基于改进D-LinkNet模型的高分遥感影像道路提取研究

doi:10.19678/j.issn.1000-3428.0058977

计算机工程 ›› 2021, Vol. 47 ›› Issue (9): 288-296. doi: 10.19678/j.issn.1000-3428.0058977

基于改进D-LinkNet模型的高分遥感影像道路提取研究

张立恒¹, 王浩¹, 薛博维², 何立明¹, 吕悦¹

1. 长安大学信息工程学院, 西安 710064;
2. 西安中科星图空间数据技术有限公司, 西安 710000

收稿日期:2020-07-17 修回日期:2020-09-03 发布日期:2020-09-09
作者简介:张立恒(1995-),男,硕士,主研方向为遥感影像处理、模式识别;王浩、薛博维,硕士;何立明,副教授、博士;吕悦,硕士。
基金资助:
中央高校基本科研业务费专项资金（300102249302）。

Research of Road Extraction from High-Resolution Remote Sensing Images Based on Improved D-LinkNet Model

ZHANG Liheng¹, WANG Hao¹, XUE Bowei², HE Liming¹, Lü Yue¹

1. School of Information Engineering, Chang'an University, Xi'an 710064, China;
2. Xi'an Zhongkexingtu Space Data Technology Co., Ltd, Xi'an 710000, China

Received:2020-07-17 Revised:2020-09-03 Published:2020-09-09

摘要/Abstract

摘要： 针对高分影像中的道路信息易受植被阴影、高楼建筑物、河流等非道路信息干扰的问题，提出一种高分遥感影像道路提取模型。在中心区域引入channel-spatial双注意力机制捕获道路信息的全局特征依赖，并基于原始模型DICE+BCE损失函数，构建新型的超参数权重损失来优化网络模型中参数迭代的误差，改善道路分割的精度。按照1：1、2：1、3：1、4：1、5：1这5种比值设定超参数权重比，通过调节超参数权值比获取模型最佳的道路分割性能。实验结果表明，与FCN-8s、U-Net等模型相比，改进D-LinkNet模型道路分割效果明显提升，能有效地规避因非道路因素对道路提取干扰而导致的“虚检”“漏检”“误检”的现象。

关键词: 高分遥感影像, 双注意力机制, 全局特征依赖, 超参数权重损失, 道路分割

Abstract: The road information in high-resolution images tend to be disturbed by non-road information such as vegetation shadows, tall buildings and rivers.To address the problem, an improved model is proposed to extract road parts from high-resolution remote sensing images.For the construction of the model, a channel-spatial bi-attention mechanism is introduced to capture the global characteristic dependence of road information in the central region.Then the new hyperparameter weight loss is constructed based on the DICE+BCE loss of the original model to reduce the error of the parameter iteration in the network model and improve the accuracy of road segmentation.The hyperparameter weight ratio is successively set to 1:1, 2:1, 3:1, 4:1 and 5:1, and the best road segmentation performance of the model is obtained based on the adjustment of the hyperparameter weight ratio. The experimental results show that compared with FCN-8s, U-Net and other models, the improved D-LinkNet model delivers a significant improvement in road segmentation effect.The algorithm can effectively avoid false detection and missed detection that are caused by interference of non-road factors in road extraction.

Key words: high-resolution remote sensing image, biattention mechanism, global characteristic dependence, hyperparameter weight loss, road segmentation

中图分类号:

TP391

张立恒, 王浩, 薛博维, 何立明, 吕悦. 基于改进D-LinkNet模型的高分遥感影像道路提取研究[J]. 计算机工程, 2021, 47(9): 288-296.

ZHANG Liheng, WANG Hao, XUE Bowei, HE Liming, Lü Yue. Research of Road Extraction from High-Resolution Remote Sensing Images Based on Improved D-LinkNet Model[J]. Computer Engineering, 2021, 47(9): 288-296.

https://www.ecice06.com/CN/Y2021/V47/I9/288

图/表 12

20210917192948

20210917192952

20210917192955

20210917192959

20210917193003

20210917193007

20210917193012

20210917193015

20210917193019

20210917193023

20210917193026

20210917193031

参考文献

[1] 熊思, 李磊民, 黄玉清.基于小波变换和K-means的非结构化道路检测[J].计算机工程, 2014, 40(2):158-161. XIONG S, LI L M, HUANG Y Q.Unstructured road detection based on wavelet transform and K-means[J].Computer Engineering, 2014, 40(2):158-161.(in Chinese)
[2] WANG W, YANG N, ZHABF Y, et al.A review of road extraction from remote sensing images[J].Journal of Traffic and Transportation Engineering, 2016, 3(3):271-282.
[3] HEROLD M, ROBERTS D.Spectral characteristics of asphalt road aging and deterioration:implications for remote-sensing applications[J].Applied Optics, 2005, 44(20):4327-4334.
[4] XU R, TAO Y, LU Z, et al.Attention-mechanism-containing neural networks for high-resolution remote sensing image classification[J].Remote Sensing, 2018, 10(10):1602-1611.
[5] 王明丽, 王刚, 郭晓新, 等.基于跨层复制连接卷积神经网络的遥感图像融合[J].吉林大学学报(理学版), 2020, 58(4):913-922. WANG M L, WANG G, GUO X X, et al.Remote sensing image fusion based on cross-layer copy connection convolutional neural network[J].Journal of Jilin University Science Edition, 2020, 58(4):913-922.(in Chinese)
[6] ZAIMBASHI A, LI J.Tunable adaptive target detection with kernels in colocated MIMO radar[J].IEEE Transactions on Signal Processing, 2020, 1(1):1-15.
[7] CORONA E, ALENY G, GABAS A, et al.Active garment recognition and target grasping point detection using deep learning[J].Pattern Recognition, 2018, 74:629-641.
[8] LI P, ZANG Y, WANG C.Road network extraction via deep learning and line integral convolution[C]//Proceedings of the 36th IEEE International Geoscience and Remote Sensing Symposium.Washington D.C., USA:IEEE Press, 2016:1599-1602.
[9] XIA W, ZHONG N, GENG D, et al.A weakly supervised road extraction approach via deep convolutional nets based image segmentation[C]//Proceedings of IEEE International Workshop on Remote Sensing with Intelligent Processing.Washington D.C., USA:IEEE Press, 2017:1-5.
[10] 董培, 石繁槐.基于小型无人机航拍图像的道路检测方法[J].计算机工程, 2015, 41(12):36-39. DONG P, SHI F K.A road detection method based on small UAV aerial image[J].Computer Engineering, 2015, 41(12):36-39.(in Chinese)
[11] ZHOU L C, ZHANG C, WU M.D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//Proceedings of the 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:182-186.
[12] CHEN L C, ZHU Y K, PAPANDREOU G, et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:833-851.
[13] HE K M.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[14] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:7132-7141.
[15] JADERBERG M, SIMONYAN K, ZISSERMAN A.Spatial transformer networks[C]//Proceedings of IEEE ANIPSʼ17.Washington D.C., USA:IEEE Press, 2015:2017-2025.
[16] FU J, LIU J, TIAN H J.Dual attention network for scene segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:3146-3154.
[17] YU C Q, WANG J B, PENG C, et al.BiSeNet:bilateral segmentation network for real-time semantic segmentation[C]//Proceedings of the 15th European Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2018:334-349.
[18] HAN X Y, WANG R D.Computation of credit portfolio loss distribution by a cross entropy method[J].Journal of Applied Mathematics and Computing, 2016, 52(1/2):287-304.
[19] COX D R.The regression analysis of binary sequences[J].Journal of the Royal Statistical Society, 1958, 20(2):215-232.
[20] CORTES C, VAPNIK V.Support-vector networks[J].Machine Learning, 1995, 20(3):273-297.
[21] RONNEBERGER O, FISCHER P, BROX T.U-net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention.Washington D.C., USA:IEEE Press, 2015:234-241.
[22] 王俊强, 李建胜, 周华春, 等.基于Deeplabv3+与CRF的遥感影像典型要素提取方法[J].计算机工程, 2019, 45(10):260-265, 271. WANG J Q, LI J S, ZHOU H C, et al.A typical element extraction method of remote sensing image based on Deeplabv3+ and CRF[J].Computer Engineering, 2019, 45(10):260-265, 271.(in Chinese)
[23] FU J, LIU J, TIAN H J.Dual attention network for scene segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA:IEEE Press.2019:3146-3154.

选择文件类型/文献管理软件名称

选择包含的内容

基于改进D-LinkNet模型的高分遥感影像道路提取研究

Research of Road Extraction from High-Resolution Remote Sensing Images Based on Improved D-LinkNet Model

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	张新华, 黄梦醒, 张雨, 李玉春, 单怡晴, 冯思玲. 基于深度学习的卫星图像道路分割算法[J]. 计算机工程, 2021, 47(10): 306-313.
[2]	姚相坤,万里红,霍宏,方涛. 基于多结构卷积神经网络的高分遥感影像飞机目标检测[J]. 计算机工程, 2017, 43(1): 259-267.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于改进D-LinkNet模型的高分遥感影像道路提取研究

Research of Road Extraction from High-Resolution Remote Sensing Images Based on Improved D-LinkNet Model

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献

相关文章 2

编辑推荐

Metrics

本文评价