Road extraction of UAV remote sensing image based on deep learning

doi:10.13474/j.cnki.11-2246.2024.0614

Abstract

Abstract: Aiming at the problems of high-resolution remote sensing images and road image datasets in the target scene in terms of difficulty in acquiring, high cost, etc., we explore the optimal image resolution of the network models to perform the extraction task at different scales, evaluate the applicability and reliability of each model on road extraction, and provide methodological reference and case study for the road recognition project. In this paper, three classical network models in the field of image segmentation are introduced, the models are trained using public datasets, and the unmanned aerial images of Chuzhou city, Anhui province are used as the test data to perform the road extraction work at different scales, to find out the optimal resolution and model applicability of each model in the new scene, and to evaluate the reliability. The experimental results show that the applicability of the D-LinkNet network model is more prominent in the road extraction task at different scales, the reliability of the DeepLabV3+ network model is poorer, and the optimal resolutions of the road extraction input images for the U-Net and D-LinkNet network models are 1.0 and 0.5 m, respectively.

Key words: high-resolution remote sensing image, semantic segmentation, road extraction, attention mechanism

CLC Number:

P237

ZHANG Wei, ZHANG Chaolong, WANG Benlin, CAI Anning. Road extraction of UAV remote sensing image based on deep learning[J]. Bulletin of Surveying and Mapping, 2024, 0(6): 77-81.

References

[1] 王培法,王丽,冯学智,等.遥感图像道路信息提取方法研究进展[J].遥感技术与应用,2009,24(3): 284-290.
[2] 胥亚,杜为财,袁立伟,等.遥感影像道路提取现状与展望[J].测绘通报,2012(S1): 427-429.
[3] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA:IEEE,2015: 3431-3440.
[4] KALCHBRENNER N,GREFENSTETTE E,BLUNSOM P.A convolutional neural network for modelling sentences[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.[S.l]:Association for Computational Linguistics,2014:655-665.
[5] 刘广进,王光辉,毕卫华,等.改进D-LinkNet模型在国产卫星影像云检测中的应用[J].测绘通报,2021(11): 54-58.
[6] 林云浩,王艳军,李少春,等.一种耦合DeepLab与Transformer的农作物种植类型遥感精细分类方法[J].测绘学报,2024,53(2): 353-366.
[7] 熊彬,张双德.基于改进PSPNet的卫星遥感图像建筑物语义分割算法[J].遥感信息,2023,38(4): 73-79.
[8] 卢晓燕.面向高分辨率遥感影像大范围道路提取的深度学习方法研究[J].武汉大学学报(信息科学版),2023,48(5): 821.
[9] 窦世卿,郑贺刚,徐勇,等.基于U-Net3+的高分遥感影像建筑物提取[J].测绘通报,2022(6): 40-44.
[10] 林娜,张小青,王岚,等.空洞卷积U-Net的遥感影像道路提取方法[J].测绘科学,2021,46(9): 109-114.
[11] ZHOU Lichen,ZHANG Chuang,WU Ming.D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City: IEEE,2018.
[12] 顾清华,薛步青,卢才武,等.基于D-LinkNet网络的露天矿道路智能识别与路网建模[J].煤炭学报,2020,45(S2): 1100-1108.
[13] 任月娟,葛小三.改进DeepLabV3+网络的遥感影像道路综合提取方法[J].测绘通报,2022(6): 55-61.
[14] MNIH V.Machine learning for aerial image labeling[D].Toronto: University of Toronto,2013.
[15] EVERINGHAM M,VAN GOOL L,WILLIAMS C K I,et al.The pascal visual object classes (VOC) challenge[J].International Journal of Computer Vision,2010,88(2): 303-338.