基于改进的YOLOv8轻量级火灾检测算法研究OACSTPCD
Research on Lightweight Fire Detection Algorithm Based on Improved YOLOv8
为提高复杂场景下火灾检测准确度,降低误检、漏检率,提高火灾检测速度,提出一种基于YOLOv8 算法的改进策略.针对YOLOv8 网络结构较深,处理复杂火灾图像或多目标检测时计算复杂度较高的问题,将初始模型的骨干网络替换为MobileViT网络,在保证检测精度的同时构建轻量化火灾检测模型,提升火灾检测速度.在颈部结构嵌入EMA跨空间学习多尺度注意力机制模块增强火灾特征图的语义和空间信息,同时保证通道维度信息的完整,提高火灾检测精度.使用MPDIoU…查看全部>>
In order to improve the accuracy of fire detection in the complex circumstances,reduce the rate of false detection and missed detection,and enhance the speed of fire detection,an improved strategy based on YOLOv8 algorithm is proposed.Focused at the problem that YOLOv8 network has a deep structure and high computational complexity when dealing with complex fire images or multi-target de-tection,the backbone network of the initial model is replaced by MobileV…查看全部>>
王召龙;张洁
南京邮电大学 计算机学院,江苏 南京 210023南京邮电大学 计算机学院,江苏 南京 210023
计算机与自动化
火灾检测YOLOv8MobileViT多尺度注意力机制MPDIoU
fire detectionYOLOv8MobileViTmulti-scale attention mechanismMPDIoU
《计算机技术与发展》 2024 (10)
61-68,8
国家重点研发计划项目(2018YFB1500902)
评论