用事件相机检测无人机，靠螺旋桨特征实现跨类型识别
EvDetMAV: Generalized MAV Detection from Moving Event Cameras
- 利用事件流中螺旋桨的时空特征，分离目标与背景噪声
- 无需训练即达83%精度、81.5%召回率，较现有方法提升超30%
- 首个包含多场景多机型的事件相机无人机数据集，适合视觉感知研究
现有微型航空器（MAV）检测方法主要依赖RGB图像中的外观特征，因多样性难以实现泛化检测。我们发现不同类型的MAV在事件流中因高速旋转螺旋桨具有共同的显著特征，而这些特征在RGB图像中难以捕捉。本文研究如何通过充分挖掘原始事件流中螺旋桨的特性，实现不同型号MAV的检测。提出的方法包含三个模块，可提取螺旋桨的显著时空特征，并有效过滤背景物体与相机运动带来的噪声。由于缺乏现有的基于事件的MAV数据集，我们构建了一个新型数据集，为首个涵盖多种场景与不同机型的事件相机MAV数据集。实验表明，无需训练，该方法在新测试集上达到83.0%精度（+30.3%）和81.5%召回率（+36.4%），显著优于现有方法。代码与数据集已开源。
原文摘要 · Abstract (English)
Existing micro aerial vehicle (MAV) detection methods mainly rely on the target's appearance features in RGB images, whose diversity makes it difficult to achieve generalized MAV detection. We notice that different types of MAVs share the same distinctive features in event streams due to their high-speed rotating propellers, which are hard to see in RGB images. This paper studies how to detect different types of MAVs from an event camera by fully exploiting the features of propellers in the original event stream. The proposed method consists of three modules to extract the salient and spatio-temporal features of the propellers while filtering out noise from background objects and camera motion. Since there are no existing event-based MAV datasets, we introduce a novel MAV dataset for the community. This is the first event-based MAV dataset comprising multiple scenarios and different types of MAVs. Without training, our method significantly outperforms state-of-the-art methods and can deal with challenging scenarios, achieving a precision rate of 83.0\% (+30.3\%) and a recall rate of 81.5\% (+36.4\%) on the proposed testing dataset. The dataset and code are available at: https://github.com/WindyLab/EvDetMAV.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。