Scalable Detection and Tracking of Geometric Extended Objects

TL;DR

This paper introduces a scalable, particle-based factor graph approach for detecting and tracking multiple extended objects, capable of handling complex shapes and high object densities in real-time scenarios.

Contribution

It presents a novel fully particle-based method for extended object tracking that jointly infers object shapes and associations, outperforming existing filters in dense environments.

Findings

Effective detection and tracking of up to twenty objects in simulations.

Reliable shape inference for various geometric objects.

Superior performance over Poisson multi-Bernoulli filters.

Abstract

Multiobject tracking provides situational awareness that enables new applications for modern convenience, public safety, and homeland security. This paper presents a factor graph formulation and a particle-based sum-product algorithm (SPA) for scalable detection and tracking of extended objects. The proposed method dynamically introduces states of newly detected objects, efficiently performs probabilistic multiple-measurement to object association, and jointly infers the geometric shapes of objects. Scalable extended object tracking (EOT) is enabled by modeling association uncertainty by measurement-oriented association variables and newly detected objects by a Poisson birth process. Contrary to conventional EOT methods, a fully particle-based approach makes it possible to describe different geometric object shapes. The proposed method can reliably detect, localize, and track a large number of closely-spaced extended objects without gating and clustering of measurements. We demonstrate significant performance advantages of our approach compared to the recently introduced Poisson multi-Bernoulli mixture filter. In particular, we consider a simulated scenarios with up to twenty closely-spaced objects and a real autonomous driving application where measurements are captured by a lidar sensor.