used adaptive patterns instead of static-patterns. We expect that the proposed method can segment road and sky areas in the various road condition in stable, and take an important role in the vision-based ITS applications.

키워드

참고문헌

  1. M. Bertozzi, A. Broggi and A. Fascioli, "Vision-based intelligent vehicles : State of the art and perspectives", Robotics and Autonomous Systems, 32, pp. 1-16, 2000. https://doi.org/10.1016/S0921-8890(99)00125-6
  2. J. McCall and M. M. Trivedi, "Visual context capture and analysis for driver attention monitoring," in Proc. IEEE Conf. Intelligent Transportation Systems, Washington, DC, pp. 332-337, Oct. 2004.
  3. N. Oliver, A.P. Pentland, "Graphical Models for Driver Behavior Recognition in a Smart Car," in Proc. IEEE. Intelligent Vehicles Symposium, pp. 7-12, 2000.
  4. Jun-yong Sung, Min-hong Han, Kwang-hyun Ro, "De velopment of a Vision-based Lane Change Assistance System for Safe Driving." Journal of The Korea Society of Computer and Information. Vol. 11. No. 5. pp. 329-336. 2006.
  5. W. Enkelmann, "Video-based driver assistance-From basic functions to applications," Int. J. Comput. Vis. vol. 45, no. 3, pp. 201-221, Dec. 2001. https://doi.org/10.1023/A:1013658100226
  6. Young-suk Ji. Young-joon Han. Hern-soo Hahn, "Real-time Forward Vehicle Detection Method based on Extended Edge," Journal of The Korea Society of Computer and Information. Vol. 15. No. 10, pp. 35-47. 2010. https://doi.org/10.9708/jksci.2010.15.10.035
  7. P. Lombardi, M. Zanin, S. Messelodi, "Switching Models for Vision based On-Board Road Detection," Proc. IEEE Conf. on Intelligent Transportation Systems, pp. 67-72, 2005.
  8. M. Foedisch, and A. Takeuchi, "Adaptive real-time road detection using neural networks," Proc. IEEE Conf. on Intelligent Transportation Systems, pp. 167-172, 2004.
  9. P. Lombardi, M. Zanin, S. Messelodi, "Unified Stereo vision for Ground, Road, and Obstacle Detection," Proc. IEEE Conf. on Intelligent Vehicles, pp. 783-788, 2005.
  10. H. D. Cheng, X. H. Jiang, Y. Sun and J. Wang, "Color image segmentation : advances and prospects," Pattern Recognition, Vol.34, No.12, pp. 2259-2281, 2001. https://doi.org/10.1016/S0031-3203(00)00149-7
  11. Nae-Joung Kwak, Young-Gil Kim. Dong-Jin Kwon, "An Edge Preserving Color Image Segmentation Using Mean Shift Algorithm and Region Merging Method," Journal of The Korea Contents Association, Vol. 6. No. 9. pp. 19-27. 2006.
  12. R. M. Haralick and L. G. shapiro, "Survey : Image segmentation techniques," Comput. Vis. Graph. Image Process.,Vol.29, No.1, pp. 100-132, 1985. https://doi.org/10.1016/S0734-189X(85)90153-7
  13. SungMo Park, "Segmentation and Road Change Detection of Urban Area Satellite Image Used Mean Shift," Chonbuk National University MS Thesis, vi, pp. 50, 2004.
  14. R. C. Gonzalez and R. E. Woods, "Digital Image Processing", Addison Wesley, pp. 458-465, 1992.
  15. Jae-Young Choi, Young-Kyu Yang, "Mean-Shift Blob Clustering and Tracking for Traffic Monitoring System," Korean Journal of Remote Sensing, Vol.24, No.3, pp. 235-243, 2008.
  16. Ming-Yang Chern and Shi-Chong Cheng. "Finding Road Boundaries from the Unstructured Rural Road Scen," 16th IPPR Conference on Computer Vision, Graphics and Image Processing(CVGIP 2003).
  17. C. J. Yang, R. Duraiswami, D. DeMenthon, and L. Davis, "Mean Shift Analysis using Quasi-Newton Methods," University of Maryland, College Park, MD 20742, 2003.
  18. OpenCV API cvPyrMeanShiftFiltering( ), http://opencv.willowgarage.com/documentation/index.html