Road Extraction in Remote Sensing Images Based on Spectral and Edge Analysis
ZHAO Wen-zhi1, LUO Li-qun1, 2, GUO Zhou1, YUE Jun1, YU Xue-ying3, LIU Hui1, WEI Jing4
1. Institute of Remote Sensing and GIS, Peking University, Beijing 100871, China 2. Unit 61243 of PLA, Urumqi 830006, China 3. Planning Bureau of Jixian County, Tianjin 301900, China 4. College of Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
Abstract:Roads are typically man-made objects in urban areas. Road extraction from high-resolution images has important applications for urban planning and transportation development. However, due to the confusion of spectral characteristic, it is difficult to distinguish roads from other objects by merely using traditional classification methods that mainly depend on spectral information. Edge is an important feature for the identification of linear objects (e. g., roads). The distribution patterns of edges vary greatly among different objects. It is crucial to merge edge statistical information into spectral ones. In this study, a new method that combines spectral information and edge statistical features has been proposed. First, edge detection is conducted by using self-adaptive mean-shift algorithm on the panchromatic band, which can greatly reduce pseudo-edges and noise effects. Then, edge statistical features are obtained from the edge statistical model, which measures the length and angle distribution of edges. Finally, by integrating the spectral and edge statistical features, SVM algorithm is used to classify the image and roads are ultimately extracted. A series of experiments are conducted and the results show that the overall accuracy of proposed method is 93% comparing with only 78% overall accuracy of the traditional. The results demonstrate that the proposed method is efficient and valuable for road extraction, especially on high-resolution images.
Key words:Spectral features of roads;Edge statistics;High-Resolution remote sensing image classification;Road extraction
[1] Du Q, Yang H. IEEE Geoscience and Remote Sensing Letters, 2008, 5(4): 564. [2] Gu Y F, Zhang Y. Proceedings of International Conference on Image Processing, 2003, 1: 801. [3] Walter V. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58(3): 225. [4] Hu X, Tao C V, Hu Y. Remote Sensing and Spatial Information Sciences,2004, 35: B3. [5] Inglada J. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 62(3): 236. [6] ZHANG Fang-li, DU Shi-hong, GUO Zhou(张方利, 杜世宏, 郭 舟). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013, 33(8): 2024. [7] Mena J B, Malpica J A. Pattern Recognition Letters,2005,26(9): 1201. [8] Trinder J C, Wang Y. Digital Signal Processing, 1998, 8(4): 215. [9] Baumgartner A, Steger C, Mayer H. Photogrammetric Engineering and Remote Sensing, 1999, 65: 777. [10] Geisler W S, Perry J S, Super B J, et al. Vision Research,2001, 41(6): 711. [11] Zhang Q, Wang J, Peng X, et al. International Journal of Remote Sensing,2002, 23(15): 3057. [12] Mokhtarzade M, Zoej M V. International Journal of Applied Earth Observation and Geoinformation, 2007, 9(1): 32. [13] De Laet V, Paulissen E, Waelkens M. Journal of Archaeological Science, 2007, 34(5): 830. [14] Weng Q. Remote Sensing of Environment, 2012, 117: 34. [15] Zhang R, Zhu D. Expert Systems with Applications, 2011, 38(4): 3647. [16] Miao Z, Shi W, Zhang H, et al. Geoscience and Remote Sensing Letters, 2013, 10(3): 583. [17] Vanegas M C, Bloch I, Inglada J. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(6): 3542. [18] Huang X, Zhang L. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(1): 161.