Performance Measures and a Data Set for Multi-target, Multi-camera Tracking

摘要

To help accelerate progress in multi-target, multi-camera tracking systems, we present (ⅰ) a new pair of precision-recall measures of performance that treats errors of all types uniformly and emphasizes correct identification over sources of error; (ⅱ) the largest fully-annotated and calibrated data set to date with more than 2 million frames of 1080 p, 60 fps video taken by 8 cameras observing more than 2,700 identities over 85min; and (ⅲ) a reference software system as a comparison baseline. We show that (ⅰ) our measures properly account for bottom-line identity match performance in the multi-camera setting; (ⅱ) our data set poses realistic challenges to current trackers; and (ⅲ) the performance of our system is comparable to the state of the art.