Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
This addresses the challenge of non-linear motion prediction in tracking for applications like autonomous driving, though it is incremental as it builds on existing tracking methods.
The paper tackles the problem of multiple object tracking and trajectory forecasting by proposing a joint learning architecture that replaces linear motion prediction methods like the Kalman filter with trajectory forecasts, resulting in reduced ID switches by 33%, 31%, and 47% on MOT16, MOT17, and MOT20 datasets compared to FairMOT.
This paper introduces a joint learning architecture (JLA) for multiple object tracking (MOT) and trajectory forecasting in which the goal is to predict objects' current and future trajectories simultaneously. Motion prediction is widely used in several state of the art MOT methods to refine predictions in the form of bounding boxes. Typically, a Kalman Filter provides short-term estimations to help trackers correctly predict objects' locations in the current frame. However, the Kalman Filter-based approaches cannot predict non-linear trajectories. We propose to jointly train a tracking and trajectory forecasting model and use the predicted trajectory forecasts for short-term motion estimates in lieu of linear motion prediction methods such as the Kalman filter. We evaluate our JLA on the MOTChallenge benchmark. Evaluations result show that JLA performs better for short-term motion prediction and reduces ID switches by 33%, 31%, and 47% in the MOT16, MOT17, and MOT20 datasets, respectively, in comparison to FairMOT.