New models and inference techniques for Gaussian process-based extended object tracking

Download

Murat_Kumru_PhD_Thesis.pdf

Date

2022-9-09

Author

Kumru, Murat

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

437
views

39
downloads

In this thesis, we consider the problem of tracking dynamic objects with unknown shapes using point cloud measurements generated by, e.g., lidars, radars, and depth cameras. The point measurements do not only convey information about the object pose, i.e., position and orientation, but they also naturally reveal the characteristics of its latent extent. Aiming to harness the full potential of the available information, we investigate the Gaussian process-based extended object tracking (GPEOT) framework. We hereby develop several three-dimensional (3D) GPEOT models that effectively use the information provided by 3D point cloud measurements. The resulting methods can accurately estimate the 3D object shape together with its kinematic properties, such as position, orientation, and velocity. Furthermore, we introduce an approximate inference method for the GPEOT models relying on the variational Bayesian technique, where the approximate posterior distributions of the kinematic and extent variables are effectively computed by fixed-point iterations. The resulting method is particularly shown to prove robust against model uncertainties. We also focus on improving the computational characteristics of the existing GPEOT algorithms without compromising their effective performance. To this end, we formulate an alternative approximate description of the underlying GP model for the extent that provides satisfactory performance at a lower computational load. This formulation is used to derive both two- and three-dimensional tracking algorithms. Additionally, we propose a novel model that does not require the star-convexity assumption, as opposed to the standard GPEOT. Therefore, this formulation expands the application of the existing GPEOT framework as it enables tracking arbitrarily-shaped objects while learning their latent extent. Comprehensive experiments are performed to demonstrate the added value of the mentioned contributions with both simulated and real measurements.

Subject Keywords

Extended object tracking, Object tracking, Gaussian processes, Variational Bayes

URI

https://hdl.handle.net/11511/99572

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

3D Extended Object Tracking Using Recursive Gaussian Processes Kumru, Murat; Özkan, Emre (2018-07-10) In this study, we consider the challenging task of tracking dynamic 3D objects with unknown shapes by using sparse point cloud measurements gathered from the surface of the objects. We propose a Gaussian process based algorithm that is capable of tracking the dynamic behavior of the object and learn its shape in 3D simultaneously. Our solution does not require any parametric model assumption for the unknown shape. The shape of the objects is learned online via a Gaussian process. The proposed method can joi...
A multimodal approach for individual tracking of people and their belongings Beyan, Çiğdem; Temizel, Alptekin (2015-04-01) In this study, a fully automatic surveillance system for indoor environments which is capable of tracking multiple objects using both visible and thermal band images is proposed. These two modalities are fused to track people and the objects they carry separately using their heat signatures and the owners of the belongings are determined. Fusion of complementary information from different modalities (for example, thermal images are not affected by shadows and there is no thermal reflection or halo effect in...
Random Matrix Based Extended Target Tracking with Orientation: A New Model and Inference Tuncer, Barkın; Özkan, Emre (2021-02-01) In this study, we propose a novel extended target tracking algorithm which is capable of representing the extent of dynamic objects as an ellipsoid with a time-varying orientation angle. A diagonal positive semi-definite matrix is defined to model objects' extent within the random matrix framework where the diagonal elements have inverse-Gamma priors. The resulting measurement equation is non-linear in the state variables, and it is not possible to find a closed-form analytical expression for the true poste...
Extended Target Tracking Using Gaussian Processes Wahlström, Niklas; Özkan, Emre (2015-08-15) In this paper, we propose using Gaussian processes to track an extended object or group of objects, that generates multiple measurements at each scan. The shape and the kinematics of the object are simultaneously estimated, and the shape is learned online via a Gaussian process. The proposed algorithm is capable of tracking different objects with different shapes within the same surveillance region. The shape of the object is expressed analytically, with well-defined confidence intervals, which can be used ...
Extended Target Tracking and Classification Using Neural Networks Tuncer, Barkın; Kumru, Murat; Özkan, Emre (2019-01-01) Extended target/object tracking (ETT) problem involves tracking objects which potentially generate multiple measurements at a single sensor scan. State-of-the-art ETT algorithms can efficiently exploit the available information in these measurements such that they can track the dynamic behaviour of objects and learn their shapes simultaneously. Once the shape estimate of an object is formed, it can naturally be utilized by high-level tasks such as classification of the object type. In this work, we propose ...

Citation Formats

M. Kumru, “New models and inference techniques for Gaussian process-based extended object tracking,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.