Loading...
Please wait, while we are loading the content...
A Study on a Complex Flame and Smoke Detection Method Using Computer Vision Detection and Convolutional Neural Network
| Content Provider | MDPI |
|---|---|
| Author | Ryu, Jinkyu Kwak, Dongkurl |
| Copyright Year | 2022 |
| Description | This study sought an effective detection method not only for flame but also for the smoke generated in the event of a fire. To this end, the flame region was pre-processed using the color conversion and corner detection method, and the smoke region could be detected using the dark channel prior and optical flow. This eliminates unnecessary background regions and allows selection of fire-related regions. Where there was a pre-processed region of interest, inference was conducted using a deep-learning-based convolutional neural network (CNN) to accurately determine whether it was a flame or smoke. Through this approach, the detection accuracy is improved by 5.5% for flame and 6% for smoke compared to when a fire is detected through the object detection model without separate pre-processing. |
| Starting Page | 108 |
| e-ISSN | 25716255 |
| DOI | 10.3390/fire5040108 |
| Journal | Fire |
| Issue Number | 4 |
| Volume Number | 5 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-07-27 |
| Access Restriction | Open |
| Subject Keyword | Fire Anesthesiology Fire Safety System Computer Vision Image Processing Deep Learning |
| Content Type | Text |
| Resource Type | Article |
