GPU-accelerated main road extraction in Polarimetric SAR images based on MRF

  title={GPU-accelerated main road extraction in Polarimetric SAR images based on MRF},
  author={Jianghua Cheng and Wenxia Ding and Xiangwei Zhu and Gui Gao},
  journal={IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society},
  • Jianghua Cheng, Wenxia Ding, Gui Gao
  • Published 1 October 2016
  • Environmental Science
  • IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society
Road extraction in SAR (Synthetic Aperture Radar) images is a difficult task because of speckle noise and various interferences. PolSAR (Polarimetric SAR) measures road's reflectivity in four polarizations and provides more information of road, which potentially indicates higher extraction performance than that in single-polarization SAR cases. However, the implementation of the traditional MRF (Markov Random Field) based road extraction method needs excessive computation operations, which is… 

Figures and Tables from this paper

Road extraction based on KFCM clustering and morphological operations
The experiment results show that, compared with the original image, the feature image can not only reduce the running time of the clustering process, but also improve the anti-interference ability of clustering and robustness in the subsequent morphological processing.
Effect of Threshold Values Used for Road Segments Detection in SAR Images on Road Network Generation
The effect of threshold values used for road segments detection in synthetic aperture radar images of road network generation is examined and software to apply and test all situations is developed.


Road extraction from high resolution dual-polarization SAR images over urban areas
This paper aims at the extraction of roads and road network from high-resolution dual-polarization synthetic aperture radar data over urban areas. According to the different features and applications
Automatic extraction of linear topographic objects, such as, roads, rivers, or power lines, is an important topic for topographic mapping. In case of roads, an automatic extraction from Synthetic
Detection of linear features in SAR images: application to road network extraction
The authors propose a two-step algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first
Linear Feature Detection in Polarimetric SAR Images
A novel method that processes the polarimetric synthetic aperture radar (Pol-SAR) images by combining the multiscale image analysis with polarIMetric information in a new fashion is proposed.
Automatic extraction of roads is a present research topic. Many applications like topographic mapping, navigation applications, or image registration could profit from such algorithms. This paper is
Road extraction in urban and rural environments exploiting a dual-band SAR system
It is shown, by comparing road network extraction using different processing chains, that fusion at the information level is the best way to combine the extraction from multi-frequency SAR data.
Scattering-model-based speckle filtering of polarimetric SAR data
A new concept in polarimetric synthetic aperture radar (POLSAR) speckle filtering that preserves the dominant scattering mechanism of each pixel is proposed and is effective inSpeckle reduction, while perfectly preserving strong point target signatures, and retains edges, linear, and curved features in the POLSAR data.
Glacier Snow Line Detection on a Polarimetric SAR Image
A new TSL detection method is proposed, in which the polarimetric SAR image is classified into three classes (wet snow, ice, and others) using support vector machines, and the boundary between wet snow and ice on the classification map is considered the TSL.
Edge Detector of SAR Images Using Gaussian-Gamma-Shaped Bi-Windows
  • P. Shui, Dong Cheng
  • Environmental Science
    IEEE Geoscience and Remote Sensing Letters
  • 2012
The experimental results to a synthetic SAR image show that the detector using GGS bi-windows attains better performance than the one using rectangle bi- windows, which can be verified by analyzing effective false maxima in the edge strength maps (ESMs).
Road Network Extraction in VHR SAR Images of Urban and Suburban Areas by Means of Class-Aided Feature-Level Fusion
This paper proposes to combine two road extractors from very high resolution synthetic aperture radar scenes: one more successful in rural areas and one explicitly designed for urban areas, using a rapid mapping filter for discriminating rural and urban scenes.