Abstract
Event cameras provide high-temporal-resolution visual sensing that is well suited for observing fast-moving aerial objects; however, their use for drone trajectory prediction remains limited. This work introduces an event-only drone forecasting method that exploits propeller-induced motion cues. Propeller rotational speed are extracted directly from raw event data and fused within an RPM-aware Kalman filtering framework. Evaluations on the FRED dataset show that the proposed method outperforms learning-based approaches and vanilla kalman filter in terms of average distance error and final distance error at 0.4s and 0.8s forecasting horizons. The results demonstrate robust and accurate short- and medium-horizon trajectory forecasting without reliance on RGB imagery or training data.
Abstract (translated)
事件相机提供高时间分辨率的视觉感知，非常适合观察快速移动的空中物体；然而，它们在无人机轨迹预测中的应用仍然有限。本研究提出了一种仅基于事件数据的无人机预测方法，利用了螺旋桨引起的运动线索。从原始事件数据中直接提取螺旋桨旋转速度，并将其融合到一个考虑转速（RPM）的卡尔曼滤波框架内。在FRED数据集上的评估显示，在0.4秒和0.8秒的预测时间范围内，所提出的方法在平均距离误差和最终距离误差方面优于基于学习的方法和普通卡尔曼滤波器。实验结果表明，该方法能够在不依赖于RGB图像或训练数据的情况下实现稳健且准确的短时和中等时长轨迹预测。
URL
https://arxiv.org/abs/2603.01997
