An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach
With an increase in both global warming and the human population, forest fires have become a major global concern. This can lead to climatic shifts and the greenhouse effect, among other adverse outcomes. Surprisingly, human activities have caused a disproportionate number of forest fires. Fast dete...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1512 |
| _version_ | 1797623222490890240 |
|---|---|
| author | Akmalbek Bobomirzaevich Abdusalomov Bappy MD Siful Islam Rashid Nasimov Mukhriddin Mukhiddinov Taeg Keun Whangbo |
| author_facet | Akmalbek Bobomirzaevich Abdusalomov Bappy MD Siful Islam Rashid Nasimov Mukhriddin Mukhiddinov Taeg Keun Whangbo |
| author_sort | Akmalbek Bobomirzaevich Abdusalomov |
| collection | DOAJ |
| description | With an increase in both global warming and the human population, forest fires have become a major global concern. This can lead to climatic shifts and the greenhouse effect, among other adverse outcomes. Surprisingly, human activities have caused a disproportionate number of forest fires. Fast detection with high accuracy is the key to controlling this unexpected event. To address this, we proposed an improved forest fire detection method to classify fires based on a new version of the Detectron2 platform (a ground-up rewrite of the Detectron library) using deep learning approaches. Furthermore, a custom dataset was created and labeled for the training model, and it achieved higher precision than the other models. This robust result was achieved by improving the Detectron2 model in various experimental scenarios with a custom dataset and 5200 images. The proposed model can detect small fires over long distances during the day and night. The advantage of using the Detectron2 algorithm is its long-distance detection of the object of interest. The experimental results proved that the proposed forest fire detection method successfully detected fires with an improved precision of 99.3%. |
| first_indexed | 2024-03-11T09:25:37Z |
| format | Article |
| id | doaj.art-c70ab6cb4212437684fca2ee8564776f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:25:37Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c70ab6cb4212437684fca2ee8564776f2023-11-16T18:02:08ZengMDPI AGSensors1424-82202023-01-01233151210.3390/s23031512An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning ApproachAkmalbek Bobomirzaevich Abdusalomov0Bappy MD Siful Islam1Rashid Nasimov2Mukhriddin Mukhiddinov3Taeg Keun Whangbo4Department of Computer Engineering, Gachon University, Sujeong-gu, Seongnam-si 461-701, Gyeonggi-do, Republic of KoreaDepartment of Computer Engineering, Gachon University, Sujeong-gu, Seongnam-si 461-701, Gyeonggi-do, Republic of KoreaDepartment of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, UzbekistanDepartment of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, UzbekistanDepartment of Computer Engineering, Gachon University, Sujeong-gu, Seongnam-si 461-701, Gyeonggi-do, Republic of KoreaWith an increase in both global warming and the human population, forest fires have become a major global concern. This can lead to climatic shifts and the greenhouse effect, among other adverse outcomes. Surprisingly, human activities have caused a disproportionate number of forest fires. Fast detection with high accuracy is the key to controlling this unexpected event. To address this, we proposed an improved forest fire detection method to classify fires based on a new version of the Detectron2 platform (a ground-up rewrite of the Detectron library) using deep learning approaches. Furthermore, a custom dataset was created and labeled for the training model, and it achieved higher precision than the other models. This robust result was achieved by improving the Detectron2 model in various experimental scenarios with a custom dataset and 5200 images. The proposed model can detect small fires over long distances during the day and night. The advantage of using the Detectron2 algorithm is its long-distance detection of the object of interest. The experimental results proved that the proposed forest fire detection method successfully detected fires with an improved precision of 99.3%.https://www.mdpi.com/1424-8220/23/3/1512forest firefire detectionDetectron2deep learningfire image dataset |
| spellingShingle | Akmalbek Bobomirzaevich Abdusalomov Bappy MD Siful Islam Rashid Nasimov Mukhriddin Mukhiddinov Taeg Keun Whangbo An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach Sensors forest fire fire detection Detectron2 deep learning fire image dataset |
| title | An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach |
| title_full | An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach |
| title_fullStr | An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach |
| title_full_unstemmed | An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach |
| title_short | An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach |
| title_sort | improved forest fire detection method based on the detectron2 model and a deep learning approach |
| topic | forest fire fire detection Detectron2 deep learning fire image dataset |
| url | https://www.mdpi.com/1424-8220/23/3/1512 |
| work_keys_str_mv | AT akmalbekbobomirzaevichabdusalomov animprovedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT bappymdsifulislam animprovedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT rashidnasimov animprovedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT mukhriddinmukhiddinov animprovedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT taegkeunwhangbo animprovedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT akmalbekbobomirzaevichabdusalomov improvedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT bappymdsifulislam improvedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT rashidnasimov improvedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT mukhriddinmukhiddinov improvedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach AT taegkeunwhangbo improvedforestfiredetectionmethodbasedonthedetectron2modelandadeeplearningapproach |