Contact pressure between the human body and its surroundings has important implications . For example, it plays a role in comfort, safety, posture, and posture . We present a method that infers contact pressure between a human bodyand a mattress from a depth image . We introduce a novel deepnetwork that we trained on an augmented dataset and evaluated with real data . The network contains an embedded human body mesh model and uses a white-box model of depth and pressure image generation . Our network successfully infersbody pose, outperforming prior work. It also infers pressure across a3D mesh model of the human human body, which is a novel capability, and does so inthe presence of occlusion from blankets. The network successfullyinfers body pose, outnumber previous work. Our network outperforms prior work . It alsoinfers pressure pressure across the

Author(s) : Henry M. Clever, Patrick Grady, Greg Turk, Charles C. Kemp

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : pressure - human - body - network - model -

Leave a Reply

Your email address will not be published. Required fields are marked *