Joint-YODNet: A Light-Weight Object Detector for UAVs to Achieve Above 100fps

Small object detection via UAV (Unmanned Aerial Vehicle) images captured from drones and radar is a complex task. This domain encompasses numerous complexities, including size and scale variations, image resolution constraints, and occlusion issues, all of which impede the accurate detection and localization of small objects. To address these challenges, we propose a novel method called Joint-YODNet for UAVs to detect small objects, leveraging a joint loss function specifically designed for this task. Our method revolves around the development of a joint loss function tailored to enhance the detection performance of small objects. Through extensive experimentation on a diverse dataset of UAV images captured under varying environmental conditions, we evaluated different variations of the loss function and determined the most effective formulation. The results demonstrate that our proposed joint loss function outperforms existing methods in accurately localizing small objects. Specifically, Joint-YODNet achieves a recall of 0.971 and a F1Score of 0.975, surpassing state-of-the-art (SOTA) techniques. Additionally, our method achieves a mAP@.5(%) of 98.6, indicating it’s robustness in detecting small objects across varying scales.