Open AccessUrban House Detection Using SAM and SIFT on Hyperspectral Remote Sensing Images
Author(s) -
Cailing Wang,
Fan Yang,
Hongwei Wang,
Peng Guo,
Jiale Hou
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1237/3/032029
Subject(s) - hyperspectral imaging , scale invariant feature transform , remote sensing , artificial intelligence , computer science , computer vision , full spectral imaging , image resolution , pattern recognition (psychology) , spectral signature , multispectral image , geography , feature extraction
The detection and identification of urban object targets have always been a research hotspot. In recent years, the spectral, spatial and temporal resolution of remote sensing images have been continuously increased, making hyperspectral remote sensing images widely used in urban object recognition. We proposed a new method for urban house detection by combining the spectral mapping results and spatial features. Firstly, the target spectral information is used to distinguish the targets in spectral domain. Then, the spatial SIFT feature algorithm is used on the results of spectral mapping, which can improve the accuracy of urban housing target recognition.