论文标题
通过端到端轨迹搜索和排名多对象跟踪
Multi-object Tracking via End-to-end Tracklet Searching and Ranking
论文作者
论文摘要
多个对象跟踪中的最新作品使用序列模型来计算检测和先前曲目之间的相似性分数。但是，在训练阶段，强迫接触地面真相会导致训练 - 推断差异问题，即暴露偏见，在这些偏差中可能会在推理中积累关联误差并使轨迹漂移。在本文中，我们提出了一种新的方法来优化曲目一致性，该方法通过引入在线，端到端的轨道搜索训练过程来直接考虑预测错误。值得注意的是，我们的方法直接优化了整个轨道分数，而不是成对亲和力。以序列模型为曲目的外观编码器，我们的跟踪器从传统的轨道关联基线获得了显着的性能增长。我们的方法还使用公共检测和在线设置实现了MOT15〜17挑战基准的最先进。
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the training-inference discrepancy problem, i.e., exposure bias, where association error could accumulate in the inference and make the trajectories drift. In this paper, we propose a novel method for optimizing tracklet consistency, which directly takes the prediction errors into account by introducing an online, end-to-end tracklet search training process. Notably, our methods directly optimize the whole tracklet score instead of pairwise affinity. With sequence model as appearance encoders of tracklet, our tracker achieves remarkable performance gain from conventional tracklet association baseline. Our methods have also achieved state-of-the-art in MOT15~17 challenge benchmarks using public detection and online settings.
