This paper presents new performance measures and a large multi-camera tracking dataset for multi-target, multi-camera (MTMC) tracking. The new measures emphasize correct identity identification over error sources, and the dataset contains over 2 million frames of 1080p video recorded by 8 cameras over 85 minutes, covering more than 2,700 identities. The paper also introduces a reference system for comparison. The measures are designed to evaluate how well computed identities align with true identities, regardless of where or why errors occur. The dataset is the first of its kind, providing a large-scale, fully annotated, and calibrated multi-camera tracking data set. The reference system is based on a single-camera tracker extended to multi-camera settings. The paper shows that the proposed measures and dataset are effective for evaluating MTMC tracking performance, and that the reference system performs comparably to state-of-the-art methods. The paper also discusses existing performance measures and datasets, highlighting their limitations. The new measures and dataset aim to address these limitations by providing a more accurate and comprehensive evaluation of MTMC tracking performance. The paper concludes that the proposed measures and dataset contribute to advancing MTMC tracking research.This paper presents new performance measures and a large multi-camera tracking dataset for multi-target, multi-camera (MTMC) tracking. The new measures emphasize correct identity identification over error sources, and the dataset contains over 2 million frames of 1080p video recorded by 8 cameras over 85 minutes, covering more than 2,700 identities. The paper also introduces a reference system for comparison. The measures are designed to evaluate how well computed identities align with true identities, regardless of where or why errors occur. The dataset is the first of its kind, providing a large-scale, fully annotated, and calibrated multi-camera tracking data set. The reference system is based on a single-camera tracker extended to multi-camera settings. The paper shows that the proposed measures and dataset are effective for evaluating MTMC tracking performance, and that the reference system performs comparably to state-of-the-art methods. The paper also discusses existing performance measures and datasets, highlighting their limitations. The new measures and dataset aim to address these limitations by providing a more accurate and comprehensive evaluation of MTMC tracking performance. The paper concludes that the proposed measures and dataset contribute to advancing MTMC tracking research.