Neural Enhanced Belief Propagation for Data Association in Multiobject Tracking

Abstract

Situation-aware technologies enabled by multiobject tracking (MOT) methods will create new services and applications in fields such as autonomous navigation and applied ocean sciences. Belief propagation (BP) is a state-of-the-art method for Bayesian MOT but fully relies on a statistical model and preprocessed sensor measurements. In this paper, we establish a hybrid method for model-based and data-driven MOT. The proposed neural enhanced belief propagation (NEBP) approach complements BP by information learned from raw sensor data with the goal to improve data association and to reject false alarm measurements. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it can outperform state-ofthe-art reference methods.

GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

“…The graph structure is a Neural Message Passing network for fully trainable data association. Neural enhanced belief propagation (NEBP) tracker [18] is an update to the Belief Propagation Tracker [8], proposing a belief propagation scheme complemented by a learned neural network. The NEBP tracker achieves superior tracking performance over its non-learningbased counterpart, namely the Belief Propagation tracker.…”