仅用检测标注训练，通过运动一致性提升跟踪精度。
No Identity, no problem: Motion through detection for people tracking
- 利用两张图的检测热图和2D运动估计，通过图像对齐提供监督信号。
- 在MOT17和WILDTRACK上达到单/多视角跟踪最优性能。
- 无需身份标注，特别适合低帧率和人群密集场景。
基于检测的行人跟踪已成为主流方法。为提升鲁棒性，现有方法常依赖外观模型和运动偏移回归，但需昂贵的身份标注。本文提出仅使用检测标注，通过预测两时刻的检测热图及两者间的2D运动估计，将一热图经运动估计进行形变后与另一热图对齐，从而在无运动标注情况下提供运动监督。该机制在训练中融合跨图像信息，显著提升拥挤场景和低帧率序列下的跟踪精度。实验表明，在MOT17和WILDTRACK数据集上，本方法在单视图和多视图多目标跟踪任务中均达到当前最优性能。
原文摘要 · Abstract (English)
Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models and regressing motion offset, which requires costly identity annotations. In this paper, we propose exploiting motion clues while providing supervision only for the detections, which is much easier to do. Our algorithm predicts detection heatmaps at two different times, along with a 2D motion estimate between the two images. It then warps one heatmap using the motion estimate and enforces consistency with the other one. This provides the required supervisory signal on the motion without the need for any motion annotations. In this manner, we couple the information obtained from different images during training and increase accuracy, especially in crowded scenes and when using low frame-rate sequences. We show that our approach delivers state-of-the-art results for single- and multi-view multi-target tracking on the MOT17 and WILDTRACK datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。