A Primer on Motion Capture with Deep Learning: Principles, Pitfalls, and Perspectives.
Journal
Neuron
ISSN: 1097-4199
Titre abrégé: Neuron
Pays: United States
ID NLM: 8809320
Informations de publication
Date de publication:
14 10 2020
14 10 2020
Historique:
received:
03
07
2020
revised:
02
09
2020
accepted:
10
09
2020
entrez:
15
10
2020
pubmed:
16
10
2020
medline:
1
12
2020
Statut:
ppublish
Résumé
Extracting behavioral measurements non-invasively from video is stymied by the fact that it is a hard computational problem. Recent advances in deep learning have tremendously advanced our ability to predict posture directly from videos, which has quickly impacted neuroscience and biology more broadly. In this primer, we review the budding field of motion capture with deep learning. In particular, we will discuss the principles of those novel algorithms, highlight their potential as well as pitfalls for experimentalists, and provide a glimpse into the future.
Identifiants
pubmed: 33058765
pii: S0896-6273(20)30717-0
doi: 10.1016/j.neuron.2020.09.017
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Review
Video-Audio Media
Langues
eng
Sous-ensembles de citation
IM
Pagination
44-65Informations de copyright
Copyright © 2020 Elsevier Inc. All rights reserved.