Research on Object Detection in Unmanned Aerial Vehicle Aerial Images Based on Improved YOLOv7

Abstract

In addressing challenges such as significant variations in target scales, limited accuracy in detecting small objects, and elevated omission rates in scenes captured by unmanned aerial vehicles, this study introduces an enhanced YOLOv7 object detection algorithm. Firstly, an additional small object detection layer is incorporated into the original YOLOv7 to adapt to object targets across different scales, thereby reducing the omission rate of small objects. Secondly, a parameter-free attention mechanism is introduced into the feature fusion network. Based on this attention mechanism, a Triplet Attention module is constructed to enhance the integration of more critical feature information within the network. Lastly, the loss function CIoU is replaced by WIoUv1 to further improve the convergence speed and detection accuracy of the model. Experimental results demonstrate the excellence of this model on the VisDrone dataset, achieving an mAP of 49.5% on the test set. Compared to the baseline YOLOv7 model, this proposed algorithm exhibits a 2.2% improvement and notably enhances the detection performance of small objects.