An object-oriented classification method of high resolution imagery based on improved AdaTree

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Xiaohe, Zhang^1 ; Liang, Zhai^1 ; Jixian, Zhang^1 ; Huiyong, Sang^1

Key Laboratory of Geo-informatics of NASG, Chinese Academy of Surveying and Mapping, Beijing, China^1

关键词: Automatic classification;    Classification rules;    High resolution imagery;    High spatial resolution;    Kappa coefficient;    Number of samples;    Object oriented classification;    Remote sensing images;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012212/pdf
DOI  :  10.1088/1755-1315/17/1/012212

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

With the popularity of the application using high spatial resolution remote sensing image, more and more studies paid attention to object-oriented classification on image segmentation as well as automatic classification after image segmentation. This paper proposed a fast method of object-oriented automatic classification. First, edge-based or FNEA-based segmentation was used to identify image objects and the values of most suitable attributes of image objects for classification were calculated. Then a certain number of samples from the image objects were selected as training data for improved AdaTree algorithm to get classification rules. Finally, the image objects could be classified easily using these rules. In the AdaTree, we mainly modified the final hypothesis to get classification rules. In the experiment with WorldView2 image, the result of the method based on AdaTree showed obvious accuracy and efficient improvement compared with the method based on SVM with the kappa coefficient achieving 0.9242.