Scene classification of remote sensing images based on hierarchical sparse coding

The Journal of Engineering

He Jie²  Xu Jiaqing³  Liu Hongjun⁴  Lv Qi⁵ 

[1] Imaging Medicine , Army Medical University , Chongqing , People'College of Biomedical Engineering &School of Computer , National University of Defense Technology , Changsha , People'Unit 31104 of PLA , Nanjing , People's Republic of China

关键词: scene classification accuracy;    optical remote sensing images;    hierarchical sparse coding;    sensing image scene classification;    remote sensing image analysis;    scene classification method;    multipath sparse coding;   

DOI  :  10.1049/joe.2018.8268

学科分类：工程和技术（综合）

来源: IET

【 摘 要 】

Remote sensing image scene classification is an important method for remote sensing image analysis and interpretation and plays an important role in civil and military fields. In this study, a scene classification method of remote sensing images based on hierarchical sparse coding is proposed. This method is essentially a kind of multi-layer, multi-scale, and multi-path sparse coding. It can extract features of optical remote sensing images more effectively, so that the features of the remote sensing images can be represented more sufficiently. The obtained codes are further used for spatial pyramid pooling (SPP) operation, and the corresponding SPP representation is obtained. SPP representations in different paths are combined and outputted to the support vector machine classifier, and the final classification results are obtained. Experiments on two data sets show that the proposed method can obtain better scene classification accuracy.

【 授权许可】

CC BY