MSSINet: Real-Time Segmentation Based on Multi-Scale Strip Integration

IF 2.3 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Lin Wang;Fenghua Zhu;Hui Zhang;Gang Xiong;Yunhu Huang;Dewang Chen
{"title":"MSSINet: Real-Time Segmentation Based on Multi-Scale Strip Integration","authors":"Lin Wang;Fenghua Zhu;Hui Zhang;Gang Xiong;Yunhu Huang;Dewang Chen","doi":"10.1109/JRFID.2024.3389088","DOIUrl":null,"url":null,"abstract":"Semantic segmentation plays a fundamental role in computer vision, underpinning applications such as autonomous driving and scene analysis. Although dual-branch networks have marked advancements in accuracy and processing speed, they falter in the context extraction phase within the low-resolution branch. Traditionally, square pooling is used at this juncture, leading to the oversight of stripe-shaped contextual information. In response, we introduce a novel architecture based on a deep aggregation pyramid, engineered for both real-time processing and precise segmentation. Central to our approach is a pioneering contextual information extractor designed to expand the effective receptive fields and fuse multi-scale context from low-resolution feature maps. Additionally, we have developed a feature fusion module to enhance the integration and differentiation of high-level semantic information across branches. To further refine the fidelity of segmentation, we implement dual deep supervisions within the high-resolution branchs intermediate layer, concentrating on boundary delineation and global features to enrich spatial detail capture. Our comprehensive experimental analysis, conducted on the Cityscapes and CamVid datasets, affirms MSSINets superior performance, showcasing its competitiveness against existing leading methodologies across a variety of scenarios.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"241-251"},"PeriodicalIF":2.3000,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE journal of radio frequency identification","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10500690/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Semantic segmentation plays a fundamental role in computer vision, underpinning applications such as autonomous driving and scene analysis. Although dual-branch networks have marked advancements in accuracy and processing speed, they falter in the context extraction phase within the low-resolution branch. Traditionally, square pooling is used at this juncture, leading to the oversight of stripe-shaped contextual information. In response, we introduce a novel architecture based on a deep aggregation pyramid, engineered for both real-time processing and precise segmentation. Central to our approach is a pioneering contextual information extractor designed to expand the effective receptive fields and fuse multi-scale context from low-resolution feature maps. Additionally, we have developed a feature fusion module to enhance the integration and differentiation of high-level semantic information across branches. To further refine the fidelity of segmentation, we implement dual deep supervisions within the high-resolution branchs intermediate layer, concentrating on boundary delineation and global features to enrich spatial detail capture. Our comprehensive experimental analysis, conducted on the Cityscapes and CamVid datasets, affirms MSSINets superior performance, showcasing its competitiveness against existing leading methodologies across a variety of scenarios.
MSSINet:基于多尺度条带集成的实时分段技术
语义分割在计算机视觉中扮演着重要角色,是自动驾驶和场景分析等应用的基础。虽然双分支网络在精确度和处理速度上有显著进步,但在低分辨率分支的上下文提取阶段却出现了问题。传统上,在这一关头使用的是方形池,导致条纹状上下文信息被忽略。为此,我们引入了一种基于深度聚合金字塔的新型架构,可实现实时处理和精确分割。我们方法的核心是开创性的语境信息提取器,旨在扩大有效感受野,并从低分辨率特征图中融合多尺度语境。此外,我们还开发了一个特征融合模块,以加强跨分支的高级语义信息的整合和区分。为了进一步提高分割的保真度,我们在高分辨率分支中间层实施了双重深度监督,集中于边界划分和全局特征,以丰富空间细节捕捉。我们在 Cityscapes 和 CamVid 数据集上进行了全面的实验分析,证实了 MSSINets 的卓越性能,展示了它在各种场景下与现有领先方法的竞争力。
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 求助全文
来源期刊
CiteScore
5.70
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信