Parsing human skeletons in an operating room

Belagiannis V, Wang X, Ben Shitrit HB, Hashimoto K, Stauder R, Aoki Y, Kranzfelder M, Schneider A, Fua P, Ilic S, Feussner H, Navab N (2016)

Publication Type: Journal article

Publication year: 2016

Journal

Machine Vision and Applications Springer Verlag (Germany)

Book Volume: 27

Pages Range: 1035-1046

Journal Issue: 7

DOI: 10.1007/s00138-016-0792-4

Abstract

Multiple human pose estimation is an important yet challenging problem. In an operating room (OR) environment, the 3D body poses of surgeons and medical staff can provide important clues for surgical workflow analysis. For that purpose, we propose an algorithm for localizing and recovering body poses of multiple human in an OR environment under a multi-camera setup. Our model builds on 3D Pictorial Structures and 2D body part localization across all camera views, using convolutional neural networks (ConvNets). To evaluate our algorithm, we introduce a dataset captured in a real OR environment. Our dataset is unique, challenging and publicly available with annotated ground truths. Our proposed algorithm yields to promising pose estimation results on this dataset.

Authors with CRIS profile

Vasileios Belagiannis

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) École Polytechnique Fédérale de Lausanne (EPFL) CH Switzerland (CH) Keio University / 慶應義塾大学 JP Japan (JP)

How to cite

APA:

Belagiannis, V., Wang, X., Ben Shitrit, H.B., Hashimoto, K., Stauder, R., Aoki, Y.,... Navab, N. (2016). Parsing human skeletons in an operating room. Machine Vision and Applications, 27(7), 1035-1046. https://doi.org/10.1007/s00138-016-0792-4

MLA:

Belagiannis, Vasileios, et al. "Parsing human skeletons in an operating room." Machine Vision and Applications 27.7 (2016): 1035-1046.

BibTeX: Download