Saved in:
Bibliographic Details
Main Authors: Smyrnakis, Nikolaos, Karakostas, Tasos, Cotton, R. James
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.12676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916131934044160
author Smyrnakis, Nikolaos
Karakostas, Tasos
Cotton, R. James
author_facet Smyrnakis, Nikolaos
Karakostas, Tasos
Cotton, R. James
contents Gait analysis from videos obtained from a smartphone would open up many clinical opportunities for detecting and quantifying gait impairments. However, existing approaches for estimating gait parameters from videos can produce physically implausible results. To overcome this, we train a policy using reinforcement learning to control a physics simulation of human movement to replicate the movement seen in video. This forces the inferred movements to be physically plausible, while improving the accuracy of the inferred step length and walking velocity.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12676
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advancing Monocular Video-Based Gait Analysis Using Motion Imitation with Physics-Based Simulation
Smyrnakis, Nikolaos
Karakostas, Tasos
Cotton, R. James
Computer Vision and Pattern Recognition
Gait analysis from videos obtained from a smartphone would open up many clinical opportunities for detecting and quantifying gait impairments. However, existing approaches for estimating gait parameters from videos can produce physically implausible results. To overcome this, we train a policy using reinforcement learning to control a physics simulation of human movement to replicate the movement seen in video. This forces the inferred movements to be physically plausible, while improving the accuracy of the inferred step length and walking velocity.
title Advancing Monocular Video-Based Gait Analysis Using Motion Imitation with Physics-Based Simulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.12676