%0 Journal Article
%T 基于锯齿空洞空间卷积池化结构的高分辨率遥感影像建筑物提取<br>High-Resolution Remote Sensing Image Building Extraction Based on Dentate Atrous Spatial Pyramid Pooling Structure
%A 陈小雨
%A 石彦坡
%A 吴少璇
%A 刘冰雨
%A 贾永红
%J Computer Science and Application
%P 558-563
%@ 2161-881X
%D 2025
%I Hans Publishing
%R 10.12677/csa.2025.155128
%X 尽管高分辨率遥感影像地物纹理清晰并且光谱异质性高&#65292;但影像中的房屋建筑存在复杂多样性问题&#65292;这导致应用卷积神经网络AASPP模型、DenseASPP模型分别进行提取建筑物时&#65292;较易产生误提取和遗漏提取。因此&#65292;本文提出了一种基于空洞金字塔卷积结构DentateASPP的高分高分辨率遥感影像建筑物提取方法&#65292;采用现有建筑物数据集和重庆高分2号影像进行试验&#65292;与AASPP和DenseASPP模型建筑物提取的结果相比&#65292;实验表明&#65292;DentateASPP模型提取建筑物误提取和漏提取最少&#65292;效果最优。<br>Despite the clear texture and high spectral heterogeneity of ground objects in high-resolution remote sensing images, there is a complex and diverse problem with the buildings in the images, which leads to errors and omissions when using convolutional neural network AASPP model and DenseASPP model to extract buildings separately. Therefore, a high-resolution remote sensing image building extraction method based on DentateASPP (Dentate Atrous Spatial pyramid pooling) are proposed. The existing building dataset and high-resolution GF-2 images were used for experiments. Compared with the results of building extraction using AASPP and DenseASPP models, the experiments show that the DentateASPP model has the least number of errors and omissions in extracting buildings, and the best performance.
%K 建筑物提取&#65292
%K 高分辨率遥感影像&#65292
%K 卷积神经网络&#65292
%K 空洞卷积池化结构<br>Building Extraction
%K High Resolution Remote Sensing Images
%K Convolutional Neural Network
%K Hollow Convolutional Pooling Structure
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=114166