MuJoCo中的光流翼拍计数：卷积、脉冲与基于注意力的时间模型比较
Optical-Flow Wingbeat Counting in MuJoCo: A Comparison of Convolutional, Spiking, and Attention-Based Temporal Models
浏览论文内容
中文总结 AI 辅助
本研究在MuJoCo中评估了基于光流的翼拍计数，比较卷积、脉冲和注意力时间模型，结果表明因果光流计数可行，但架构排名未定。
中文摘要 AI 辅助
对扑翼飞行器的视觉监测需要从运动强度和平均频率中区分出单个翼拍。本文在MuJoCo环境中进行了一项受控评估，通过安装在Crazyflie飞行器上的虚拟相机观察到的带符号光流来进行翼拍计数。记录了三种扑翼模型在1.5米和3.0米光学距离下的数据，从240个配对场景配置中产生了1,440个片段，并按场景级别以3:1的比例划分训练集和测试集。一个共享的空间卷积编码器分别与因果时间卷积网络、循环泄漏积分-发放（LIF）脉冲网络或因果自注意力相结合。每个模型预测相位和活动性，随后使用相同的定向穿越事件计数器。保留了六个现有的卷积模型，所有十二个新模型在生成测试预测前均被冻结。在1.5米距离下，精确计数准确率分别为96.67%、95.00%和96.67%；在3.0米距离下分别为94.44%、92.22%和95.00%。所有配对场景自助法区间在精确计数准确率差异上均包含零。七个远距离脉冲模型片段尽管事件时间不匹配，但总数正确，这说明了为什么必须同时报告总计数和事件级测量结果。结果支持在所测试设置中进行因果光流计数的可行性，并识别出边界敏感错误。这些结果并未在重复训练、真实飞行鲁棒性或硬件效率方面建立架构排名。
英文摘要
Visual monitoring of flapping-wing vehicles requires distinguishing individual wingbeats from motion strength and average frequency. This paper presents a controlled MuJoCo evaluation of wingbeat counting from signed optical flow observed by virtual cameras mounted on Crazyflie vehicles. Three flapping-wing models were recorded at optical distances of 1.5 and 3.0 m, producing 1,440 clips from 240 paired scene configurations with a scene-level 3:1 training-test split. A common spatial convolutional encoder was combined with a causal temporal convolutional network, a recurrent leaky integrate-and-fire spiking network, or causal self-attention. Each model predicted phase and activity, followed by the same directed-crossing event counter. The six existing convolutional models were retained, and all twelve new models were frozen before their test predictions were generated. Exact-count accuracies at 1.5 m were 96.67%, 95.00%, and 96.67%, respectively; at 3.0 m they were 94.44%, 92.22%, and 95.00%. All paired scene-bootstrap intervals for differences in exact-count accuracy included zero. Seven far-distance spiking-model clips had correct totals despite event-timing mismatches, demonstrating why total-count and event-level measurements must be reported together. The results support the feasibility of causal optical-flow counting in the tested setting and identify boundary-sensitive errors. They do not establish an architecture ranking across repeated training, real-flight robustness, or hardware efficiency.
发表机构
- Universiti Sains Malaysia（马来西亚理科大学）
机构由 AI 辅助整理，请以论文原文为准。
