EBR-YOLO: A Lightweight Detection Method for Non-Motorized Vehicles Based on Drone Aerial Images

Modern city construction focuses on developing smart transportation, but the recognition of the large number of non-motorized vehicles in the city is still not sufficient. Compared to fixed recognition equipment, drones have advantages in image acquisition due to their flexibility and maneuverability. With the dataset collected from aerial images taken by drones, this study proposed a novel lightweight architecture for small objection detection based on YOLO framework, named EBR-YOLO. Firstly, since the targets in the application scenario are generally small, the number of Backbone layers is reduced, and the AZML module is proposed to enrich the detail information and enhance the model learning capability. Secondly, the C2f module is reconstructed using part of the convolutional PConv to reduce the network's computational volume and improve the detection speed. Finally, the downsampling operation is reshaped by combining with the introduced ADown module to further reduce the computational amount of the model. The experimental results show that the algorithm achieves an mAP of 98.9% and an FPS of 89.8 on the self-built dataset of this paper, which is only 0.2% and 0.3 lower compared to the original YOLOv8 network, respectively, and the number of parameters is 70% lower compared to the baseline, which ensures the accuracy and computational speed of the model while reducing its computational volume greatly. At the same time, the model generalization experiments are carried out on the UCAS-AOD and CARPK datasets, and the performance of the model is almost the same as the baseline.