| 419 | 2 | 342 |
| 下载次数 | 被引频次 | 阅读次数 |
针对遥感图像建筑物的轮廓分割不完整、边界分割模糊和阴影干扰等导致的错误分割问题，提出一种基于VGG16的卷积块注意力深度可分离卷积U-Net网络(VGG16 Convolutional Block Attention and Deep Separable Convolution U-Net, VCDG-UNet)。为对建筑物特征进行提取，编码器部分模型以具有强大特征提取能力的VGG16作为骨干网络；解码器部分用深度可分离卷积代替普通卷积来减少参数量并融合不同尺度的特征；引入卷积块注意力模块(Convolutional Block Attention Module, CBAM)加入跳跃连接中，使其更有效地从不同尺度的图像中提取上下文信息并提高其对重要区域的关注度；为解决网络训练过程中的梯度消失问题，使用了高斯误差线性单元(Gaussian Error Linear Unit, GELU)。实验结果显示，改进后的网络在WHU和INRIA数据集上的平均交并比(mean Intersection over Union, mIoU)和F1-score分别达到了94.20%、96.83%和89.69%、94.51%,相较于基础模型高出了1.59%、0.76%和2.8%、1.59%。
Abstract：To solve the problem of incorrect segmentation caused by incomplete contour segmentation, blurred boundary segmentation, and shadow interference in remote sensing building image, an improved end-to-end convolutional neural network VGG16 Convolutional Block Attention and Deep Separable Convolution U-Net(VCDG-UNet) based on the U-Net encoder-decoder structure is proposed. In the encoder part, the model uses the VGG16 backbone network with strong feature extraction capability to extract building features. In the decoder part, replace the regular convolution with depthwise separable convolution to reduce the number of parameters and fuse features of different scales. The Convolutional Block Attention Module(CBAM) is introduced into the skip connections to more effectively extract context information from multi-scale images and increase the attention on important regions. The Gaussian Error Linear Unit(GELU) activation method is used to replace the RELU activation method to solve the problem of vanishing gradients during the network training. According to the experimental results, the improved network achieves mIoU and F1-score of 94.20%, 96.83% and 89.69%, 94.51% on the WHU and INRIA datasets respectively, which are 1.59%, 0.76% and 2.8%, 1.59% higher than the baseline model.
[1] YIN J C,WU F,QI Y Y.Vector Mapping Method for Buildings in Remote Sensing Images Based on Joint Semantic-Geometric Learning[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2023,16:9067-9076.
[2] 郑泰皓，王庆涛，李家国，等.基于深度学习的高分六号影像水体自动提取[J].科学技术与工程，2021,21(4):1459-1470.
[3] ZHAO W F,NA J M,LI M M,et al.Rotation-aware Building Instance Segmentation from High-resolution Remote Sensing Images[J].IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
[4] 熊风光，董彪，张鑫，等.基于改进Mask RCNN算法的遥感建筑物检测[J].计算机工程与设计，2023,44(1):218-223.
[5] CHE Z H,SHEN L,HUO L Z,et al.MAFF-HRNet:Multi-attention Feature Fusion HRNet for Building Segmentation in Remote Sensing Images[J].Remote Sensing,2023,15(5):1382.
[6] LUO L,LI P P,YAN X S.Deep Learning-based Building Extraction from Remote Sensing Images:A Comprehensive Review[J].Energies,2021,14(23):7982.
[7] CHEN L C C,ZHU Y K,PAPANDREOU G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV).Munich:Springer,2018:833-851.
[8] SHELHAMER E,LONG J,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[9] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]// Medical Image Computing and Computer:Assisted Intervention.Munich:Springer,2015:234-241.
[10] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.UNet++:A Nested U-Net Architecture for Medical Image Segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada:Springer,2018:3-11.
[11] LIU Y H,GROSS L,LI Z Q,et al.Automatic Building Extraction on High-resolution Remote Sensing Imagery Using Deep Convolutional Encoder-Decoder with Spatial Pyramid Pooling[J].IEEE Access,2019,7:128774-128786.
[12] QIN X B,ZHANG Z C,HUANG C Y,et al.U2-Net:Going Deeper with Nested U-structure for Salient Object Detection[J].Pattern Recognition,2020,106:107404.
[13] CUI X N,WANG Q C,DAI J P,et al.Intelligent Crack Detection Based on Attention Mechanism in Convolution Neural Network[J].Advances in Structural Engineering,2021,24(9):1859-1868.
[14] YU M Y,CHEN X X,ZHANG W Z,et al.AGs-Unet:Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network[J].Sensors,2022,22(8):2932.
[15] WANG Y,GU L J,JIANG T,et al.MDE-UNet:A Multitask Deformable UNet Combined Enhancement Network for Farmland Boundary Segmentation[J].IEEE Geoscience and Remote Sensing Letters,2023,20:1-5.
[16] FU L X,CHEN J B,WANG Z Y,et al.MSFANet:Multi-scale Fusion Attention Network for Mangrove Remote Sensing lmage Segmentation Using Pattern Recognition[J].Journal of Cloud Computing,2024,13(1):1-20.
[17] 周耀威，孔令军，李慧刚，等.基于通道注意力机制与金字塔池化的包裹破损检测算法[J].无线电工程，2023,53(11):2626-2634.
[18] CHEN J,XIA M,WANG D H,et al.Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images[J].Remote Sensing,2023,15(6):1536.
[19] 陈燕，陆嘉豪，胡小春，等.基于VGG-UNet的食用菌菌丝体表型参数自动测量方法[J].农业机械学报，2024,55(1):233-240.
[20] 董乙杉，郭靖圆，李明泽，等.基于反向瓶颈和LCBAM设计的X光违禁品检测[J].计算机科学与探索，2024,18(5):1259-1270.
[21] 杨阳，杨帅，闫敏，等.基于UDD-YOLO的边缘端绝缘子放电严重程度评估算法[J].电子测量与仪器学报，2024,38(1):219-227.
[22] 杨建宇，周振旭，杜贞容，等.基于SegNet语义模型的高分辨率遥感影像农村建设用地提取[J].农业工程学报，2019,35(5):251-258.
[23] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[24] CHAURASIA A,CULURCIELLO E.LinkNet:Exploiting Encoder Representations for Efficient Semantic Segmentation[C]//2017 IEEE Visual Communications and Image Processing (VCIP).St.Petersburg:IEEE,2017:1-4.
[25] DUAN X J,SUN Y Y,WANG J M.ECA-UNet for Coronary Artery Segmentation and Three-dimensional Reconstruction[J].Signal,Image and Video Processing,2022,17:783-789.
[26] 季长清，高志勇，秦静，等.基于Transformer的航空目标检测算法[J].无线电工程，2023,53(12):2811-2819.
基本信息:
中图分类号:TP751
引用信息:
[1]郑海洋,于淼,于晓鹏.VCDG-UNet模型在遥感图像分割中的应用[J].无线电工程,2025,55(01):94-104.
基金信息:
吉林省科技发展计划项目(YDZJ202301ZYTS285)~~
2024-08-21
2024-08-21
2024-08-21