Multi-object tracking in videos requires to solve a fundamental problem of
one-to-one assignment between objects in adjacent frames. Most methods address
the problem by first discarding impossible pairs whose feature distances are
larger than a threshold, followed by linking objects using Hungarian algorithm
to minimize the overall distance. However, we find that the distribution of the
distances computed from Re-ID features may vary significantly for different
videos. So there isn't a single optimal threshold which allows us to safely
discard impossible pairs. To address the problem, we present an efficient
approach to compute a marginal probability for each pair of objects in real
time. The marginal probability can be regarded as a normalized distance which
is significantly more stable than the original feature distance. As a result,
we can use a single threshold for all videos. The approach is general and can
be applied to the existing trackers to obtain about one point improvement in
terms of IDF1 metric. It achieves competitive results on MOT17 and MOT20
benchmarks. In addition, the computed probability is more interpretable which
facilitates subsequent post-processing operations.

本文提出了一种基于边缘概率计算的目标多目标追踪方法，可以取代原始特征距离，解决了不同视频中距离分布变化引起的单一特征距离阈值不准确的问题，并在 MOT17 和 MOT20 基准测试中获得了较好的结果，并且计算得到的概率更易于解释，有利于后续的后处理操作。

通过边缘推断实现鲁棒多目标跟踪

Robust Multi-Object Tracking by Marginal Inference

Existing instance segmentation methods have achieved impressive performance
but still suffer from a common dilemma: redundant representations (e.g.,
multiple boxes, grids, and anchor points) are inferred for one instance, which
leads to multiple duplicated predictions. Thus, mainstream methods usually rely
on a hand-designed non-maximum suppression (NMS) post-processing step to select
the optimal prediction result, which hinders end-to-end training. To address
this issue, we propose a box-free and NMS-free end-to-end instance segmentation
framework, termed UniInst, that yields only one unique representation for each
instance. Specifically, we design an instance-aware one-to-one assignment
scheme, namely Only Yield One Representation (OYOR), which dynamically assigns
one unique representation to each instance according to the matching quality
between predictions and ground truths. Then, a novel prediction re-ranking
strategy is elegantly integrated into the framework to address the misalignment
between the classification score and the mask quality, enabling the learned
representation to be more discriminative. With these techniques, our UniInst,
the first FCN-based box-free and NMS-free instance segmentation framework,
achieves competitive performance, e.g., 39.0 mask AP using ResNet-50-FPN and
40.2 mask AP using ResNet-101-FPN, against mainstream methods on COCO test-dev
2017. Moreover, the proposed instance-aware method is robust to occlusion
scenes, outperforming common baselines by remarkable mask AP on the
heavily-occluded OCHuman benchmark. Code is available at
this https URL.

提出了一种基于 UniInst 的全新实例分割框架，该框架采用了 “只产生一个表征” 的实例感知一对一分配方案（OYOR），消除了传统方法中存在的冗余表征问题，并将预测重排策略与框架相结合，以使得学习到的表征更有辨别能力。结果，该框架在 COCO test-dev2017 数据集上取得了 39.0 mask AP 和 40.2 mask AP 的竞争优势，并在 OCHuman 跑步车上表现稳健。