EventGait: 向事件流中实现鲁棒的步态识别
EventGait: Towards Robust Gait Recognition with Event Streams
AI总结：
本文提出EventGait，一种端到端的双流框架，通过事件相机捕捉动态和形状信息，提升在复杂光照和运动环境下的步态识别鲁棒性，并通过合成数据集和新基准测试验证了其有效性。
摘要：
步态识别能够实现非侵入性和隐私保护的识别，但在不受控环境中由于传统相机的光照和运动敏感性而面临挑战。本文探讨了使用事件相机进行步态识别，事件相机提供微秒级时间分辨率和高动态范围，自然捕捉鲁棒的动态特征并抑制静态噪声。现有基于事件的方法通常将事件流聚合为事件图像，从而丢弃了对步态识别至关重要的细粒度运动动态。因此，我们提出了EventGait，一种端到端的双流框架，分别建模运动和形状，同时保留事件的优势。我们的动态流利用混合脉冲专家（MoSE）和多样化的神经元常数，以在复杂的运动和光照场景中实现稳健的动态感知，而静态流通过跨模态结构对齐（CroSA）学习密集的形状表示，使用大规模视觉基础模型。为了解决大规模基于事件的步态数据集的缺乏，我们引入了合成管道并发布了两个新的基准：SUSTech1K-E和CCGR-Mini-E。广泛的实验表明，基于事件的步态识别不仅在正常条件下实现了与基于相机的步态识别相当的结果，而且在低光场景中显著优于前者。我们的方法在合成和真实世界基于事件的步态基准上均达到了新的状态，突显了事件驱动步态分析的鲁棒性和潜力。代码和数据集已发布在https://github.com/QUEAHREN/EventGait。
英文摘要：
Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity of conventional cameras. In this work, we explore gait recognition using event cameras, which offer microsecond temporal resolution and high dynamic range, naturally capturing robust dynamic cues and suppressing static noise. Existing event-based approaches typically aggregate event streams into event images over long time windows, thereby discarding fine-grained motion dynamics critical for gait recognition. Therefore, we propose \textbf{EventGait}, an end-to-end dual-stream framework that separately models motion and shape while preserving the advantages of events. Our dynamic stream leverages a Mixture of Spiking Experts (MoSE) with diverse neuron constants for robust dynamic perception across complex motion and illumination scenes, while the static stream learns dense shape representations via Cross-modal Structure Alignment (CroSA) with large vision foundation models. To address the absence of large-scale event-based gait datasets, we introduce a synthesis pipeline and release two new benchmarks: SUSTech1K-E and CCGR-Mini-E. Extensive experiments have shown that event-based gait recognition not only achieves results comparable to camera-based gait recognition under normal conditions but also significantly outperforms it in low-light scenarios. Our approach sets a new state of the art on both synthesized and real-world event-based gait benchmarks, highlighting the robustness and potential of event-driven gait analysis. The code and datasets are released at https://github.com/QUEAHREN/EventGait.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
