Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios
In this study, we propose using a thermal imaging camera (TIC) with a deep learning model as an intelligent human detection approach during emergency evacuations in a low-visibility smoky fire scenarios. We use low-wavelength infrared (LWIR) images taken by a TIC qualified with the National Fire Pro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5351 |
| _version_ | 1797443842454061056 |
|---|---|
| author | Pei-Fen Tsai Chia-Hung Liao Shyan-Ming Yuan |
| author_facet | Pei-Fen Tsai Chia-Hung Liao Shyan-Ming Yuan |
| author_sort | Pei-Fen Tsai |
| collection | DOAJ |
| description | In this study, we propose using a thermal imaging camera (TIC) with a deep learning model as an intelligent human detection approach during emergency evacuations in a low-visibility smoky fire scenarios. We use low-wavelength infrared (LWIR) images taken by a TIC qualified with the National Fire Protection Association (NFPA) 1801 standards as input to the YOLOv4 model for real-time object detection. The model trained with a single Nvidia GeForce 2070 can achieve >95% precision for the location of people in a low-visibility smoky scenario with 30.1 frames per second (FPS). This real-time result can be reported to control centers as useful information to help provide timely rescue and provide protection to firefighters before entering dangerous smoky fire situations. |
| first_indexed | 2024-03-09T13:02:54Z |
| format | Article |
| id | doaj.art-870afb98ddc14f18b2542f227f4a59da |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T13:02:54Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-870afb98ddc14f18b2542f227f4a59da2023-11-30T21:52:17ZengMDPI AGSensors1424-82202022-07-012214535110.3390/s22145351Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke ScenariosPei-Fen Tsai0Chia-Hung Liao1Shyan-Ming Yuan2Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanDepartment of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanDepartment of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanIn this study, we propose using a thermal imaging camera (TIC) with a deep learning model as an intelligent human detection approach during emergency evacuations in a low-visibility smoky fire scenarios. We use low-wavelength infrared (LWIR) images taken by a TIC qualified with the National Fire Protection Association (NFPA) 1801 standards as input to the YOLOv4 model for real-time object detection. The model trained with a single Nvidia GeForce 2070 can achieve >95% precision for the location of people in a low-visibility smoky scenario with 30.1 frames per second (FPS). This real-time result can be reported to control centers as useful information to help provide timely rescue and provide protection to firefighters before entering dangerous smoky fire situations.https://www.mdpi.com/1424-8220/22/14/5351thermal imaging cameraLWIRinfrared thermal cameraconvolutional neural networkevacuation in firehuman detection |
| spellingShingle | Pei-Fen Tsai Chia-Hung Liao Shyan-Ming Yuan Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios Sensors thermal imaging camera LWIR infrared thermal camera convolutional neural network evacuation in fire human detection |
| title | Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios |
| title_full | Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios |
| title_fullStr | Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios |
| title_full_unstemmed | Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios |
| title_short | Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios |
| title_sort | using deep learning with thermal imaging for human detection in heavy smoke scenarios |
| topic | thermal imaging camera LWIR infrared thermal camera convolutional neural network evacuation in fire human detection |
| url | https://www.mdpi.com/1424-8220/22/14/5351 |
| work_keys_str_mv | AT peifentsai usingdeeplearningwiththermalimagingforhumandetectioninheavysmokescenarios AT chiahungliao usingdeeplearningwiththermalimagingforhumandetectioninheavysmokescenarios AT shyanmingyuan usingdeeplearningwiththermalimagingforhumandetectioninheavysmokescenarios |