Research on YOLOv8 Object Detection Algorithm in UAV Scenarios

Abstract Aerial images captured by Unmanned Aerial Vehicles (UAVs) often exhibit characteristics such as high object density, small targets, and wide coverage, which lead to the occurrence of false positives and false negatives in existing object detectors. In order to improve detection accuracy, this study proposes an enhanced YOLOv8 object detection model. Firstly, the Deformable Convolutional Networks v2 (DConv2) is incorporated into the backbone's C2F module to expand the receptive field of the image and enhance the detection accuracy of small objects. Secondly, the Fousion Block module is employed in the neck network to increase network depth and strengthen feature fusion capability. Subsequently, the model incorporates up sampling operations and discards large object detection layers, further improving the detection progress for small objects. Finally, the Efficient Intersection over Union (ECIoU) loss function is adopted to replace the Complete Intersection over Union (CIoU) loss function, accelerating the model's convergence speed and enhancing object detection precision. The improved model is validated using the VisDrone2019-DET-train dataset, and the results demonstrate that the enhanced model Yolov8sUAU achieves anmAP of 49. 5%, representing a 7. 3% improvement over traditional models. With the capability to maintain UAV detection speed, the proposed model can more accurately accomplish the detection tasks for small targets during UAV aerial photography processes.