Publicação
Deep learning tools to study collective behaviour
| datacite.subject.fos | Neurosciences | pt_PT |
| dc.contributor.advisor | Polavieja, Gonzalo García de | |
| dc.contributor.author | Ferrero, Francisco | |
| dc.date.accessioned | 2021-07-25T22:47:20Z | |
| dc.date.available | 2022-06-01T00:33:02Z | |
| dc.date.issued | 2021-04-28 | |
| dc.date.submitted | 2021-04 | |
| dc.description.abstract | "collectives. The main strength of this approach is the ability to produce very accurate models. We developed idtracker.ai to extract from a video the trajectory of each animal in the collective. idtracker.ai is a marker-less multi-animal tracking system that works by identifying each animal, like its predecessor idTracker. The difference is that it trains a convolutional neural network in a self-supervised manner for animal identification. With this strategy, idtracker.ai can track with high identification accuracy sparse collectives of any species of up to 100 individuals even if animals touch or occlude each other frequently along the video. A new tool, idmatcher.ai, works seamlessly with idtracker.ai to identify animals across different videos. We also tested how deep nets can help to find interaction rules among animals in collectives.(...)" | pt_PT |
| dc.identifier.tid | 101726813 | |
| dc.identifier.uri | http://hdl.handle.net/10362/121640 | |
| dc.language.iso | eng | pt_PT |
| dc.relation | SFHR/BD/105946/2014 | pt_PT |
| dc.subject | multi-animal tracking system | pt_PT |
| dc.subject | identify animals | pt_PT |
| dc.title | Deep learning tools to study collective behaviour | pt_PT |
| dc.type | doctoral thesis | |
| dspace.entity.type | Publication | |
| person.familyName | Romero Ferrero | |
| person.givenName | Francisco | |
| person.identifier.ciencia-id | 9911-F1C2-E879 | |
| person.identifier.orcid | 0000-0002-4353-7997 | |
| rcaap.embargofct | Artigos por publicar | pt_PT |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | doctoralThesis | pt_PT |
| relation.isAuthorOfPublication | c2a9f81b-a32d-451e-b5e3-383eb3e52ddc | |
| relation.isAuthorOfPublication.latestForDiscovery | c2a9f81b-a32d-451e-b5e3-383eb3e52ddc | |
| thesis.degree.name | Dissertation presented to obtain the Ph.D degree in Neurosciences | pt_PT |
Ficheiros
Principais
1 - 1 de 1
A carregar...
- Nome:
- FranciscoRomero_PhDThesis.pdf
- Tamanho:
- 44.8 MB
- Formato:
- Adobe Portable Document Format