ImmersiveIML – Immersive interactive machine learning for 3D point cloud classification: the neural network at your fingertips
dc.rights.license | open | en_US |
hal.structure.identifier | The University of Queensland [UQ [All campuses : Brisbane, Dutton Park Gatton, Herston, St Lucia and other locations]] | |
dc.contributor.author | CORDEIL, Maxime | |
hal.structure.identifier | The University of Queensland [UQ [All campuses : Brisbane, Dutton Park Gatton, Herston, St Lucia and other locations]] | |
dc.contributor.author | BILLY, Thomas | |
hal.structure.identifier | Centre National de la Recherche Scientifique [CNRS] | |
hal.structure.identifier | Structural Models and Tools in Computer Graphics [IRIT-STORM] | |
dc.contributor.author | MELLADO, Nicolas | |
hal.structure.identifier | Institut de recherche en informatique de Toulouse [IRIT] | |
hal.structure.identifier | Université Toulouse III - Paul Sabatier [UT3] | |
dc.contributor.author | BARTHE, Loic | |
hal.structure.identifier | ESTIA - Institute of technology [ESTIA] | |
dc.contributor.author | COUTURE, Nadine
ORCID: 0000-0001-7959-5227 IDREF: 111534275 | |
hal.structure.identifier | Laboratoire Bordelais de Recherche en Informatique [LaBRI] | |
hal.structure.identifier | ESTIA - Institute of technology [ESTIA] | |
hal.structure.identifier | Melting the frontiers between Light, Shape and Matter [MANAO] | |
dc.contributor.author | REUTER, Patrick
IDREF: 081908210 | |
dc.date.accessioned | 2024-01-31T11:08:37Z | |
dc.date.available | 2024-01-31T11:08:37Z | |
dc.date.conference | 2023-10-16 | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/187687 | |
dc.description.abstractEn | We propose an initial exploration of an interactive machine-learning (IML) dialogue in immersive, interactive Virtual Reality (VR) for the classification of points in 3D point clouds. We contribute ImmersiveIML, an Immersive Analytics tool which builds on humanmachine learning trial-and-error dialogue to support an iterative classification process of points in the 3D point cloud. The interactions in ImmersiveIML are designed to be both expressive and minimal; we designed the iterative process to be supported by (1) 6-DOF controllers to allow direct interaction in large 3D point clouds via a minimal brushing technique, (2) a fast trainable machine learning model, and (3) the direct visual feedback of classification results. This constitutes an iterative human-in-the-loop process that eventually converges to a classification according to human intent. We argue that this approach is a novel contribution that supports a constant improvement of the classification model and fast tracks classification tasks with this type of data, in an immersive scenario. We report on the design and implementation of ImmersiveIML and demonstrate its capabilities with two emblematic application scenarios: edge detection in 3D and classification of trees in a city LiDAR dataset. | |
dc.description.sponsorship | Espace d'échelles pour l'apprentissage machine sur des nuages de points 3d - ANR-22-CE23-0004 | en_US |
dc.language.iso | EN | en_US |
dc.publisher | IEEE | en_US |
dc.subject.en | Gestural input | |
dc.subject.en | Interaction paradigms | |
dc.subject.en | Virtual reality | |
dc.subject.en | Computing methodologies | |
dc.subject.en | Neural networks | |
dc.subject.en | Human-centered computing | |
dc.subject.en | Visualization | |
dc.subject.en | Visu- alization techniques | |
dc.subject.en | Interaction techniques | |
dc.title.en | ImmersiveIML – Immersive interactive machine learning for 3D point cloud classification: the neural network at your fingertips | |
dc.type | Communication dans un congrès | en_US |
dc.identifier.doi | 10.1109/ISMAR-Adjunct60411.2023.00025 | en_US |
dc.subject.hal | Informatique [cs]/Interface homme-machine [cs.HC] | en_US |
dc.subject.hal | Informatique [cs]/Intelligence artificielle [cs.AI] | en_US |
dc.subject.hal | Informatique [cs]/Synthèse d'image et réalité virtuelle [cs.GR] | en_US |
bordeaux.page | 81-85 | en_US |
bordeaux.hal.laboratories | ESTIA - Recherche | en_US |
bordeaux.institution | Université de Bordeaux | en_US |
bordeaux.institution | Bordeaux INP | en_US |
bordeaux.institution | Bordeaux Sciences Agro | en_US |
bordeaux.conference.title | IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct 2023) | en_US |
bordeaux.country | au | en_US |
bordeaux.title.proceeding | ISMAR 2023 - IEEE International Symposium on Mixed and Augmented Reality Adjunct | en_US |
bordeaux.conference.city | Sydney | en_US |
bordeaux.import.source | hal | |
hal.identifier | hal-04246601 | |
hal.version | 1 | |
hal.invited | non | en_US |
hal.proceedings | oui | en_US |
hal.conference.end | 2023-10-16 | |
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.spage=81-85&rft.epage=81-85&rft.au=CORDEIL,%20Maxime&BILLY,%20Thomas&MELLADO,%20Nicolas&BARTHE,%20Loic&COUTURE,%20Nadine&rft.genre=unknown |