Impact of Deep Convolutional Neural Network Structure on Photovoltaic Array Extraction from High Spatial Resolution Remote Sensing Images
文献类型:期刊论文
作者 | Li, Liang2,3; Lu, Ning1,3; Jiang, Hou3; Qin, Jun1,3 |
刊名 | REMOTE SENSING |
出版日期 | 2023-09-01 |
卷号 | 15期号:18页码:16 |
关键词 | high spatial resolution remote sensing images photovoltaic array extraction deep convolutional neural networks low- and high-level features |
DOI | 10.3390/rs15184554 |
通讯作者 | Lu, Ning(lvn@lreis.ac.cn) |
英文摘要 | Accurate information on the location, shape, and size of photovoltaic (PV) arrays is essential for optimal power system planning and energy system development. In this study, we explore the potential of deep convolutional neural networks (DCNNs) for extracting PV arrays from high spatial resolution remote sensing (HSRRS) images. While previous research has mainly focused on the application of DCNNs, little attention has been paid to investigating the influence of different DCNN structures on the accuracy of PV array extraction. To address this gap, we compare the performance of seven popular DCNNs-AlexNet, VGG16, ResNet50, ResNeXt50, Xception, DenseNet121, and EfficientNetB6-based on a PV array dataset containing 2072 images of 1024 x 1024 size. We evaluate their intersection over union (IoU) values and highlight four DCNNs (EfficientNetB6, Xception, ResNeXt50, and VGG16) that consistently achieve IoU values above 94%. Furthermore, through analyzing the difference in the structure and features of these four DCNNs, we identify structural factors that contribute to the extraction of low-level spatial features (LFs) and high-level semantic features (HFs) of PV arrays. We find that the first feature extraction block without downsampling enhances the LFs' extraction capability of the DCNNs, resulting in an increase in IoU values of approximately 0.25%. In addition, the use of separable convolution and attention mechanisms plays a crucial role in improving the HFs' extraction, resulting in a 0.7% and 0.4% increase in IoU values, respectively. Overall, our study provides valuable insights into the impact of DCNN structures on the extraction of PV arrays from HSRRS images. These findings have significant implications for the selection of appropriate DCNNs and the design of robust DCNNs tailored for the accurate and efficient extraction of PV arrays. |
资助项目 | We are grateful to the Geographic Information Center of Jiangsu Province for providing computational resources, and the GitHub user Bubbliiiing for sharing the DeeplabV3_plus code ( |
WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | MDPI |
WOS记录号 | WOS:001072961000001 |
资助机构 | We are grateful to the Geographic Information Center of Jiangsu Province for providing computational resources, and the GitHub user Bubbliiiing for sharing the DeeplabV3_plus code ( |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/198179] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Lu, Ning |
作者单位 | 1.Nanjing Normal Univ, Jiangsu Ctr Collaborat Innovat Geog Informat Resou, 1 Wenyuan Rd, Nanjing 210023, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Liang,Lu, Ning,Jiang, Hou,et al. Impact of Deep Convolutional Neural Network Structure on Photovoltaic Array Extraction from High Spatial Resolution Remote Sensing Images[J]. REMOTE SENSING,2023,15(18):16. |
APA | Li, Liang,Lu, Ning,Jiang, Hou,&Qin, Jun.(2023).Impact of Deep Convolutional Neural Network Structure on Photovoltaic Array Extraction from High Spatial Resolution Remote Sensing Images.REMOTE SENSING,15(18),16. |
MLA | Li, Liang,et al."Impact of Deep Convolutional Neural Network Structure on Photovoltaic Array Extraction from High Spatial Resolution Remote Sensing Images".REMOTE SENSING 15.18(2023):16. |
入库方式: OAI收割
来源:地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。