An improved YOLOv5 for object detection in visible and thermal infrared images based on contrastive learning

Frontiers in Physics

Physics

Bokai Liu¹  Lin Wei²  Yan Hu³  Houqiang Hua³  Jianhua Liu³  Zihao Yuan³  Xiaoguang Tu⁴ 

[1] College of Aviation Engineering, Civil Aviation Flight University of China, Guanghan, China;College of Flight Technology, Civil Aviation Flight University of China, Guanghan, China;Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan, China;Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan, China;School of Computer Science, Sichuan University, Chengdu, China;

关键词: deep learning;    YOLOv5;    object detection;    contrastive learning;    infrared thermal image;   

DOI  :  10.3389/fphy.2023.1193245

 received in 2023-03-24, accepted in 2023-04-21,  发布年份 2023

来源: Frontiers

【 摘 要 】

An improved algorithm has been proposed to address the challenges encountered in object detection using visible and thermal infrared images. These challenges include the diversity of object detection perspectives, deformation of the object, occlusion, illumination, and detection of small objects. The proposed algorithm introduces the concept of contrastive learning into the YOLOv5 object detection network. To extract image features for contrastive loss calculation, object and background image regions are randomly cropped from image samples. The contrastive loss is then integrated into the YOLOv5 network, and the combined loss function of both object detection and contrastive learning is used to optimize the network parameters. By utilizing the strategy of contrastive learning, the distinction between the background and the object in the feature space is improved, leading to enhanced object detection performance of the YOLOv5 network. The proposed algorithm has shown pleasing detection results in both visible and thermal infrared images.

【 授权许可】

Unknown   
Copyright © 2023 Tu, Yuan, Liu, Liu, Hu, Hua and Wei.