Machine learning systems and methods of estimating body shape from images
2020
Patent
ps
Disclosed is a method including receiving an input image including a human, predicting, based on a convolutional neural network that is trained using examples consisting of pairs of sensor data, a corresponding body shape of the human and utilizing the corresponding body shape predicted from the convolutional neural network as input to another convolutional neural network to predict additional body shape metrics.
Author(s): | Black, M. and Rachlin, E. and Heron, N. and Loper, M. and Weiss, A. and Hu, K. and Hinkle, T. and Kristiansen, M. |
Number (issue): | US Patent 10,679,046 |
Year: | 2020 |
Month: | June |
Department(s): | Perceiving Systems |
Bibtex Type: | Patent (patent) |
Paper Type: | Patent |
BibTex @patent{BodyLabs:Patent:2020, title = {Machine learning systems and methods of estimating body shape from images}, author = {Black, M. and Rachlin, E. and Heron, N. and Loper, M. and Weiss, A. and Hu, K. and Hinkle, T. and Kristiansen, M.}, number = {US Patent 10,679,046}, month = jun, year = {2020}, doi = {}, month_numeric = {6} } |