Urban Green Plastic Cover Mapping Based on VHR Remote Sensing Images and a Deep Semi-Supervised Learning Framework

被引:12
作者
Liu, Jiantao [1 ]
Feng, Quanlong [2 ]
Wang, Ying [3 ,4 ]
Batsaikhan, Bayartungalag [5 ]
Gong, Jianhua [6 ]
Li, Yi [6 ]
Liu, Chunting [1 ]
Ma, Yin [7 ]
机构
[1] Shandong Jianzhu Univ, Sch Surveying & Geoinformat, Jinan 250101, Peoples R China
[2] China Agr Univ, Coll Land Sci & Technol, Beijing 100083, Peoples R China
[3] Chinese Acad Sci, Inst Urban Environm, Key Lab Urban Environm & Hlth, Xiamen 361021, Peoples R China
[4] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[5] Mongolian Acad Sci, Inst Geog & Geoecol, Ulan Bator 15170, Mongolia
[6] Chinese Acad Sci, Aerosp Informat Res Inst, Natl Engn Res Ctr Geoinformat, Beijing 100101, Peoples R China
[7] China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
关键词
green plastic cover; semi-supervised learning; deep learning; urban land cover mapping; RANDOM FOREST; CONVOLUTIONAL NETWORKS; LAND-COVER; CLASSIFICATION; PIXEL;
D O I
10.3390/ijgi9090527
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid process of both urban sprawl and urban renewal, large numbers of old buildings have been demolished in China, leading to wide spread construction sites, which could cause severe dust contamination. To alleviate the accompanied dust pollution, green plastic mulch has been widely used by local governments of China. Therefore, timely and accurate mapping of urban green plastic covered regions is of great significance to both urban environmental management and the understanding of urban growth status. However, the complex spatial patterns of the urban landscape make it challenging to accurately identify these areas of green plastic cover. To tackle this issue, we propose a deep semi-supervised learning framework for green plastic cover mapping using very high resolution (VHR) remote sensing imagery. Specifically, a multi-scale deformable convolution neural network (CNN) was exploited to learn representative and discriminative features under complex urban landscapes. Afterwards, a semi-supervised learning strategy was proposed to integrate the limited labeled data and massive unlabeled data for model co-training. Experimental results indicate that the proposed method could accurately identify green plastic-covered regions in Jinan with an overall accuracy (OA) of 91.63%. An ablation study indicated that, compared with supervised learning, the semi-supervised learning strategy in this study could increase the OA by 6.38%. Moreover, the multi-scale deformable CNN outperforms several classic CNN models in the computer vision field. The proposed method is the first attempt to map urban green plastic-covered regions based on deep learning, which could serve as a baseline and useful reference for future research.
引用
收藏
页数:18
相关论文
共 50 条
[31]   Automatic Leaf Recognition Based on Deep Semi-Supervised Learning [J].
Wu H. ;
Xiao F. ;
Shi Z. ;
Wen Z. .
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2023, 35 (10) :1469-1478
[32]   A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping [J].
Benjamin Lucas ;
Charlotte Pelletier ;
Daniel Schmidt ;
Geoffrey I. Webb ;
François Petitjean .
Machine Learning, 2023, 112 :1941-1973
[33]   Credence-Net: a semi-supervised deep learning approach for medical images [J].
Mall, Pawan Kumar ;
Singh, Pradeep Kumar .
INTERNATIONAL JOURNAL OF NANOTECHNOLOGY, 2023, 20 (5-10) :897-914
[34]   A study of a Gaussian mixture model for urban land-cover mapping based on VHR remote sensing imagery [J].
Tao, Jianbin ;
Shu, Ning ;
Wang, Yu ;
Hu, Qingwu ;
Zhang, Yanbing .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2016, 37 (01) :1-13
[35]   Learning Remote Sensing Aleatoric Uncertainty for Semi-Supervised Change Detection [J].
Shen, Jinhao ;
Zhang, Cong ;
Zhang, Mingwei ;
Li, Qiang ;
Wang, Qi .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
[36]   Semi-supervised deep learning framework for milk analysis using NIR spectrometers [J].
Said, Mai ;
Wahba, Ayman ;
Khalil, Diaa .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2022, 228
[37]   Cross-spatiotemporal land-cover classification from VHR remote sensing images with deep learning based domain adaptation [J].
Luo, Muying ;
Ji, Shunping .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2022, 191 :105-128
[38]   Semi-supervised object detection with uncurated unlabeled data for remote sensing images [J].
Liu, Nanqing ;
Xu, Xun ;
Gao, Yingjie ;
Zhao, Yitao ;
Li, Heng-Chao .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2024, 129
[39]   SemiPSENet: A Novel Semi-Supervised Change Detection Network for Remote Sensing Images [J].
Hu, Lei ;
Li, Supeng ;
Ruan, Jiachen ;
Gao, Feng .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
[40]   Co-training with Clustering for the Semi-supervised Classification of Remote Sensing Images [J].
Aydav, Prem Shankar Singh ;
Minz, Sonjharia .
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION TECHNOLOGIES, IC3T 2015, VOL 2, 2016, 380 :659-667