卷积神经网络滑窗识别结合语义推理的城市功能区分类  

Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning

作　　者：王严 刘万军[2] 谭亚丽 李玉[1] WANG Yan;LIU Wanjun;TAN Yali;LI Yu(School of Geomatics,Liaoning Technical University,Fuxin 123000,China;School of Software,Liaoning Technical University,Huludao 125000,China)

机构地区：[1]辽宁工程技术大学测绘与地理科学学院,辽宁阜新123000 [2]辽宁工程技术大学软件学院,辽宁葫芦岛125000

出　　处：《武汉大学学报（信息科学版）》2023年第6期950-959,共10页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(41801368);辽宁省教育厅重点项目(LJ2020ZD003);辽宁省教育厅科研经费项目(LJKZ0350)。

摘　　要：目前基于遥感图像的城市功能区分类方法通常采用光谱特征解译、兴趣点数据辅助、评价策略优化等方式,依赖大量人工操作,并借助遥感图像外的其他信息源。为了解决以上问题,提出利用卷积神经网络进行滑窗识别,提取图像语义标签,结合语义推理机制实现城市功能区分类的滑窗-推理方法。首先,建立两级城市功能区分类,以二级城市功能区为标识标注训练样本,并以此训练卷积神经网络作为识别器;然后,设计有重叠的滑窗识别模式,使用识别器辨识滑窗区域内图像块的二级城市功能区类型;最后,提出一个带权重的打分机制,作为语义推理方式,语义推理对象为全部识别结果,确定各图像块的一级城市功能区类型,实现遥感图像城市功能区分类。实验使用模拟图像和高分辨率遥感图像,两种图像的总分类精度分别可达94.50%、92.04%。滑窗-推理方法旨在通过语义推理处理滑窗识别产生的多语义标签,根据多语义标签确定对象的真实城市功能区。实验结果表明,所提方法无需辅助信息,直接利用遥感图像进行城市功能区分类是可行和有效的。Objectives:Although remote sensing image is one of the main data sources for the classification of urban functional areas,it is rare to use remote sensing images to classify urban functional areas and extract their attribute information.At present,the classification methods of urban functional areas based on remote sensing images usually need manual interpretation,point of interest data assistance,information questionnaire survey and so on.This kind of method not only needs a lot of manual operation,but also needs other external information sources except remote sensing images.Methods:In order to solve the above problems,a sliding window-reasoning method for urban functional area classification is proposed by using convolutional neural network(CNN) to identify sliding window,extract image semantic tags,and combine semantic reasoning mechanism,which can quickly realize urban functional area classification only by remote sensing images.First,a two-level classification table of urban functional areas is established,and the training samples are marked with the second-level urban functional areas,and the training CNN is used as the recognizer.Second,using the designed overlapping sliding window recognition pattern,the trained recognizer is used to identify the types of features in the sliding window area,and to determine the type of urban functional area.Finally,a weighted scoring mechanism is designed as the implementation of semantic reasoning,and the semantic reasoning objects are all the recognition results.And,the type of urban functional areas of each region is determined,and the urban functional areas of large-scale remote sensing images are classified.Results:Using simulated images and high-resolution remote sensing image experiments,the total classification accuracy of simulated image experiments based on confusion matrix can reach 94.50%,and the total classification accuracy of real remote sensing image experiments based on confusion matrix can reach 92.04%.Conclusions:The purpose of the sliding window-reaso

关 键 词：城市功能区 图像分类 卷积神经网络 滑窗识别 语义推理 投票机制 

分 类 号：P237[天文地球—摄影测量与遥感]