作者:Andreu GirbauFerran MarquésShin'ichi Satoh

作者单位:日本东京国家信息学研究所,西班牙巴塞罗那加泰罗那理工大学

发布时间:2022

发布期刊/会议:

出版商:Arxiv

论文全称:Multiple Object Tracking from appearance by hierarchically clustering tracklets

论文地址:

论文代码:

https://github.com/nii-satoh-lab/mot_fcg

一、摘要

Current approaches in Multiple Object Tracking (MOT) rely on the spatio-temporal coherence between detections combined with object appearance to match objects from consecutive frames. In this work, we explore MOT using object appearances as the main source of association between objects in a video, using spatial and temporal priors as weighting factors. We form initial tracklets by leveraging on the idea that instances of an object that are close in time should be similar in appearance, and build the final object tracks by fusing the tracklets in a hierarchical fashion. We conduct extensive experiments that show the effectiveness of our method over three different MOT benchmarks, MOT17, MOT20, and DanceTrack, being competitive in MOT17 and MOT20 and establishing state-of-the-art results in DanceTrack.

二、FCG

本文算法的核心思想:同一对象的实例在时间邻域中具有相似的外观