This paper introduces two metrics, MOTP (Multiple Object Tracking Precision) and MOTA (Multiple Object Tracking Accuracy), for evaluating the performance of multiple object trackers. These metrics are designed to assess the precision of object location estimation, the accuracy of object configuration recognition, and the consistency of object labeling over time. The metrics were used in two large-scale international evaluations, the 2006 and 2007 CLEAR evaluations, to measure and compare the performance of multiple object trackers across various tracking tasks. The evaluations included tasks such as 3D person tracking, 2D face tracking, 2D person and vehicle tracking, and acoustic and multimodal person tracking. The results showed that the MOT metrics effectively captured the strengths and weaknesses of different tracking systems, allowing for objective comparisons. The metrics were found to be intuitive, general, and applicable to a wide range of tracking scenarios. The paper also discusses the design and computation of the metrics, highlighting their importance in systematically evaluating and comparing multiple object tracking systems.This paper introduces two metrics, MOTP (Multiple Object Tracking Precision) and MOTA (Multiple Object Tracking Accuracy), for evaluating the performance of multiple object trackers. These metrics are designed to assess the precision of object location estimation, the accuracy of object configuration recognition, and the consistency of object labeling over time. The metrics were used in two large-scale international evaluations, the 2006 and 2007 CLEAR evaluations, to measure and compare the performance of multiple object trackers across various tracking tasks. The evaluations included tasks such as 3D person tracking, 2D face tracking, 2D person and vehicle tracking, and acoustic and multimodal person tracking. The results showed that the MOT metrics effectively captured the strengths and weaknesses of different tracking systems, allowing for objective comparisons. The metrics were found to be intuitive, general, and applicable to a wide range of tracking scenarios. The paper also discusses the design and computation of the metrics, highlighting their importance in systematically evaluating and comparing multiple object tracking systems.