论文标题
边际推理强大的多对象跟踪
Robust Multi-Object Tracking by Marginal Inference
论文作者
论文摘要
视频中的多目标跟踪需要解决相邻帧中对象之间一对一分配的基本问题。大多数方法通过首先丢弃不可能的对距离大于阈值的不可能对解决问题，然后使用匈牙利算法将对象链接起来以最大程度地减少整体距离。但是，我们发现不同视频中从重新ID特征计算出的距离的分布可能会有很大差异。因此，没有一个最佳阈值可以使我们可以安全地丢弃不可能的对。为了解决该问题，我们提出了一种有效的方法，可以实时计算每对对象的边际概率。边缘概率可以视为标准化距离，比原始特征距离明显稳定。结果，我们可以为所有视频使用一个阈值。该方法是一般的，可以应用于现有的跟踪器，以在IDF1度量方面获得大约一个点改进。它在MOT17和MOT20基准测试中取得了竞争成果。此外，计算的概率更容易解释，从而有助于随后的后处理操作。
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.
