Improved YOLOv5 Based on Attention Mechanism and FasterNet for Foreign Object Detection on Railway and Airway tracks

TL;DR

This paper presents an enhanced YOLOv5 model integrated with FasterNet and attention mechanisms, designed for more accurate and efficient foreign object detection on railway and airport runways, supported by a new comprehensive dataset.

Contribution

It introduces a novel YOLOv5-based architecture with FasterNet and attention modules, along with the AARFOD dataset, achieving improved detection accuracy and reduced computational complexity.

Findings

Detection precision increased by 1.2%.

Model parameters reduced by 25.12%.

GFLOPs decreased by 10.63%.

Abstract

In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways. These objects can include pedestrians, vehicles, animals, and debris. This paper introduces an improved YOLOv5 architecture incorporating FasterNet and attention mechanisms to enhance the detection of foreign objects on railways and Airport runways. This study proposes a new dataset, AARFOD (Aero and Rail Foreign Object Detection), which combines two public datasets for detecting foreign objects in aviation and railway systems.The dataset aims to improve the recognition capabilities of foreign object targets. Experimental results on this large dataset have demonstrated significant performance improvements of the proposed model over the baseline YOLOv5 model, reducing computational requirements.Improved YOLO model shows a significant improvement in precision by 1.2%, recall rate by 1.0%, and mAP@.5 by 0.6%, while mAP@.5-.95 remained unchanged. The parameters were reduced by approximately 25.12%, and GFLOPs were reduced by about 10.63%. In the ablation experiment, it is found that the FasterNet module can significantly reduce the number of parameters of the model, and the reference of the attention mechanism can slow down the performance loss caused by lightweight.