Robust Articulated-ICP for Real-Time Hand Tracking

dc.contributor.authorTagliasacchi, Andreaen_US
dc.contributor.authorSchröder, Matthiasen_US
dc.contributor.authorTkach, Anastasiaen_US
dc.contributor.authorBouaziz, Sofienen_US
dc.contributor.authorBotsch, Marioen_US
dc.contributor.authorPauly, Marken_US
dc.contributor.editorMirela Ben-Chen and Ligang Liuen_US
dc.date.accessioned2015-07-06T05:00:43Z
dc.date.available2015-07-06T05:00:43Z
dc.date.issued2015en_US
dc.description.abstractWe present a robust method for capturing articulated hand motions in realtime using a single depth camera. Our system is based on a realtime registration process that accurately reconstructs hand poses by fitting a 3D articulated hand model to depth images. We register the hand model using depth, silhouette, and temporal information. To effectively map low-quality depth maps to realistic hand poses, we regularize the registration with kinematic and temporal priors, as well as a data-driven prior built from a database of realistic hand poses. We present a principled way of integrating such priors into our registration optimization to enable robust tracking without severely restricting the freedom of motion. A core technical contribution is a new method for computing tracking correspondences that directly models occlusions typical of single-camera setups. To ensure reproducibility of our results and facilitate future research, we fully disclose the source code of our implementation.en_US
dc.description.number5en_US
dc.description.sectionheadersRegistrationen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume34en_US
dc.identifier.doi10.1111/cgf.12700en_US
dc.identifier.pages101-114en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12700en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleRobust Articulated-ICP for Real-Time Hand Trackingen_US
Files