基于改进YOLOv5的轻量化早期舰船火灾烟雾检测算法OA
Early ship fire and smoke detection based on improved YOLOv5
为改进当前目标检测技术对舰船环境下早期火灾烟雾小目标的检测精度不足、速度较慢与特征表达能力不充分的现状,对改进YOLOv5的轻量化早期舰船火灾烟雾检测方法进行了研究.首先,对YOLOv5网络结构进行分析;其次,从主干网络MobileNetv3架构轻量化、检测颈Bi-FPN特征融合金字塔改进、优化Alpha-IoU损失函数与改进Soft-NMS四方面改进YOLOv5算法;最后,构建消融与对比实验验证改进性能.改进模型训练时间减少34.1%,mAP较…查看全部>>
In order to improve the current target detection technology's insufficient accuracy,slow speed and insufficient feature expression ability for early fire smoke detection of small targets in ship environment,the lightweight early ship fire smoke detection method with improved YOLOv5 was studied.Firstly,the network structure of YOLOv5 is analyzed.Secondly,the YOLOv5 algorithm is improved from four aspects:lightweight architecture of backbone network MobileNetv…查看全部>>
康斓;蒋晓刚;苑志江
海军大连舰艇学院,辽宁大连 116018海军大连舰艇学院,辽宁大连 116018海军大连舰艇学院,辽宁大连 116018
安全科学
火灾烟雾检测目标检测注意力机制特征融合舰船安全
Fire smoke detectionObject detectionAttention mechanismFeature fusionShip safety
《通信与信息技术》 2024 (2)
21-26,6
评论