Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Body pose estimation in depth images for infant motion analysis

: Hesse, Nikolas; Schröder, Sebastian A.; Müller-Felber, Wolfgang; Bodensteiner, Christoph; Arens, Michael; Hofmann, Ulrich G.

Postprint urn:nbn:de:0011-n-4562413 (1.2 MByte PDF)
MD5 Fingerprint: 0dce7f3efe860210c61d6ae4c243f26c
Created on: 20.7.2017

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Engineering in Medicine and Biology Society -EMBS-:
EMBC 2017, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society : July 11 to 15, 2017, Jeju Island, Korea
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-2809-2
ISBN: 978-1-5090-2810-8
Engineering in Medicine and Biology Society (EMBC Annual International Conference) <39, 2017, Jeju Island>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Motion analysis of infants is used for early detection of movement disorders like cerebral palsy. For the development of automated methods, capturing the infant’s pose accurately is crucial. Our system for predicting 3D joint positions is based on a recently introduced pixelwise body part classifier using random ferns, to which we propose multiple enhancements. We apply a feature selection step before training random ferns to avoid the inclusion of redundant features. We introduce a kinematic chain reweighting scheme to identify and to correct misclassified pixels, and we achieve rotation invariance by performing PCA on the input depth image. The proposed methods improve pose estimation accuracy by a large margin on multiple recordings of infants. We demonstrate the suitability of the approach for motion analysis by comparing predicted knee angles to ground truth angles.