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

TL;DR

JointYODNet is a lightweight UAV object detection method that uses a novel joint loss function to achieve high accuracy and over 100fps, outperforming existing techniques in small object detection.

Contribution

The paper introduces a new joint loss function specifically designed for small object detection in UAV imagery, enabling real-time performance and improved accuracy.

Findings

Achieves a recall of 0.971 and F1Score of 0.975

Attains a mAP@.5 of 98.6%

Runs at over 100fps

Abstract

Small object detection via UAV (Unmanned Aerial Vehicle) images captured from drones and radar is a complex task with several formidable challenges. This domain encompasses numerous complexities that impede the accurate detection and localization of small objects. To address these challenges, we propose a novel method called JointYODNet 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, our method achieves a recall of 0.971, and a F1Score of 0.975, surpassing state-of-the-art techniques. Additionally, our method achieves a mAP@.5(%) of 98.6, indicating its robustness in detecting small objects across varying scales