Marker-based Optical Motion Capture Research Articles

Agreement between An Inertia and Optical Based Motion Capture during the VU-Return-to-Play- Field-Test.

The validity of an inertial sensor-based motion capture system (IMC) has not been examined within the demands of a sports-specific field movement test. This study examined the validity of an IMC during a field test (VU®) by comparing it to an optical marker-based motion capture system (MMC). Expected accuracy and precision benchmarks were computed by comparing the outcomes of a linear and functional joint fitting model within the MMC. The kinematics from the IMC in sagittal plane demonstrated correlations (r2) between 0.76 and 0.98 with root mean square differences (RMSD) < 5°, only the knee bias was within the benchmark. In the frontal plane, r2 ranged between 0.13 and 0.80 with RMSD < 10°, while the knee and hip bias was within the benchmark. For the transversal plane, r2 ranged 0.11 to 0.93 with RMSD < 7°, while the ankle, knee and hip bias remained within the benchmark. The findings indicate that ankle kinematics are not interchangeable with MMC, that hip flexion and pelvis tilt higher in IMC than MMC, while other measures are comparable to MMC. Higher pelvis tilt/hip flexion in the IMC can be explained by a one sensor tilt estimation, while ankle kinematics demonstrated a considerable level of disagreement, which is likely due to four reasons: A one sensor estimation, sensor/marker attachment, movement artefacts of shoe sole and the ankle model used.

Depth camera based statistical shape fitting approach for the creation of an individualized lower body biomechanical model: validity and reliability

Systems for instrumented motion analysis depend on an accurate biomechanical model. In this work an existing statistical shape fitting approach was adapted to register a parametrized human surface model with annotated anatomical landmarks to a point cloud obtained from one frontal depth camera view. Based on the obtained landmark positions joint centers, segment lengths and segment orientations of the lower body were calculated. The outcome was validated among two groups of healthy and impaired subjects, using a marker-based optical motion capture system. The results reveal a valid and reliable approach for obtaining an individualized lower body biomechanical model with minimum effort.

Human movement and ergonomics: An industry-oriented dataset for collaborative robotics

Improving work conditions in industry is a major challenge that can be addressed with new emerging technologies such as collaborative robots. Machine learning techniques can improve the performance of those robots, by endowing them with a degree of awareness of the human state and ergonomics condition. The availability of appropriate datasets to learn models and test prediction and control algorithms, however, remains an issue. This article presents a dataset of human motions in industry-like activities, fully labeled according to the ergonomics assessment worksheet EAWS, widely used in industries such as car manufacturing. Thirteen participants performed several series of activities, such as screwing and manipulating loads under different conditions, resulting in more than 5 hours of data. The dataset contains the participants’ whole-body kinematics recorded both with wearable inertial sensors and marker-based optical motion capture, finger pressure force, video recordings, and annotations by three independent annotators of the performed action and the adopted posture following the EAWS postural grid. Sensor data are available in different formats to facilitate their reuse. The dataset is intended for use by researchers developing algorithms for classifying, predicting, or evaluating human motion in industrial settings, as well as researchers developing collaborative robotics solutions that aim at improving the workers’ ergonomics. The annotation of the whole dataset following an ergonomics standard makes it valuable for ergonomics-related applications, but we expect its use to be broader in the robotics, machine learning, and human movement communities.

Measurement and Analysis of Gait Pattern during Stair Walk for Improvement of Robotic Locomotion Rehabilitation System.

Background Robotic locomotion rehabilitation systems have been used for gait training in patients who have had a stroke. Most commercialized systems allow patients to perform simple exercises such as balancing or level walking, but an additional function such as stair-walk training is required to provide a wide range of recovery cycle rehabilitation. In this study, we analyzed stair-gait patterns and applied the result to a robotic rehabilitation system that can provide a vertical motion of footplates. Methods To obtain applicable data for the robotic system with vertically movable footplates, stair-walk action was measured using an optical marker-based motion capture system. The spatial position data of joints during stair walking was obtained from six healthy adults who participated in the experiment. The measured marker data were converted into joint kinematic data by using an algorithm that included resampling and normalization. The spatial position data are represented as angular trajectories and the relative displacement of each joint on the anatomical sagittal plane and movements of hip joints on the anatomical transverse plane. Results The average range of motion (ROM) of each joint was estimated as (−6.75°, 48.69°) at the hip, (8.20°, 93.78°) at the knee, and (−17.78°, 11.75°) at the ankle during ascent and as (6.41°, 31.67°) at the hip, (7.38°, 91.93°) at the knee, and (−24.89°, 24.18°) at the ankle during descent. Additionally, we attempted to create a more natural stair-gait pattern by analyzing the movement of the hip on the anatomical transverse plane. The hip movements were estimated to within ±1.57 cm and ±2.00 cm for hip translation and to within ±2.52° and ±2.70° for hip rotation during stair ascent and stair descent, respectively. Conclusions Based on the results, standard patterns of stair ascent and stair descent were derived and applied to a lower-limb rehabilitation robot with vertically movable footplates. The relative trajectory from the experiment ascertained that the function of stair walking in the robotic system properly worked within a normal ROM.

Online optical marker-based hand tracking with deep labels

Optical marker-based motion capture is the dominant way for obtaining high-fidelity human body animation for special effects, movies, and video games. However, motion capture has seen limited application to the human hand due to the difficulty of automatically identifying (or labeling) identical markers on self-similar fingers. We propose a technique that frames the labeling problem as a keypoint regression problem conducive to a solution using convolutional neural networks. We demonstrate robustness of our labeling solution to occlusion, ghost markers, hand shape, and even motions involving two hands or handheld objects. Our technique is equally applicable to sparse or dense marker sets and can run in real-time to support interaction prototyping with high-fidelity hand tracking and hand presence in virtual reality.

Validation of foot pitch angle estimation using inertial measurement unit against marker-based optical 3D motion capture system.

Gait analysis is relevant to a broad range of clinical applications in areas of orthopedics, neurosurgery, rehabilitation and the sports medicine. There are various methods available for capturing and analyzing the gait cycle. Most of gait analysis methods are computationally expensive and difficult to implement outside the laboratory environment. Inertial measurement units, IMUs are considered a promising alternative for the future of gait analysis. This study reports the results of a systematic validation procedure to validate the foot pitch angle measurement captured by an IMU against Vicon Optical Motion Capture System, considered the standard method of gait analysis. It represents the first phase of a research project which aims to objectively evaluate the ankle function and gait patterns of patients with dorsiflexion weakness (commonly called a "drop foot") due to a L5 lumbar radiculopathy pre- and post-lumbar decompression surgery. The foot pitch angle of 381 gait cycles from 19 subjects walking trails on a flat surface have been recorded throughout the course of this study. Comparison of results indicates a mean correlation of 99.542% with a standard deviation of 0.834%. The maximum root mean square error of the foot pitch angle measured by the IMU compared with the Vicon Optical Motion Capture System was 3.738° and the maximum error in the same walking trail between two measurements was 9.927°. These results indicate the level of correlation between the two systems.

Vertical Jump Height Estimation Algorithm Based on Takeoff and Landing Identification Via Foot-Worn Inertial Sensing.

Vertical jump height is widely used for assessing motor development, functional ability, and motor capacity. Traditional methods for estimating vertical jump height rely on force plates or optical marker-based motion capture systems limiting assessment to people with access to specialized laboratories. Current wearable designs need to be attached to the skin or strapped to an appendage which can potentially be uncomfortable and inconvenient to use. This paper presents a novel algorithm for estimating vertical jump height based on foot-worn inertial sensors. Twenty healthy subjects performed countermovement jumping trials and maximum jump height was determined via inertial sensors located above the toe and under the heel and was compared with the gold standard maximum jump height estimation via optical marker-based motion capture. Average vertical jump height estimation errors from inertial sensing at the toe and heel were -2.2±2.1 cm and -0.4±3.8 cm, respectively. Vertical jump height estimation with the presented algorithm via inertial sensing showed excellent reliability at the toe (ICC(2,1)=0.98) and heel (ICC(2,1)=0.97). There was no significant bias in the inertial sensing at the toe, but proportional bias (b=1.22) and fixed bias (a=-10.23cm) were detected in inertial sensing at the heel. These results indicate that the presented algorithm could be applied to foot-worn inertial sensors to estimate maximum jump height enabling assessment outside of traditional laboratory settings, and to avoid bias errors, the toe may be a more suitable location for inertial sensor placement than the heel.

Design and evaluation of reduced marker layouts for hand motion capture

AbstractWe present a method for automatically generating reduced marker layouts for marker‐based optical motion capture of human hands. The employed motion reconstruction method is based on subspace‐constrained inverse kinematics, which allows for the recovery of realistic hand movements even from sparse input data. We additionally present a user‐specific hand model calibration procedure that fits an articulated hand model to point cloud data of the user's hand. Our marker layout optimization is sensitive to the kinematic structure and the subspace representations of hand articulations utilized in the reconstruction method, in order to generate sparse marker configurations that are optimal for solving the constrained inverse kinematics problem. We propose specific quality criteria for reduced marker sets that combine numerical stability with geometric feasibility of the resulting layout. These criteria are combined in an objective function that is minimized using a specialized surface‐constrained particle swarm optimization scheme, which generates marker layouts bound to the surface of an animated hand model. Our method provides a principled way for determining reduced marker layouts based on subspace representations of hand articulations. We demonstrate the effectiveness of our motion reconstruction and model calibration methods in a thorough evaluation.

Towards Fully Automated Motion Capture of Signs -- Development and Evaluation of a Key Word Signing Avatar

Motion capture of signs provides unique challenges in the field of multimodal data collection. The dense packaging of visual information requires high fidelity and high bandwidth of the captured data. Even though marker-based optical motion capture provides many desirable features such as high accuracy, global fitting, and the ability to record body and face simultaneously, it is not widely used to record finger motion, especially not for articulated and syntactic motion such as signs. Instead, most signing avatar projects use costly instrumented gloves, which require long calibration procedures. In this article, we evaluate the data quality obtained from optical motion capture of isolated signs from Swedish sign language with a large number of low-cost cameras. We also present a novel dual-sensor approach to combine the data with low-cost, five-sensor instrumented gloves to provide a recording method with low manual postprocessing. Finally, we evaluate the collected data and the dual-sensor approach as transferred to a highly stylized avatar. The application of the avatar is a game-based environment for training Key Word Signing (KWS) as augmented and alternative communication (AAC), intended for children with communication disabilities.

Data-driven control of flapping flight

We present a physically based controller that simulates the flapping behavior of a bird in flight. We recorded the motion of a dove using marker-based optical motion capture and high-speed video cameras. The bird flight data thus acquired allow us to parameterize natural wingbeat cycles and provide the simulated bird with reference trajectories to track in physics simulation. Our controller simulates articulated rigid bodies of a bird's skeleton and deformable feathers to reproduce the aerodynamics of bird flight. Motion capture from live birds is not as easy as human motion capture because of the lack of cooperation from subjects. Therefore, the flight data we could acquire were limited. We developed a new method to learn wingbeat controllers even from sparse, biased observations of real bird flight. Our simulated bird imitates life-like flapping of a flying bird while actively maintaining its balance. The bird flight is interactively controllable and resilient to external disturbances.

Recognition of human periodic movements from unstructured information using a motion-based frequency domain approach

Feature-based motion cues play an important role in biological visual perception. We present a motion-based frequency-domain scheme for human periodic motion recognition. As a baseline study of feature based recognition we use unstructured feature-point kinematic data obtained directly from a marker-based optical motion capture (MoCap) system, rather than accommodate bootstrapping from the low-level image processing of feature detection. Motion power spectral analysis is applied to a set of unidentified trajectories of feature points representing whole body kinematics. Feature power vectors are extracted from motion power spectra and mapped to a low dimensionality of feature space as motion templates that offer frequency domain signatures to characterise different periodic motions. Recognition of a new instance of periodic motion against pre-stored motion templates is carried out by seeking best motion power spectral similarity. We test this method through nine examples of human periodic motion using MoCap data. The recognition results demonstrate that feature-based spectral analysis allows classification of periodic motions from low-level, un-structured interpretation without recovering underlying kinematics. Contrasting with common structure-based spatio-temporal approaches, this motion-based frequency-domain method avoids a time-consuming recovery of underlying kinematic structures in visual analysis and largely reduces the parameter domain in the presence of human motion irregularities.