An RNN-based IMM Filter Surrogate
This work addresses pedestrian tracking for applications like autonomous vehicles, but it is incremental as it adapts a deep learning approach to an existing Bayesian method.
The paper tackled the problem of tracking pedestrians with varying dynamics by proposing an RNN-based surrogate for the IMM filter, which outputs a multi-modal distribution over future trajectories, with evaluation conducted on synthetic data.
The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers.