发表机构
School of Aerospace Engineering, Engineering Campus; Universiti Sains Malaysia（工程学院航空航天学院; 马来西亚理科大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对相机运动下事件相机拍翅计数问题，构建受控MuJoCo基准，证明运动感知训练显著降低计数误差，但简单背景补偿效果有限，且神经模型并非总是最优。
AI 中文摘要
统计完成的拍翅次数需要识别单个周期，包括在频率变化和暂停期间的周期；仅估计主频率是不够的。相机运动进一步在事件观测中混合了目标和背景的亮度变化。我们提出了一个受控的MuJoCo基准，将运动训练与仅事件图像平移补偿分离。采集包含来自24个独立场景的324个流，三种扑动几何形状，两个距离（1.5米和3.0米），以及静态、中等运动和较强运动视角。十五个场景用于拟合，三个用于验证，六个用于保留测试。一个固定的因果时间卷积网络在匹配的2x2消融中评估，使用三个初始化种子，并与岭回归、傅里叶、自相关和改编的EEPPR基线进行比较。在中等运动下，配对运动训练将计数平均绝对误差从31.130降至3.185个周期（1.5米处），从42.019降至5.444个周期（3.0米处）。添加所测试的补偿将这些误差分别增加到4.630和10.185。傅里叶基线在1.5米处中等运动下达到0.944个周期，表明神经模型并非普遍最优。我们报告了精确计数准确性和时间匹配的周期F1以及计数误差。这些发现支持在这个小型合成基准中进行运动感知训练，同时揭示了简单事件背景稳定化的局限性。它们并未确立真实传感器性能、空气动力学飞行或对未见车辆类型的泛化能力。
英文摘要
Counting completed wingbeats requires identifying individual cycles, including during frequency changes and pauses; estimating a dominant frequency alone is insufficient. Camera motion further mixes target and background brightness changes in event observations. We present a controlled MuJoCo benchmark that separates motion training from event-only image translation compensation. The acquisition contains 324 streams from 24 independent scenes, three flapping geometries, two distances (1.5 and 3.0 m), and static, moderate-motion and stronger-motion views. Fifteen scenes are used for fitting, three for validation and six for held-out testing. A fixed causal temporal convolutional network is evaluated in a matched 2 x 2 ablation with three initialization seeds and compared with ridge, Fourier, autocorrelation and an adapted EEPPR baseline. Under moderate motion, paired motion training reduces count mean absolute error from 31.130 to 3.185 cycles at 1.5 m and from 42.019 to 5.444 at 3.0 m. Adding the tested compensation increases these errors to 4.630 and 10.185, respectively. A Fourier baseline achieves 0.944 cycles at 1.5 m under moderate motion, showing that the neural model is not uniformly best. We report exact-count accuracy and temporally matched cycle F1 alongside count error. These findings support motion-aware training in this small synthetic benchmark, while exposing limits of simple event-background stabilization. They do not establish real-sensor performance, aerodynamic flight, or generalization to unseen vehicle types.
Comments10 pages, 1 figure, 6 tables. Controlled simulation study with an ideal contrast-event sensor. Follow-up to arXiv:2609.17308 using new event-only acquisitions and a motion ablation protocol
