Accurate extraction of urban buildings is a key problem in urban remote sensing image processing. It can be applied to many kinds of urban problems, such as data statistics of urban management and smart cities. In recent years, the deep learning model based on convolutional neural network is widely used in the field of target recognition and semantic segmentation. In this paper, based on U-Net for urban building extraction from remote sensing image, we propose a neural network architecture for urban building extraction from remote sensing image. We use depth separable convolution to improve it and adjust the process of network super parametric optimization according to the characteristics of building. We call this new architecture XU-Net. We evaluate the performance of XU-Net through experiments with INRIA aerial image data set. The result shows that XU-Net is not only feasible but also efficient. Moreover, XU-Net reduces number of parameters 89%, from 18.8M to 2.13M, compared to classical architecture U-Net, at the same time, it guarantees the accuracy can reach 97.5%.
SongH.B., SrinivasanR., SookoorT. and JeschkeS., Smart Cities: Foundations, Principles and Applications, Hoboken, NJ: Wiley, 2017.
2.
ZouW., JingW., ChenG., LuY. and SongH., A survey of big data analytics for smart forestry, IEEE Access7 (2019), 46621–46636. DOI: 10.1109/ACCESS.2019.2907999
3.
LiR., LiuW., LeiY., SunS., HuW., ZhangF. and LiW., DeepUNet: A Deep Fully convolutional network for pixel-level sea-land segmentation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing11(11) (2018), 3954–3962. DOI: 10.1109/JSTARS.2018.2833382
4.
YangX.J., Urban Remote sensing: Monitoring, synthesis and modeling in the urban environment, UK: Wiley & Sons Press, 2011.
5.
XianG.Z., Remote sensing applications for the urban environment, FL: CRC Press, 2016.
6.
GuoY.X., TangQ.H. and GongD.Y., Estimating ground level PM2.5 concentrations in Beijing using a satellite based geographically and temporally weighted regression model, Remote sensing of Environment198 (2017), 140–149.
7.
VolodymyrM., Machine learning for aerial image labeling, Doctor, University of Toronto (Canada), 2013.
8.
MadanS. and PranjaliC., A Review of Machine Learning Techniques Using Decision Tree and Support Vector Machine, International conference on computing Communication Control & Automation Piscataway, IEEE, 2017, 1–7. DOI: 10.1109/ICCUBEA.2016.-7860040
9.
ChingT., ZhuX. and GarmireL., Cox-net: An artificial neural network method for prognosis prediction of high-through put omics data, PLOS Computational Biology14(4) (2018), 1–18. DOI: 10.1371/journal.pcbi.1006076
10.
CuiB.G., XieX., MaX., RenG. and MaY., Superpixel-based extended random walker for hyperspectral image classification, IEEE Transactions on Geoscience and Remote Sensing56(6) (2018), 3233–3243.
11.
SherrahJ., Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery, arXiv, 2016, 1–22. https://arxiv.org/pdf/1606.02585
12.
YangH.L., YuanJ.Y., LungaD. and LaverdiereM., Building extraction at scale using convolutional neural network: Mapping of the United States, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing11(8) (2018), 2600–2614.
13.
LinJ., JingW. and SongH., ESFNet: Efficient network for building extraction from high-resolution aerial images, IEEE Access7 (2019), 54285–54294. DOI: 10.1109/ACCESS.2019.2912822
14.
AlexK., IlyaS. and HintonG., ImageNet Classification with Deep Convolutional Neural Networks, NIPS’12 Proceedings of the 25th International Conference on Neural Information Processing Systems, 2012, 1097–1105. DOI: 10.1145/3065386
15.
HussamQ., AbhishekV. and DavidF., Compressed residual-VGG16 CNN model for big data places image recognition, 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), 2018, 1–7.
16.
XieS., ZhengX. and ChenY., Artifact removal using improved GoogLeNet for Sparse-view CT Reconstruction, SciRep8 (2018), 6700. DOI: 10.1038/s41598-018-25153-w
17.
SzegedyC., IoffeS., VanhouckeV. and AlemiA., Inception-v4, inception-resnet and the impact of residual connections on learning, Conference of ICLR, 2016, 1–12.
18.
LiL.H., QianB., LianJ., ZhengW.N. and ZhouY.F., Study on semantic image segmentation based on convolutional neural network, Journal of Intelligent & Fuzzy Systems33(6) (2017), 3397–3404. DOI: 10.3233/JIFS-162254
19.
HuangH., DengH., ShengY. and YeX., Accelerating convolutional neural network-based malware traffic detection through ant-colony clustering, Journal of Intelligent & Fuzzy Systems37 (2019), 409–423. DOI: 10.3233/JIFS-179096
20.
LongJ., ShelhamerE. and DarrellT., Fully convolutional networks for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence39(4) (2017), 640–651. DOI: 10.1109/TPAMI.2016.2572683
21.
RonnebergerO., FischerP. and BroxT., Medical Image Computing and Computer-Assisted Intervention, U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer, 2015, 234–241.
22.
BadrinarayananV., KendallA. and CipollaR., SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, Conference of CVPR, 2016, 1–14.
23.
ChenL.C., GeorgeP., IasonasK., KevinM. and AlanL., DeepLab: Semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs, IEEE Transactions on Pattern Analysis and Machine Intelligence40(4) (2018), 834–848.
24.
ChenL.C., PapandreouG., SchroffF. and AdamH., Rethinking Atrous Convolution for Semantic Image Segmentation, Conference of CVPR, 2017, 1–14.
25.
PanJ.S., KongL., SungT.W., TsaiP.W. and SnaselV., Alpha-fraction first strategy for hierarchical wireless sensor networks, Journal of Internet Technology19(6) (2018), 1717–1726.
26.
PanJ.S., LeeC.Y., SghaierA., ZeghidM. and XieJ., Novel systolization of subquadratic space complexity multipliers based on Toeplitz Matrix–vector product approach, IEEE Transactions on Very Large Scale Integration Systems27(7) (2019), 1614–1622.
27.
ChenC.M., WangK.H., YehK.H., XiangB. and WuT.Y., Attacks and solutions on a three-party password-based authenticated key exchange protocol for wireless communications, Journal of Ambient Intelligence and Humanized Computing10(8) (2019), 3133–3142.
28.
ChenC.M., XiangB., LiuY. and WangK.H., A secure authentication protocol for internet of vehicles, IEEE ACCESS7(1) (2019), 12047–12057.
29.
WuJ.M.T., LinJ.C.W. and TamrakarA., High-Utility Itemset Mining with Effective Pruning Strategies, ACM Transactions on Knowledge Discovery from Data, 2019, 1–10. DOI: 10.1145/3363571.
30.
WuT.Y., ChenC.M., WangK.H., MengC. and WangE.K., A provably secure certificateless public key encryption with keyword search, Journal of the Chinese Institute of Engineers42(1) (2019), 20–28.
31.
Çiçek,Özgün,
AbdulkadirA.,
LienkampS.S.,
BroxT. and RonnebergerO., 3D U-net: learning dense volumetric segmentation from sparse annotation, Conference of MICCAI2016, 424–432. DOI: 10.1007/978-3-319-46723-8_49
32.
CuiB.G., DongF., ShaoG., LuY. and ChuJ., Extracting raft aquaculture areas from remote sensing images via an improved U-net with a PSE structure, Remote Sensing11(17) (2019), 2053–2062.
33.
ZhouX.Y. and ZhengJ.Q., Atrous Convolutional Neural Network (ACNN) for Semantic Image Segmentation with full-scale Feature Maps. ArXiv, 2019, 1–7, https://arxiv.org/-abs/1901.09203v3
34.
PaszkeA., ChaurasiaA. and KimS., Enet: A deep neural network architecture for real-time semantic segmentation, Arxiv, 2016, 1–10, https://arxiv.org/abs/1606.02147
35.
HowardA.G., ZhuM., ChenB., KalenichenkoD., WangW., WeyandT., AndreettoM. and AdamH., MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, arXiv, 2017, 1–9, https://arxiv.org/abs/-1704.04861
36.
SandlerM., HowardA., ZhuM., ZhmoginovA. and ChenL.C., MobileNetv2: Inverted residuals and linear bottlenecks, Conference of CVPR, 2018, 4510–4520.
37.
HowardA., SandlerM., ChuG., ChenL.C., ChenB., TanM., WangW., ZhuY., PangR. and VasudevanV., Searching for MobileNetV3, Conference for ICCV2019. https://arxiv.org/abs/-1905.02244
38.
FrancoisC., Xception: Deep learning with depthwise separable convolutions, Computer Vision and Pattern Recognitionv3 (2017), 1–8.
39.
XiaX., XuC. and NanB., Inception-v3 for flower classification, 2017 2nd International Conference on Image, Vision and Computing (ICIVC), IEEE, 2017, 783–787. DOI: 10.1109/ICIVC.2017.7984661
40.
MaN., ZhangX., ZhengH.T. and SunJ., ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design, ECCV, Springer, 2018, 122–138.
41.
LinJ., JingW., SongH. and ChenG., ESFNet: Efficient Network for Building ExTraction from High-Resolution Aerial Images, IEEE Access2019, 1–10. DOI: 10.1109/ACCESS.2019.2912822
42.
LexieY.H., YuanJ. and LungaD., Building extraction at scale using convolutional neural network: Mapping of the United States, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing11(8) (2018), 2600–2614. DOI: 10.1109/JSTARS.2018.2835377
