Heavy vehicle detection using optical remote sensing images and deep learning

Abstract

Recently, object detection has experienced significant progress. However, in the field of remote sensing, it is still under investigation for real-time detection of small objects because of the limited resolution and information. The detection of a predefined object, such as heavy vehicle, is vital in some applications. This study aims to improve the detection accuracy of the heavy vehicle. We train the latest model, YOLOv5 on our dataset in this paper. The results show that YOLOv5 can be well applied in the field of heavy vehicle detection.