Neural Enhanced Belief Propagation for Multiobject Tracking

by   Mingchao Liang, et al.

Algorithmic solutions for multi-object tracking (MOT) are a key enabler for applications in autonomous navigation and applied ocean sciences. State-of-the-art MOT methods fully rely on a statistical model and typically use preprocessed sensor data as measurements. In particular, measurements are produced by a detector that extracts potential object locations from the raw sensor data collected for a discrete time step. This preparatory processing step reduces data flow and computational complexity but may result in a loss of information. State-of-the-art Bayesian MOT methods that are based on belief propagation (BP) systematically exploit graph structures of the statistical model to reduce computational complexity and improve scalability. However, as a fully model-based approach, BP can only provide suboptimal estimates when there is a mismatch between the statistical model and the true data-generating process. Existing BP-based MOT methods can further only make use of preprocessed measurements. In this paper, we introduce a variant of BP that combines model-based with data-driven MOT. The proposed neural enhanced belief propagation (NEBP) method complements the statistical model of BP by information learned from raw sensor data. This approach conjectures that the learned information can reduce model mismatch and thus improve data association and false alarm rejection. Our NEBP method improves tracking performance compared to model-based methods. At the same time, it inherits the advantages of BP-based MOT, i.e., it scales only quadratically in the number of objects, and it can thus generate and maintain a large number of object tracks. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it has state-of-the-art performance.


Neural Enhanced Belief Propagation for Data Assocation in Multiobject Tracking

Situation-aware technologies enabled by multiobject tracking (MOT) metho...

Neural Enhanced Belief Propagation for Cooperative Localization

Location-aware networks will introduce innovative services and applicati...

Approximate evaluation of marginal association probabilities with belief propagation

Data association, the problem of reasoning over correspondence between t...

Seamless Tracking of Group Targets and Ungrouped Targets Using Belief Propagation

This paper considers the problem of tracking a large-scale number of gro...

Decoding of Polar Codes Based on Q-Learning-Driven Belief Propagation

This paper presents an enhanced belief propagation (BP) decoding algorit...

A Brownian Motion Model and Extreme Belief Machine for Modeling Sensor Data Measurements

As the title suggests, we will describe (and justify through the present...

Shape Estimation from Defocus Cue for Microscopy Images via Belief Propagation

In recent years, the usefulness of 3D shape estimation is being realized...

Please sign up or login with your details

Forgot password? Click here to reset