Remote Sensing (Aug 2016)

An Image Matching Algorithm Integrating Global SRTM and Image Segmentation for Multi-Source Satellite Imagery

  • Xiao Ling,
  • Yongjun Zhang,
  • Jinxin Xiong,
  • Xu Huang,
  • Zhipeng Chen

DOI
https://doi.org/10.3390/rs8080672
Journal volume & issue
Vol. 8, no. 8
p. 672

Abstract

Read online

This paper presents a novel image matching method for multi-source satellite images, which integrates global Shuttle Radar Topography Mission (SRTM) data and image segmentation to achieve robust and numerous correspondences. This method first generates the epipolar lines as a geometric constraint assisted by global SRTM data, after which the seed points are selected and matched. To produce more reliable matching results, a region segmentation-based matching propagation is proposed in this paper, whereby the region segmentations are extracted by image segmentation and are considered to be a spatial constraint. Moreover, a similarity measure integrating Distance, Angle and Normalized Cross-Correlation (DANCC), which considers geometric similarity and radiometric similarity, is introduced to find the optimal correspondences. Experiments using typical satellite images acquired from Resources Satellite-3 (ZY-3), Mapping Satellite-1, SPOT-5 and Google Earth demonstrated that the proposed method is able to produce reliable and accurate matching results.

Keywords