Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT), which often leads to inferior tracking results due to the missing detected objects. The common practice in multi-object tracking is re-identifying the missed objects after their reappearance. Though tracking performance can be boosted by the re-identification, the annotation of identity is required to train the model. In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector. In this paper, we focus on online multi-object tracking and design two novel modules, the unsupervised re-identification learning module and the occlusion estimation module, to handle these problems. Specifically, the proposed unsupervised re-identification learning module does not require any (pseudo) identity information nor suffer from the scalability issue. The proposed occlusion estimation module tries to predict the locations where occlusions happen, which are used to estimate the positions of missed objects by the detector. Our study shows that, when applied to state-of-the-art MOT methods, the proposed unsupervised re-identification learning is comparable to supervised re-identification learning, and the tracking performance is further improved by the proposed occlusion estimation module.
翻译:多目标跟踪(MOT)中,不同对象之间的隔离是一个典型的挑战。 多目标跟踪(MOT)中,不同对象之间的隔离往往导致因被检测到的天体缺失而导致跟踪结果的低劣。多目标跟踪(MOT)的常见做法是再次发现未找到的天体后重新识别。虽然跟踪性能可以通过重新识别来提高,但模型的培训需要身份识别说明。此外,这种重新识别的做法仍然无法追踪被检测者错失的高度隐蔽天体。在本文中,我们侧重于在线多目标跟踪和设计两个新模块,即未经监督的再识别学习模块和隐蔽估计模块,以处理这些问题。具体地说,拟议的未经监督的再识别学习模块并不需要任何(假)身份信息,也不需要受到可缩放问题的影响。提议的隐蔽估计模块试图预测发生隐蔽的地点,用来估计探测器失密天体的位置。我们的研究显示,在应用状态应用无监督的重新识别模块时,通过可比较的跟踪性定位,拟议的不监督性定位模块是进一步学习。