FireLite: Leveraging Transfer Learning for Efficient Fire Detection in Resource-Constrained Environments
Mahamudul Hasan, Md Maruf Al Hossain Prince, Mohammad Samar Ansari, Sabrina Jahan, Abu Saleh Musa Miah, Jungpil Shin
TL;DR
FireLite tackles fire detection in transport scenarios where embedded IP cameras have limited computational resources. It employs transfer learning with a pre-trained MobileNet backbone, freezing most layers and training a lightweight classifier to deliver high accuracy with a small parameter count. On the FireNet dataset, FireLite achieves 99.18% accuracy with only 34,978 parameters, outperforming several larger FireNet-based models while maintaining real-time feasibility. This approach demonstrates the practicality of deploying accurate, efficient fire detectors in resource-constrained, real-world settings, with potential improvements through dataset expansion and robustness enhancements.
Abstract
Fire hazards are extremely dangerous, particularly in sectors such as the transportation industry, where political unrest increases the likelihood of their occurrence. By employing IP cameras to facilitate the setup of fire detection systems on transport vehicles, losses from fire events may be prevented proactively. However, the development of lightweight fire detection models is required due to the computational constraints of the embedded systems within these cameras. We introduce FireLite, a low-parameter convolutional neural network (CNN) designed for quick fire detection in contexts with limited resources, in response to this difficulty. With an accuracy of 98.77\%, our model -- which has just 34,978 trainable parameters achieves remarkable performance numbers. It also shows a validation loss of 8.74 and peaks at 98.77 for precision, recall, and F1-score measures. Because of its precision and efficiency, FireLite is a promising solution for fire detection in resource-constrained environments.