DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking

TL;DR

DIMM introduces a decoupled multi-hierarchy Kalman filter framework that enhances 3D object tracking accuracy by effectively combining multiple motion models in each direction using an adaptive fusion network.

Contribution

The paper proposes a novel decoupled multi-hierarchy Kalman filter framework (DIMM) that expands model combination space and employs a learned adaptive fusion network for improved 3D object tracking.

Findings

Significantly improves tracking accuracy by up to 99.23%.

Outperforms existing methods in diverse motion scenarios.

Demonstrates robustness to measurement uncertainty.

Abstract

State estimation is challenging for 3D object tracking with high maneuverability, as the target's state transition function changes rapidly, irregularly, and is unknown to the estimator. Existing work based on interacting multiple model (IMM) achieves more accurate estimation than single-filter approaches through model combination, aligning appropriate models for different motion modes of the target object over time. However, two limitations of conventional IMM remain unsolved. First, the solution space of the model combination is constrained as the target's diverse kinematic properties in different directions are ignored. Second, the model combination weights calculated by the observation likelihood are not accurate enough due to the measurement uncertainty. In this paper, we propose a novel framework, DIMM, to effectively combine estimates from different motion models in each direction, thus increasing the 3D object tracking accuracy. First, DIMM extends the model combination solution space of conventional IMM from a hyperplane to a hypercube by designing a 3D-decoupled multi-hierarchy filter bank, which describes the target's motion with various-order linear models. Second, DIMM generates more reliable combination weight matrices through a differentiable adaptive fusion network for importance allocation rather than solely relying on the observation likelihood; it contains an attention-based twin delayed deep deterministic policy gradient (TD3) method with a hierarchical reward. Experiments demonstrate that DIMM significantly improves the tracking accuracy of existing state estimation methods by 31.61%~99.23%.