近年来城郊山区成为城镇居民郊游佳选，而密集性的旅客出游及村民生产活动给山林带来火灾安全隐患。道路信息是森林防火应急信息化核心要素之一，但因城郊山区道路存在遮挡、阴影、路窄且多分支等问题，使得常规道路提取算法在城郊山区效果欠佳。故提出一种道路语义分割模型，以及一种将道路二类问题转化成多类问题的语义分割模型训练方法，迫使模型侧重学习空间距离信息，以生成空间连续性更优的道路结果。在本研究自主研制的城郊山区Yajishan道路数据集和公开数据集Massachusetts道路数据集上验证本文模型及训练方法的有效性。此外，验证该训练方法同样适用于U-Net、DeepLabV3等常用语义分割模型。还基于道路提取结果进行后处理，输出道路面、道路中心线矢量数据及道路宽度信息，并在北京丫髻山进行消防车通行性分析。研究成果在一定程度上缓解了商业电子地图在城郊山区少人处道路信息不足的问题，为森林防火应急救援提供信息化技术支撑。
陈若男
,
彭玲
,
刘玉菲
,
卫志超
,
吕蓓茹
,
陈德跃
. 引入空间距离信息的城郊山区道路提取与应用[J]. 中国科学院大学学报, 2022
, 39(5)
: 658
-667
.
DOI: 10.7523/j.ucas.2021.0004
In recent years, suburban mountain areas have become a good choice for urban residents to go outing. Intensive tourist outings and villagers' production activities bring fire safety hazards to mountains and forests. And road information is vital information for forest fire prevention emergency. However, due to the problems of occlusion, shadow, narrow and multiple branches in suburban mountainous roads, conventional urban road extraction algorithms have poor performance in suburban mountain areas. This paper proposes a road semantic segmentation model and a training method that transforms the binary into a multi-class classification problem, forcing the model to focus on learning spatial distance information to generate road results with better spatial continuity. Then, experiments were carried out on the Yajishan road dataset made by ourselves and the Massachusetts public road dataset respectively to verify the effectiveness of our model and training method. In addition, it is verified that the training method is also applicable to other commonly used semantic segmentation models such as U-Net and DeepLabV3. Finally, this paper also conducts post-processing research based on the above road extraction results to output road surface, road centerline vector data with road width information, and conducts fire truck traffic analysis application in Beijing Yaji Mountain. The research results have alleviated the problem of insufficient road information for commercial electronic maps in the suburban mountain areas with few people, and provided information technology support for forest fire emergency rescue.
[1] 杨朝斌, 张树文, 卜坤, 等. 高分辨率遥感影像在城市LUCC中的应用[J]. 中国科学院大学学报, 2016, 33(3):289-297.DOI:10.7523/j.issn.2095-6134.2016.03.001.
[2] Hu J X, Razdan A, Femiani J C, et al. Road network extraction and intersection detection from aerial images by tracking road footprints[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12):4144-4157.DOI:10.1109/TGRS.2007.906107.
[3] 左娟, 李勇军. 结合纹理与形状特征的高分辨率遥感影像道路提取[J]. 测绘, 2013, 36(3):111-113.DOI:10.3969/j.issn.1674-5019.2013.03.005.
[4] Singh P P, Garg R D. Automatic road extraction from high resolution satellite image using adaptive global thresholding and morphological operations[J]. Journal of the Indian Society of Remote Sensing, 2013, 41(3):631-640.DOI:10.1007/s12524-012-0241-4.
[5] 劳小敏, 张哲伦, 张丰, 等. 基于邻域总变分和边缘检测的遥感影像道路提取[J]. 浙江大学学报(理学版), 2013, 40(6):705-709,725.DOI:10.3785/j.issn.1008-9497.2013.06.018.
[6] 李书晓, 常红星. 基于总变分和形态学的航空图像道路检测算法[J]. 计算机学报, 2007, 30(12):2173-2180.DOI:10.3321/j.issn:0254-4164.2007.12.014.
[7] 曹婷, 王欢. 基于二值空间线特征的道路检测方法[J]. 计算机工程与应用, 2018, 54(6):161-167.
[8] 朱恩泽, 宋伟东, 戴激光. 改进支持向量机的高分遥感影像道路提取[J]. 测绘科学, 2016, 41(12):224-228.DOI:10.16251/j.cnki.1009-2307.2016.12.044.
[9] Mnih V. Machine learning for aerial image labeling[D]. Toronto:University of Toronto, 2013.
[10] Zhang Z X, Liu Q J, Wang Y H. Road extraction by deep residual U-net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5):749-753.DOI:10.1109/LGRS.2018.2802944.
[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]//2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR2018). June 18-22, 2018, Salt Lake City, UT, USA.IEEE, 2018:182-186.DOI:10.1109/CVPRW.2018.00034.
[12] Xu Y Y, Xie Z, Feng Y X, et al. Road extraction from high-resolution remote sensing imagery using deep learning[J]. Remote Sensing, 2018, 10(9):1461.DOI:10.3390/rs10091461.
[13] Kestur R, Farooq S, Abdal R, et al. UFCN:a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle[J]. Journal of Applied Remote Sensing, 2018, 12:016020.DOI:10.1117/1.JRS.12.016020.
[14] Ye Q Z. The signed Euclidean distance transform and its applications[C]//19889th International Conference on Pattern Recognition. November 14-17,1988,Rome, Italy.IEEE, 1988:495-499.DOI:10.1109/ICPR.1988.28276.
[15] Loshchilov I, Hutter F. SGDR:stochastic gradient descent with warm restarts[EB/OL].arXiv:1608.03983.(2017-05-03)[2020-10-20].http://arXiv.org/abs/1608.03983.
[16] 周雪梅, 黎应飞. 基于Bowyer-Watson三角网生成算法的研究[J]. 计算机工程与应用, 2013, 49(6):198-200.DOI:10.3778/j.issn.1002-8331.1108-0137.
[17] 蔡红玥, 米素娟, 阳柯. 基于高分遥感影像的道路宽度自动提取研究进展综述[J]. 电子测试, 2019(11):59-60.DOI:10.16520/j.cnki.1000-8519.2019.11.020.
[18] 靳彩娇. 高分辨率遥感影像道路提取方法研究[D]. 郑州:解放军信息工程大学, 2013.
[19] 侯阳阳, 王欢. 基于笔画宽度变换的无人机视觉道路检测[J]. 计算机与数字工程, 2018, 46(1):182-186.DOI:10.3969/j.issn.1672-9722.2018.01.038.
[20] 刘小丹, 刘岩. 基于Hough变换和数学形态学的遥感影像城区道路提取[J]. 南京师大学报(自然科学版), 2010, 33(4):128-133.DOI:10.3969/j.issn.1001-4616.2010.04.026.
[21] 赵焕新. 一种高分辨率遥感影像道路提取方法[J]. 教育教学论坛, 2016(17):199-200.
[22] Chen L C, Zhu Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//European Conference on Computer Vision (ECCV), Munich, Germany. 2018:833-851.DOI:10.1007/978-3-030-01234-2_49.
[23] Ronneberger O, Fischer P, Brox T. U-net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015). Springer,Cham, 2015:234-241.DOI:10.1007/978-3-319-24574-4_28.
[24] 中国计划出版社. 《建筑设计防火规范》GB 50016-2014引用标准规范汇编[M]. 北京:中国计划出版社, 2015.
