基于改进YOLOv8的火灾识别算法

杜 雪倩, 张 莉苓
重庆三峡学院计算机科学与工程学院

摘要


火灾识别是保障生命安全、经济资产与生态环境的核心技术。本研究提出一种改进型YOLOv8算法用于火
灾实时检测。针对火焰目标的多尺度特性及烟雾干扰问题本研究提出的改进YOLOv8算法通过融合MSDA注意
力机制。实验结果表明改进后的YOLOv8-MSDA模型性能优势明显与原始YOLOv8模型相比改进模型在精确
率指标上较基线模型增加3.3%识别召回率提升1.8%均值平均精度提高1.7%F1Score增长2.5%表明了改进模
型在多尺度目标检测上表现卓越能够满足火灾识别的准确性要求。

关键词


目标检测；深度学习；火灾识别

全文:

PDF


参考


[1]Sohan M , Sai Ram T , Rami Reddy C V .A Review

on YOLOv8 and Its Advancements[C]//International

Conference on Data Intelligence and Cognitive Informatics.

Springer, Singapore, 2024.

[2]LIU S, QI L, QIN. Path aggregation network

for instance segmentation [C]. ce on computer vision.

2019:6023-6032.Proceedings of the IEEE conference on

computer vision and pattern recognition. 2018:8759-8768

[3]Kim J H,Kim N,Park Y W,et al.Object detection

and classification based on YOLO-V5 with improved

maritime dataset[J].Journal of Marine Science and

Engineering,2022,10(3):377.

[4]Jiao J,Tang Y M,Lin K Y,et al.Dilateformer:Multiscale dilated transformer for visual recognition[J].IEEE

Transactions on Multimedia,2023.

[5]邢钰，郭喆伊，苏小囡.基于机器学习算法的我

国原油期货价格的极端风险预测[J].长春工程学院学报

（社会科学版），2024，25（04）：40-44.

[6]Redmon J , Farhadi A .YOLOv3: An Incremental

Improvement[J].arXiv e-prints, 2018.

[7]Goel L , Patel P .Improving YOLOv6 using advanced

PSO optimizer for weight selection in lung cancer detection

and classification[J].Multimedia Tools & Applications, 2024,

83(32).




DOI: http://dx.doi.org/10.12361/2661-3654-07-04-146137

Refbacks

  • 当前没有refback。