基于SPUD-ResNet的遥感影像道路提取网络

doi:10.3778/j.issn.1002-8331.2007-0342

摘要/Abstract

摘要：

针对遥感影像中道路目标细节丰富且呈带状分布的特点，造成狭长的道路结构提取困难的问题，设计并实现了一种基于SPUD-ResNet的道路提取方法。该方法利用空洞卷积构建残差网络编码器，并通过跳跃连接与对应解码器相连，有效加速网络的收敛并保留道路的细节信息；为了更有效地捕获狭长道路结构的长距离依赖关系，分别构建条形池化模块和混合池化模块，增强网络对条形道路结构特征的获取能力；利用道路结构的几何信息和结构相似性指数设计混合损失函数，精细化道路边界，去除道路提取结果中的模糊预测。在Massachusetts Roads数据集上的实验结果表明，所提方法在召回率、精确度和F1-score指标分别达到了83.4%、84.5%和83.9%，提升了道路提取的效果。

关键词: 遥感影像, 道路提取, 条形池化, 深度学习, ResNet

Abstract:

A road extraction method based on SPUD-ResNet is designed and implemented to solve the problem of extracting long and narrow road structures due to the rich detail and strip distribution of road targets in remote sensing images. Firstly, the residual network encoder is constructed by using void convolution, and then connected to the corresponding decoder by skip connection, which effectively accelerates the convergence of the network and preserves the detailed road information. Secondly, in order to capture the long-distance dependence of the narrow road structure more effectively, the strip pooling module and the mixed pooling module are built respectively to enhance the ability of the network to obtain the strip road characteristics. Finally, a mixed loss function is designed by using the geometric information of the road structure and the structural similarity index to refine the road boundary and remove the fuzzy prediction from the road extracted results. Experimental results on the Massachusetts Roads dataset show that the proposed method achieves 83.4%, 84.5% and 83.9% in recall, accuracy and F1-score indicators, respectively, which improves the effect of road extraction.

Key words: remote sensing image, road extraction, strip pool, deep learning, ResNet

李代栋，赫晓慧，李盼乐，田智慧，周广胜. 基于SPUD-ResNet的遥感影像道路提取网络[J]. 计算机工程与应用, 2021, 57(23): 240-247.

LI Daidong, HE Xiaohui, LI Panle, TIAN Zhihui, ZHOU Guangsheng. Road Extraction Network of Remote Sensing Image Based on SPUD-ResNet[J]. Computer Engineering and Applications, 2021, 57(23): 240-247.

参考文献

[1] 马新江，刘如飞，蔡永宁，等.一种基于路缘特征的点云道路边界提取方法[J].遥感信息，2019，34（2）：80-85.
MA Xinjiang，LIU Rufei，CAI Yongning，et al.A road boundary extraction method from point clouds based on curb features[J].Remote Sensing Information，2019，34（2）：80-85.
[2] LONG J，SHELHAMER E，DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，39（4）：640-651.
[3] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention（MICCAI），2015：234-241.
[4] BADRINARAYANAN V，KENDALL A，CIPOLLA R.SegNet：a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（12）：2481-2495.
[5] CHEN L，PAPANDREOU G，KOKKINOS I，et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[J].arXiv：1412.7062，2014.
[6] CHEN L，PAPANDREOU G，KOKKINOS I，et al.DeepLab：semantic image segmentation with deep convolutional nets，atrous convolution，and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40（4）：834-848.
[7] ZHAO H，SHI J，QI X，et al.Pyramid scene parsing network[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：6230-6239.
[8] 苏健民，杨岚心，景维鹏.基于U-Net的高分辨率遥感图像语义分割方法[J].计算机工程与应用，2019，55（7）：207-213.
SU Jianmin，YANG Lanxin，JING Weipeng.U-Net based semantic segmentation method for high resolution remote sensing image[J].Computer Engineering and Applications，2019，55（7）：207-213.
[9] 祖宝开，夏克文，牛文佳，等.分块低秩图的遥感影像半监督分类应用[J].计算机科学与探索，2019，13（7）：1217-1226.
ZU Baokai，XIA Kewen，NIU Wenjia，et al.Semi-supervised classification application of remote sensing image based on block low-rank images[J].Journal of Frontiers of Computer Science and Technology，2019，13（7）：1217-1226.
[10] 李森森，吴清.改进Mask R-CNN的遥感图像多目标检测与分割[J].计算机工程与应用，2020，56（14）：183-190.
LI Sensen，WU Qing.Multi-target detection and segmentation of remote sensing images based on improved Mask RCNN[J].Computer Engineering and Applications，2020，56（14）：183-190.
[11] PANBOONYUEN T，JITKAJORNWANICH K，LAWA-WIROJWONG S，et al.Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields[J].Remote Sens，2017，9：680.
[12] BUSLAEV A V，SEFERBEKOV S，IGLOVIKOV V，et al.Fully convolutional network for automatic road extraction from satellite imagery[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018.
[13] CONSTANTIN A，DING J，LEE Y，et al.Accurate road detection from satellite images using modified U-net[C]//Asia Pacific Conference on Circuits and Systems，2018：423-426.
[14] LU X，ZHONG Y，ZHENG Z，et al.Multi-scale and multi-task deep learning framework for automatic road extraction[J].IEEE Transactions on Geoscience and Remote Sensing，2019，57（11）：9362-9377.
[15] LI P，HE X，CHENG X，et al.Object extraction from very high-resolution images using a convolutional neural network based on a noisy large-scale dataset[J].IEEE Access，2019：122784-122795.
[16] WEI Y，WANG Z，XU M，et al.Road structure refined CNN for road extraction in aerial image[J].IEEE Geoscience and Remote Sensing Letters，2017，14（5）：709-713.
[17] 贺浩，王仕成，杨东方，等.基于Encoder-Decoder网络的遥感影像道路提取方法[J].测绘学报，2019，48（3）：330-338.
HE Hao，WANG Shicheng，YANG Dongfang，et al.An road extraction method for remote sensing image based on Encoder-Decoder network[J].Acta Geodaetica et Cartographica Sinica，2019，48（3）：330-338.
[18] HE J，DENG Z，ZHOU L，et al.Adaptive pyramid context network for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2019：7519-7528.
[19] ZHOU L，ZHANG C，WU M，et al.D-LinkNet：LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：192-1924.
[20] YU F，KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv：1511.07122，2015.
[21] 宋廷强，李继旭，张信耶.基于深度学习的高分辨率遥感图像建筑物识别[J].计算机工程与应用，2020，56（8）：26-34.
SONG Tingqiang，LI Jixu，ZHANG Xinye.Building recognition in high-resolution remote sensing image based on deep learning[J].Computer Engineering and Applications，2020，56（8）：26-34.
[22] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition，2014.
[23] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition，2016.
[24] WANG Z，SIMONCELLI E P，BOVIK A C，et al.Multi-scale structural similarity for image quality assessment[C]//Asilomar Conference on Signals，Systems and Computers，2003：1398-1402.
[25] WANG Z，BOVIK A C，SHEIKH H R，et al.Image quality assessment：from error visibility to structural similarity[J].IEEE Transactions on Image Processing，2004，13（4）：600-612.