Development of a Low-Cost Fire Detection System Using Webcam-Based Spectrometer

Fire detection plays a vital role in preventing loss of life and property. Conventional systems often suffer from false alarms and limited sensitivity. This work proposes a low-cost (around$15), real-time fire detection system using a webcam-based spectrometer, utilizing a simple optical setup to capture and analyze the emission spectra of various sources. Fire is detected by comparing the real-time spectral signature of the source with reference fire spectra using the Pearson Correlation Coefficient (PCC). Experimental results demonstrate that the proposed system successfully detects fire within a range of 2 meters with 100% accuracy, even for smaller fire sources. This approach offers an affordable, portable, and reliable alternative for fire detection, especially suitable for environments where traditional methods become inadequate.