事件视觉系统在无人机避障中实现毫秒级低延迟，比传统摄像头更准更快。
Towards Low-Latency Event-based Obstacle Avoidance on a FPGA-Drone
- 用事件相机替代摄像头，提升实时避障精度与速度
- 避障延迟仅2.14毫秒，事件处理占1毫秒，推理0.94毫秒
- 在动态和静态状态识别上精度高出59个百分点，抗过拟合强
本文定量评估了事件视觉系统（EVS）与传统RGB模型在FPGA加速器上的碰撞避让动作预测性能。实验表明，EVS模型有效帧率达1 kHz，时间误差降低至-20 ms，空间误差减少至-20 mm，尤其在分布外数据测试中表现更优。其在选择最优规避动作方面更具鲁棒性：在区分运动与静止状态时，精度达78%（对比RGB的19%），提升59个百分点，F1分数达0.73（对比RGB的0.06），凸显RGB模型易过拟合。不同空间类别组合下，EVS性能保持一致。端到端测试显示系统延迟约2.14毫秒，其中事件聚合（1毫秒）和处理单元推理（0.94毫秒）为主要耗时环节。结果验证了事件视觉在实时避障中的优势，具备在资源受限环境部署的潜力。
原文摘要 · Abstract (English)
This work quantitatively evaluates the performance of event-based vision systems (EVS) against conventional RGB-based models for action prediction in collision avoidance on an FPGA accelerator. Our experiments demonstrate that the EVS model achieves a significantly higher effective frame rate (1 kHz) and lower temporal (-20 ms) and spatial prediction errors (-20 mm) compared to the RGB-based model, particularly when tested on out-of-distribution data. The EVS model also exhibits superior robustness in selecting optimal evasion maneuvers. In particular, in distinguishing between movement and stationary states, it achieves a 59 percentage point advantage in precision (78% vs. 19%) and a substantially higher F1 score (0.73 vs. 0.06), highlighting the susceptibility of the RGB model to overfitting. Further analysis in different combinations of spatial classes confirms the consistent performance of the EVS model in both test data sets. Finally, we evaluated the system end-to-end and achieved a latency of approximately 2.14 ms, with event aggregation (1 ms) and inference on the processing unit (0.94 ms) accounting for the largest components. These results underscore the advantages of event-based vision for real-time collision avoidance and demonstrate its potential for deployment in resource-constrained environments.
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。