SCU-CGAN: Enhancing Fire Detection through Synthetic Fire Image Generation and Dataset Augmentation

TL;DR

This paper introduces SCU-CGAN, a novel generative model that creates realistic fire images to augment datasets, significantly improving fire detection accuracy in IoT systems.

Contribution

The paper presents a new fire image generation model combining U-Net, CBAM, and an additional discriminator, outperforming existing models in image quality and detection accuracy.

Findings

SCU-CGAN achieved a 41.5% improvement in KID score over CycleGAN.

Augmented datasets increased fire detection model accuracy, notably a 56.5% increase in mAP@0.5:0.95 for YOLOv5 nano.

Generated fire images are realistic and enhance dataset diversity.

Abstract

Fire has long been linked to human life, causing severe disasters and losses. Early detection is crucial, and with the rise of home IoT technologies, household fire detection systems have emerged. However, the lack of sufficient fire datasets limits the performance of detection models. We propose the SCU-CGAN model, which integrates U-Net, CBAM, and an additional discriminator to generate realistic fire images from nonfire images. We evaluate the image quality and confirm that SCU-CGAN outperforms existing models. Specifically, SCU-CGAN achieved a 41.5% improvement in KID score compared to CycleGAN, demonstrating the superior quality of the generated fire images. Furthermore, experiments demonstrate that the augmented dataset significantly improves the accuracy of fire detection models without altering their structure. For the YOLOv5 nano model, the most notable improvement was observed in the mAP@0.5:0.95 metric, which increased by 56.5%, highlighting the effectiveness of the proposed approach.