IEEE Trans Image Process. 2019 Jan;28(1):240-252. doi: 10.1109/TIP.2018.2866955. Epub 2018 Aug 23.
This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet process mixture model. The tracking problem is cast as a topic-discovery task, where the video sequence is treated analogously to a document. It addresses tracking issues such as object exclusivity constraints as well as tracking management without the need for heuristic thresholds. Variation of object appearance is modeled as the dynamics of word co-occurrence and handled by updating the cluster parameters across the sequence in the dynamical clustering procedure. We develop two kinds of visual representation based on super-pixel and deformable part model and integrate them into the model of automatic topic discovery for tracking rigid and non-rigid objects, respectively. In experiments on public data sets, we demonstrate the effectiveness of the proposed algorithm.
本文提出了一种基于语义主题发现的多目标跟踪新方法。我们逐帧动态聚类检测结果，并将目标视为主题，从而可以应用狄利克雷过程混合模型。跟踪问题被视为主题发现任务，即将视频序列视为文档。它解决了一些跟踪问题，例如对象排他性约束以及无需启发式阈值的跟踪管理。对象外观的变化被建模为词共现的动态，并通过在动态聚类过程中跨序列更新聚类参数来处理。我们分别基于超像素和可变形部件模型开发了两种视觉表示，并将它们集成到自动主题发现模型中，以分别跟踪刚体和非刚体目标。在公共数据集上的实验表明，所提出算法的有效性。
