An automatic road segmentation algorithm using one-class SVM

Sheng Zheng, Jian Liu, Wen Zhong Shi, Guangxi Zhu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)


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.
Original languageEnglish
Title of host publicationGeoinformatics 2006
Subtitle of host publicationRemotely Sensed Data and Information
Publication statusPublished - 1 Dec 2006
EventGeoinformatics 2006: Remotely Sensed Data and Information - Wuhan, China
Duration: 28 Oct 200629 Oct 2006


ConferenceGeoinformatics 2006: Remotely Sensed Data and Information


  • Image segmentation
  • One-class support vector machine (SVM)
  • Pixel-based method
  • Road extraction

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'An automatic road segmentation algorithm using one-class SVM'. Together they form a unique fingerprint.

Cite this