LCZ classification based on deep learning概况（持续更新）

目录

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 DatasetMSPPF-NETS: A DEEP LEARNING ARCHITECTURE FOR REMOTE SENSING IMAGE CLASSIFICATIONComparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat imagesFUSING MULTI-SEASONAL SENTINEL-2 IMAGES WITH RESIDUAL CONVOLUTIONAL NEURAL NETWORKS FOR LOCAL CLIMATE ZONE-DERIVED URBAN LAND COVER CLASSIFICATIONTowards large-scale mapping of local climate zones using multitemporal Sentinel 2 data and convolutional neural networksLocal climate zone mapping as remote sensing scene classification using deep learning: A case study of metropolitan ChinaEffective Classification of Local Climate Zones Based on Multi-Source Remote Sensing DataEmbranchment CNN based Local Climate Zone Classification using SAR and Multispectral Remote Sensing DataDeveloping High Quality Training Samples for Deep Learning Based Local Climate Zone Classification in Korea

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Chunping Qiu等，使用LCZ42数据集中的Sentinel-2数据，提出Sen2LCZ-Net-MF，对不同的网络训练结果进行了比较，ResNet、DenseNet、VGG16、Xception，Sen2LCZ-Net-MF结果指标最好

C. Qiu, X. Tong, M. Schmitt, B. Bechtel and X. X. Zhu, “Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 2793-2806, 2020, doi: 10.1109/JSTARS.2020.2995711.

MSPPF-NETS: A DEEP LEARNING ARCHITECTURE FOR REMOTE SENSING IMAGE CLASSIFICATION

Yang等，使用LCZ42数据集中的Sentinel-2影像，提出以DenseNet为基本结构的MSPPF-Nets，分类精度有所提升

Yang R , Zhang Y , Zhao P , et al. MSPPF-Nets: A Deep Learning Architecture for Remote Sensing Image Classification[C]// IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019.

Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images

YOO等，将CNN与RF进行比较，对Landsat8进行分类

Yoo C , Han D , Im J , et al. Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 157(Nov.):155-170.

FUSING MULTI-SEASONAL SENTINEL-2 IMAGES WITH RESIDUAL CONVOLUTIONAL NEURAL NETWORKS FOR LOCAL CLIMATE ZONE-DERIVED URBAN LAND COVER CLASSIFICATION

Qiu，融合多个季节的sentinel-2影像，ResNet

Qiu, Chunping & Schmitt, Michael & Zhu, Xiao. (2019). Fusing Multi-Seasonal Sentinel-2 Images with Residual Convolutional Neural Networks for Local Climate Zone-Derived Urban Land Cover Classification. 5037-5040. 10.1109/IGARSS.2019.8898223.

Towards large-scale mapping of local climate zones using multitemporal Sentinel 2 data and convolutional neural networks

Rosentreter等，Sentinel-2影像，CNN与RF比较

Rosentreter J , Hagensieker R , Waske B . Towards large-scale mapping of local climate zones using multitemporal Sentinel 2 data and convolutional neural networks[J]. Remote Sensing of Environment, 2020, 237:111472.

Local climate zone mapping as remote sensing scene classification using deep learning: A case study of metropolitan China

Liu等，将LCZ分类视为场景分类问题，选择中国的15个城市作为研究区域，残差学习与SE模块结合，提出LCZNet，分析了影像块尺寸对训练结果的影响

Liu S , Shi Q . Local climate zone mapping as remote sensing scene classification using deep learning: A case study of metropolitan China[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 164:229-242.

Effective Classification of Local Climate Zones Based on Multi-Source Remote Sensing Data

Jing Hao，使用SAR与多光谱影像，sentinel-1和sentinel-2，使用ResNeXT，结果说明加入SAR影像精度也只有微小的提高。

Jing H , Feng Y , Zhang W , et al. Effective Classification of Local Climate Zones Based on Multi-Source Remote Sensing Data[C]// IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019.

Embranchment CNN based Local Climate Zone Classification using SAR and Multispectral Remote Sensing Data

Feng等，基于DenseNet的双分支CNN，使用SAR和多光谱影像，考虑到SAR与多光谱影像的成像机制不同，在不同分支内进行特征提取

Developing High Quality Training Samples for Deep Learning Based Local Climate Zone Classification in Korea

链接: link. 大概就是建了一个韩国的分类数据集