A Multi-object Detection Method for Building Fire Warnings through Artificial Intelligence Generated Content
发表于 Scientific Reports, 2025
本研究提出基于 AIGC 的建筑火灾多目标检测方法,通过构建 AIGC 数据集解决真实样本匮乏问题,改进模型后实现 95.7% 的火焰与烟雾检测精度,能在火灾发生 2 秒内完成预警,效率较传统报警器提升 6.5 倍以上,为人员疏散和救援提供及时预警支持。
引用方式: Fu, J., Xu, Z.*, Yue, Q., Lin, J., Zhang, N., Zhao, Y., Gu, D. (2025). A Multi-object Detection Method for Building Fire Warnings through Artificial Intelligence Generated Content. Scientific Reports, 15, 18434. doi: 10.1038/s41598-025-02865-4 http://doi.org/10.1038/s41598-025-02865-4