通过事件衍生的瞬态线索实现严重遮挡下的跟踪
Tracking through Severe Occlusion via Event-Derived Transient Cues
将事件相机微秒级时间戳用于帧间位移预测的双向运动一致性约束，并用高斯掩码模拟遮挡退化来学习不变外观表征，为严重遮挡下的跟踪提供了可复用的事件-帧融合与遮挡增广思路。
原文依据 event cameras with microsecond-level temporal resolution provide transient dynamic cues that facilitate modeling nonlinear motion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在遮挡条件下跟踪具有高速与非线性运动的目标仍然具有挑战性，其原因在于视觉线索缺失所导致的空间外观信息匮乏与时序轨迹断裂。现有方法通常要么动态更新模板以维持外观相似性，要么采用自回归模型从历史轨迹中预测目标。然而，由于模板污染以及复杂运动下帧率受限，这些方法在严重遮挡下效果不佳。在本工作中，我们观察到遮挡本质上会削弱空间匹配机制，从而凸显了时序线索的重要性。与此同时，具有微秒级时间分辨率的事件相机能够提供瞬态动态线索，有助于对非线性运动进行建模。基于此，我们提出 EvoTrack，一种通过事件衍生的瞬态演化实现遮挡鲁棒跟踪的框架，包含基于事件的运动自回归与目标感知的外观匹配。具体而言，在运动自回归方面，事件的细粒度时间戳天然编码了目标的方向与速度，由此启发了一种双向运动一致性，用于约束非线性运动下的帧间位移预测。在外观匹配方面，我们采用高斯掩码策略模拟遮挡退化，引导模型关注目标区域并学习不变表征。此外，我们构建了一个像素对齐的帧-事件跟踪数据集，具有更高的空间分辨率与显式的遮挡标签。大量实验证明了 EvoTrack 在具有挑战性的遮挡场景中的有效性。
英文原文摘要 1654 字符
Tracking targets with high-speed and nonlinear motion under occlusion remains challenging due to spatial appearance deprivation and temporal trajectory fragmentation caused by missing visual cues. Existing methods typically either dynamically update templates to maintain appearance similarity or employ autoregressive models to predict targets from historical trajectories. However, these methods are ineffective under severe occlusion owing to template contamination and limited frame rates for complex motion. In this work, we observe that occlusion inherently degrades the spatial matching mechanism, highlighting the importance of temporal cues. Meanwhile, event cameras with microsecond-level temporal resolution provide transient dynamic cues that facilitate modeling nonlinear motion. In light of this, we propose EvoTrack, an occlusion-robust tracking framework via event-derived transient evolution, which comprises event-based motion autoregression and target-aware appearance matching. Specifically, for motion autoregression, the fine-grained timestamps of events naturally encode the target's direction and speed, motivating a bidirectional motion consistency that constrains inter-frame displacement prediction under nonlinear motion. For appearance matching, we adopt a Gaussian masking strategy to simulate occlusion degradation, guiding the model to focus on target regions and learn invariant representations. Furthermore, we build a pixel-aligned Frame-Event tracking dataset with higher spatial resolution and explicit occlusion labels. Extensive experiments demonstrate the effectiveness of EvoTrack in challenging occlusion scenes.