Examination on Fire Detection Methods using Computer Vision

Fire detection is important in fire alarms, firefighting robots, and other applications. Traditional techniques for detecting the presence of a fire using smoke sensors are not always effective. Fire detection has become much more effective in real time due to computer vision approaches. This study...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2022 International Conference on Automation, Computing and Renewable Systems (ICACRS) s. 1251 - 1258
Hlavní autoři:	V C, Sikhin, Subramanian, S Sankara, R V, Sreelekshmi
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 13.12.2022
Témata:	Computational modeling Computer vision fire detection Haar Cascade HSV Image color analysis Image processing Image segmentation Lighting RGB Training Training data YCbCr YOLO
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Fire detection is important in fire alarms, firefighting robots, and other applications. Traditional techniques for detecting the presence of a fire using smoke sensors are not always effective. Fire detection has become much more effective in real time due to computer vision approaches. This study analyses various fire detection methods that make use of image processing and object detection. Furthermore, this research study compares the performance of various colour detection models such as RGB (Red; Green; Blue), HSV (Hue; Saturation; Value), and YcbCr (Luminance; Chroma; Blue; Chroma; Red), as well as object detection algorithms such as Haar-cascade and YOLO (You Only Look Once) for fire detection. Moreover, this study also aims to make a breakthrough in existing fire detection methods by experimenting with colour models and object detection methods.
DOI:	10.1109/ICACRS55517.2022.10029088