DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors

TL;DR

DeepMoCap introduces a novel marker-based optical motion capture system utilizing multiple depth sensors and retro-reflectors, employing deep learning to automatically localize reflectors and accurately capture 3D motion data.

Contribution

It presents a multi-stage FCN architecture for automatic reflector localization and temporal correlation modeling, advancing marker-based optical motion capture with deep learning.

Findings

Outperforms existing methods on the DMC2.5D dataset in 2D keypoint accuracy.

Achieves 4.5% higher 3D PCK accuracy compared to other RGB-D and inertial fusion approaches.

Provides publicly available datasets for benchmarking motion capture methods.

Abstract

In this paper, a marker-based, single-person optical motion capture method (DeepMoCap) is proposed using multiple spatio-temporally aligned infrared-depth sensors and retro-reflective straps and patches (reflectors). DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space. Introducing a non-parametric representation to encode the temporal correlation among pairs of colorized depthmaps and 3D optical flow frames, a multi-stage Fully Convolutional Network (FCN) architecture is proposed to jointly learn reflector locations and their temporal dependency among sequential frames. The extracted reflector 2D locations are spatially mapped in 3D space, resulting in robust 3D optical data extraction. The subject's motion is efficiently captured by applying a template-based fitting technique on the extracted optical data. Two datasets have been created and made publicly available for evaluation purposes; one comprising multi-view depth and 3D optical flow annotated images (DMC2.5D), and a second, consisting of spatio-temporally aligned multi-view depth images along with skeleton, inertial and ground truth MoCap data (DMC3D). The FCN model outperforms its competitors on the DMC2.5D dataset using 2D Percentage of Correct Keypoints (PCK) metric, while the motion capture outcome is evaluated against RGB-D and inertial data fusion approaches on DMC3D, outperforming the next best method by 4.5% in total 3D PCK accuracy.