A guided approach for cross-view geolocalization estimation with land cover semantic segmentation
Geolocalization is a crucial process that leverages environmental information and contextual data to accurately identify a position. In particular, cross-view geolocalization utilizes images from various perspectives, such as satellite and ground-level images, which are relevant for applications lik...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Biomimetic Intelligence and Robotics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667379724000664 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856664182259712 |
|---|---|
| author | Nathan A.Z. Xavier Elcio H. Shiguemori Marcos R.O.A. Maximo Mubarak Shah |
| author_facet | Nathan A.Z. Xavier Elcio H. Shiguemori Marcos R.O.A. Maximo Mubarak Shah |
| author_sort | Nathan A.Z. Xavier |
| collection | DOAJ |
| description | Geolocalization is a crucial process that leverages environmental information and contextual data to accurately identify a position. In particular, cross-view geolocalization utilizes images from various perspectives, such as satellite and ground-level images, which are relevant for applications like robotics navigation and autonomous navigation. In this research, we propose a methodology that integrates cross-view geolocalization estimation with a land cover semantic segmentation map. Our solution demonstrates comparable performance to state-of-the-art methods, exhibiting enhanced stability and consistency regardless of the street view location or the dataset used. Additionally, our method generates a focused discrete probability distribution that acts as a heatmap. This heatmap effectively filters out incorrect and unlikely regions, enhancing the reliability of our estimations. Code is available at https://github.com/nathanxavier/CVSegGuide. |
| format | Article |
| id | doaj-art-5dfe2a771e4e44d6b1512457173e896a |
| institution | Kabale University |
| issn | 2667-3797 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Biomimetic Intelligence and Robotics |
| spelling | doaj-art-5dfe2a771e4e44d6b1512457173e896a2025-02-12T05:33:06ZengElsevierBiomimetic Intelligence and Robotics2667-37972025-06-0152100208A guided approach for cross-view geolocalization estimation with land cover semantic segmentationNathan A.Z. Xavier0Elcio H. Shiguemori1Marcos R.O.A. Maximo2Mubarak Shah3Technical College of UFMG, Federal University of Minas Gerais, Belo Horizonte 31270-901, Brazil; Aeronautics Institute of Technology, São José dos Campos 12228-900, Brazil; Center for Research in Computer Vision, University of Central Florida, Orlando 32816, USA; Corresponding author.Aeronautics Institute of Technology, São José dos Campos 12228-900, Brazil; Institute for Advanced Studies, São José dos Campos 12228-001, Brazil; National Institute for Space Research, São José dos Campos 12227-010, BrazilAeronautics Institute of Technology, São José dos Campos 12228-900, BrazilCenter for Research in Computer Vision, University of Central Florida, Orlando 32816, USAGeolocalization is a crucial process that leverages environmental information and contextual data to accurately identify a position. In particular, cross-view geolocalization utilizes images from various perspectives, such as satellite and ground-level images, which are relevant for applications like robotics navigation and autonomous navigation. In this research, we propose a methodology that integrates cross-view geolocalization estimation with a land cover semantic segmentation map. Our solution demonstrates comparable performance to state-of-the-art methods, exhibiting enhanced stability and consistency regardless of the street view location or the dataset used. Additionally, our method generates a focused discrete probability distribution that acts as a heatmap. This heatmap effectively filters out incorrect and unlikely regions, enhancing the reliability of our estimations. Code is available at https://github.com/nathanxavier/CVSegGuide.http://www.sciencedirect.com/science/article/pii/S2667379724000664Cross-view geolocalizationSemantic segmentationSatellite and ground image fusionSimultaneous localization and mapping (SLAM) |
| spellingShingle | Nathan A.Z. Xavier Elcio H. Shiguemori Marcos R.O.A. Maximo Mubarak Shah A guided approach for cross-view geolocalization estimation with land cover semantic segmentation Biomimetic Intelligence and Robotics Cross-view geolocalization Semantic segmentation Satellite and ground image fusion Simultaneous localization and mapping (SLAM) |
| title | A guided approach for cross-view geolocalization estimation with land cover semantic segmentation |
| title_full | A guided approach for cross-view geolocalization estimation with land cover semantic segmentation |
| title_fullStr | A guided approach for cross-view geolocalization estimation with land cover semantic segmentation |
| title_full_unstemmed | A guided approach for cross-view geolocalization estimation with land cover semantic segmentation |
| title_short | A guided approach for cross-view geolocalization estimation with land cover semantic segmentation |
| title_sort | guided approach for cross view geolocalization estimation with land cover semantic segmentation |
| topic | Cross-view geolocalization Semantic segmentation Satellite and ground image fusion Simultaneous localization and mapping (SLAM) |
| url | http://www.sciencedirect.com/science/article/pii/S2667379724000664 |
| work_keys_str_mv | AT nathanazxavier aguidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT elciohshiguemori aguidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT marcosroamaximo aguidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT mubarakshah aguidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT nathanazxavier guidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT elciohshiguemori guidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT marcosroamaximo guidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation AT mubarakshah guidedapproachforcrossviewgeolocalizationestimationwithlandcoversemanticsegmentation |