电子科技2026，Vol.39Issue(6)：46-53,8.DOI:10.16180/j.cnki.issn1007-7820.2026.06.006
基于改进UNet的轻量级实时语义分割方法
Lightweight Real-Time Semantic Segmentation Method Based on Improved UNet
摘要
Abstract
Semantic segmentation plays a significant role in the field of autonomous driving,enabling autono-mous vehicles to parse rich environmental information from road images.However,traditional semantic segmentation techniques have a relatively large computational burden and a high demand for hardware memory.To solve this prob-lem,a lightweight real-time semantic segmentation method based on improved UNet(Convolutional Networks for Bio-medical Image Segmentation)is proposed.An innovative LDIB(Lightweight Double-branch Interactive Bottleneck)is integrated in the backbone network of the model,thereby significantly improving the accuracy of the model for target segmentation.LDIB integrates depthwise separable convolution technology with the feature fusion strategy of element-by-element multiplication,which not only effectively reduces the number of parameters of the model but also enhances the fusion effect of features.The experimental results show that the proposed model can quickly and accurately seg-ment different targets in road scenarios with dense targets.The mIoU(mean Intersection-over-Union)ratio in the open-source dataset Cityscapes is 71.5%,and the mIoU in CamVid is 69.49%.关键词
自动驾驶/深度学习/UNet/语义分割/轻量级网络/特征融合/深度可分离卷积/密集目标分割Key words
autonomous driving/deep learning/UNet/semantic segmentation/lightweight network/feature fusion/depth separable convolution/intensive target segmentation分类
信息技术与安全科学引用本文复制引用
邱杨杨,高广谓..基于改进UNet的轻量级实时语义分割方法[J].电子科技,2026,39(6):46-53,8.基金项目
国家自然科学基金(61972212) （61972212）
江苏省自然科学基金(BK20190089) （BK20190089）
江苏省"六大人才高峰"项目(RJFW-011) （RJFW-011）
苏州大学江苏省计算机信息处理技术重点实验室开放课题(KJS1840)National Natural Science Foundation of China(61972212) （KJS1840）
Natural Science Foundation of Jiangsu(BK20190089) （BK20190089）
Jiangsu Province"Six Talent Summits"Programs(RJFW-011) （RJFW-011）
Open Subjects of Jiangsu Key Laboratory of Computer Information Processing Technology,Soochow University(KJS1840) （KJS1840）
