A unified approach for multi-object triangulation, tracking and camera calibration

TL;DR

This paper presents a unified Bayesian framework utilizing disparity space and PHD filtering for joint multi-object tracking, triangulation, and camera calibration, demonstrating improved effectiveness over traditional methods in simulated scenarios.

Contribution

It introduces a novel unified approach combining disparity space parametrization and PHD filtering for simultaneous multi-object tracking, triangulation, and camera calibration.

Findings

Disparity space approach outperforms non-linear Kalman and particle filters.

PHD filter enables measurement association without explicit data association.

Method successfully calibrates cameras using static or moving objects in simulations.

Abstract

Object triangulation, 3-D object tracking, feature correspondence, and camera calibration are key problems for estimation from camera networks. This paper addresses these problems within a unified Bayesian framework for joint multi-object tracking and sensor registration. Given that using standard filtering approaches for state estimation from cameras is problematic, an alternative parametrisation is exploited, called disparity space. The disparity space-based approach for triangulation and object tracking is shown to be more effective than non-linear versions of the Kalman filter and particle filtering for non-rectified cameras. The approach for feature correspondence is based on the Probability Hypothesis Density (PHD) filter, and hence inherits the ability to update without explicit measurement association, to initiate new targets, and to discriminate between target and clutter. The PHD filtering approach then forms the basis of a camera calibration method from static or moving objects. Results are shown on simulated data.