| 747 | 2 | 308 |
| 下载次数 | 被引频次 | 阅读次数 |
遥感图像的语义分割在城市规划和发展中发挥着至关重要的作用。如何对高复杂度、多类别的遥感影像进行自动、快速、有效的语义分割已成为研究的关键。现有的基于深度学习的分割方法存在模型复杂、计算成本较高等问题。提出一种端到端的轻量级多尺度特征提取分割网络(Multi-Scale Feature Extraction and Segmentation Network MSNET),旨在解决在高准确性情况下降低计算成本的问题。主干是基于轻量级网络MobileNetV2的编码网络和基于MSConv的解码网络构成的整个主干，其中MSConv是一种新的多尺度卷积模块。还提出了一种特征融合注意力模块(Feature Fusion Attention Module, MSAM)来有效地整合通道和空间维度上注意机制的全局信息。引入更加轻量化的局部重要性池化(Local Importance Pooling, LIP)代替普通池化操作以及添加了空洞空间卷积池化金字塔(Atrous Spatial Pyramid Pooling, ASPP)模块进一步提取丰富的特征。在公开数据集WHDLD上进行对比评估，F1达到83.12%,推理时间仅为0.007 4 s。
Abstract：Semantic segmentation of remote sensing images plays an important role in urban planning and development. How to perform automatic, fast and effective semantic segmentation for highly complex and multi-class remote sensing images has become the key of research. However, the existing segmentation methods based on deep learning have the problems of complex model and high computational cost. An end-to-end lightweight Multi-Scale Feature Extraction and Segmentation Network(MSNET) is proposed to reduce the computational cost in the case of high accuracy. Firstly, the backbone is composed of a coding network based on lightweight network MobileNetV2 and a decoding network based on MSConv. MSConv is a new multi-scale convolutional module. In addition, a Feature Fusion Attention Module(MSAM) is proposed to effectively integrate the global information of attention mechanisms in channel and spatial dimensions. Secondly, a more lightweight Local Importance Pooling(LIP) is introduced to replace the common pooling operation, and the Atrous Spatial Pyramid Pooling(ASPP) module is added to further extract rich features. Finally, the comparison evaluation on the public dataset WHDLD showed that F1 reaches 83.12% and the inference time is only 0.007 4 s.
[1] SHEN Y L,AI T H,CHEN H,et al.Multilevel Mapping from Remote Sensing Images:A Case Study of Urban Buildings[J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-16.
[2] 胥智杰，杨小兵，何灵敏，等.多尺度遥感语义分割网络[J].计算机工程与应用，2020,56(21):210-217.
[3] 黄鹏，郑淇，梁超.图像分割方法综述[J].武汉大学学报(理学版),2020,66(6):519-531.
[4] LV K,WANG W X,ZHOU Z,et al.An Improved Watershed Algorithm on Multi-directional Edge Detection for Road Extraction in Remote Images[J].International Journal of Innovative Computing,Information and Control,2022,18(3):851-866.
[5] JIN J H,ZHOU W J,YANG R W,et al.Edge Detection Guide Network for Semantic Segmentation of Remote-sensing Images[J].IEEE Geoscience and Remote Sensing Letters,2023,20:1-5.
[6] YAZID H,BASAH S N,RAHIM S A,et al.Performance Analysis of Entropy Thresholding for Successful Image Segmentation[J].Multimedia Tools and Applications,2022,81(5):6433-6450.
[7] LI Q H,GENG J B,SONG D Q,et al.Automatic Recognition of Erosion Area on the Slope of Tailings Dam Using Region Growing Segmentation Algorithm[J].Arabian Journal of Geosciences,2022,15(5):438.
[8] YU A Z,QUAN Y J,YU R,et al.Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data:A Survey[J].Remote Sensing,2023,15(20):4987.
[9] ALAM M,WANG J F,CONG G P,et al.Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images[J].Mobile Networks and Applications,2021,26:200-215.
[10] SRAVYA N,PRIYANKA,LAL S,et al.DPPNet:An Efficient and Robust Deep Learning Network for Land Cover Segmentation from High-resolution Satellite Images[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2022,7(1):128-139.
[11] SHEN Z R,LI X,XU S.RMNET:A Residual and Multi-scale Feature Fusion Network For High-resolution Image Semantic Segmentation[EB/OL].[2023-10-20].https://elib.bsu.by/bitstream/123456789/306208/1/101-106.pdf.
[12] ZHAO H S,QI X J,SHEN X Y,et al.ICNet for Real-time Semantic Segmentation on High-resolution Images[EB/OL].(2017-04-27)[2023-10-10].https://arxiv.org/abs/1704.08545.
[13] PASZKE A,CHAURASIA A,KIM S,et al.ENet:A Deep Neural Network Architecture for Real-time Semantic Segmentation[EB/OL].(2016-06-07)[2023-10-11].https://arxiv.org/abs/1606.02147.
[14] WU T Y,TANG S,ZHANG R,et al.CGNet:A Light-weight Context Guided Network for Semantic Segmentation[J].IEEE Transactions on Image Processing,2020,30:1169-1179.
[15] SANDLER M,HOWARD A,ZHU M L,et al.MobileNetV2:Inverted Residuals and Linear Bottlenecks[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:4510-4520.
[16] QIU X J.U-Net-ASPP:U-Net Based on Atrous Spatial Pyramid Pooling Model for Medical Image Segmentation in COVID-19[J].Journal of Applied Science and Engineering,2022,25(6):1015-1024.
[17] GAO Z T,WANG L M,WU G S.LIP:Local Importance-based Pooling[C]//2019 IEEE/CVF International Conference on Computer Vision.Seoul:IEEE,2019:3355-3364.
[18] WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module[C]//Proceedings of the European Conference on Computer Vision (ECCV).Munich:Springer,2018:3-19.
[19] LIU Z,MAO H Z,WU C Y,et al.A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022:11966-11976.
[20] SHAO Z F,ZHOU W X,DENG X Q,et al.Multilabel Remote Sensing Image Retrieval Based on Fully Convolutional Network[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:318-328.
基本信息:
中图分类号:TP751
引用信息:
[1]雷帮军,余楷,吴正平.一种轻量化多尺度遥感图像分割方法[J].无线电工程,2024,54(08):1928-1935.
基金信息:
国家自然科学基金(61871258); 水电工程智能视觉监测湖北省重点实验室建设(2019ZYYD007); 湖北省重点实验室开放基金(2018SDSJ05)~~
2024-03-02
2024-03-02
2024-03-02