Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
IEEE Trans Image Process. 2011 Jun;20(6):1652-67. doi: 10.1109/TIP.2010.2102045. Epub 2010 Dec 23.
Multiple object tracking (MOT) is a very challenging task yet of fundamental importance for many practical applications. In this paper, we focus on the problem of tracking multiple players in sports video which is even more difficult due to the abrupt movements of players and their complex interactions. To handle the difficulties in this problem, we present a new MOT algorithm which contributes both in the observation modeling level and in the tracking strategy level. For the observation modeling, we develop a progressive observation modeling process that is able to provide strong tracking observations and greatly facilitate the tracking task. For the tracking strategy, we propose a dual-mode two-way Bayesian inference approach which dynamically switches between an offline general model and an online dedicated model to deal with single isolated object tracking and multiple occluded object tracking integrally by forward filtering and backward smoothing. Extensive experiments on different kinds of sports videos, including football, basketball, as well as hockey, demonstrate the effectiveness and efficiency of the proposed method.
多目标跟踪（MOT）是一项极具挑战性的任务，但对于许多实际应用来说却至关重要。在本文中，我们专注于体育视频中多个运动员的跟踪问题，由于运动员的剧烈运动和复杂的相互作用，使得该问题更加困难。为了解决这个问题中的难点，我们提出了一种新的 MOT 算法，该算法在观测建模和跟踪策略两个层面都有贡献。在观测建模方面，我们开发了一个渐进式观测建模过程，该过程能够提供强大的跟踪观测，并极大地简化了跟踪任务。在跟踪策略方面，我们提出了一种双模双向贝叶斯推断方法，该方法能够通过前向滤波和后向平滑，在离线通用模型和在线专用模型之间动态切换，从而整体处理单个孤立目标跟踪和多个遮挡目标跟踪。在不同类型的体育视频上进行的广泛实验，包括足球、篮球和曲棍球，验证了所提出方法的有效性和高效性。
