基于遥感影像的城市功能区识别  

Urban Functional Area Identification Based on Remote Sensing Images

作　　者：吴施瑶 曹华泽雨 封惠雯 董菁玮 田启川 WU Shiyao;CAO Huazeyu;FENG Huiwen;DONG Jingwei;TIAN Qichuan(School of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China;Beijing Key Laboratory of Intelligent Processing for Building Big Data,Beijing University of Civil Engineering and Arch lecture,Beijing 100044,China)

机构地区：[1]北京建筑大学电气与信息工程学院,北京100044 [2]北京建筑大学建筑大数据智能处理方法研究北京市重点实验室,北京100044

出　　处：《信息与电脑》2021年第10期169-172,共4页Information & Computer

基　　金：北京高等学校高水平人才交叉培养“实培计划”支持项目“可变形三维人脸模型设计及三维人脸识别研究”(项目编号:2020-23);“人脸照片比对系统”(项目编号:2020-4)。

摘　　要：针对城市遥感影像中的数据不均衡、功能区识别难度大的问题,笔者提出一种基于残差网络的城市功能区识别模型,通过搭建ResNet152预训练模型提取功能区遥感影像的深度特征,并对模型进行优化。在2019年"一带一路"国际大数据竞赛数据集上的实验结果表明,城市功能区识别算法有效,且其性能优于其他算法。Aiming at the problem of unbalanced data in urban remote sensing images and difficulty in identifying functional areas. A model of urban functional area recognition based on residual network is proposed. By building a ResNet152 pre-training model, the depth features of remote sensing images in functional areas are extracted and the model is optimized. The experimental results on the data set of the "One Belt One Road" international big data competition in 2019 show that the urban functional area identification algorithm is effective. And its performance is better than other algorithms.

关 键 词：城市功能区识别 残差网络 遥感影像 数据增强 

分 类 号：TU984[建筑科学—城市规划与设计] P208[天文地球—地图制图学与地理信息工程]