An improved DeepLabv3+ lightweight network for remote-sensing image semantic segmentation

IF 5 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Complex & Intelligent Systems Pub Date : 2023-12-15 DOI:10.1007/s40747-023-01304-z

{"title":"An improved DeepLabv3+ lightweight network for remote-sensing image semantic segmentation","authors":"","doi":"10.1007/s40747-023-01304-z","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>To improve the accuracy of remote-sensing image semantic segmentation in complex scenario, an improved DeepLabv3+ lightweight neural network is proposed. Specifically, the lightweight network MobileNetv2 is used as the backbone network. In atrous spatial pyramid pooling (ASPP), to alleviate the gridding effect, the Dilated Convolution in original DeepLabv3+ network is replaced with the Hybrid Dilated Convolution (HDC) module. In addition, the traditional spatial mean pooling is replaced by the strip pooling module (SPN) to improve the local segmentation effect. In the decoder, to obtain the rich low-level target edge information, the ResNet50 residual network is added after the low-level feature fusion. To enhance the shallow semantic information, the efficient and lightweight Normalization-based Attention Module (NAM) is added to capture the feature information of small target objects. The results show that, under the INRIA Aerial Image Dataset and same parameter setting, the Mean Pixel Accuracy (MPA) and Mean Intersection over Union (MIoU) are generally best than DeepLabv3+ , U-Net, and PSP-Net, which are respectively improved by 1.22%, − 0.22%, and 2.22% and 2.17%, 1.35%, and 3.42%. Our proposed method has also a good performance on the small object segmentation and multi-object segmentation. What’s more, it significantly converges faster with fewer model parameters and stronger computing power while ensuring the segmentation effect. It is proved to be robust and can provide a methodological reference for high-precision remote-sensing image semantic segmentation.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"34 1","pages":""},"PeriodicalIF":5.0000,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Complex & Intelligent Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s40747-023-01304-z","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

To improve the accuracy of remote-sensing image semantic segmentation in complex scenario, an improved DeepLabv3+ lightweight neural network is proposed. Specifically, the lightweight network MobileNetv2 is used as the backbone network. In atrous spatial pyramid pooling (ASPP), to alleviate the gridding effect, the Dilated Convolution in original DeepLabv3+ network is replaced with the Hybrid Dilated Convolution (HDC) module. In addition, the traditional spatial mean pooling is replaced by the strip pooling module (SPN) to improve the local segmentation effect. In the decoder, to obtain the rich low-level target edge information, the ResNet50 residual network is added after the low-level feature fusion. To enhance the shallow semantic information, the efficient and lightweight Normalization-based Attention Module (NAM) is added to capture the feature information of small target objects. The results show that, under the INRIA Aerial Image Dataset and same parameter setting, the Mean Pixel Accuracy (MPA) and Mean Intersection over Union (MIoU) are generally best than DeepLabv3+ , U-Net, and PSP-Net, which are respectively improved by 1.22%, − 0.22%, and 2.22% and 2.17%, 1.35%, and 3.42%. Our proposed method has also a good performance on the small object segmentation and multi-object segmentation. What’s more, it significantly converges faster with fewer model parameters and stronger computing power while ensuring the segmentation effect. It is proved to be robust and can provide a methodological reference for high-precision remote-sensing image semantic segmentation.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

用于遥感图像语义分割的改进型 DeepLabv3+ 轻量级网络

摘要为了提高复杂场景下遥感图像语义分割的精度，提出了一种改进的DeepLabv3+轻量级神经网络。具体来说，使用轻量级网络MobileNetv2作为骨干网。在非均匀空间金字塔池(ASPP)中，为了缓解网格化效应，将原来DeepLabv3+网络中的Dilated Convolution替换为Hybrid Dilated Convolution (HDC)模块。此外，采用条带池化模块(SPN)代替传统的空间均值池化，提高了局部分割效果。在解码器中，为了获得丰富的底层目标边缘信息，在底层特征融合后加入ResNet50残差网络。为了增强浅层语义信息，加入了高效轻量级的基于归一化的注意力模块(NAM)来捕获小目标对象的特征信息。结果表明，在相同参数设置下，INRIA航拍图像数据集的平均像素精度(MPA)和平均交叉度(MIoU)总体上优于DeepLabv3+、U-Net和sp - net，分别提高了1.22%、- 0.22%、2.22%和2.17%、1.35%和3.42%。该方法在小目标分割和多目标分割方面也具有良好的性能。在保证分割效果的前提下，以更少的模型参数和更强的计算能力显著加快了收敛速度。结果表明，该方法具有较强的鲁棒性，可为高精度遥感图像语义分割提供方法参考。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Complex & Intelligent Systems COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-

CiteScore

9.60

自引率

10.30%

发文量

297

期刊介绍： Complex & Intelligent Systems aims to provide a forum for presenting and discussing novel approaches, tools and techniques meant for attaining a cross-fertilization between the broad fields of complex systems, computational simulation, and intelligent analytics and visualization. The transdisciplinary research that the journal focuses on will expand the boundaries of our understanding by investigating the principles and processes that underlie many of the most profound problems facing society today.