A unified approach for multi-object triangulation, tracking and camera calibration
This addresses estimation challenges in camera networks, but it appears incremental as it builds on existing PHD filtering and disparity space concepts.
The paper tackles the joint problems of multi-object triangulation, tracking, and camera calibration by proposing a unified Bayesian framework that uses disparity space and PHD filtering, showing it outperforms Kalman and particle filters on simulated data.
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.