Data-Driven Approaches for Modelling Target Behaviour
This is an incremental study for tracking algorithm developers, comparing existing machine learning methods to improve motion modeling.
This paper tackled the problem of poor tracking algorithm performance due to mismatched motion models by comparing three data-driven methods (Gaussian Processes, Interacting Multiple Model filter, and LSTM) against an Extended Kalman Filter benchmark in simulated and real-world scenarios, showing their respective strengths.
The performance of tracking algorithms strongly depends on the chosen model assumptions regarding the target dynamics. If there is a strong mismatch between the chosen model and the true object motion, the track quality may be poor or the track is easily lost. Still, the true dynamics might not be known a priori or it is too complex to be expressed in a tractable mathematical formulation. This paper provides a comparative study between three different methods that use machine learning to describe the underlying object motion based on training data. The first method builds on Gaussian Processes (GPs) for predicting the object motion, the second learns the parameters of an Interacting Multiple Model (IMM) filter and the third uses a Long Short-Term Memory (LSTM) network as a motion model. All methods are compared against an Extended Kalman Filter (EKF) with an analytic motion model as a benchmark and their respective strengths are highlighted in one simulated and two real-world scenarios.