Multiple Object Tracking from appearance by hierarchically clustering tracklets
Multiple Object Tracking from appearance by hierarchically clustering tracklets
复制标题
DOI：
10.48550/arxiv.2210.03355
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Andreu Girbau;F. Marqu'es;Shin’ichi Satoh
中科院分区：
文献类型：
--
作者：
Andreu Girbau;F. Marqu'es;Shin’ichi Satoh
多目标跟踪（MOT）中的当前方法依赖于检测之间的时空相干性结合对象外观来匹配来自连续帧的对象。在这项工作中，我们探索MOT使用对象外观作为视频中的对象之间的关联的主要来源，使用空间和时间先验作为加权因子。我们形成初始的tracklets利用的想法，即在时间上接近的对象的实例应该是相似的外观，并建立最终的对象轨迹融合的tracklets在一个层次化的方式。我们进行了大量的实验，显示了我们的方法在三个不同的MOT基准，MOT17，MOT20和DanceTrack的有效性，在MOT17和MOT20中具有竞争力，并在DanceTrack中建立了最先进的结果。
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.