南京信息工程大学学报2023，Vol.15Issue(6)：676-683,8.DOI:10.13878/j.cnki.jnuist.20220710001
复杂环境下小尺度烟火目标检测研究
Small scale smoke&fire target detection in complex environment
摘要
Abstract
To address the low efficiency and accuracy of smoke&fire detection due to the small size of target and the confusion of fire feature with actual scene in complex environment,a small scale smoke&fire target detection method based on improved YOLOv5 is proposed.First,a fourth detection layer is added to the third detection layer output in the original YOLOv5 model,so as to obtain a larger feature map for small target detection and strengthen the feature extraction capability of the network model.Second,to solve the easy missing detection of target in shiel-ded scene,DIoU_Loss is used to replace the GIoU_Loss in calculating the regression loss function of the target frame.Finally,TensorRT is used to compress and accelerate the optimization of the model,and then deployed to the Jetson TX2 development board for accelerated inference experiments.In addition,more smoke&fire scene data are constructed by replication enhancement.Experimental results show that the proposed method has fast convergence speed and high accuracy for small scale smoke&fire detection,possessing the prospect for popularization and appli-cation.关键词
烟火检测/改进YOLOv5/DIoU_Loss/优化加速Key words
smoke&fire detection/improved YOLOv5/DIoU_Loss/optimization and acceleration分类
信息技术与安全科学引用本文复制引用
温秀兰,焦良葆,李子康,姚波,唐国寅..复杂环境下小尺度烟火目标检测研究[J].南京信息工程大学学报,2023,15(6):676-683,8.基金项目
国家自然科学基金(51675259) （51675259）
江苏省智能感知技术与装备工程研究中心开放基金(ITS202103) （ITS202103）
南京工程学院研究生科技创新基金(TB202217004) （TB202217004）
