Multi-camera multiple people tracking has become an increasingly important area of research due to the growing demand for accurate and efficient indoor people tracking systems, particularly in settings such as retail, healthcare centers, and transit hubs. We proposed a novel multi-camera multiple people tracking method that uses anchor-guided clustering for cross-camera re-identification and spatio-temporal consistency for geometry-based cross-camera ID reassigning. Our approach aims to improve the accuracy of tracking by identifying key features that are unique to every individual and utilizing the overlap of views between cameras to predict accurate trajectories without needing the actual camera parameters. The method has demonstrated robustness and effectiveness in handling both synthetic and real-world data. The proposed method is evaluated on CVPR AI City Challenge 2023 dataset, achieving IDF1 of 95.36% with the first-place ranking in the challenge. The code is available at: https://github.com/ipl-uw/AIC23_Track1_UWIPL_ETRI.

翻译：多摄像机多人跟踪因在零售、医疗中心和交通枢纽等场景中对高精度室内人员跟踪系统的需求日益增长，已成为越来越重要的研究方向。本文提出一种新颖的多摄像机多人跟踪方法，该方法采用锚点引导聚类实现跨摄像机行人重识别，并利用时空一致性进行基于几何约束的跨摄像机ID重新分配。我们的方法通过识别每个个体独有的关键特征，并利用摄像机间的视角重叠区域（无需实际摄像机参数）来预测准确轨迹，从而提升跟踪精度。该方法在合成数据与真实数据上均展现出鲁棒性与有效性。在CVPR AI City Challenge 2023数据集上的评估结果表明，该方法以95.36%的IDF1指标获得挑战赛第一名。代码已开源：https://github.com/ipl-uw/AIC23_Track1_UWIPL_ETRI