论文标题
使用暹罗轨道RCNN的多对象跟踪
Multi-Object Tracking with Siamese Track-RCNN
论文作者
论文摘要
多对象跟踪系统通常包括检测器的组合，短期链接器，重新识别功能提取器和求解器，该求解器从这些单独的组件中获取输出并做出最终预测。从不同的角度来看，这项工作旨在在单个跟踪系统中统一所有这些。在此方面，我们提出了Siamese Track-Rcnn，这是一个两个阶段检测和轨道框架，由三个功能分支组成：（1）检测分支本地化对象实例； （2）基于暹罗的轨道分支估计对象运动，（3）对象重新识别分支在重新出现时重新激活先前终止的轨道。我们在Motchallenge的两个流行数据集上测试了我们的跟踪系统。 Siamese Track-Rcnn取得的成绩明显高于最先进的结果，同时由于其统一的设计，也更加有效。
Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these separate components and makes a final prediction. Differently, this work aims to unify all these in a single tracking system. Towards this, we propose Siamese Track-RCNN, a two stage detect-and-track framework which consists of three functional branches: (1) the detection branch localizes object instances; (2) the Siamese-based track branch estimates the object motion and (3) the object re-identification branch re-activates the previously terminated tracks when they re-emerge. We test our tracking system on two popular datasets of the MOTChallenge. Siamese Track-RCNN achieves significantly higher results than the state-of-the-art, while also being much more efficient, thanks to its unified design.
