Evaluation of 3D markerless motion capture accuracy using OpenPose with multiple video cameras

Abstract

There is a need within human movement sciences for a markerless motion capture system, which is easy to use and sufficiently accurate to evaluate motor performance. This study aims to develop a 3D markerless motion capture technique, using OpenPose with multiple synchronized video cameras, and examine its accuracy in comparison with optical marker-based motion capture. Participants performed three motor tasks (walking, countermovement jumping, and ball throwing), with these movements measured using both marker-based optical motion capture and OpenPose-based markerless motion capture. The differences in corresponding joint positions, estimated from the two different methods throughout the analysis, were presented as a mean absolute error (MAE). The results demonstrated that, qualitatively, 3D pose estimation using markerless motion capture could correctly reproduce the movements of participants. Quantitatively, of all the mean absolute errors calculated, approximately 47% were less than 20 mm and 80% were less than 30 mm. However, 10% were greater than 40 mm. The primary reason for mean absolute errors exceeding 40mm was that OpenPose failed to track the participant's pose in 2D images owing to failures, such as recognition of an object as a human body segment, or replacing one segment with another depending on the image of each frame. In conclusion, this study demonstrates that, if an algorithm that corrects all apparently wrong tracking can be incorporated into the system, OpenPose-based markerless motion capture can be used for human movement science with an accuracy of 30mm or less.

Validity of an Artificial Intelligence-Assisted Motion-Analysis System Using a Smartphone for Evaluating Weight-Bearing Activities in Individuals with Patellofemoral Pain Syndrome

“…Although markerless motionanalysis systems are less accurate than marker-based motion-analysis systems, the former system is more suitable for use in clinical rehabilitation and sports, where it is difficult to perform marker-based motion analysis. 23 A previous study reported that markerless motion analysis provided measurements with low validity, as tracking using an automated skeleton and relatively low camera sample rates was difficult. 24 In addition, a recent systematic review reported that the outcomes of low-cost video-based motion-analysis and 3D motion-analysis systems exhibited "poor" (r=0.025) to "strong" agreement (r=0.992).…”

The Potential of Computer Vision-Based Marker-Less Human Motion Analysis for Rehabilitation

“…The measurements thus indicated that 3D pose estimation with marker-less motion capture was a correct reproduction of the test participants' movements. A rough estimate is therefore that the knee angle measurement has approximately the same accuracy as the proposal by Nakano et al 52 Schmitz et al 53 compare the accuracy of single camera markerless motion capture with a ten-camera marker-based motion analysis system for 6 different postures of a jig simulating a human leg. A digital inclinometer with an accuracy of 0.1° measured the abduction-adduction angles, which both the markerbased system and the marker-less system calculated as the mean of 30 frames.…”

“…Another proposal uses OpenPose with multiple synchronized video cameras to compare marker-less motion capture accuracy with optical marker-based motion capture accuracy for 2 tested participants' walking, countermovement jumping and ball throwing. 52 Mean absolute errors (MAE) measured test participants' corresponding joint position differences. For approximately 47% of all measurement MAE < 20 mm and for 80% of all measurement MAE < 30 mm.…”

Remote Physical Therapy: Requirements for a Single RGB Camera Motion Sensing

“…Nakano examined the accuracy of the RGB based system in his research. He used Vicon as a reference system [4]. His research shows that the accuracy of detecting key points using standard cameras from a distance of several meters is about a few centimeters.…”