Plant detection from ultra high resolution remote sensing images: A Semantic Segmentation approach based on fuzzy loss
| dc.rights.license | open | en_US |
| hal.structure.identifier | Observation de l’environnement par imagerie complexe [OBELIX] | |
| dc.contributor.author | PANDE, Shivam | |
| hal.structure.identifier | Observation de l’environnement par imagerie complexe [OBELIX] | |
| dc.contributor.author | UZUN, Baki | |
| hal.structure.identifier | Department of Computer Science [Aalto] | |
| dc.contributor.author | GUIOTTE, Florent | |
| hal.structure.identifier | Observation de l’environnement par imagerie complexe [OBELIX] | |
| dc.contributor.author | PHAM, Minh-Tan | |
| hal.structure.identifier | Littoral, Environnement, Télédétection, Géomatique [LETG - Rennes ] | |
| dc.contributor.author | CORPETTI, Thomas | |
| hal.structure.identifier | Environnements et Paléoenvironnements OCéaniques [EPOC] | |
| dc.contributor.author | DELERUE, Florian
IDREF: 17229567X | |
| hal.structure.identifier | Observation de l’environnement par imagerie complexe [OBELIX] | |
| dc.contributor.author | LEFÈVRE, Sébastien | |
| dc.date.accessioned | 2025-04-02T07:37:09Z | |
| dc.date.available | 2025-04-02T07:37:09Z | |
| dc.date.issued | 2024 | |
| dc.date.conference | 2024-07-07 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/205891 | |
| dc.description.abstractEn | In this study, we tackle the challenge of identifying plant species from ultra high resolution (UHR) remote sensing images. Our approach involves introducing an RGB remote sensing dataset, characterized by millimeter-level spatial resolution, meticulously curated through several field expeditions across a mountainous region in France covering various landscapes. The task of plant species identification is framed as a semantic segmentation problem for its practical and efficient implementation across vast geographical areas. However, when dealing with segmentation masks, we confront instances where distinguishing boundaries between plant species and their background is challenging. We tackle this issue by introducing a fuzzy loss within the segmentation model. Instead of utilizing one-hot encoded ground truth (GT), our model incorporates Gaussian filter refined GT, introducing stochasticity during training. First experimental results obtained on both our UHR dataset and a public dataset are presented, showing the relevance of the proposed methodology, as well as the need for future improvement. | |
| dc.description.sponsorship | Interactions Plantes-Plantes Positives et Patrons spatiaux dans les résidus Post-mines des Pyrénées - ANR-19-CE02-0013 | en_US |
| dc.language.iso | EN | en_US |
| dc.publisher | IEEE | en_US |
| dc.subject.en | Artificial Intelligence (cs.AI) | |
| dc.subject.en | FOS: Computer and information sciences | |
| dc.subject.en | Semantic segmentation | |
| dc.subject.en | fuzzy loss | |
| dc.subject.en | ultrahigh resolution | |
| dc.subject.en | plant detection | |
| dc.subject.en | Computer Vision and Pattern Recognition (cs.CV) | |
| dc.title.en | Plant detection from ultra high resolution remote sensing images: A Semantic Segmentation approach based on fuzzy loss | |
| dc.type | Communication dans un congrès | en_US |
| dc.identifier.doi | 10.1109/IGARSS53475.2024.10641972 | en_US |
| dc.subject.hal | Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV] | en_US |
| dc.subject.hal | Sciences de l'environnement/Ingénierie de l'environnement | en_US |
| bordeaux.hal.laboratories | EPOC : Environnements et Paléoenvironnements Océaniques et Continentaux - UMR 5805 | en_US |
| bordeaux.institution | Université de Bordeaux | en_US |
| bordeaux.institution | CNRS | en_US |
| bordeaux.conference.title | IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) | en_US |
| bordeaux.team | ECOBIOC | en_US |
| bordeaux.conference.city | Athènes | en_US |
| bordeaux.import.source | hal | |
| hal.identifier | hal-04778954 | |
| hal.version | 1 | |
| hal.invited | non | en_US |
| hal.proceedings | oui | en_US |
| hal.conference.end | 2024-07-12 | |
| hal.popular | non | en_US |
| hal.audience | Internationale | en_US |
| hal.export | false | |
| workflow.import.source | hal | |
| dc.rights.cc | Pas de Licence CC | en_US |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2024&rft.au=PANDE,%20Shivam&UZUN,%20Baki&GUIOTTE,%20Florent&PHAM,%20Minh-Tan&CORPETTI,%20Thomas&rft.genre=unknown |