Domain Adaption for Fine-Grained Urban Village Extraction From Satellite Images

被引：67

作者：

Shi, Qian ^{[1
]}

Liu, Mengxi ^{[1
]}

Liu, Xiaoping ^{[1
]}

Liu, Penghua ^{[1
]}

Zhang, Pengyuan ^{[1
]}

Yang, Jinxing ^{[2
]}

Li, Xia ^{[3
,4
]}

机构：

[1] Sun Yat Sen Univ, Sch Geog & Planning, Guangdong Key Lab Urbanizat & Geosimulat, Guangzhou 510275, Peoples R China

[2] Guangzhou Univ, Sch Geog Sci, Guangzhou 510006, Peoples R China

[3] East China Normal Univ, Sch Geog Sci, Shanghai 200241, Peoples R China

[4] East China Normal Univ, Minist Educ, Key Lab Geog Informat Sci, Shanghai 200241, Peoples R China

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2020年 / 17卷 / 08期

基金：

中国国家自然科学基金;

关键词：

Image segmentation; Semantics; Training; Feature extraction; Adaptation models; Deep learning; Satellites; Adversarial learning; domain adaptation; satellite images; semantic segmentation; urban village (UV); REMOTE-SENSING IMAGES;

D O I：

10.1109/LGRS.2019.2947473

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Urban villages (UVs) are distinctive products formed in the process of rapid urbanization. The fine-grained mapping of UVs from satellite images has always been a considerable challenge because of the complex urban structures and the insufficiency of labeled samples. In this letter, we propose using the domain adaptation strategy to tackle the domain shift problem by employing adversarial learning to tune the semantic segmentation network so as to adaptively obtain similar outputs for input images from different domains. The proposed method was coupled with several segmentation networks, including U-Net, RefineNet, and DeepLab v3+, and the results show that domain adaptation can significantly improve the pixel-level mapping of UVs.

引用

页码：1430 / 1434

页数：5

共 26 条

[1] Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
Bousmalis, Konstantinos
Silberman, Nathan
Dohan, David
Erhan, Dumitru
Krishnan, Dilip
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 95 - 104
[2] Chen L.C.E., 2018, P EUR C COMP VIS ECC, P833, DOI [10.1007/978-3-030-01234-2_49, DOI 10.1007/978-3-030-01234-2_49, DOI 10.1007/978-3-030-01234-249]
[3] Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images
Cheng, Gong
Zhou, Peicheng
Han, Junwei
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (12): : 7405 - 7415
[4] Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
[5] Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning
Han, Junwei
Zhang, Dingwen
Cheng, Gong
Guo, Lei
Ren, Jinchang
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (06): : 3325 - 3337
[6] Hoffmann Johannes, 2016, 2016 Conference on Precision Electromagnetic Measurements (CPEM), P1, DOI 10.1109/CPEM.2016.7540615
[7] Automatic Recognition of Village in Remote Sensing Images by Support Vector Machine Using Co-Occurrence Matrices
Li, Li
Chen, Yingyi
Gao, Hongju
Li, Daoliang
[J]. SENSOR LETTERS, 2012, 10 (1-2) : 523 - 528
[8] RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
Lin, Guosheng
Milan, Anton
Shen, Chunhua
Reid, Ian
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5168 - 5177
[9] Building Footprint Extraction from High-Resolution Images via Spatial Residual Inception Convolutional Neural Network
Liu, Penghua
Liu, Xiaoping
Liu, Mengxi
Shi, Qian
Yang, Jinxing
Xu, Xiaocong
Zhang, Yuanying
[J]. REMOTE SENSING, 2019, 11 (07)
[10] High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform
Liu, Xiaoping
Hu, Guohua
Chen, Yimin
Li, Xia
Xu, Xiaocong
Li, Shaoying
Pei, Fengsong
Wang, Shaojian
[J]. REMOTE SENSING OF ENVIRONMENT, 2018, 209 : 227 - 239

← 1 2 3 →