空间信息感知语义分割模型的高分辨率遥感影像道路提取
Road extraction method of high-resolution remote sensing image on the basis of the spatial information perception semantic segmentation model
- 2022年26卷第9期 页码：1872-1885
DOI： 10.11834/jrs.20210021
扫 描 看 全 文
摘要
道路信息自动化提取已经成为遥感领域热门的研究方向，而基于深度学习的遥感影像道路信息提取方法已经取得了许多成果。但由于受到网络中卷积和池化等操作的影响，基于深度学习的道路提取方法存在着空间特征和地物细节信息丢失等问题，造成许多误提现象。针对此问题，本文设计了一种改进的道路提取语义分割网络模型，该网络以改进的ResNet网络为主体，并引入坐标卷积和全局信息增强模块，用于增强空间信息和全局上下文信息的感知能力，突出道路边缘特征进而确保道路分类的精确性。本文方法在公开道路数据集和高分数据集上获得了显著的提取效果，与其它方法相比取得了明显提高；并且，在一定程度上减少了树木、建筑阴影等自然场景因素遮挡的影响，可以完整准确地提取出道路；此外，模型对多尺度道路也可以实现有效地提取。
Abstract
With the rapid development of remote sensing satellite technology, the automatic extraction of high-resolution remote sensing images has become a popular research direction in the field of remote sensing. Deep learning methods have been applied in remote sensing image road information extraction and achieved significant results. However, due to convolution and pooling and other operations in network, road extraction methods based on the deep learning have some problems, such as the loss of spatial features and ground object details and the frequent occurrence of false extraction during road extraction. In order to solve these problems, this paper designs an improved road extraction semantic segmentation network model to mitigate the impact of the above network structure.,The proposed method is based on ResNet and introduces coordinate convolution and a global information enhancement module before and after the coding structure, respectively. First, the network structure is mainly composed of residual units of ResNet, which has powerful feature extraction and multiplexing capabilities, and extracts road features of different scales and levels. Second, coordinate convolution reduces the spatial information loss and enhances the edge information. The coordinate convolution before the coding structure introduces spatial coordinate information, which is beneficial to enhancing the extraction of effective spatial information. Finally, global pooling can improve global context awareness. The global information enhancement module after the coding structure can effectively extract global context information through global pooling, thereby improving the accuracy of road classification and reducing the influence of natural scene factors, such as houses and tree shadows, to a certain extent.,In this paper, the Massachusetts Roads dataset was used in the experiment, and the results obtained exhibited good accuracy. The Recall rate was 71.02%, the comprehensive evaluation index (F1 Score) was 76.35%, and the IoU reached 62.18%. The F1 Score and IoU indicators of the proposed method are approximately 1% higher than those in U-net and D-LinkNet and exceed those of DeeplabV3+ and Segnet, which are lower than D-LinkNet in the recall index only.,The comparison of the experimental results indicates that the proposed method can effectively alleviate the spatial feature and context information losses on the basis of the deep learning road extraction method and completely extract the roads in remote sensing images. Moreover, the proposed method can effectively extract the road in the case of trees and building shadows, and multi-scale roads can also be accurately extracted.
关键词
深度学习遥感影像道路提取坐标卷积全局信息增强模块
Keywords
deep learningremote sensing imageroad extractioncoordinate convolutionglobal information enhancement module
references
Alshehhi R, Marpu P R, Woon W L and Mura M D. 2017. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, 130: 139-149 [DOI: 10.1016/j.isprsjprs.2017.05.002http://dx.doi.org/10.1016/j.isprsjprs.2017.05.002]
Badrinarayanan V, Kendall A and Cipolla R. 2017. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495 [DOI: 10.1109/TPAMI.2016.2644615http://dx.doi.org/10.1109/TPAMI.2016.2644615]
Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation//15th European Conference on Computer Vision. Munich: Springer: 833-851 [DOI: 10.1007/978-3-030-01234-2_49http://dx.doi.org/10.1007/978-3-030-01234-2_49]
Chen Z, Ma H C and Li Y F. 2013. Extraction of road intersection from LiDAR point cloud data based on ATS and Snake. Remote Sensing for Land and Resources, 25(4): 79-84
陈卓, 马洪超, 李云帆. 2013. 结合角度纹理信息和Snake方法从LiDAR点云数据中提取道路交叉口. 国土资源遥感, 25(4): 79-84 [DOI: 10.6046/gtzyyg.2013.04.13http://dx.doi.org/10.6046/gtzyyg.2013.04.13]
Fu Z L, Yang Y W, Gao X J, Zhao X Y and Fan L. 2016. An optimization algorithm for multi-characteristics road network matching. Acta Geodaetica et Cartographica Sinica, 45(5): 608-615
付仲良, 杨元维, 高贤君, 赵星源, 范亮. 2016. 道路网多特征匹配优化算法. 测绘学报, 45(5): 608-615 [DOI: 10.11947/j.AGCS.2016.20150388http://dx.doi.org/10.11947/j.AGCS.2016.20150388]
Haverkamp D S. 2002. Extracting straight road structure in urban environments using IKONOS satellite imagery. Optical Engineering, 41(9): 2107-2110 [DOI: 10.1117/1.1496785http://dx.doi.org/10.1117/1.1496785]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]
Hong M Z, Guo J Q, Dai Y Z and Yin Z Y. 2019. A novel FMH model for road extraction from high-resolution remote sensing images in urban areas. Procedia Computer Science, 147: 49-55 [DOI: 10.1016/j.procs.2019.01.183http://dx.doi.org/10.1016/j.procs.2019.01.183]
Jiang Y T. 2019. Research on road extraction of remote sensing image based on convolutional neural network. EURASIP Journal on Image and Video Processing, 2019(1): 31 [DOI: 10.1186/s13640-019-0426-7http://dx.doi.org/10.1186/s13640-019-0426-7]
Kingma D P and Ba J. 2015. Adam: a method for stochastic optimization//3rd International Conference on Learning Representations. International Conference on Learning Representations Ithaca, NYarXiv.org,abs/1412.6980[DOI: 10.48550/arXiv.1412.6980http://dx.doi.org/10.48550/arXiv.1412.6980]
Li J and Zhang Q D. 2017. Extracting and identifying urban roads from remote sensing images based on Hough transform. Computer Knowledge and Technology, 13(3): 172-174
李建, 张其栋. 2017. 基于霍夫变换的遥感图像城市道路的提取识别. 电脑知识与技术, 13(3): 172-174 [DOI: 10.14004/j.cnki.ckt.2017.0306http://dx.doi.org/10.14004/j.cnki.ckt.2017.0306]
Liu R, Lehman J, Molino P, Such F P, Frank E, Sergeev A and Yosinski J. 2018. An intriguing failing of convolutional neural networks and the CoordConv solution//32nd Conference on Neural Information Processing Systems. Montréal: Curran Associates Inc.: 9628-9639[DOI: 10.48550/arXiv.1807.03247http://dx.doi.org/10.48550/arXiv.1807.03247]
Mnih V. 2013. Machine Learning for Aerial Image Labeling. Toronto: University of Toronto,70-90[DOI: 10. 5555/ 978-0-494-96184-1http://dx.doi.org/10.5555/978-0-494-96184-1]
Mnih V and Hinton G E. 2010. Learning to detect roads in high-resolution aerial images//11th European Conference on Computer Vision. Heraklion: Springer: 210-223 [DOI: 10.1007/978-3-642-15567-3_16http://dx.doi.org/10.1007/978-3-642-15567-3_16]
Mu H L, Zhang Y, Li H B, Guo Y R and Zhuang Y. 2016. Road extraction base on Zernike algorithm on SAR image//Proceedings of IEEE International Geoscience and Remote Sensing Symposium. Beijing: IEEE: 1274-1277 [DOI: 10.1109/IGARSS.2016.7729323http://dx.doi.org/10.1109/IGARSS.2016.7729323]
Nogueira K, Penatti O A B and dos Santos J A. 2017. Towards better exploiting convolutional neural networks for remote sensing scene classification. Pattern Recognition, 61: 539-556 [DOI: 10.1016/j.patcog.2016.07.001http://dx.doi.org/10.1016/j.patcog.2016.07.001]
Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P and Vateekul P. 2017. Road segmentation of remotely-Sensed images using deep convolutional neural networks with landscape metrics and conditional random fields. Remote Sensing, 9(7): 680 [DOI: 10.3390/rs9070680http://dx.doi.org/10.3390/rs9070680]
Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer: 234-241 [DOI: 10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]
Sherrah J. 2016. Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery. Computer Vision and Pattern Recognition [DOI:10.48550/arXiv.1606.02585http://dx.doi.org/10.48550/arXiv.1606.02585]
Song M J and Civco D. 2004. Road extraction using SVM and image segmentation. Photogrammetric Engineering and Remote Sensing, 70(12): 1365-1371 [DOI: 10.14358/PERS.70.12.1365http://dx.doi.org/10.14358/PERS.70.12.1365]
Wen G J and Wang R S. 2000. Automatic extraction of main roads from aerial remote sensing images. Journal of Software, 11(7): 957-964
文贡坚, 王润生. 2000. 从航空遥感图像中自动提取主要道路. 软件学报, 11(7): 957-964 [DOI: 10.13328/j.cnki.jos.2000.07.014http://dx.doi.org/10.13328/j.cnki.jos.2000.07.014]
Wu Y X and He K M. 2018. Group normalization//15th European Conference on Computer Vision (ECCV). Munich: Springer: 3-19 [DOI: 10.1007/978-3-030-01261-8_1http://dx.doi.org/10.1007/978-3-030-01261-8_1]
Xu R. 2014. A method of urban road extraction from remote sensing image combining shape features and homogeneity. Journal of Geomatics Science and Technology, 31(1): 53-56
许锐. 2014. 结合形状与同质特征的遥感影像城市道路提取方法. 测绘科学技术学报, 31(1): 53-56 [DOI: 10.3969/j.issn.1673-6338.2014.01.012http://dx.doi.org/10.3969/j.issn.1673-6338.2014.01.012]
Yu C Q, Wang J B, Peng C, Gao C X, Yu G and Sang N. 2018. Learning a discriminative feature network for semantic segmentation//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE: 1857-1866 [DOI: 10.1109/CVPR.2018.00199http://dx.doi.org/10.1109/CVPR.2018.00199]
Zhang Y H, He J, Kan X, Xia G H, Zhu L L and Ge T T. 2018. Summary of road extraction methods for remote sensing images. Computer Engineering and Applications, 54(13): 1-10, 51
张永宏, 何静, 阚希, 夏广浩, 朱灵龙, 葛涛涛. 2018. 遥感图像道路提取方法综述[J]. 计算机工程与应用, 54(13): 1-10, 51 [DOI: 10.3778/j.issn.1002-8331.1804-0271http://dx.doi.org/10.3778/j.issn.1002-8331.1804-0271]
Zhang Z X, Liu Q J and Wang Y H. 2018. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753 [DOI: 10.1109/LGRS.2018.2802944http://dx.doi.org/10.1109/LGRS.2018.2802944]
Zhou J X, Zhou A F, Tao C, Gao C Q and Li J. 2013. A methodology for urban roads network extraction from high resolution remote sensing imagery. Journal of Central South University (Science and Technology), 44(6): 2385-2391
周家香, 周安发, 陶超, 高陈强, 李静. 2013. 一种高分辨率遥感影像城区道路网提取方法. 中南大学学报(自然科学版), 44(6): 2385-2391 [DOI: CNKI:SUN:ZNGD.0.2013-06-028http://dx.doi.org/CNKI:SUN:ZNGD.0.2013-06-028]
Zhou L C, Zhang C and Wu M. 2018. D-LinkNet: linkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake City: IEEE: 182-186 [DOI: 10.1109/CVPRW.2018.00034http://dx.doi.org/10.1109/CVPRW.2018.00034]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
昆明理工大学 国土资源工程学院
云南省高校高原山区空间信息测绘技术应用工程研究中心
西南林业大学 大数据与人工智能研究院
辽宁工程技术大学 测绘与地理科学学院
昆明理工大学国土资源工程学院
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部