This paper proposes a fully automated generative network (“SynFAGnet”) for automatically creating a realistic-looking synthetic fire image. SynFAGnet is used as a data augmentation technique to create diverse data for training models, thereby solving problems related to real data acquisition and data imbalances. SynFAGnet comprises two main parts: an object-scene placement net (OSPNet) and a local–global context-based generative adversarial network (LGC-GAN). The OSPNet identifies suitable positions and scales for fires corresponding to the background scene. The LGC-GAN enhances the realistic appearance of synthetic fire images created by a given fire object-background scene pair by assembling effects such as halos and reflections in the surrounding area in the background scene. A comparative analysis shows that SynFAGnet achieves better outcomes than previous studies for both the Fréchet inception distance and learned perceptual image patch similarity evaluation metrics (values of 17.232 and 0.077, respectively). In addition, SynFAGnet is verified as a practically applicable data augmentation technique for training datasets, as it improves the detection and instance segmentation performance.

本文提出了一种全自动生成网络（“SynFAGnet”），用于自动创建逼真的合成火灾图像。 SynFAGnet用作数据增强技术，为训练模型创建多样化的数据，从而解决与实际数据获取和数据不平衡相关的问题。 SynFAGnet 包括两个主要部分：对象场景放置网络（OSPNet）和基于本地-全局上下文的生成对抗网络（LGC-GAN）。 OSPNet 识别与背景场景相对应的火灾的合适位置和规模。 LGC-GAN 通过组合背景场景中周围区域的光晕和反射等效果，增强了由给定火灾对象-背景场景对创建的合成火灾图像的真实感。比较分析表明，SynFAGnet 在 Fréchet 起始距离和学习感知图像块相似性评估指标（值分别为 17.232 和 0.077）方面均取得了比之前研究更好的结果。此外，SynFAGnet 被验证为一种用于训练数据集的实际适用的数据增强技术，因为它提高了检测和实例分割性能。