GMT：面向多相机多目标跟踪的有效全局框架
GMT: Effective Global Framework for Multi-Camera Multi-Target Tracking
提出全局轨迹-目标匹配框架，用跨视角特征一致性增强模块减少视角间特征差异，并将同一目标在不同视角的历史编码为全局轨迹，为多相机跟踪提供可复用的全局关联思路。
原文依据 we propose a Cross-View Feature Consistency Enhancement(CFCE) module to reduce the feature discrepancies across different views
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的多相机多目标（MCMT）跟踪模型通常采用两阶段框架，即先进行单相机跟踪，再进行相机间跟踪。然而，在这种范式下，多视角的利用仅限于恢复第一阶段中遗漏的匹配，对整体跟踪的贡献有限。为解决这一问题，我们提出了一种新颖的全局MCMT跟踪框架GMT，通过执行全局级别的轨迹-目标匹配来有效利用多视角优势。具体而言，我们不再为每个视角独立分配轨迹，而是提出跨视角特征一致性增强（CFCE）模块来减少不同视角间的特征差异，并将不同视角下同一历史目标编码为全局轨迹。随后引入全局轨迹关联（GTA）模块，将新目标关联到全局轨迹，使模型在跟踪过程中能够联合利用视角内和视角间的线索。与两阶段框架相比，GMT在现有数据集上取得了显著提升，CVMA in指标提升高达13.1%，CVIDF1指标提升高达19.2%。此外，我们提出了VisionTrack，一个高质量、大规模MCMT数据集，涵盖具有不同光照和目标分布的多样场景，其多样性显著优于现有数据集。我们的代码和数据集将在https://github.com/FoxCanned/GMT发布。
英文原文摘要 1481 字符
Existing Multi-Camera Multi-Target (MCMT) tracking models typically adopt a two-stage framework, involving single-camera tracking followed by inter-camera tracking. However, in this paradigm, the use of multiple views is confined to recovering missed matches in the first stage, providing a limited contribution to overall tracking. To address this issue, we propose a novel global MCMT tracking framework termed GMT, which effectively leverages the advantage of multi-view by performing global-level trajectory-target matching. Specifically, instead of assigning trajectories independently for each view, we propose a Cross-View Feature Consistency Enhancement(CFCE) module to reduce the feature discrepancies across different views, and encode the same historical targets across different views as global trajectories. The Global Trajectory Associate (GTA) module is then introduced to associate new targets to global trajectories, allowing the model to jointly exploit both intra-view and inter-view cues during tracking. Compared with the two-stage framework, the GMT achieves significant improvements on existing datasets, with gains of up to 13.1% in CVMA in and 19.2% in CVIDF1. Moreover, we present VisionTrack, a high-quality, large-scale MCMT dataset encompassing diverse scenes with varying illumination and target distributions, providing significantly greater diversity than existing datasets. Our code and dataset will be released at https://github.com/FoxCanned/GMT.