Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China
This paper presents a novel approach for semantic segmentation of building roofs in dense urban environments with a Deep Convolution Neural Network (DCNN) using Chinese Very High Resolution (VHR) satellite (i.e., GF2) imagery. To provide an operational end-to-end approach for accurately mapping buil...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/5/1164 |
| _version_ | 1811213448708620288 |
|---|---|
| author | Yuchu Qin Yunchao Wu Bin Li Shuai Gao Miao Liu Yulin Zhan |
| author_facet | Yuchu Qin Yunchao Wu Bin Li Shuai Gao Miao Liu Yulin Zhan |
| author_sort | Yuchu Qin |
| collection | DOAJ |
| description | This paper presents a novel approach for semantic segmentation of building roofs in dense urban environments with a Deep Convolution Neural Network (DCNN) using Chinese Very High Resolution (VHR) satellite (i.e., GF2) imagery. To provide an operational end-to-end approach for accurately mapping build roofs with feature extraction and image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform building roof segmentation. We selected typical cities with dense and diverse urban environments in different metropolitan regions of China as study areas, and sample images were collected over cities. High performance GPU-mounted workstations are employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with convolution layers is developed for building roof segmentation. The validation shows that the overall accuracy (OA) and the mean Intersection Over Union (mIOU) of DCNN-based semantic segmentation results are 94.67% and 0.85, respectively, and the CRF-refined segmentation results achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas in dense urban environments with different building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline of operational built-up area monitoring, and the timely update of building roof map could be applied in urban management and assessment of human settlement-related sustainable development goals over large areas. |
| first_indexed | 2024-04-12T05:45:51Z |
| format | Article |
| id | doaj.art-ed47f859a0f24802a43091b6aab4d076 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-12T05:45:51Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ed47f859a0f24802a43091b6aab4d0762022-12-22T03:45:27ZengMDPI AGSensors1424-82202019-03-01195116410.3390/s19051164s19051164Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in ChinaYuchu Qin0Yunchao Wu1Bin Li2Shuai Gao3Miao Liu4Yulin Zhan5State Key Lab of Remote Sensing Sciences, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100101, ChinaBeijing Municipal Institute of City Planning & Design, Beijing 100045, ChinaState Key Lab of Remote Sensing Sciences, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100101, ChinaState Key Lab of Remote Sensing Sciences, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100101, ChinaDepartment of Mathematics & Statistics, South Dakota State University, Brookings, 57006 SD, USAState Key Lab of Remote Sensing Sciences, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100101, ChinaThis paper presents a novel approach for semantic segmentation of building roofs in dense urban environments with a Deep Convolution Neural Network (DCNN) using Chinese Very High Resolution (VHR) satellite (i.e., GF2) imagery. To provide an operational end-to-end approach for accurately mapping build roofs with feature extraction and image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform building roof segmentation. We selected typical cities with dense and diverse urban environments in different metropolitan regions of China as study areas, and sample images were collected over cities. High performance GPU-mounted workstations are employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with convolution layers is developed for building roof segmentation. The validation shows that the overall accuracy (OA) and the mean Intersection Over Union (mIOU) of DCNN-based semantic segmentation results are 94.67% and 0.85, respectively, and the CRF-refined segmentation results achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas in dense urban environments with different building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline of operational built-up area monitoring, and the timely update of building roof map could be applied in urban management and assessment of human settlement-related sustainable development goals over large areas.http://www.mdpi.com/1424-8220/19/5/1164VHR imagebuilding roofsegmentationGF2deep convolution neural network |
| spellingShingle | Yuchu Qin Yunchao Wu Bin Li Shuai Gao Miao Liu Yulin Zhan Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China Sensors VHR image building roof segmentation GF2 deep convolution neural network |
| title | Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China |
| title_full | Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China |
| title_fullStr | Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China |
| title_full_unstemmed | Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China |
| title_short | Semantic Segmentation of Building Roof in Dense Urban Environment with Deep Convolutional Neural Network: A Case Study Using GF2 VHR Imagery in China |
| title_sort | semantic segmentation of building roof in dense urban environment with deep convolutional neural network a case study using gf2 vhr imagery in china |
| topic | VHR image building roof segmentation GF2 deep convolution neural network |
| url | http://www.mdpi.com/1424-8220/19/5/1164 |
| work_keys_str_mv | AT yuchuqin semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina AT yunchaowu semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina AT binli semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina AT shuaigao semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina AT miaoliu semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina AT yulinzhan semanticsegmentationofbuildingroofindenseurbanenvironmentwithdeepconvolutionalneuralnetworkacasestudyusinggf2vhrimageryinchina |