Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery
Urban land cover and land use mapping plays an important role in urban planning and management. In this paper, novel multi-scale deep learning models, namely ASPP-Unet and ResASPP-Unet are proposed for urban land cover classification based on very high resolution (VHR) satellite imagery. The propose...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/18/11/3717 |
| _version_ | 1811308009665593344 |
|---|---|
| author | Pengbin Zhang Yinghai Ke Zhenxin Zhang Mingli Wang Peng Li Shuangyue Zhang |
| author_facet | Pengbin Zhang Yinghai Ke Zhenxin Zhang Mingli Wang Peng Li Shuangyue Zhang |
| author_sort | Pengbin Zhang |
| collection | DOAJ |
| description | Urban land cover and land use mapping plays an important role in urban planning and management. In this paper, novel multi-scale deep learning models, namely ASPP-Unet and ResASPP-Unet are proposed for urban land cover classification based on very high resolution (VHR) satellite imagery. The proposed ASPP-Unet model consists of a contracting path which extracts the high-level features, and an expansive path, which up-samples the features to create a high-resolution output. The atrous spatial pyramid pooling (ASPP) technique is utilized in the bottom layer in order to incorporate multi-scale deep features into a discriminative feature. The ResASPP-Unet model further improves the architecture by replacing each layer with residual unit. The models were trained and tested based on WorldView-2 (WV2) and WorldView-3 (WV3) imageries over the city of Beijing. Model parameters including layer depth and the number of initial feature maps (IFMs) as well as the input image bands were evaluated in terms of their impact on the model performances. It is shown that the ResASPP-Unet model with 11 layers and 64 IFMs based on 8-band WV2 imagery produced the highest classification accuracy (87.1% for WV2 imagery and 84.0% for WV3 imagery). The ASPP-Unet model with the same parameter setting produced slightly lower accuracy, with overall accuracy of 85.2% for WV2 imagery and 83.2% for WV3 imagery. Overall, the proposed models outperformed the state-of-the-art models, e.g., U-Net, convolutional neural network (CNN) and Support Vector Machine (SVM) model over both WV2 and WV3 images, and yielded robust and efficient urban land cover classification results. |
| first_indexed | 2024-04-13T09:15:21Z |
| format | Article |
| id | doaj.art-596c51baaea942278b76052816417024 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T09:15:21Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-596c51baaea942278b760528164170242022-12-22T02:52:45ZengMDPI AGSensors1424-82202018-11-011811371710.3390/s18113717s18113717Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite ImageryPengbin Zhang0Yinghai Ke1Zhenxin Zhang2Mingli Wang3Peng Li4Shuangyue Zhang5Laboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaLaboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaLaboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaLaboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaLaboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaLaboratory Cultivation Base of Environment Process and Digital Simulation, Capital Normal University, Beijing 100048, ChinaUrban land cover and land use mapping plays an important role in urban planning and management. In this paper, novel multi-scale deep learning models, namely ASPP-Unet and ResASPP-Unet are proposed for urban land cover classification based on very high resolution (VHR) satellite imagery. The proposed ASPP-Unet model consists of a contracting path which extracts the high-level features, and an expansive path, which up-samples the features to create a high-resolution output. The atrous spatial pyramid pooling (ASPP) technique is utilized in the bottom layer in order to incorporate multi-scale deep features into a discriminative feature. The ResASPP-Unet model further improves the architecture by replacing each layer with residual unit. The models were trained and tested based on WorldView-2 (WV2) and WorldView-3 (WV3) imageries over the city of Beijing. Model parameters including layer depth and the number of initial feature maps (IFMs) as well as the input image bands were evaluated in terms of their impact on the model performances. It is shown that the ResASPP-Unet model with 11 layers and 64 IFMs based on 8-band WV2 imagery produced the highest classification accuracy (87.1% for WV2 imagery and 84.0% for WV3 imagery). The ASPP-Unet model with the same parameter setting produced slightly lower accuracy, with overall accuracy of 85.2% for WV2 imagery and 83.2% for WV3 imagery. Overall, the proposed models outperformed the state-of-the-art models, e.g., U-Net, convolutional neural network (CNN) and Support Vector Machine (SVM) model over both WV2 and WV3 images, and yielded robust and efficient urban land cover classification results.https://www.mdpi.com/1424-8220/18/11/3717urban land cover classificationhigh spatial resolution satellite imagerydeep learningU-NetCNN |
| spellingShingle | Pengbin Zhang Yinghai Ke Zhenxin Zhang Mingli Wang Peng Li Shuangyue Zhang Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery Sensors urban land cover classification high spatial resolution satellite imagery deep learning U-Net CNN |
| title | Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery |
| title_full | Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery |
| title_fullStr | Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery |
| title_full_unstemmed | Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery |
| title_short | Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery |
| title_sort | urban land use and land cover classification using novel deep learning models based on high spatial resolution satellite imagery |
| topic | urban land cover classification high spatial resolution satellite imagery deep learning U-Net CNN |
| url | https://www.mdpi.com/1424-8220/18/11/3717 |
| work_keys_str_mv | AT pengbinzhang urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery AT yinghaike urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery AT zhenxinzhang urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery AT mingliwang urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery AT pengli urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery AT shuangyuezhang urbanlanduseandlandcoverclassificationusingnoveldeeplearningmodelsbasedonhighspatialresolutionsatelliteimagery |