Recent publications
2023
Brizzi, Michele; Neri, Alessandro
Multi-ride Fusion for Rail Digital Map Construction Proceedings Article
In: 2023 IEEE/ION Position Location and Navigation Symposium (PLANS), The Institute of Navigation Monterey, CA, 2023.
@inproceedings{Brizzi_PLANS_2023,
title = {Multi-ride Fusion for Rail Digital Map Construction},
author = {Michele Brizzi and Alessandro Neri},
year = {2023},
date = {2023-04-25},
urldate = {2023-04-25},
booktitle = {2023 IEEE/ION Position Location and Navigation Symposium (PLANS)},
address = {Monterey, CA},
organization = {The Institute of Navigation},
abstract = {A novel technique for building a detailed Digital Map of the rail environment has been implemented and tested. It is based on the fusion of multiple rides acquired by means of on-board GNSS receivers, IMUs and visual sensors from trains in commercial operation. More in detail, an efficient incremental procedure for processing the collected data to reduce the computational complexity and storage requirements has been proposed. We demonstrate that the proposed system is able to obtain accurate track geometry and trackside objects position information while being robust to signal degradations typical of the rail environment.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A novel technique for building a detailed Digital Map of the rail environment has been implemented and tested. It is based on the fusion of multiple rides acquired by means of on-board GNSS receivers, IMUs and visual sensors from trains in commercial operation. More in detail, an efficient incremental procedure for processing the collected data to reduce the computational complexity and storage requirements has been proposed. We demonstrate that the proposed system is able to obtain accurate track geometry and trackside objects position information while being robust to signal degradations typical of the rail environment.
Lamichhane, Kamal; Neri, Michael; Paudyal, Pradip; Battisti, Federica; Carli, Marco
No-Reference Light Field Image Quality Assessment Exploiting Saliency Journal Article
In: IEEE Transactions on Broadcasting, pp. 1-11, 2023.
@article{Lamicchane_2023_TBC,
title = {No-Reference Light Field Image Quality Assessment Exploiting Saliency},
author = {Kamal Lamichhane and Michael Neri and Pradip Paudyal and Federica Battisti and Marco Carli},
doi = {10.1109/TBC.2023.3242150},
year = {2023},
date = {2023-04-03},
urldate = {2023-04-03},
journal = {IEEE Transactions on Broadcasting},
pages = {1-11},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Brizzi, Michele; D’Orazio, Francesca; Neri, Alessandro
Rail Digital Map Construction on GNSS Denied Areas Proceedings Article
In: Proceedings of the 2023 International Technical Meeting of The Institute of Navigation, pp. 1143-1153, ION Long Beach, California, 2023.
@inproceedings{Brizzi_ITM_2023,
title = {Rail Digital Map Construction on GNSS Denied Areas},
author = {Michele Brizzi and Francesca D'Orazio and Alessandro Neri},
doi = {10.33012/2023.18643},
year = {2023},
date = {2023-01-26},
urldate = {2023-01-26},
booktitle = {Proceedings of the 2023 International Technical Meeting of The Institute of Navigation},
pages = {1143-1153},
address = {Long Beach, California},
organization = {ION},
abstract = {A Digital Map of the rail infrastructure in a key element to support the adoption of GNSS in railway signalling and satisfy the strict accuracy and integrity requirements even in the presence of feared events that may hinder the positioning solution. In this work, we tackle the issue of providing an accurate rail Digital Map for localization purposes, bridging the gaps produced by the loss of GNSS coverage using forward and backward post-processing of inertial navigation. Experimental results show that the proposed method is able to increase the accuracy of the resulting Digital Map.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A Digital Map of the rail infrastructure in a key element to support the adoption of GNSS in railway signalling and satisfy the strict accuracy and integrity requirements even in the presence of feared events that may hinder the positioning solution. In this work, we tackle the issue of providing an accurate rail Digital Map for localization purposes, bridging the gaps produced by the loss of GNSS coverage using forward and backward post-processing of inertial navigation. Experimental results show that the proposed method is able to increase the accuracy of the resulting Digital Map.
Brizzi, Michele; Chiocchio, Sandro; Persia, Arianna; Neri, Alessandro
On the Performance of a Cascade of Barriers of Multipath Feared Events for High Accuracy High Integrity Train Positioning Proceedings Article
In: Proceedings of the 2023 International Technical Meeting of The Institute of Navigation, pp. 454 – 468, ION Long Beach, California, 2023.
@inproceedings{Brizzi_Barriers_ITM_2023,
title = {On the Performance of a Cascade of Barriers of Multipath Feared Events for High Accuracy High Integrity Train Positioning},
author = {Michele Brizzi and Sandro Chiocchio and Arianna Persia and Alessandro Neri},
doi = {10.33012/2023.18604},
year = {2023},
date = {2023-01-25},
urldate = {2023-01-25},
booktitle = {Proceedings of the 2023 International Technical Meeting of The Institute of Navigation},
pages = {454 - 468},
address = {Long Beach, California},
organization = {ION},
abstract = {Detection of multipath feared events is a fundamental capability of current and future High Accuracy High Integrity positioning systems for rail transport based on Global Navigation Satellite Systems. In this work, a method based on a cascade of barriers is proposed for Signal In Space measurement selection and integrity monitoring. To this aim, a mathematical framework for the analytic assessment of the achievable performance of Fault Detection and Exclusion algorithms based on Solution Separation is defined, accounting for the impact that exclusion of a Signal In Space observable has on the PVT accuracy and integrity. An adaptive logic based on Gaussian Mixtures models is also introduced for the computation of the exclusion thresholds in order to assure a constant False Exclusion probability.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Detection of multipath feared events is a fundamental capability of current and future High Accuracy High Integrity positioning systems for rail transport based on Global Navigation Satellite Systems. In this work, a method based on a cascade of barriers is proposed for Signal In Space measurement selection and integrity monitoring. To this aim, a mathematical framework for the analytic assessment of the achievable performance of Fault Detection and Exclusion algorithms based on Solution Separation is defined, accounting for the impact that exclusion of a Signal In Space observable has on the PVT accuracy and integrity. An adaptive logic based on Gaussian Mixtures models is also introduced for the computation of the exclusion thresholds in order to assure a constant False Exclusion probability.
Brizzi, Michele; Battisti, Federica; Carli, Marco; Neri, Alessandro
Selective video enhancement in the Laguerre-Gauss domain Journal Article
In: Signal Processing: Image Communication, vol. 110, 2023, ISSN: 0923-5965.
@article{Brizzi_SPIC_2023,
title = {Selective video enhancement in the Laguerre-Gauss domain},
author = {Michele Brizzi and Federica Battisti and Marco Carli and Alessandro Neri},
url = {https://www.sciencedirect.com/science/article/pii/S0923596522001552},
doi = {https://doi.org/10.1016/j.image.2022.116876},
issn = {0923-5965},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Signal Processing: Image Communication},
volume = {110},
abstract = {Traditional image and video enhancement techniques do not consider the subjective preferences of the user, who might be interested in modifying or highlighting specific elements of a scene. In fact, most image or video post-processing techniques are applied to the entire image or frame. In this work, a framework for selective video enhancement is presented. It is based on an adaptive multi-resolution edge enhancement technique performed in the Laguerre-Gauss complex wavelet domain. In the proposed scheme, edges are selectively enhanced or attenuated according to the inputs of the user, taking into account the characteristics of the content, the response of the human visual system, and the masking effects induced by textured background. Two scenarios have been implemented and tested: (i) an interactive video editing system, where the user selects the objects to enhance through a graphical interface and the system automatically propagates the selection through the following video frames belonging to the same shot, (ii) a perceptually-driven technique to improve the quality of RGB plus Depth videos, which uses depth maps as additional features to guide the enhancement.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Traditional image and video enhancement techniques do not consider the subjective preferences of the user, who might be interested in modifying or highlighting specific elements of a scene. In fact, most image or video post-processing techniques are applied to the entire image or frame. In this work, a framework for selective video enhancement is presented. It is based on an adaptive multi-resolution edge enhancement technique performed in the Laguerre-Gauss complex wavelet domain. In the proposed scheme, edges are selectively enhanced or attenuated according to the inputs of the user, taking into account the characteristics of the content, the response of the human visual system, and the masking effects induced by textured background. Two scenarios have been implemented and tested: (i) an interactive video editing system, where the user selects the objects to enhance through a graphical interface and the system automatically propagates the selection through the following video frames belonging to the same shot, (ii) a perceptually-driven technique to improve the quality of RGB plus Depth videos, which uses depth maps as additional features to guide the enhancement.