Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió publicadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/190703
End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
Despite recent advances in 3-D pose estimation of human hands, thanks to the advent of convolutional neural networks (CNNs) and depth cameras, this task is still far from being solved in uncontrolled setups. This is mainly due to the highly non-linear dynamics of fingers and self-occlusions, which make hand model training a challenging task. In this study, a novel hierarchical tree-like structured CNN is exploited, in which branches are trained to become specialised in predefined subsets of hand joints called local poses. Further, local pose features, extracted from hierarchical CNN branches, are fused to learn higher order dependencies among joints in the final pose by end-to-end training. Lastly, the loss function used is also defined to incorporate appearance and physical constraints about doable hand motions and deformations. Finally, a non-rigid data augmentation approach is introduced to increase the amount of training depth data. Experimental results suggest that feeding a tree-shaped CNN, specialised in local poses, into a fusion network for modelling joints' correlations and dependencies, helps to increase the precision of final estimations, showing competitive results on NYU, MSRA, Hands17 and SyntheticHand datasets.
Matèries (anglès)
Citació
Citació
MADADI, Meysam, ESCALERA GUERRERO, Sergio, BARÓ I SOLÉ, Xavier, GONZÀLEZ SABATÉ, Jordi. End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data. _IET Computer Vision_. 2021. Vol. 16, núm. 1, pàgs. 50-66. [consulta: 24 de gener de 2026]. ISSN: 1751-9632. [Disponible a: https://hdl.handle.net/2445/190703]