Abstract
Person re-identification (Re-ID) across visible and infrared modalities is crucial for 24-hour surveillance systems, but existing datasets primarily focus on ground-level perspectives. While ground-based IR systems offer nighttime capabilities, they suffer from occlusions, limited coverage, and vulnerability to obstructions--problems that aerial perspectives uniquely solve. To address these limitations, we introduce this http URL, the first aerial-ground cross-modality video-based person Re-ID dataset. This dataset captures 1,837 identities across 4,861 tracklets (124,855 frames) using both UAV-mounted and fixed CCTV cameras in RGB and infrared modalities. this http URL presents unique challenges including cross-viewpoint variations, modality discrepancies, and temporal dynamics. Additionally, we propose TCC-VPReID, a novel three-stream architecture designed to address the joint challenges of cross-platform and cross-modality person Re-ID. Our approach bridges the domain gaps between aerial-ground perspectives and RGB-IR modalities, through style-robust feature learning, memory-based cross-view adaptation, and intermediary-guided temporal modeling. Experiments show that this http URL presents distinctive challenges compared to existing datasets, with our TCC-VPReID framework achieving significant performance gains across multiple evaluation protocols. Dataset and code are available at this https URL.
Abstract (translated)
跨可见光与红外模态的人员再识别（Person Re-ID）对于全天候监控系统至关重要，但现有数据集主要关注地面视角。虽然基于地面的IR系统提供了夜间工作能力，但由于遮挡、覆盖范围有限和易受障碍物影响等问题，它们表现不佳——这些问题可以通过空中视角来解决。为了解决这些局限性，我们引入了[此处应有一个链接]（请替换为实际的数据集链接），这是第一个跨模态视频基的空地人员再识别数据集。该数据集使用无人机搭载和固定CCTV摄像机在RGB和红外模式下记录了1,837个身份跨越4,861个轨迹片段（共124,855帧）。此数据集带来了独特的挑战，包括跨视角变化、模态差异以及时间动态性。此外，我们提出了一种新的三流架构TCC-VPReID，旨在解决跨平台和跨模式人员再识别的联合挑战。我们的方法通过风格稳健的功能学习、基于记忆的跨视图适应以及中介引导的时间建模来弥合空地视角之间及RGB-IR模态之间的领域差距。实验表明，[此处应有一个链接]（请替换为实际的数据集链接）与现有数据集相比具有独特的挑战性，并且我们的TCC-VPReID框架在多种评估协议中取得了显著的性能提升。该数据集和代码可在[此处应有一个链接]（请替换为实际的网址）获取。 请注意，您需要将方括号内的占位符文本替换成实际的数据集链接和相关网站地址。
URL
https://arxiv.org/abs/2507.17995
