Self-Training Classification Framework with Spatial-Contextual Information for Local Climate Zones

被引:10
|
作者
Zhao, Nan [1 ,2 ]
Ma, Ailong [1 ,2 ]
Zhong, Yanfei [1 ,2 ]
Zhao, Ji [3 ]
Cao, Liqin [4 ]
机构
[1] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Peoples R China
[2] Wuhan Univ, Hubei Prov Engn Res Ctr Nat Resources Remote Sens, Wuhan 430079, Peoples R China
[3] China Univ Geosci, Coll Comp Sci, Wuhan 430074, Peoples R China
[4] Wuhan Univ, Sch Printing & Packing, Wuhan 430079, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
local climate zones (LCZ); spatial-contextual information; self-training; conditional random fields (CRF); URBAN AREAS; LAND-USE; DIFFERENCE; PATTERN; INDEX; WUDAPT; FOREST; ERROR; LCZ;
D O I
10.3390/rs11232828
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Local climate zones (LCZ) have become a generic criterion for climate analysis among global cities, as they can describe not only the urban climate but also the morphology inside the city. LCZ mapping based on the remote sensing classification method is a fundamental task, and the protocol proposed by the World Urban Database and Access Portal Tools (WUDAPT) project, which consists of random forest classification and filter-based spatial smoothing, is the most common approach. However, the classification and spatial smoothing lack a unified framework, which causes the appearance of small, isolated areas in the LCZ maps. In this paper, a spatial-contextual information-based self-training classification framework (SCSF) is proposed to solve this LCZ classification problem. In SCSF, conditional random field (CRF) is used to integrate the classification and spatial smoothing processing into one model and a self-training method is adopted, considering that the lack of sufficient expert-labeled training samples is always a big issue, especially for the complex LCZ scheme. Moreover, in the unary potentials of CRF modeling, pseudo-label selection using a self-training process is used to train the classifier, which fuses the regional spatial information through segmentation and the local neighborhood information through moving windows to provide a more reliable probabilistic classification map. In the pairwise potential function, SCSF can effectively improve the classification accuracy by integrating the spatial-contextual information through CRF. The experimental results prove that the proposed framework is efficient when compared to the traditional mapping product of WUDAPT in LCZ classification.
引用
收藏
页数:28
相关论文
共 50 条
  • [1] Spatial-Contextual Discrepancy Information Compensation for GAN Inversion
    Zhang, Ziqiang
    Yan, Yan
    Xue, Jing-Hao
    Wang, Hanzi
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 7, 2024, : 7432 - 7440
  • [2] Fast self-training based on spatial-spectral information for hyperspectral image classification
    Jin, Yao
    Dong, Yanni
    Du, Bo
    [J]. National Remote Sensing Bulletin, 2024, 28 (01) : 219 - 230
  • [3] Self-training with Neighborhood Information for the Classification of Remote Sensing Images
    Aydav, Prem Shankar Singh
    Minz, Sonajharia
    [J]. INFORMATION AND COMMUNICATION TECHNOLOGY FOR COMPETITIVE STRATEGIES, 2019, 40 : 465 - 474
  • [4] A Spatial-Contextual Support Vector Machine for Remotely Sensed Image Classification
    Li, Cheng-Hsuan
    Kuo, Bor-Chen
    Lin, Chin-Teng
    Huang, Chih-Sheng
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (03): : 784 - 799
  • [5] A ONE-CLASS CLASSIFICATION BY SPATIAL-CONTEXTUAL FOR REMOTELY SENSED IMAGE
    Wang Xiaofei
    Wu Shuang
    Zhang Ye
    Wang Aihua
    Hou Chuanlong
    [J]. 2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, : 437 - 440
  • [6] Spatial-Contextual Supervised Classifiers Explored: A Challenging Example of Lithostratigraphy Classification
    Cracknell, Matthew J.
    Reading, Anya M.
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (03) : 1371 - 1384
  • [7] Spatial-Contextual Information Utilization Framework for Land Cover Change Detection With Hyperspectral Remote Sensed Images
    Lv, Zhiyong
    Zhang, Ming
    Sun, Weiwei
    Benediktsson, Jon Atli
    Lei, Tao
    Falco, Nicola
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 (1-11): : 1 - 11
  • [8] Pedestrian Classification Using Self-Training Algorithm
    Jiralerspong, Trongmun
    [J]. 2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2019, : 515 - 520
  • [9] Using OpenStreetMap (OSM) to enhance the classification of local climate zones in the framework of WUDAPT
    Fonte, Cidalia C.
    Lopes, Patricia
    See, Linda
    Bechtel, Benjamin
    [J]. URBAN CLIMATE, 2019, 28
  • [10] SLADE: A Self-Training Framework For Distance Metric Learning
    Duan, Jiali
    Lin, Yen-Liang
    Son Tran
    Davis, Larry S.
    Kuo, C-C Jay
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 9639 - 9648