A lightweight global awareness deep network model for flame and smoke detection

Abstract:

Aiming at the trouble of low detection accuracy and the problem of large model size, this paper proposes a lightweight flame-and-smoke detection model depending on global awareness of images, named GAL-YOLOv5. The proposed method replaces the CBS module of original YOLOv5 in the backbone with DBS, and the C3 module with GC3, and thus constructs a lightweight backbone network DGNet. Besides, Involution (InvC3) module is proposed to enhance the global modeling ability and compress the model size, and a module using adaptive receptive fields, named FConv, is proposed to enhance the model’s perception capacity for foreground complex flame-and-smoke information in feature maps. Experimental results show that GAL-YOLOv5 increases mAP@0.5 to 70.8%, mAP@0.5:0.95 to 39.7%, reduces the number of parameters to 3.57M and the amount of calculation to 7.4GFLOPs under the premise of ensuring the detection speed. It has been verified that the model can achieve high-precision real-time detection of flame and smoke.

Key words:Object detection, flame, smoke, lightweight CNN, Involution, FRelu