首页|基于改进YOLOv5s算法的尾气黑度测量方法研究

基于改进YOLOv5s算法的尾气黑度测量方法研究

扫码查看
原文链接
  • 万方数据
  • 维普
针对传统尾气黑度测量方法精度低、环境适应性差等问题,文章提出一种基于改进YOLOv5s算法的尾气黑度测量方法.考虑到尾气形状多变、背景复杂,在现有YOLOv5s网络中添加自适应特征融合(adap-tively spatial feature fusion,ASFF)和全局注意力机制(global attention mechanism,GAM),提高尾气目标的检测准确度;同时,为减少光照等环境因素对尾气目标检测的影响,基于尾气的高温特性,利用红外图像提高尾气区域检测准确度;并基于标准的林格曼黑度对被检测区域内的尾气黑度进行等级判定.实验结果表明:改进后的YOLOv5s对红外尾气目标的检测准确率高达95.3％,比现有YOLOv5s检测准确度提高了 3.4％;同时还降低了光照等环境因素对尾气目标检测结果的影响,改善了算法的鲁棒性;最终尾气黑度判定精度达到0.5级,可有效满足现有移动源尾气黑度高精度检测需求.
Research on detection method of Ringelmann emittance of exhaust based on improved YOLOv5s algorithm
For the problems of low accuracy and poor environmental adaptability of traditional detection methods of Ringelmann emittance of exhaust,this paper proposes a detection method of Ringelmann emittance of exhaust based on improved YOLOv5s algorithm.Considering the variable shape and com-plex background of exhaust,adaptively spatial feature fusion(ASFF)and global attention mechanism(GAM)are added to the existing YOLOv5s network to improve the detection accuracy of exhaust tar-gets.At the same time,in order to reduce the impact of environmental factors such as illumination on exhaust target detection,based on the high temperature characteristics of exhaust,infrared images are used to improve the accuracy of exhaust region detection.Based on the standard Ringelmann emit-tance,the Ringelmann Emittance level of exhaust in the detected area is determined.The experimen-tal results show that the detection accuracy of the improved YOLOv5s is as high as 95.3％,which is 3.4％higher than that of the existing YOLOv5s;the influence of illumination and other environmen-tal factors on the detection results of exhaust targets is reduced,and the robustness of the algorithm is improved;the final determination accuracy of Ringelmann emittance of exhaust can reach level 0.5,which can effectively meet the high-precision detection requirements of Ringelmann emittance of exist-ing mobile source exhaust.

Ringelmann emittancevehicle exhaust target detectionRingelmann emittance level deter-minationinfrared imageYOLOv5s algorithm

程硕、王焕钦、胡俊涛、夏王进、虞发军、方勇

展开 >

合肥工业大学光电技术研究院,安徽 合肥 230009

中国科学院合肥物质科学研究院智能机械研究所,安徽 合肥 230031

合肥工业大学智能制造技术研究院,安徽 合肥 230051

林格曼黑度 机动车尾气目标检测 黑度等级判定 红外图像 YOLOv5s算法

国家自然科学基金民航联合研究基金资助项目安徽省科技重大专项资助项目安徽省科技重大专项资助项目合肥工业大学智能制造技术研究院科研基金资助项目

U2133212202003a07020005202203a07020004IMICZ2019001

2024

10.3969/j.issn.1003-5060.2024.10.007

合肥工业大学学报(自然科学版)
合肥工业大学

合肥工业大学学报(自然科学版)

CSTPCD北大核心
影响因子：0.608
ISSN：1003-5060
年,卷(期)：2024.47(10)