Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand
It is necessary to ensure security and community safety around High Voltage Transmission Poles (HVTP). Legislation requires a safety perimeter around HVTP and the High Voltage Lines (HVL) where no building and tree can be located. However, surveying thousands of kilometers of circuit is an expensive...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Systems and Soft Computing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772941924000097 |
| _version_ | 1797258691277225984 |
|---|---|
| author | Bastien Marty Raphael Gaudin Tom Piperno Didier Rouquette Cyrille Schwob Laurent Mezeix |
| author_facet | Bastien Marty Raphael Gaudin Tom Piperno Didier Rouquette Cyrille Schwob Laurent Mezeix |
| author_sort | Bastien Marty |
| collection | DOAJ |
| description | It is necessary to ensure security and community safety around High Voltage Transmission Poles (HVTP). Legislation requires a safety perimeter around HVTP and the High Voltage Lines (HVL) where no building and tree can be located. However, surveying thousands of kilometers of circuit is an expensive and challenging task that is currently performed by human inspection. Therefore, the use of automatic detection methods enables to facilitate the inspection is necessary to reduce time and cost. Convolutional Neural Network (CNN) is proposed in this work to detect, from Google Earth images, buildings and trees within the safety perimeter of HVTP. A dedicated 3 class (House, forest and HVTP) dataset of approximately 1 million tiles with a resolution of 0.09 m/pixel is created. Tiles size for trees and building classes is 64 × 64 pixels while for the HVTP 128 × 128 pixels is used. Three CNN models are built and optimized to classify each of these classes. Models validation shows that, except for houses where the accuracy is only 84 %, the other two classes have an accuracy of over 89 %. Moreover, by analyzing the classified HVTP, type can be identified. Finally, buildings and trees within the safety perimeter around the HVTP can be identified and displayed on the image demonstrating the usefulness of the tool. |
| first_indexed | 2024-04-24T22:57:33Z |
| format | Article |
| id | doaj.art-e849cd921bc0452bb740d1205ebc53c8 |
| institution | Directory Open Access Journal |
| issn | 2772-9419 |
| language | English |
| last_indexed | 2024-04-24T22:57:33Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Systems and Soft Computing |
| spelling | doaj.art-e849cd921bc0452bb740d1205ebc53c82024-03-18T04:34:54ZengElsevierSystems and Soft Computing2772-94192024-12-016200080Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in ThailandBastien Marty0Raphael Gaudin1Tom Piperno2Didier Rouquette3Cyrille Schwob4Laurent Mezeix5INSA Toulouse, 135 Avenue de Rangueil, 31400 Toulouse Cedex, FranceINSA Toulouse, 135 Avenue de Rangueil, 31400 Toulouse Cedex, FranceINSA Toulouse, 135 Avenue de Rangueil, 31400 Toulouse Cedex, FranceAirbus Defence and Space, 5 rue des Satellites, BP 14359 F-31030, Toulouse Cedex 4, FranceAirbus Singapore, 12 Seletar Aerospace Link, 797553, SingaporeFaculty of Engineering, Burapha University, 169 Long-Hard Bangsaen Road Chonburi 20131, Thailand; Corresponding author.It is necessary to ensure security and community safety around High Voltage Transmission Poles (HVTP). Legislation requires a safety perimeter around HVTP and the High Voltage Lines (HVL) where no building and tree can be located. However, surveying thousands of kilometers of circuit is an expensive and challenging task that is currently performed by human inspection. Therefore, the use of automatic detection methods enables to facilitate the inspection is necessary to reduce time and cost. Convolutional Neural Network (CNN) is proposed in this work to detect, from Google Earth images, buildings and trees within the safety perimeter of HVTP. A dedicated 3 class (House, forest and HVTP) dataset of approximately 1 million tiles with a resolution of 0.09 m/pixel is created. Tiles size for trees and building classes is 64 × 64 pixels while for the HVTP 128 × 128 pixels is used. Three CNN models are built and optimized to classify each of these classes. Models validation shows that, except for houses where the accuracy is only 84 %, the other two classes have an accuracy of over 89 %. Moreover, by analyzing the classified HVTP, type can be identified. Finally, buildings and trees within the safety perimeter around the HVTP can be identified and displayed on the image demonstrating the usefulness of the tool.http://www.sciencedirect.com/science/article/pii/S2772941924000097Convolutional neural networkImage processingLand coverUtility poleInfrastructure mapping |
| spellingShingle | Bastien Marty Raphael Gaudin Tom Piperno Didier Rouquette Cyrille Schwob Laurent Mezeix Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand Systems and Soft Computing Convolutional neural network Image processing Land cover Utility pole Infrastructure mapping |
| title | Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand |
| title_full | Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand |
| title_fullStr | Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand |
| title_full_unstemmed | Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand |
| title_short | Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand |
| title_sort | methodology to classify high voltage transmission poles using cnn approach from satellite images for safety public regulation application study case of rural area in thailand |
| topic | Convolutional neural network Image processing Land cover Utility pole Infrastructure mapping |
| url | http://www.sciencedirect.com/science/article/pii/S2772941924000097 |
| work_keys_str_mv | AT bastienmarty methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand AT raphaelgaudin methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand AT tompiperno methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand AT didierrouquette methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand AT cyrilleschwob methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand AT laurentmezeix methodologytoclassifyhighvoltagetransmissionpolesusingcnnapproachfromsatelliteimagesforsafetypublicregulationapplicationstudycaseofruralareainthailand |