Combing rough set and RBF neural network for large-scale ship recognition in optical satellite images

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Chunyan, Lu^1 ; Huanxin, Zou^1 ; Hao, Sun^1 ; Shilin, Zhou^1

College of Electronic Science and Engineering, National University of Defense Technology, Changsha, China^1

关键词: Classification rates;    Maritime surveillance;    Optical remote sensing;    Optical satellite images;    RBF Neural Network;    Recognition features;    Ship recognition;    State-of-the-art methods;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012218/pdf
DOI  :  10.1088/1755-1315/17/1/012218

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Large scale ship recognition in optical remote sensing images is of great importance for many military applications. It aims to recognize the category information of the detected ships for effective maritime surveillance. The contributions of the paper can be summarized as follows: Firstly, based on the rough set theory, the common discernibility degree is used to compute the significance weight of each candidate feature and select valid recognition features automatically; Secondly, RBF neural network is constructed based on the selected recognition features. Experiments on recorded optical satellite images show the proposed method is effective and can get better classification rates at a higher speed than the state of the art methods.