Cargando…

Leveraging cross-view geo-localization with ensemble learning and temporal awareness

The Global Navigation Satellite System (GNSS) is unreliable in some situations. To mend the poor GNSS signal, an autonomous vehicle can self-localize by matching a ground image against a database of geotagged aerial images. However, this approach has challenges because of the dramatic differences in...

Descripción completa

Detalles Bibliográficos
Autores principales: Ghanem, Abdulrahman, Abdelhay, Ahmed, Salah, Noor Eldeen, Nour Eldeen, Ahmed, Elhenawy, Mohammed, Masoud, Mahmoud, Hassan, Ammar M., Hassan, Abdallah A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10062671/
https://www.ncbi.nlm.nih.gov/pubmed/36996050
http://dx.doi.org/10.1371/journal.pone.0283672
_version_ 1785017546940874752
author Ghanem, Abdulrahman
Abdelhay, Ahmed
Salah, Noor Eldeen
Nour Eldeen, Ahmed
Elhenawy, Mohammed
Masoud, Mahmoud
Hassan, Ammar M.
Hassan, Abdallah A.
author_facet Ghanem, Abdulrahman
Abdelhay, Ahmed
Salah, Noor Eldeen
Nour Eldeen, Ahmed
Elhenawy, Mohammed
Masoud, Mahmoud
Hassan, Ammar M.
Hassan, Abdallah A.
author_sort Ghanem, Abdulrahman
collection PubMed
description The Global Navigation Satellite System (GNSS) is unreliable in some situations. To mend the poor GNSS signal, an autonomous vehicle can self-localize by matching a ground image against a database of geotagged aerial images. However, this approach has challenges because of the dramatic differences in the viewpoint between aerial and ground views, harsh weather and lighting conditions, and the lack of orientation information in training and deployment environments. In this paper, it is shown that previous models in this area are complementary, not competitive, and that each model solves a different aspect of the problem. There was a need for a holistic approach. An ensemble model is proposed to aggregate the predictions of multiple independently trained state-of-the-art models. Previous state-of-the-art (SOTA) temporal-aware models used heavy-weight network to fuse the temporal information into the query process. The effect of making the query process temporal-aware is explored and exploited by an efficient meta block: naive history. But none of the existing benchmark datasets was suitable for extensive temporal awareness experiments, a new derivative dataset based on the BDD100K dataset is generated. The proposed ensemble model achieves a recall accuracy R@1 (Recall@1: the top most prediction) of 97.74% on the CVUSA dataset and 91.43% on the CVACT dataset (surpassing the current SOTA). The temporal awareness algorithm converges to R@1 of 100% by looking at a few steps back in the trip history.
format Online
Article
Text
id pubmed-10062671
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-100626712023-03-31 Leveraging cross-view geo-localization with ensemble learning and temporal awareness Ghanem, Abdulrahman Abdelhay, Ahmed Salah, Noor Eldeen Nour Eldeen, Ahmed Elhenawy, Mohammed Masoud, Mahmoud Hassan, Ammar M. Hassan, Abdallah A. PLoS One Research Article The Global Navigation Satellite System (GNSS) is unreliable in some situations. To mend the poor GNSS signal, an autonomous vehicle can self-localize by matching a ground image against a database of geotagged aerial images. However, this approach has challenges because of the dramatic differences in the viewpoint between aerial and ground views, harsh weather and lighting conditions, and the lack of orientation information in training and deployment environments. In this paper, it is shown that previous models in this area are complementary, not competitive, and that each model solves a different aspect of the problem. There was a need for a holistic approach. An ensemble model is proposed to aggregate the predictions of multiple independently trained state-of-the-art models. Previous state-of-the-art (SOTA) temporal-aware models used heavy-weight network to fuse the temporal information into the query process. The effect of making the query process temporal-aware is explored and exploited by an efficient meta block: naive history. But none of the existing benchmark datasets was suitable for extensive temporal awareness experiments, a new derivative dataset based on the BDD100K dataset is generated. The proposed ensemble model achieves a recall accuracy R@1 (Recall@1: the top most prediction) of 97.74% on the CVUSA dataset and 91.43% on the CVACT dataset (surpassing the current SOTA). The temporal awareness algorithm converges to R@1 of 100% by looking at a few steps back in the trip history. Public Library of Science 2023-03-30 /pmc/articles/PMC10062671/ /pubmed/36996050 http://dx.doi.org/10.1371/journal.pone.0283672 Text en © 2023 Ghanem et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Ghanem, Abdulrahman
Abdelhay, Ahmed
Salah, Noor Eldeen
Nour Eldeen, Ahmed
Elhenawy, Mohammed
Masoud, Mahmoud
Hassan, Ammar M.
Hassan, Abdallah A.
Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title_full Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title_fullStr Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title_full_unstemmed Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title_short Leveraging cross-view geo-localization with ensemble learning and temporal awareness
title_sort leveraging cross-view geo-localization with ensemble learning and temporal awareness
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10062671/
https://www.ncbi.nlm.nih.gov/pubmed/36996050
http://dx.doi.org/10.1371/journal.pone.0283672
work_keys_str_mv AT ghanemabdulrahman leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT abdelhayahmed leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT salahnooreldeen leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT noureldeenahmed leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT elhenawymohammed leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT masoudmahmoud leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT hassanammarm leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness
AT hassanabdallaha leveragingcrossviewgeolocalizationwithensemblelearningandtemporalawareness