DOI QR코드

DOI QR Code

A Road Extraction Algorithm using Mean-Shift Segmentation and Connected-Component

평균이동분할과 연결요소를 이용한 도로추출 알고리즘

  • Lee, Tae-Hee (Dept. of Electronics & Communication Engineering, Hanyang University) ;
  • Hwang, Bo-Hyun (Dept. of EECI Engineering, Hanyang University) ;
  • Yun, Jong-Ho (Dept. of Electrical & Computer Engineering, Hanyang University) ;
  • Park, Byoung-Soo (Dept. of Computer System Engineering, Sangmyung University) ;
  • Choi, Myung-Ryul (Dept. of Electronics & Communication Engineering, Hanyang University)
  • 이태희 (한양대학교 전자통신공학과) ;
  • 황보현 (한양대학교 전자전기제어계측공학과) ;
  • 윤종호 (한양대학교 전자통신전파공학과) ;
  • 박병수 (상명대학교 컴퓨터시스템공학과) ;
  • 최명렬 (한양대학교 전자통신공학과)
  • Received : 2013.10.31
  • Accepted : 2014.01.20
  • Published : 2014.01.28

Abstract

In this paper, we propose a method for extracting a road area by using the mean-shift method and connected-component method. Mean-shift method is very effective to divide the color image by the method of non-parametric statistics to find the center mode. Generally, the feature points of road are extracted by using the information located in the middle and bottom of the road image. And it is possible to extract a road region by using this feature-point and the partitioned color image. However, if a road region is extracted with only the color information and the position information of a road image, it is possible to detect not only noise but also off-road regions. This paper proposes the method to determine the road region by eliminating the noise with the closing / opening operation of the morphology, and by extracting only the portion of the largest area using a connected-components method. The proposed method is simulated and verified by applying the captured road images.

본 논문은 평균이동방법과 연결요소방법을 이용하여 도로 영역을 추출하는 알고리즘을 제안하였다. 평균 이동 방법은 중심 모드를 찾기 위한 비모수적 통계 방법으로 컬러 영상을 분할하는데 효율적이다. 일반적으로, 영상의 중 하단에 위치하는 정보를 활용하여 도로의 특징점이 추출된다. 이 특징점과 분할된 컬러 영상을 이용하면, 도로의 영역을 추출할 수 있다. 그러나, 도로의 위치정보와 색상정보만으로 도로영역을 추출할 경우, 잡음과 도로 이외의 영역까지 추출되는 단점이 있다. 본 논문에서는 모폴로지 열기 닫기 연산을 이용하여 잡음을 제거하고, 연결요소 방법을 통하여 가장 큰 영역의 부분만을 추출하여 도로 영역으로 결정하는 방법을 제안한다. 제안된 방법은 실험을 통하여 잡음 제거와 보다 정확한 도로 검출됨을 검증한다.

Keywords

References

  1. Kyoung-Hwan Park, Chi-Won Lee, Chang-Woo Lee, "Road Detection using Mean Shift Algorithm and Similarity Region Merging method", Workshop presentatio file, Korea Information Science Society, vol. 36, no.4, pp.437-440, 2009.
  2. Nae-Joung Kwak, Young-Gil Kim, Dong-Jin Kwon, "An Edge Preserving Color Image Segmentation Using Mean Shift Algorithm and Region Merging Method", The Korea Contents Association, vol. 9, no.6, pp19-27, 2006.
  3. Jeong-Won Ko, Byung-In Choi, Frank Chung-hoon Rhee, "A Density Estimation based Fuzzy C-Means Algorithm for Image Segmentation", Journal of fuzzy logic and intelligent systems, vol. 17, no. 2, pp196-201, 2007. https://doi.org/10.5391/JKIIS.2007.17.2.196
  4. Shin-Won Lee, Won-Hee Lee, "Refining Initial Seeds using Max Average Distance for K-Means Clustering", Journal of korean society for internet information, vol. 12, no. 2, pp.103-111, 2011.
  5. Gary Bradski, Adrian Kaehler, "Learning OpenCV: Computer Vision with the OpenCV Library", O'Reilly Media; 1st edition, 2008.
  6. Kyoil Kim, "Binary Connected-component Labeling with Block-based Labels and Pixel-based Scan Mask", Journal of the Institute of Electronics Engineers of Korea Vol. 50, No. 5, May 2013.

Cited by

  1. A Road Region Extraction Using OpenCV CUDA To Advance The Processing Speed vol.12, pp.6, 2014, https://doi.org/10.14400/JDC.2014.12.6.231