Browse > Article

Exploring Optimal Threshold of RGB Pixel Values to Extract Road Features from Google Earth  

Park, Jae-Young (경북대학교 공간정보학과)
Um, Jung-Sup (경북대학교 지리학과)
Publication Information
Journal of Korea Spatial Information System Society / v.12, no.1, 2010 , pp. 66-75 More about this Journal
Abstract
The authors argues that the current road updating system based on traditional aerial photograph or multi-spectral satellite image appears to be non-user friendly due to lack of the frequent cartographic representation for the new construction sites. Google Earth are currently being emerged as one of important places to extract road features since the RGB satellite image with high multi-temporal resolution can be accessed freely over large areas. This paper is primarily intended to evaluate optimal threshold of RGB pixel values to extract road features from Google Earth. An empirical study for five experimental sites was conducted to confirm how a RGB picture provided Google Earth can be used to extact the road feature. The results indicate that optimal threshold of RGB pixel values to extract road features was identified as 126, 125, 127 for manual operation which corresponds to 25%, 30%, 19%. Also, it was found that display scale difference of Google Earth was not very influential in tracking required RGB pixel value. As a result the 61cm resolution of Quickbird RGB data has shown the potential to realistically identified the major type of road feature by large scale spatial precision while the typical algorithm revealed successfully the area-wide optimal threshold of RGB pixel for road appeared in the study area.
Keywords
Google Earth; Road; RGB data; Pixel;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Gramling, C., "Google Planet: with Virtual Globes, earth scientists see a new world," Geotimes, vol.52, no.2, 2007, pp. 38-39.
2 Matthew, A. Z., and Mark, G. M., "The creative reconstruction of the Internet: Google and the privatization of cyberspace and DigiPlace," Geoforum, vol.38, 2007, pp. 1322-1343.   DOI   ScienceOn
3 Mokhtarzade, M., Ebadi, H., "Road Detection from High Resolution Satellite Imagery Using Texture Parameters in Neural Network," First Joint Congress on Fuzzy and Intelligent Systems Ferdowsi University of Mashhad, Iran, 2007, pp. 29-31.
4 서정, "Road Detecion using Neural Network in Real Images," 영남대학교 석사학위논문, 2008.
5 한유경, 최재완, 이재빈, 유기윤, 김용일, "기대최대화 알고리즘을 활용한 도로노면 training 자료 자동추출에 관한 연구-감독분류를 통한 도로 네트워크의 자동추출을 위하여," 한국측량학회지, 제27권 제2호, 2009, pp. 289-297.   과학기술학회마을
6 Shackelford, A. K., and Davis, C. H., "Fully automate road network extraction from high-resolution satellite multispectral imagery," Proceedings of International Geoscience and Remote Sensing Symposium(IGRSS), vol.1, Toulouse, France, 21-25, 2003, pp. 461-463.
7 Haverkamp, D., "Extraction straight road structure in urban environments using IKONOS satellite imagery," Optical Engineering, vol.41, no.9, 2002, pp. 2107-2110.   DOI   ScienceOn
8 Song, M., and Civco, D., "Road extraction using SVM and image segmentation," Photogrammetric Engineering & Remote Sensing, vol.70, no.12, 2004, pp. 1365-1371.   DOI
9 양성철, 김용일, 유기윤, "컬러영상 경계추출을 위한 CIEL*Ch 색체계 변환의 적용," 한국공간정보시스템학회 2005년도 GIS/RS 공동 춘계학술대회, 2005 May 19, 2005, pp.273-278.
10 주인학, 최경호, 유재준, 황태현, 이종훈, "공간정보에 기반한 도로 데이터 자동생성 방법," 한국공간정보시스템학회 논문지, 제4권 제2호, 2002, pp. 55-64.   과학기술학회마을
11 김준모, 황병연, "지리정보시스템에서 고속도로 연결문제의 가변적 근사기법," 한국공간정보시스템학회 논문지, 제7권 제2호, 2005, pp. 57-64.   과학기술학회마을
12 Heipke, C., Mayer, H., Wiedemann, C., and Jamet, O., "Evaluation of automatic road extraction," International Archives of Photogrammetry and Remote Sensing, vol.32, no.3, 1997, pp. 47-56.
13 엄정섭, "Google Earth를 이용한 경북대와 홍콩대 캠퍼스의 불투수율 비교평가," 한국지역지리학회지 제15권 제3호, 2009, pp. 421-433.   과학기술학회마을
14 Google Earth, "Welcome to Google Earth Outreach," Http://earth.google.com/outreach/tour.html(검색일:2010.1.5일)