基于深度学习的高分遥感图像建筑物识别  

Building Recognition of High-Resolution Remote Sensing Images Based on Deep Learning

作　　者：李成范 孟令奎[1] 刘学锋[3] LI Chengfan;MENG Lingkui;LIU Xuefeng(Key Laboratory of National Geographic Census and Monitoring,Ministry of Natural Resources,Wuhan University,Wuhan 430079,Hubei,China;School of Computer Engineering and Science,Shanghai University,Shanghai 200444,China;School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China Received:2023-03-21 Published:2024-06-06)

机构地区：[1]武汉大学自然资源部地理国情监测重点实验室,湖北武汉430079 [2]上海大学计算机工程与科学学院,上海200444 [3]上海大学通信与信息工程学院,上海200444

出　　处：《应用科学学报》2024年第3期375-387,共13页Journal of Applied Sciences

基　　金：上海市自然科学基金(No.22ZR1423200);自然资源部地理国情监测重点实验室开放基金(No.2022NGCM12);上海市科技创新行动计划项目(No.21142202400);东华理工大学江西省数字国土重点实验室开放课题(No.DLLJ202103)资助。

摘　　要：该文面向高分遥感图像建筑物深度学习检测与识别的具体需求,在归纳和分析现有深度学习与建筑物提取方法的基础上,重点探讨了高分遥感图像建筑物深度学习识别方法和深度学习识别系统,并探讨了未来可能的研究方向。所提方法将为高分遥感图像深度学习目标检测中样本库和遥感数据库的建设提供参考,为利用深度学习开展多尺度、多源高分遥感建筑物检测与识别提供支持。This paper focuses on deep learning methods for detection and recognition of the buildings in the high-resolution remote sensing images.It provides a summary and analysis of the existing deep learning and building extraction methods and highlights future research directions.The study aims to contribute to the construction of sample libraries and remote sensing databases for deep learning-based target detection in high-resolution remote sensing images.This study can provide a reference for the construction of sample libraries and remote sensing databases for the deep learning-based target detection of high-resolution remote sensing images.It also supports the building detection and recognition by deep learning in multi-scale and multi-source high-resolution remote sensing.

关 键 词：建筑物识别 高分遥感图像 卷积神经网络 样本集 数据集 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]