Top-down model fitting for hand pose recovery in sequences of depth images

State-of-the-art approaches on hand pose estimation from depth images have reported promising results under quite controlled considerations. In this paper we propose a two-step pipeline for recovering the hand pose from a sequence of depth images. The pipeline has been designed to deal with images t...

Descripción completa

Detalles Bibliográficos
Autores: Madadi, Meysam, Escalera, Sergio, Carruesco Llorens, Àlex, Andújar Gran, Carlos Antonio|||0000-0002-8480-4713, Baró, Xavier, Gonzàlez, Jordi
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/130123
Acceso en línea:https://hdl.handle.net/2117/130123
https://dx.doi.org/10.1016/j.imavis.2018.09.006
Access Level:acceso abierto
Palabra clave:Three dimensional imaging
Hand pose recovery
Shape description
Depth image
Hand segmentation
Temporal modeling
Infografia tridimensional
Àrees temàtiques de la UPC::Informàtica::Infografia
Descripción
Sumario:State-of-the-art approaches on hand pose estimation from depth images have reported promising results under quite controlled considerations. In this paper we propose a two-step pipeline for recovering the hand pose from a sequence of depth images. The pipeline has been designed to deal with images taken from any viewpoint and exhibiting a high degree of finger occlusion. In a first step we initialize the hand pose using a part-based model, fitting a set of hand components in the depth images. In a second step we consider temporal data and estimate the parameters of a trained bilinear model consisting of shape and trajectory bases. We evaluate our approach on a new created synthetic hand dataset along with NYU and MSRA real datasets. Results demonstrate that the proposed method outperforms the most recent pose recovering approaches, including those based on CNNs.