Improving UAV Aerial Imagery Detection Method via Superresolution Synergy

Abstract

Unmanned aerial vehicles (UAVs) have emerged as versatile tools across various industries, providing valuable insights through aerial image analysis. However, the efficacy of UAV-deployed image detection systems is often limited by the resolution of captured images and the altitudinal constraints of UAV operations. This article introduces a novel integration of the detection system with superresolution networks and image reconstruction techniques, inspired by the exceptional visual capabilities of eagles, to enhance image detail and detection recall from aerial perspectives. The superresolution component utilizes advanced algorithms to upscale the resolution of images captured by UAVs, thereby improving the granularity and clarity of the visual data. Concurrently, image reconstruction techniques are applied to enhance the quality of original images further. In addition, we propose an innovative adaptive feature fusion technique, which not only surpasses traditional concatenation methods in integrating multiscale features effectively but also demonstrates remarkable improvement in feature utilization and further refinement of the fusion process. Extensive experiments conducted on VisDrone2019 and DOTA datasets demonstrate that our integrated system significantly outperforms existing methods in terms of detection precision and recall. Compared to YOLOv5s, recall and mAP50 have increased by 8.89% and 11.11%, respectively, with only a slight increase in the number of parameters and complexity.

Keywords

• Eagle-eye vision system
• object detection
• unmanned aerial vehicle (UAV) imagery
• YOLOv5