Early Stage Fire Detection System Based on Shallow Guide Deep Network

Abstract

This work concerns how to effectively detect the fire in early stage using computer vision method. As known, the flame of early fire is small and cannot be effectively detected by traditional fire detectors. Inspired by color characteristics of flame, we proposed a Shallow Guide Deep Network (SGDNet) to address the problems in existing early fire detection models. We first investigate the feature of fire in YCbCr color space, then design an SGD module to fuse shallow features, so as to guide the fusion of deep features. Backbone, anchors, head and IoU of model are redesigned according to the features of early fire to not only fuse the deep features but also reduce the size and infer time. Finally, we implement a Early Stage Fire Detection System based on our SGDNet, using embedded device as computing platform, connecting 4 IP cameras for test. Multithread is widely utilized in system for detecting and the reading and conversion operations of video streams, which effectively improves the execution efficiency and reduces the delay of system. Experimental results on dataset show high performance of our model with the advantage of small size and parameter. Application in actual scenarios proves that the delay for detection is about 1.2 s, which fulfills the requirement of early fire warning.