Translator Disclaimer
28 October 2006 An automatic road segmentation algorithm using one-class SVM
Author Affiliations +
Proceedings Volume 6419, Geoinformatics 2006: Remotely Sensed Data and Information; 64191B (2006)
Event: Geoinformatics 2006: GNSS and Integrated Geospatial Applications, 2006, Wuhan, China
Automatic feature extraction for road information plays a central role in applications related to terrains. In this paper, we propose a new road extraction method using the one-class support vector machine (SVM). For a manually segmented seed road region, only a part of pixels are really road, some pixels locating on the sideway, shadows of the building, and the cars etc., are not really road pixels. The one-class SVM is used to estimate a decision function that takes the value +1 in a small feature region capturing most of the data points in the seed road area, and -1 elsewhere. Since the road pixels in the satellite image have the similar properties, such as the spectral feature in multi-spectral image, the novelty pixel is discriminated by the estimated decision function for road segmentation. Many computation experiments are undertaken on the IKONOS high resolution image. The results demonstrate that the proposed method is effective and has much higher computation efficiency than the standard pixel-based SVM classification method.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sheng Zheng, Jian Liu, Wenzhong Shi, and Guangxi Zhu "An automatic road segmentation algorithm using one-class SVM", Proc. SPIE 6419, Geoinformatics 2006: Remotely Sensed Data and Information, 64191B (28 October 2006);

Back to Top