Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
This work addresses occlusion challenges in multi-object tracking for video analysis, offering incremental improvements by integrating unsupervised learning and occlusion handling into existing methods.
The paper tackles the problem of occlusion in online multi-object tracking by proposing an unsupervised re-identification learning module that avoids identity annotations and an occlusion estimation module to predict missed object positions, showing comparable performance to supervised methods and improved tracking results.
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.