2024
Şahin, Kurtuluş Kerem; Balcı, Ali Emre; Özkan, Emre
Random matrix extended target tracking for trajectory‐aligned and drifting targets Journal Article
In: IET Radar Sonar & Navi, vol. 18, no. 11, pp. 2247–2263, 2024, ISSN: 1751-8792.
@article{Şahin2024,
title = {Random matrix extended target tracking for trajectory‐aligned and drifting targets},
author = {Kurtuluş Kerem Şahin and Ali Emre Balcı and Emre Özkan},
url = {https://github.com/Metu-Sensor-Fusion-Lab/RM_ETT_for_trajectory_aligned_and_drifting_targets},
doi = {10.1049/rsn2.12628},
issn = {1751-8792},
year = {2024},
date = {2024-11-00},
urldate = {2024-11-00},
journal = {IET Radar Sonar & Navi},
volume = {18},
number = {11},
pages = {2247--2263},
publisher = {Institution of Engineering and Technology (IET)},
abstract = {<jats:title>Abstract</jats:title><jats:p>In this paper, we propose two random matrix based extended target tracking models, which apply to the <jats:italic>trajectory‐aligned</jats:italic> and <jats:italic>drifting</jats:italic> target motions. The trajectory‐aligned model is specifically designed to handle targets moving along the direction of their extent orientations, while the drift model is tailored to targets whose trajectories deviate from their orientations in time. We utilise the well‐known variational Bayes method to perform inference and obtain posterior densities via computationally efficient, analytical, iterative steps. Through comprehensive experiments conducted on simulated and real data, our methods have demonstrated superior performance compared to previous approaches in scenarios involving both drifting and trajectory‐aligned targets. These results highlight the efficacy of our proposed models in accurately tracking targets and estimating their extent.</jats:p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<jats:title>Abstract</jats:title><jats:p>In this paper, we propose two random matrix based extended target tracking models, which apply to the <jats:italic>trajectory‐aligned</jats:italic> and <jats:italic>drifting</jats:italic> target motions. The trajectory‐aligned model is specifically designed to handle targets moving along the direction of their extent orientations, while the drift model is tailored to targets whose trajectories deviate from their orientations in time. We utilise the well‐known variational Bayes method to perform inference and obtain posterior densities via computationally efficient, analytical, iterative steps. Through comprehensive experiments conducted on simulated and real data, our methods have demonstrated superior performance compared to previous approaches in scenarios involving both drifting and trajectory‐aligned targets. These results highlight the efficacy of our proposed models in accurately tracking targets and estimating their extent.</jats:p>
Kumru, Murat; Özkan, Emre
Tracking Arbitrarily Shaped Extended Objects Using Gaussian Processes Proceedings Article
In: 2024 27th International Conference on Information Fusion (FUSION), pp. 1-8, 2024.
@inproceedings{Kumru2024,
title = {Tracking Arbitrarily Shaped Extended Objects Using Gaussian Processes},
author = {Murat Kumru and Emre Özkan},
url = {https://ieeexplore.ieee.org/abstract/document/10706470},
doi = {10.23919/fusion59988.2024.10706470},
year = {2024},
date = {2024-07-08},
urldate = {2024-07-08},
booktitle = {2024 27th International Conference on Information Fusion (FUSION)},
pages = {1-8},
abstract = {In this paper, we consider the problem of tracking dynamic objects with unknown shapes using point cloud measurements generated by sensors such as lidars and radars. Specifically, our objective is to extend the Gaussian process-based extended object tracking (GPEOT) framework to encompass a broader class of objects. The derivation of the existing GPEOT algorithms is based on the assumption that the object of interest is star-convex. This assumption enables the modeling of the object’s extent through a radial distance function, which is described by a Gaussian process (GP). To enhance the flexibility of the resulting trackers, we propose the utilization of a potential function to indicate the unknown object extent. This approach enables the representation of objects with arbitrary shapes, including those that are non-convex and composed of disconnected components. Closely following the original formulation of GPEOT, the potential function is then modeled by a GP, which systematically accounts for the intrinsic spatial correlation of the extent. Furthermore, we develop a state-space model that incorporates both kinematic variables and an approximate description of the underlying GP model. The state vector can be estimated via a standard Bayesian technique, leading to an EOT algorithm. Through simulation experiments, we demonstrate the suggested method can satisfactorily estimate the kinematic variables of the objects while simultaneously learning their complex shapes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we consider the problem of tracking dynamic objects with unknown shapes using point cloud measurements generated by sensors such as lidars and radars. Specifically, our objective is to extend the Gaussian process-based extended object tracking (GPEOT) framework to encompass a broader class of objects. The derivation of the existing GPEOT algorithms is based on the assumption that the object of interest is star-convex. This assumption enables the modeling of the object’s extent through a radial distance function, which is described by a Gaussian process (GP). To enhance the flexibility of the resulting trackers, we propose the utilization of a potential function to indicate the unknown object extent. This approach enables the representation of objects with arbitrary shapes, including those that are non-convex and composed of disconnected components. Closely following the original formulation of GPEOT, the potential function is then modeled by a GP, which systematically accounts for the intrinsic spatial correlation of the extent. Furthermore, we develop a state-space model that incorporates both kinematic variables and an approximate description of the underlying GP model. The state vector can be estimated via a standard Bayesian technique, leading to an EOT algorithm. Through simulation experiments, we demonstrate the suggested method can satisfactorily estimate the kinematic variables of the objects while simultaneously learning their complex shapes.
Yurdakul, Oğul Can; Çetinkaya, Mehmet; Çelebi, Enescan; Özkan, Emre
A Rao-Blackwellized Particle Filter for Superelliptical Extended Target Tracking Proceedings Article
In: 2024 27th International Conference on Information Fusion (FUSION), pp. 1-8, IEEE, 2024.
@inproceedings{Yurdakul2024,
title = {A Rao-Blackwellized Particle Filter for Superelliptical Extended Target Tracking},
author = {Oğul Can Yurdakul and Mehmet Çetinkaya and Enescan Çelebi and Emre Özkan},
url = {https://ieeexplore.ieee.org/document/10706504},
doi = {10.23919/fusion59988.2024.10706504},
year = {2024},
date = {2024-07-08},
urldate = {2024-07-08},
booktitle = {2024 27th International Conference on Information Fusion (FUSION)},
pages = {1-8},
publisher = {IEEE},
abstract = {In this work, we propose a new method to track extended targets of different shapes such as ellipses, rectangles and rhombi. We provide an analytical framework to express these shapes as superelliptical contours and propose a Bayesian filtering scheme that can handle measurements from the contour of the object. The method utilizes the Rao-Blackwellized particle filtering algorithm with novel sensor-object geometry constraints. The success of the algorithm is demonstrated using both simulations and real-data experiments, and the algorithm has been demonstrated to be of high performance in various challenging scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this work, we propose a new method to track extended targets of different shapes such as ellipses, rectangles and rhombi. We provide an analytical framework to express these shapes as superelliptical contours and propose a Bayesian filtering scheme that can handle measurements from the contour of the object. The method utilizes the Rao-Blackwellized particle filtering algorithm with novel sensor-object geometry constraints. The success of the algorithm is demonstrated using both simulations and real-data experiments, and the algorithm has been demonstrated to be of high performance in various challenging scenarios.
2022
Balcı, Ali Emre; Sahin, Kurtuluş Kerem; Kumru, Firat; Pektas, Fatih; Özkan, Emre; Orguner, Umut
Association and Fusion of Range- Azimuth Tracks Proceedings Article
In: 2022 25th International Conference on Information Fusion (FUSION), pp. 1-8, IEEE, 2022, ISBN: 978-1-7377497-2-1.
@inproceedings{9841272,
title = {Association and Fusion of Range- Azimuth Tracks},
author = {Ali Emre Balcı and Kurtuluş Kerem Sahin and Firat Kumru and Fatih Pektas and Emre Özkan and Umut Orguner},
url = {https://ieeexplore.ieee.org/abstract/document/9841272},
doi = {10.23919/FUSION49751.2022.9841272},
isbn = {978-1-7377497-2-1},
year = {2022},
date = {2022-07-01},
urldate = {2022-07-01},
booktitle = {2022 25th International Conference on Information Fusion (FUSION)},
pages = {1-8},
publisher = {IEEE},
abstract = {In this paper, novel association and fusion methods for range-azimuth tracks are proposed. The association method requires calculating the distance between two tracks that lack elevation information. An iterative algorithm is proposed to find the closest distance between the two arcs defined by the range azimuth tracks. This procedure provides elevation in-formation for track pairs, which is also used for the track fusion process. The performance of the algorithms is illustrated in experiments with simulated and real data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, novel association and fusion methods for range-azimuth tracks are proposed. The association method requires calculating the distance between two tracks that lack elevation information. An iterative algorithm is proposed to find the closest distance between the two arcs defined by the range azimuth tracks. This procedure provides elevation in-formation for track pairs, which is also used for the track fusion process. The performance of the algorithms is illustrated in experiments with simulated and real data.
Tuncer, Barkın; Orguner, Umut; Özkan, Emre
Multi-Ellipsoidal Extended Target Tracking With Variational Bayes Inference Journal Article
In: IEEE Transactions on Signal Processing, vol. 70, pp. 3921-3934, 2022.
BibTeX | Links:
@article{9837107b,
title = {Multi-Ellipsoidal Extended Target Tracking With Variational Bayes Inference},
author = {Barkın Tuncer and Umut Orguner and Emre Özkan},
url = {https://github.com/Metu-Sensor-Fusion-Lab/Multi-Ellipsoidal-Extended-Target-Tracking-with-Variational-Bayes-Inference},
doi = {10.1109/TSP.2022.3192617},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {IEEE Transactions on Signal Processing},
volume = {70},
pages = {3921-3934},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2021
Kumru, Murat; Köksal, Hilal; Özkan, Emre
Variational Measurement Update for Extended Object Tracking Using Gaussian Processes Journal Article
In: IEEE Signal Processing Letters, vol. 28, pp. 538-542, 2021.
@article{9357970,
title = {Variational Measurement Update for Extended Object Tracking Using Gaussian Processes},
author = {Murat Kumru and Hilal Köksal and Emre Özkan},
url = {https://ieeexplore.ieee.org/document/9357970
https://github.com/Metu-Sensor-Fusion-Lab},
doi = {10.1109/LSP.2021.3060316},
year = {2021},
date = {2021-02-18},
journal = {IEEE Signal Processing Letters},
volume = {28},
pages = {538-542},
abstract = {We present an alternative inference framework for the Gaussian process-based extended object tracking (GPEOT) models. The method provides an approximate solution to the Bayesian filtering problem in GPEOT by relying on a new measurement update, which we derive using variational Bayes techniques. The resulting algorithm effectively computes approximate posterior densities of the kinematic and the extent states. We conduct various experiments on simulated and real data and examine the performance compared with a reference method, which employs an extended Kalman filter for inference. The proposed algorithm significantly improves the accuracy of both the kinematic and the extent estimates and proves robust against model uncertainties.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We present an alternative inference framework for the Gaussian process-based extended object tracking (GPEOT) models. The method provides an approximate solution to the Bayesian filtering problem in GPEOT by relying on a new measurement update, which we derive using variational Bayes techniques. The resulting algorithm effectively computes approximate posterior densities of the kinematic and the extent states. We conduct various experiments on simulated and real data and examine the performance compared with a reference method, which employs an extended Kalman filter for inference. The proposed algorithm significantly improves the accuracy of both the kinematic and the extent estimates and proves robust against model uncertainties.
Tuncer, Barkın; Orguner, Umut; Özkan, Emre
Multi-Ellipsoidal Extended Target Tracking with Variational Bayes Inference Online
2021.
BibTeX | Links:
@online{2021c,
title = {Multi-Ellipsoidal Extended Target Tracking with Variational Bayes Inference},
author = {Barkın Tuncer and Umut Orguner and Emre Özkan},
url = {https://www.techrxiv.org/articles/preprint/Multi-Ellipsoidal_Extended_Target_Tracking_with_Variational_Bayes_Inference/14178494/1},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {online}
}
Tuncer, Barkın; Özkan, Emre
Random Matrix Based Extended Target Tracking with Orientation: A New Model and Inference Journal Article
In: IEEE Transactions on Signal Processing, pp. 1-1, 2021.
@article{2021,
title = {Random Matrix Based Extended Target Tracking with Orientation: A New Model and Inference},
author = {Barkın Tuncer and Emre Özkan},
url = {https://ieeexplore.ieee.org/document/9374715
https://github.com/Metu-Sensor-Fusion-Lab/Random-Matrix-Based-Extended-Target-Tracking-With-Orientation},
doi = {10.1109/TSP.2021.3065136},
year = {2021},
date = {2021-00-00},
urldate = {2021-00-00},
journal = {IEEE Transactions on Signal Processing},
pages = {1-1},
abstract = {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 posterior because of the absence of conjugacy. We use the variational Bayes technique to perform approximate inference, where the Kullback-Leibler divergence between the true and the approximate posterior is minimized by performing fixed-point iterations. The update equations are easy to implement, and the algorithm can be used in real-time tracking applications. We illustrate the performance of the method in simulations and experiments with real data. The proposed method outperforms the state-of-the-art methods when compared with respect to accuracy and robustness.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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 posterior because of the absence of conjugacy. We use the variational Bayes technique to perform approximate inference, where the Kullback-Leibler divergence between the true and the approximate posterior is minimized by performing fixed-point iterations. The update equations are easy to implement, and the algorithm can be used in real-time tracking applications. We illustrate the performance of the method in simulations and experiments with real data. The proposed method outperforms the state-of-the-art methods when compared with respect to accuracy and robustness.
Kumru, Murat; Özkan, Emre
Three-Dimensional Extended Object Tracking and Shape Learning Using Gaussian Processes Journal Article
In: IEEE Transactions on Aerospace and Electronic Systems, 2021.
@article{2021b,
title = {Three-Dimensional Extended Object Tracking and Shape Learning Using Gaussian Processes},
author = {Murat Kumru and Emre Özkan},
url = {https://arxiv.org/abs/1909.11358},
doi = {10.1109/TAES.2021.3067668},
year = {2021},
date = {2021-00-00},
urldate = {2021-00-00},
journal = {IEEE Transactions on Aerospace and Electronic Systems},
abstract = {In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including position, velocity and orientation, together with the shape of the object in an online fashion. We describe the unknown shape by a radial function in 3D, and induce a correlation structure via a Gaussian process. Furthermore, we propose an efficient algorithm to reduce the computational complexity of working with 3D data. This is accomplished by casting the tracking problem into projection planes which are attached to the object's local frame. The proposed methods provide an analytical expression for the object shape together with confidence intervals. The confidence intervals, which quantify the uncertainty in the shape estimate, can later be used for solving the gating and association problems inherent in object tracking. The performance of the methods is demonstrated both on simulated and real data. The results are compared with an existing random matrix model, which is commonly used for extended object tracking in the literature.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including position, velocity and orientation, together with the shape of the object in an online fashion. We describe the unknown shape by a radial function in 3D, and induce a correlation structure via a Gaussian process. Furthermore, we propose an efficient algorithm to reduce the computational complexity of working with 3D data. This is accomplished by casting the tracking problem into projection planes which are attached to the object's local frame. The proposed methods provide an analytical expression for the object shape together with confidence intervals. The confidence intervals, which quantify the uncertainty in the shape estimate, can later be used for solving the gating and association problems inherent in object tracking. The performance of the methods is demonstrated both on simulated and real data. The results are compared with an existing random matrix model, which is commonly used for extended object tracking in the literature.
2020
Kumru, Murat; Özkan, Emre
Comments on "Spatio-Temporal Gaussian Process Models for Extended and Group Object Tracking with Irregular Shapes" Online
arXiv preprint 2020.
@online{2002.08065,
title = {Comments on "Spatio-Temporal Gaussian Process Models for Extended and Group Object Tracking with Irregular Shapes"},
author = {Murat Kumru and Emre Özkan},
url = {https://arxiv.org/abs/2002.08065},
year = {2020},
date = {2020-01-01},
organization = {arXiv preprint},
abstract = {In the study "Spatio-temporal Gaussian process models for extended and group object tracking with irregular shapes" (IEEE Trans. Veh. Tech., vol. 68, no. 3, pp. 2137-2151, Mar. 2019), the extended object tracking problem was tackled by an approach based on spatio-temporal Gaussian processes (STGP). The performance of the proposed STGP-based trackers was comparatively evaluated through simulations and real data together with another state-of-the-art method (referred to as GP-EKF) proposed in "Extended target tracking using Gaussian processes" (IEEE Trans. Signal Process., vol. 63, no. 16, pp. 4165-4178, Aug. 2015). Unfortunately, we recognized that there are major errors in the implementation of the experiments presented in the STGP paper, which led to incorrect performance evaluation results. In this correspondence, our aim is to share the correct results of these experiments and to respond to some claims regarding GP-EKF, which we believe, would contribute to a better understanding of the methods.},
keywords = {},
pubstate = {published},
tppubtype = {online}
}
In the study "Spatio-temporal Gaussian process models for extended and group object tracking with irregular shapes" (IEEE Trans. Veh. Tech., vol. 68, no. 3, pp. 2137-2151, Mar. 2019), the extended object tracking problem was tackled by an approach based on spatio-temporal Gaussian processes (STGP). The performance of the proposed STGP-based trackers was comparatively evaluated through simulations and real data together with another state-of-the-art method (referred to as GP-EKF) proposed in "Extended target tracking using Gaussian processes" (IEEE Trans. Signal Process., vol. 63, no. 16, pp. 4165-4178, Aug. 2015). Unfortunately, we recognized that there are major errors in the implementation of the experiments presented in the STGP paper, which led to incorrect performance evaluation results. In this correspondence, our aim is to share the correct results of these experiments and to respond to some claims regarding GP-EKF, which we believe, would contribute to a better understanding of the methods.
Tuncer, Barkın; Özkan, Emre
Random Matrix Based Extended Target Tracking with Orientation: A New Model and Inference Online
2020.
@online{2010.08820,
title = {Random Matrix Based Extended Target Tracking with Orientation: A New Model and Inference},
author = {Barkın Tuncer and Emre Özkan},
year = {2020},
date = {2020-01-01},
keywords = {},
pubstate = {published},
tppubtype = {online}
}
2019
Kara, S. Fatih; Özkan, Emre
Multiellipsoidal extended target tracking with known extent using sequential Monte Carlo framework Journal Article
In: Turkish Journal of Electrical Engineering and Computer Science, vol. 27, pp. 1546 - 1558, 2019, ISSN: 1300-0632.
@article{tbtkelektrik574619,
title = {Multiellipsoidal extended target tracking with known extent using sequential Monte Carlo framework},
author = {S. Fatih Kara and Emre Özkan},
url = {https://dergipark.org.tr/tr/pub/tbtkelektrik/issue/45636/574619},
issn = {1300-0632},
year = {2019},
date = {2019-01-01},
journal = {Turkish Journal of Electrical Engineering and Computer Science},
volume = {27},
pages = {1546 - 1558},
publisher = {TÜBİTAK},
abstract = {In this paper, we consider a variant of the extended target tracking (ETT) problem, namely the multiellipsoidal ETT problem. In multiellipsoidal ETT, target extent is represented by multiple ellipses, which correspond to the origin of the measurements on the target surface. The problem involves estimating the target's kinematic state and solving the association problem between the measurements and the ellipses. We cast the problem in a sequential Monte Carlo (SMC) framework and investigate different marginalization strategies to find an efficient particle filter. Under the known extent assumption, we define association variables to find the correct association between the measurements and the ellipses; hence, the posterior involves both discrete and continuous random variables. By expressing the measurement likelihood as a mixture of Gaussians we derive and employ a marginalized particle filter for the independent association variables without sampling the discrete states. We compare the performance of the method with its alternatives and illustrate the gain in nonstandard marginalization.},
key = {cite},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we consider a variant of the extended target tracking (ETT) problem, namely the multiellipsoidal ETT problem. In multiellipsoidal ETT, target extent is represented by multiple ellipses, which correspond to the origin of the measurements on the target surface. The problem involves estimating the target's kinematic state and solving the association problem between the measurements and the ellipses. We cast the problem in a sequential Monte Carlo (SMC) framework and investigate different marginalization strategies to find an efficient particle filter. Under the known extent assumption, we define association variables to find the correct association between the measurements and the ellipses; hence, the posterior involves both discrete and continuous random variables. By expressing the measurement likelihood as a mixture of Gaussians we derive and employ a marginalized particle filter for the independent association variables without sampling the discrete states. We compare the performance of the method with its alternatives and illustrate the gain in nonstandard marginalization.
Tuncer, Barkın; Kumru, Murat; Özkan, Emre
Extended Target Tracking and Classification Using Neural Networks Proceedings Article
In: 2019 22th International Conference on Information Fusion (FUSION), pp. 1-7, 2019.
@inproceedings{9011255,
title = {Extended Target Tracking and Classification Using Neural Networks},
author = {Barkın Tuncer and Murat Kumru and Emre Özkan},
url = {https://ieeexplore.ieee.org/document/9011255},
year = {2019},
date = {2019-01-01},
booktitle = {2019 22th International Conference on Information Fusion (FUSION)},
pages = {1-7},
abstract = {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 to use a naively deep neural network, which consists of one input, two hidden and one output layers, to classify dynamic objects regarding their shape estimates. The proposed method shows superior performance in comparison to a Bayesian classifier for simulation experiments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
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 to use a naively deep neural network, which consists of one input, two hidden and one output layers, to classify dynamic objects regarding their shape estimates. The proposed method shows superior performance in comparison to a Bayesian classifier for simulation experiments.
Kumru, Murat; Özkan, Emre
Three-Dimensional Extended Object Tracking and Shape Learning Using Gaussian Processes Online
arXiv preprint 2019.
@online{1909.11358,
title = {Three-Dimensional Extended Object Tracking and Shape Learning Using Gaussian Processes},
author = {Murat Kumru and Emre Özkan},
url = {https://arxiv.org/abs/1909.11358},
year = {2019},
date = {2019-01-01},
organization = {arXiv preprint},
abstract = {In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including position, velocity and orientation, together with the shape of the object in an online fashion. We describe the unknown shape by a radial function in 3D, and induce a correlation structure via a Gaussian process. Furthermore, we propose an efficient algorithm to reduce the computational complexity of working with 3D data. This is accomplished by casting the tracking problem into projection planes which are attached to the object's local frame. The proposed methods provide an analytical expression for the object shape together with confidence intervals. The confidence intervals, which quantify the uncertainty in the shape estimate, can later be used for solving the gating and association problems inherent in object tracking. The performance of the methods is demonstrated both on simulated and real data. The results are compared with an existing random matrix model, which is commonly used for extended object tracking in the literature.},
keywords = {},
pubstate = {published},
tppubtype = {online}
}
In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including position, velocity and orientation, together with the shape of the object in an online fashion. We describe the unknown shape by a radial function in 3D, and induce a correlation structure via a Gaussian process. Furthermore, we propose an efficient algorithm to reduce the computational complexity of working with 3D data. This is accomplished by casting the tracking problem into projection planes which are attached to the object's local frame. The proposed methods provide an analytical expression for the object shape together with confidence intervals. The confidence intervals, which quantify the uncertainty in the shape estimate, can later be used for solving the gating and association problems inherent in object tracking. The performance of the methods is demonstrated both on simulated and real data. The results are compared with an existing random matrix model, which is commonly used for extended object tracking in the literature.
2018
Tuncer, Barkın; Kumru, Murat; Özkan, Emre; Alatan, A. Aydın
Extended Object Tracking and Shape Classification Proceedings Article
In: 2018 21st International Conference on Information Fusion (FUSION), pp. 1-5, 2018.
@inproceedings{8455464,
title = {Extended Object Tracking and Shape Classification},
author = {Barkın Tuncer and Murat Kumru and Emre Özkan and A. Aydın Alatan},
doi = {10.23919/ICIF.2018.8455464},
year = {2018},
date = {2018-07-01},
booktitle = {2018 21st International Conference on Information Fusion (FUSION)},
pages = {1-5},
abstract = {Recent extended target tracking algorithms provide reliable shape estimates while tracking objects. The estimated extent of the objects can also be used for online classification. In this work, we propose to use a Bayesian classifier to identify different objects based on their contour estimates during tracking. The proposed method uses the uncertainty information provided by the estimation covariance of the tracker.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Recent extended target tracking algorithms provide reliable shape estimates while tracking objects. The estimated extent of the objects can also be used for online classification. In this work, we propose to use a Bayesian classifier to identify different objects based on their contour estimates during tracking. The proposed method uses the uncertainty information provided by the estimation covariance of the tracker.
Kara, S. Fatih; Özkan, Emre
Multi-Ellipsoidal Extended Target Tracking Using Sequential Monte Carlo Proceedings Article
In: 2018 21st International Conference on Information Fusion (FUSION), pp. 1-8, 2018.
@inproceedings{8455436,
title = {Multi-Ellipsoidal Extended Target Tracking Using Sequential Monte Carlo},
author = {S. Fatih Kara and Emre Özkan},
doi = {10.23919/ICIF.2018.8455436},
year = {2018},
date = {2018-07-01},
booktitle = {2018 21st International Conference on Information Fusion (FUSION)},
pages = {1-8},
abstract = {In this paper, we consider the problem of extended target tracking, where the target extent cannot be represented by a single ellipse accurately. We model the target extent with multiple ellipses and solve the resulting inference problem, which involves data association between the measurements and sub-objects. We cast the inference problem into sequential Monte Carlo (SMC) framework and propose a simplified approach for the solution. Furthermore, we make use of the Rao-Blackwellization, aka marginalization, idea and derive an efficient filter to approximate the joint posterior density of the target kinematic states and target extent. Conditional analytical expressions, which are essential for Rao-Blackwellization, are not available in our problem. We use variational Bayes technique to approximate the conditional densities and enable Rao-Blackwellization. The performance of the method is demonstrated through simulations. A comparison with a recent method in the literature is performed.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we consider the problem of extended target tracking, where the target extent cannot be represented by a single ellipse accurately. We model the target extent with multiple ellipses and solve the resulting inference problem, which involves data association between the measurements and sub-objects. We cast the inference problem into sequential Monte Carlo (SMC) framework and propose a simplified approach for the solution. Furthermore, we make use of the Rao-Blackwellization, aka marginalization, idea and derive an efficient filter to approximate the joint posterior density of the target kinematic states and target extent. Conditional analytical expressions, which are essential for Rao-Blackwellization, are not available in our problem. We use variational Bayes technique to approximate the conditional densities and enable Rao-Blackwellization. The performance of the method is demonstrated through simulations. A comparison with a recent method in the literature is performed.