arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.01775cs.CV
收藏

多目标、多摄像机跟踪的性能指标和数据集

Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking

Duke University(杜克大学);University of Modena and Reggio Emilia(摩德纳和雷焦艾米利亚大学)

Ergys Ristani, Francesco Solera, Roger S. Zou, Rita Cucchiara, Carlo Tomasi

摘要:

为了帮助加速多目标、多摄像机跟踪系统的进展,我们提出了(i)一对新的精确度-召回率性能指标,该指标统一对待所有类型的错误,并强调对错误源的正确识别;(ii)迄今为止最大的完全注释和校准数据集,由8台摄像机拍摄的超过200万帧1080 p,60 fps的视频,观察超过2,700个身份超过85分钟;和(iii)作为比较基线的参考软件系统。我们表明,(i)我们的措施正确地考虑了多摄像头设置中的底线身份匹配性能;(ii)我们的数据集对当前的跟踪器构成了现实的挑战;(iii)我们的系统的性能与最先进的系统相当。

英文摘要:

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 1080p, 60fps video taken by 8 cameras observing more than 2,700 identities over 85 minutes; 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑