Towards Single Camera Human 3D-Kinematics

TL;DR

This paper introduces a novel deep learning method for direct 3D human kinematic estimation from videos, outperforming traditional multi-step approaches and enabling real-time analysis suitable for clinical use.

Contribution

The authors propose an end-to-end deep neural network approach for direct 3D human kinematic estimation from videos, eliminating the need for multi-step pose detection and model fitting.

Findings

Outperforms multi-step pipelines with 35% reduction in joint angle error.

Runs at video framerate speeds, enabling real-time analysis.

Demonstrates potential for clinical applications using mobile devices.

Abstract

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos. Most current techniques work in a multi-step approach by first detecting the pose of the body and then fitting a musculoskeletal model to the data for accurate kinematic estimation. Errors in training data of the pose detection algorithms, model scaling, as well the requirement of multiple cameras limit the use of these techniques in a clinical setting. Our goal is to pave the way toward fast, easily applicable and accurate 3D kinematic estimation \xdeleted{in a clinical setting}. To this end, we propose a novel approach for direct 3D human kinematic estimation D3KE from videos using deep neural networks. Our experiments demonstrate that the proposed end-to-end training is robust and outperforms 2D and 3D markerless motion capture based kinematic estimation pipelines in terms of joint angles error by a large margin (35\% from 5.44 to 3.54 degrees). We show that D3KE is superior to the multi-step approach and can run at video framerate speeds. This technology shows the potential for clinical analysis from mobile devices in the future.