Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 741-747, 2016
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/741/2016/
doi:10.5194/isprs-archives-XLI-B3-741-2016
 
10 Jun 2016
POOR TEXTURAL IMAGE MATCHING BASED ON GRAPH THEORY
Shiyu Chen1, Xiuxiao Yuan1,2, Wei Yuan1,3, and Yang Cai1 1School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2Collaborative Innovation Center for Geospatial Technology, Wuhan University, Wuhan 430079, China
3Center for Spatial Information Science, University of Tokyo, Kashiwa 277-8568, Japan
Keywords: Poor Textural Image, Image Matching, Graph Matching, Affinity Tensor, Power Iteration Algorithm Abstract. Image matching lies at the heart of photogrammetry and computer vision. For poor textural images, the matching result is affected by low contrast, repetitive patterns, discontinuity or occlusion, few or homogeneous textures. Recently, graph matching became popular for its integration of geometric and radiometric information. Focused on poor textural image matching problem, it is proposed an edge-weight strategy to improve graph matching algorithm. A series of experiments have been conducted including 4 typical landscapes: Forest, desert, farmland, and urban areas. And it is experimentally found that our new algorithm achieves better performance. Compared to SIFT, doubled corresponding points were acquired, and the overall recall rate reached up to 68%, which verifies the feasibility and effectiveness of the algorithm.
Conference paper (PDF, 1062 KB)


Citation: Chen, S., Yuan, X., Yuan, W., and Cai, Y.: POOR TEXTURAL IMAGE MATCHING BASED ON GRAPH THEORY, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 741-747, doi:10.5194/isprs-archives-XLI-B3-741-2016, 2016.

BibTeX EndNote Reference Manager XML