Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
This addresses the issue of hand-crafted components in multi-object tracking for computer vision applications, offering a more efficient and data-driven solution.
The paper tackles the problem of multi-object tracking by proposing an end-to-end learning-based association approach that unifies feature learning and data association, achieving state-of-the-art performance on MOT2016 and MOT2017 benchmarks with over 20x faster training than a similar method.
Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature. In this paper, we present a new multiple object tracking (MOT) framework with data-driven association method, named as Tracklet Association Tracker (TAT). The framework aims at gluing feature learning and data association into a unity by a bi-level optimization formulation so that the association results can be directly learned from features. To boost the performance, we also adopt the popular hierarchical association and perform the necessary alignment and selection of raw detection responses. Our model trains over 20X faster than a similar approach, and achieves the state-of-the-art performance on both MOT2016 and MOT2017 benchmarks.