The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XL-4/W3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-4/W3, 117–121, 2013
https://doi.org/10.5194/isprsarchives-XL-4-W3-117-2013
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-4/W3, 117–121, 2013
https://doi.org/10.5194/isprsarchives-XL-4-W3-117-2013

  13 Nov 2013

13 Nov 2013

Information Extraction of High-Resolution Remotely Sensed Image based on Multiresolution Segmentation

P. Shao, G.-D. Yang, X.-F. Niu, X.-P. Zhang, F.-L. Zhan, and T.-Q. Tang P. Shao et al.
  • College of Geoexploration Science and Technology, Jilin University, Changchun City, Jilin Province, 130026, China

Keywords: Edge-detection, Object-oriented. Multiresolution segmentation, Spectral features, Geometrical features, Confusion matrix

Abstract. The principle of multiresolution segmentation was represented in detail in this study, and the canny algorithm was applied for edge-detection of remotely sensed image based on this principle. The target image was divided into regions based on objectoriented multiresolution segmentation and edge-detection. Further, object hierarchy was created, and a series of features (water bodies, vegetation, roads, residential areas, bare land and other information) were extracted by the spectral and geometrical features. The results indicates that edge-detection make a positive effect on multiresolution segmentation, and overall accuracy of information extraction reaches to 94.6% through confusion matrix.