Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model
Nowadays, the world is in a transition towards renewable energy solar being one of the most promising sources used today. However, Solar Photovoltaic (PV) systems present great challenges for their proper performance such as dirt and environmental conditions that may reduce the output energy of the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/14/6524 |
| _version_ | 1797527650110013440 |
|---|---|
| author | Andrés Pérez-González Álvaro Jaramillo-Duque Juan Bernardo Cano-Quintero |
| author_facet | Andrés Pérez-González Álvaro Jaramillo-Duque Juan Bernardo Cano-Quintero |
| author_sort | Andrés Pérez-González |
| collection | DOAJ |
| description | Nowadays, the world is in a transition towards renewable energy solar being one of the most promising sources used today. However, Solar Photovoltaic (PV) systems present great challenges for their proper performance such as dirt and environmental conditions that may reduce the output energy of the PV plants. For this reason, inspection and periodic maintenance are essential to extend useful life. The use of unmanned aerial vehicles (UAV) for inspection and maintenance of PV plants favor a timely diagnosis. UAV path planning algorithm over a PV facility is required to better perform this task. Therefore, it is necessary to explore how to extract the boundary of PV facilities with some techniques. This research work focuses on an automatic boundary extraction method of PV plants from imagery using a deep neural network model with a U-net structure. The results obtained were evaluated by comparing them with other reported works. Additionally, to achieve the boundary extraction processes, the standard metrics Intersection over Union (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>o</mi><mi>U</mi></mrow></semantics></math></inline-formula>) and the Dice Coefficient (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>D</mi><mi>C</mi></mrow></semantics></math></inline-formula>) were considered to make a better conclusion among all methods. The experimental results evaluated on the Amir dataset show that the proposed approach can significantly improve the boundary and segmentation performance in the test stage up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.42</mn></mrow></semantics></math></inline-formula>% and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.42</mn></mrow></semantics></math></inline-formula>% as calculated by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>o</mi><mi>U</mi></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>D</mi><mi>C</mi></mrow></semantics></math></inline-formula> metrics, respectively. Furthermore, the training period was faster. Consequently, it is envisaged that the proposed U-Net model will be an advantage in remote sensing image segmentation. |
| first_indexed | 2024-03-10T09:45:48Z |
| format | Article |
| id | doaj.art-399a25c69bf94fc484ffd2e245daa970 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:45:48Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-399a25c69bf94fc484ffd2e245daa9702023-11-22T03:11:08ZengMDPI AGApplied Sciences2076-34172021-07-011114652410.3390/app11146524Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net ModelAndrés Pérez-González0Álvaro Jaramillo-Duque1Juan Bernardo Cano-Quintero2Research Group in Efficient Energy Management (GIMEL), Electrical Engineering Department, Universidad de Antioquia, Calle 67 No. 53-108, Medellín 050010, ColombiaResearch Group in Efficient Energy Management (GIMEL), Electrical Engineering Department, Universidad de Antioquia, Calle 67 No. 53-108, Medellín 050010, ColombiaResearch Group in Efficient Energy Management (GIMEL), Electrical Engineering Department, Universidad de Antioquia, Calle 67 No. 53-108, Medellín 050010, ColombiaNowadays, the world is in a transition towards renewable energy solar being one of the most promising sources used today. However, Solar Photovoltaic (PV) systems present great challenges for their proper performance such as dirt and environmental conditions that may reduce the output energy of the PV plants. For this reason, inspection and periodic maintenance are essential to extend useful life. The use of unmanned aerial vehicles (UAV) for inspection and maintenance of PV plants favor a timely diagnosis. UAV path planning algorithm over a PV facility is required to better perform this task. Therefore, it is necessary to explore how to extract the boundary of PV facilities with some techniques. This research work focuses on an automatic boundary extraction method of PV plants from imagery using a deep neural network model with a U-net structure. The results obtained were evaluated by comparing them with other reported works. Additionally, to achieve the boundary extraction processes, the standard metrics Intersection over Union (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>o</mi><mi>U</mi></mrow></semantics></math></inline-formula>) and the Dice Coefficient (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>D</mi><mi>C</mi></mrow></semantics></math></inline-formula>) were considered to make a better conclusion among all methods. The experimental results evaluated on the Amir dataset show that the proposed approach can significantly improve the boundary and segmentation performance in the test stage up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.42</mn></mrow></semantics></math></inline-formula>% and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.42</mn></mrow></semantics></math></inline-formula>% as calculated by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>o</mi><mi>U</mi></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>D</mi><mi>C</mi></mrow></semantics></math></inline-formula> metrics, respectively. Furthermore, the training period was faster. Consequently, it is envisaged that the proposed U-Net model will be an advantage in remote sensing image segmentation.https://www.mdpi.com/2076-3417/11/14/6524deep learning (DL)unmanned aerial vehicle (UAV)photovoltaic (PV) systemsimage-processingimage segmentationsemantic segmentation |
| spellingShingle | Andrés Pérez-González Álvaro Jaramillo-Duque Juan Bernardo Cano-Quintero Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model Applied Sciences deep learning (DL) unmanned aerial vehicle (UAV) photovoltaic (PV) systems image-processing image segmentation semantic segmentation |
| title | Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model |
| title_full | Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model |
| title_fullStr | Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model |
| title_full_unstemmed | Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model |
| title_short | Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model |
| title_sort | automatic boundary extraction for photovoltaic plants using the deep learning u net model |
| topic | deep learning (DL) unmanned aerial vehicle (UAV) photovoltaic (PV) systems image-processing image segmentation semantic segmentation |
| url | https://www.mdpi.com/2076-3417/11/14/6524 |
| work_keys_str_mv | AT andresperezgonzalez automaticboundaryextractionforphotovoltaicplantsusingthedeeplearningunetmodel AT alvarojaramilloduque automaticboundaryextractionforphotovoltaicplantsusingthedeeplearningunetmodel AT juanbernardocanoquintero automaticboundaryextractionforphotovoltaicplantsusingthedeeplearningunetmodel |