基于改进YOLOv5的小目标火灾检测模型研究  

Research on small target fire detection model based on improved YOLOv5

作　　者：李坊朴 芮雪 李孜军[3] 宋卫国[1] LI Fangpu;RUI Xue;LI Zijun;SONG Weiguo(State Key Laboratory of Fire Science,University of Science and Technology of China.,Hefei 230026,China;School of Emergency Management,Nanjing University of Information Science and Technology.,Nanjing 210044,China;School of Resources and Safety Engineering,Central South University.,Changsha 410083,China)

机构地区：[1]中国科学技术大学火灾科学国家重点实验室,合肥230026 [2]南京信息工程大学应急管理学院,南京210044 [3]中南大学资源与安全工程学院,长沙410083

出　　处：《清华大学学报(自然科学版)》2025年第4期655-663,共9页Journal of Tsinghua University(Science and Technology)

基　　金：国家重点研发计划项目(2021YFC3000300);国家自然科学基金创新研究群体项目(52321003)。

摘　　要：目标检测技术已被广泛应用于各领域,然而火灾目标检测技术在小目标、低光照等具有挑战性的场景下通常表现不佳,且缺乏专门的公开数据集对该类技术的相应性能进行评估。该文针对YOLOv5算法细节提取能力弱、密集目标预测效果不佳等问题进行了研究。首先,制备了小目标火焰图像数据集用于模型训练和性能测试。其次,基于YOLOv5s模型引入3项改进:拓展多尺度检测层、嵌入swin transformer模块、优化后处理函数;构建了改进模型YOLOv5s-SSS(swin transformer with soft-NMS for small target)并进行参数优化。最后,对新模型进行了定性和定量评价。实验结果表明,YOLOv5s-SSS模型相对YOLOv5s模型的平均精确率在小目标火焰图像上提高了16.3%,在常规尺寸烟雾图像上提高了5.9%。该文制备的数据集可有效支撑改进火灾检测模型的训练与测试;构建的YOLOv5s-SSS模型性能测试可靠,为火灾图像检测技术提供了一种新的改进方案。[Objective]Fires are disaster events with destructive power.In relation to fire-related accidents,fire monitoring is one of the effective measures to reduce the casualties and economic losses caused by such incidents.Compared to traditional methods in fire monitoring,target detection has shown its strengths in terms of cost and outcome.Many researchers have investigated various ways to improve the efficiency of target detection by proposing new algorithms.Thus,numerous algorithms suited for fire monitoring applications have been proposed.However,these typically lack the capacity to detect small targets,which is the main characteristic of flame targets in incipient fires.To enhance the capacity to detect small targets for fire target detection,this paper improved the YOLOv5 algorithm and trained a model based on it with corresponding datasets collected.[Methods]First,a fire image dataset with small target scene conditions is prepared for model training and performance testing.In the validation set,eight sets of mutually exclusive sub-datasets of environmental conditions are divided for the purpose of performance testing.Second,three improvements are introduced to improve the YOLOv5 algorithm:a)expansion of the multiscale detection layer to improve its receptive resolution;b)enhancement of the multiscale feature extraction capability by embedding the Swin transformer module,thus reducing the cost of calculation in algorithm deployment;and c)optimization of the postprocessing function by replacing the original algorithm with soft-NMS algorithm to maintain more potential adjacent targets.Next,an improved model YOLOv5s-SSS(swin transformer with soft-NMS for small target)is proposed.To verify the effect of every improvement and their contributions to the final model,the new model is evaluated using four sets of ablation experiments.After parameter optimization,a set of fire images is inputted into the models in the ablation experiment to compare and verify their outputs.[Results]The ablation experimental results indica

关 键 词：深度学习 图像识别 火灾监测 YOLOv5 小目标检测 

分 类 号：X932[环境科学与工程—安全科学]