Recognition and extraction of high-resolution satellite remote sensing image buildings based on deep learning

作     者：Zeng, Yifu Guo, Yi Li, Jiayi 

作者机构：Changsha Univ Coll Comp Engn & Appl Math Changsha Peoples R China Changsha Univ Hunan Prov Key Lab Ind Internet Technol & Secur Changsha Peoples R China South China Univ Technol Guangzhou Inst Micro Sci & Art SCUT Sch Design State Key Lab Subtrop Bldg Sci Guangzhou 510006 Guangdong Peoples R China Polytech Univ Turin Dept Control & Comp Engn I-10129 Turin Italy 

出 版 物：《NEURAL COMPUTING & APPLICATIONS》 (神经网络计算与应用)

年 卷 期：2022年第34卷第4期

页      面：2691-2706页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Changsha Municipal Natural Science Foundation [KQ2007084] Research Foundation of Education Bureau of Hunan Province, China [19B321] NSFC Guangdong philosophy and Social Science Planning Project [GD19YYS08] Guangdong University Youth Innovation Talent Project [:2020WQNCX001] 

主　　题：Deep convolutional neural network High-resolution remote sensing satellite Image recognition and processing Building feature extraction Principal component analysis Correction neural network model 

摘      要：Extracting and recognizing buildings from high-resolution remote sensing images faces many problems due to the complexity of the buildings on the surface. The purpose is to improve the recognition and extraction capabilities of remote sensing satellite images. The Gao Fen-2 (GF-2) high-resolution remote sensing satellite is taken as the research object. The deep convolutional neural network (CNN) serves as the core of image feature extraction, and PCA (principal component analysis) is adopted to reduce the dimensionality of the data. A correction neural network model, that is, boundary regulated network (BR-Net) is proposed. The features of remote sensing images are extracted through convolution, pooling, and classification. Different data collection models are utilized for comparative analysis to verify the performance of the proposed model. Results demonstrate that when using CNN to recognize remote sensing images, the recognition accuracy is much higher than that of traditional image recognition models, which can reach 95.3%. Compared with the newly researched models, the performance is improved by 15%, and the recognition speed is increased by 20%. When extracting buildings with higher accuracy, the proposed model can also ensure clear boundaries, thereby obtaining a complete building image. Therefore, using deep learning technology to identify and extract buildings from high-resolution satellite remote sensing images is of great significance for advancing the deep learning applications in image recognition.