期刊文献+

基于改进YOLOv5s的图像融合交通检测方法

Image Fusion Traffic Detection Method Based on Improved YOLOv5
下载PDF
导出
摘要 针对复杂交通环境下YOLOv5s模型识别精度低、网络模型参数量大的问题,提出一种基于红外图像和可见光图像特征融合的行人与车辆目标检测算法。基于YOLOv5s算法进行改进,首先,使用渐进式图像融合网络生成可见光与红外图像数据集;其次,在特征融合部分采用GSConv卷积替换原始卷积,减少模型参数量和计算量,并且引入CA位置注意力机制,使网络更加关注位置信息;采用EIOU-Loss损失函数替换原始损失函数,加快收敛速度提高回归精度;最后,在M3FD数据集上对行人与车辆进行目标检测识别实验。实验结果表明,对于复杂背景的红外条件下的交通检测,改进后的YOLOv5s相较于原始网络的mAP提升了11.6%,模型大小减少了4.20%,参数量减少了8.05%,检测速度提升了9.09%。 Aiming at the problem of low recognition accuracy of YOLOv5s model and large number of network model parameters in complex traffic environment,an algorithm for pedestrian and vehicle target detection based on feature fusion of infrared and visible images is proposed.Based on the YOLOv5s algorithm,firstly,a progressive image fusion network is used to generate visible and infrared image datasets;secondly,GSConv convolution is used to replace the original convolution in the feature fusion part,which reduces the number of model parameters and computational volume,and the CA position attention mechanism is introduced so that the network pays more attention to the positional information;and the EIOU-Loss loss function is used to replace the original loss function to accelerate the convergence speed and improve the regression accuracy.Finally,the target detection and recognition experiments for pedestrians and vehicles are carried out on the M3FD dataset.The experimental results show that the improved YOLOv5s improves the mAP by 11.6%,the model size by 4.20%,the number of parameters by 8.05%,and the detection speed by 9.09%compared with the original network for traffic detection under infrared conditions with complex background.
作者 江晟 王博文 许文娟 JIANG Sheng;WANG Bowen;XU Wenjuan(School of Physics,Changchun University of Science and Technology,Changchun 130022)
出处 《长春理工大学学报(自然科学版)》 2024年第2期66-74,共9页 Journal of Changchun University of Science and Technology(Natural Science Edition)
基金 国家自然科学基金(12274041,U2031113)。
关键词 红外与可见光图像 目标检测 图像融合 注意力机制 infrared and visible light images traffic target detection image fusion attention mechanism
  • 引文网络
  • 相关文献

参考文献6

二级参考文献28

共引文献117

;
使用帮助 返回顶部