Information extraction from high resolution remote sensing image and parcel unit extraction based on features
Dongping Ming, Jiancheng Luo, Zhou Chenghu, Min Wang, Zheng Wu Jiang, Qiuxiao Chen, Zhanfeng Shen · Institute of Geographic Sciences and Natural Resources Research, CAS Institutional Repository · 2005
The advantages of remote sensing image process based on per-parcel are analyzed compared to the per-pixel. Based on huaman's visual mechanism and theory of the scale spatial, this paper designs the technique flow of multi-scale information extraction from high resolution remote sensing images based on features: rough classification-parcel unit extraction-expression of feature-intelligent illation-information extraction or target recognition. Especially, this paper presents the technical route of parcel unit extraction and gives an experiment with IKONOS and QUICKBIRD images. Experiment shows that the methods is convenient to integrating visual and environmental knowledge and can improve the level of automatization and intelligentization of remote sensing data process and application.