Body Motion Tracking Research Articles

Electrical percolation and dynamic piezoresistivity of silver nanoparticle/polydimethylsiloxane films

Electrical percolation and piezo-resistivity under cyclic load were studied for silver nanoparticle (AgNP)/polydimethylsiloxane (PDMS) films. Attention was focused on the percolation process and the impacts of the percolation stage and load frequency on the piezoresistivity of the films. A power law was uncovered between the electrical resistance and the surface mass density (md) of AgNP layer. Dependence of piezoresistive sensitivity and linearity on md and cyclic load frequency were also investigated and interpreted in terms of the physical changes of the AgNP layer and the dynamics of the strain-induced microcracks. In particular, a peak gauge factor 75 was achieved at md = 0.32 mg cm−2 and the load frequency 0.5 Hz, and excellent linearity was found at the frequency 1 Hz or higher. These new findings provide important guidance for the design and applications of AgNP/PDMS films in body motion tracking, fatigue load monitoring and surface vibration detecting.

Dynamic human body reconstruction and motion tracking with low-cost depth cameras

We present a novel approach for dynamic human body reconstruction and motion tracking using low-cost depth cameras. Our reconstruction system is able to produce a sequence of dynamic 3D human body models from the noisy input depth data. To accurately align the template model with noisy input data, we combine skeleton-driven deformation and mesh deformation techniques to enhance the registration robustness to depth missing, occlusions, and severe noise. In addition, a novel data-driven 3D human body model is introduced to efficiently reconstruct human body models with wide shape and pose variations only using a limited number of training databases with standard standing pose. We perform quantitative and qualitative experiments to evaluate our method and compare it with other methods for body reconstruction on both synthetic and real datasets. Experimental results demonstrate the effectiveness of the proposed approach.

Improving the realism of a wheelchair simulator through tracking of upper body movements

Introduction Safe and efficient use of a manual wheelchair (MWC) requires appropriate training. New MWC users should learn how to maneuver in different environments (restricted spaces, uneven surfaces, etc.). Learning of appropriate balance skills is also crucial, to avoid falls when handling forward or side slopes. Moreover, long-term MWC use can lead to repetitive shoulder strain injuries, which can be avoided through adequate propulsion technique (increasing push amplitude, while decreasing cadence). We have developed a virtual reality MWC simulator for the training of MWC skills. The velocities of the rear wheels control a virtual MWC in a 3D scene presented on a computer screen in front of the participant, while force feedback simulates the effects of gravity and inertia. Our objective was to improve the realism of our existing wheelchair simulator, through the addition of upper body motion tracking that will provide feedback on trunk posture and propulsion movement. Material and methods Ten MWC users participated in the study. They propelled the virtual MWC while their trunk and arm movements were simultaneously recorded by three systems: – five inertial sensors placed on the trunk, arms and forearms; – a markerless, 3D depth camera system; – a high-precision motion capture system (gold standard). Upper body position as measured by the two low-cost approaches (inertial system and depth camera) was compared to the motion capture system. Results and conclusion Findings from this interdisciplinary study will optimize mobility of MWC users, through better MWC skills (balance and propulsion techniques), while possibly decreasing the incidence of falls and shoulder injuries.

Mimicking Human and Biological Skins for Multifunctional Skin Electronics

AbstractElectronic skin (e‐skin) technology is an exciting frontier to drive the next generation of wearable electronics owing to its high level of wearability, enabling high accuracy to harvest information of users and their surroundings. Recently, biomimicry of human and biological skins has become a great inspiration for realizing novel wearable electronic systems with exceptional multifunctionality as well as advanced sensory functions. This review covers and highlights bioinspired e‐skins mimicking perceptive features of human and biological skins. In particular, five main components in tactile sensation processes of human skin are individually discussed with recent advances of e‐skins that mimic the unique sensing mechanisms of human skin. In addition, diverse functionalities in user‐interactive, skin‐attachable, and ultrasensitive e‐skins are introduced with the inspiration from unique architectures and functionalities, such as visual expression of stimuli, reversible adhesion, easy deformability, and camouflage, in biological skins of natural creatures. Furthermore, emerging wearable sensor systems using bioinspired e‐skins for body motion tracking, healthcare monitoring, and prosthesis are described. Finally, several challenges that should be considered for the realization of next‐generation skin electronics are discussed with recent outcomes for addressing these challenges.

Uncertainty-Based IMU Orientation Tracking Algorithm for Dynamic Motions

With the recent technological advancement in low-cost wireless inertial motion trackers, measuring three-dimensional motion for biomechanics research becomes more facile. However, the methods of acceleration modeling in off-the-shelf filters do not hold for all movements in sports activities with significant and long-lasting accelerations. This paper presents a robust algorithm for orientation tracking in the presence of large active accelerations lasting longer than the maximum time the MEMS gyroscopes can solely keep track of the body orientation. We particularly model the uncertainty of active acceleration and take it into explicit account in an extended Kalman filter based orientation estimator for applying measurement updates accurately in dynamic motions such as sports activities. The proposed tracker also estimates the magnetic disturbances by using an uncertainty model to improve the heading estimation. Benchmarking the results with the Vicon Optical as ground truth and the MTw kit with a specific filter for body motion tracking shows the robustness of our method against variations of acceleration in different types of motion. Our tracker performs orientation estimation in real time with fast convergence during acceleration shocks and low root-mean-square error, particularly when experiencing large accelerations in periodic motions.

Two Approaches to Supporting Improvisational Ensemble for Music Beginners based on Body Motion Tracking

Melody recognition consists of three cognitive elements: pitch contour, rhythm, and tonality. Pitch contour and rhythm can be relatively easily represented by body motion. In comparison, tonality is difficult to understand and to represent for music beginners. In this paper, we focus on two approaches to supporting improvisational ensemble for music beginners on the basis of body motion tracking: (1) an approach by using a 3D motion capture camera and (2) an approach by using sensors in a smartphone. Users of our systems can participate in improvisational ensembles by making hand movements that correspond to the pitch contour and rhythm without considering tonality because the generated pitch is automatically adjusted to a consonant pitch with the chords of a background tune. To deal with the delay in gesture recognition by using the 3D motion capture camera, we improved a method for recognizing gestures. The experimental results show that the delay of our method was improved over that of the conventional one. Furthermore, we implemented a method for motion tracking on the basis of smartphone sensors. The experimental results show the difficulties of motion tracking with smartphone sensors. Moreover, we discuss perspectives on social reuse of improvisational melody data shared it as open data.

Co-Reading as a Generative Ontology

This paper discusses the immersive full body motion tracking installation Dark Matter, developed by the author and completed in early 2016. The paper outlines the conceptual focus of the project, including the use of the metaphor of dark matter to explore questions around interactive systems and assemblage. The primary technical considerations involved in the project are also outlined. ‘Co-reading' is proposed as a framework for a generative ontology, within the context of assemblage theory, deployed within a multimodal multi-agent interactive system.

Cognitive load reduces the effects of optic flow on gait and electrocortical dynamics during treadmill walking.

During navigation of complex environments, the brain must continuously adapt to both external demands, such as fluctuating sensory inputs, and internal demands, such as engagement in a cognitively demanding task. Previous studies have demonstrated changes in behavior and gait with increased sensory and cognitive load, but the underlying cortical mechanisms remain largely unknown. In the present study, in a mobile brain/body imaging (MoBI) approach, 16 young adults walked on a treadmill with high-density EEG while 3-dimensional (3D) motion capture tracked kinematics of the head and feet. Visual load was manipulated with the presentation of optic flow with and without continuous mediolateral perturbations. The effects of cognitive load were assessed by the performance of a go/no-go task on half of the blocks. During increased sensory load, participants walked with shorter and wider strides, which may indicate a more restrained pattern of gait. Interestingly, cognitive task engagement attenuated these effects of sensory load on gait. Using an independent component analysis and dipole-fitting approach, we found that cautious gait was accompanied by neuro-oscillatory modulations localized to frontal (supplementary motor area, anterior cingulate cortex) and parietal (inferior parietal lobule, precuneus) areas. Our results show suppression in alpha/mu (8-12 Hz) and beta (13-30 Hz) rhythms, suggesting enhanced activation of these regions with unreliable sensory inputs. These findings provide insight into the neural correlates of gait adaptation and may be particularly relevant to older adults who are less able to adjust to ongoing cognitive and sensory demands while walking. NEW & NOTEWORTHY The neural underpinnings of gait adaptation in humans are poorly understood. To this end, we recorded high-density EEG combined with three-dimensional body motion tracking as participants walked on a treadmill while exposed to full-field optic flow stimulation. Perturbed visual input led to a more cautious gait pattern with neuro-oscillatory modulations localized to premotor and parietal regions. Our findings show a possible brain-behavior link that might further our understanding of gait and mobility impairments.

Preferred treatment position between supine and prone for pelvic radiation therapy; quantification of the intrafractional body motion component by 3D surface imaging system

Purpose: We investigated the preferred treatment position between supine and prone during pelvic radiation treatment using real time tracking data from AlignRT. Our findings will provide valuable information regarding the role of intrafractional body motion in answering the question of prone versus supine position for pelvis radiation. Methods: Ten patients receiving pelvic radiation were enrolled in this study. For each patient, two simulation helical CT scans were performed, one in supine and one in prone position. Body surface contours were automatically generated and then exported to the AlignRT system as reference images. AlignRT continuous patient body motion tracking (1.5 to 2 minutes) was performed for both positions for each patient once per week for five weeks. The equivalent patient body motion along three principle directions was calculated from the six degree of freedom real time patient displacements data. The maximum and the standard deviation (STD) of equivalent patient body motion were calculated, so as the average of maximum and STD of equivalent patient motion over five fractions. These were then compared between supine and prone orientations. Results: A correlation was observed between the intrafractional body motion and large BMI. For overweight/obese patients, the intrafractional body motion was smaller for the supine position in both vertical and longitudinal directions. For normal range BMI patients, we observed no clear advantage for either supine or prone position in both vertical and longitudinal directions. In lateral direction, the intrafractional motion did not have statistically difference between two positions. Conclusion: Our study shows that the amount of intrafractional body motion between supine and prone orientation is correlated with patient BMI. Overweight/obese patients experienced significantly less overall body motion in supine orientation. The preferred treatment position for normal BMI patients was seen to be individually variable.

Kinematic Model-Based Pedestrian Dead Reckoning for Heading Correction and Lower Body Motion Tracking.

In this paper, we present a method for finding the enhanced heading and position of pedestrians by fusing the Zero velocity UPdaTe (ZUPT)-based pedestrian dead reckoning (PDR) and the kinematic constraints of the lower human body. ZUPT is a well known algorithm for PDR, and provides a sufficiently accurate position solution for short term periods, but it cannot guarantee a stable and reliable heading because it suffers from magnetic disturbance in determining heading angles, which degrades the overall position accuracy as time passes. The basic idea of the proposed algorithm is integrating the left and right foot positions obtained by ZUPTs with the heading and position information from an IMU mounted on the waist. To integrate this information, a kinematic model of the lower human body, which is calculated by using orientation sensors mounted on both thighs and calves, is adopted. We note that the position of the left and right feet cannot be apart because of the kinematic constraints of the body, so the kinematic model generates new measurements for the waist position. The Extended Kalman Filter (EKF) on the waist data that estimates and corrects error states uses these measurements and magnetic heading measurements, which enhances the heading accuracy. The updated position information is fed into the foot mounted sensors, and reupdate processes are performed to correct the position error of each foot. The proposed update-reupdate technique consequently ensures improved observability of error states and position accuracy. Moreover, the proposed method provides all the information about the lower human body, so that it can be applied more effectively to motion tracking. The effectiveness of the proposed algorithm is verified via experimental results, which show that a 1.25% Return Position Error (RPE) with respect to walking distance is achieved.

Development of a new homecare sleep monitor using body sounds and motion tracking

Abstract This paper presents the development of a sleep monitor to provide a comfortable way of detecting sleep-related breathing disorders like the obstructive sleep apnea syndrome (OSAS). OSAS is traditionally diagnosed using polysomnography, which requires a whole night stay at the sleep laboratory of a hospital with multiple electrodes and sensors attached to the patient’s body. However, body sound and motion tracking also provide extensive information about sleep course. A unique recording device offering a good body sound extraction, noise suppression and a small size is developed. Using this device a reliable detection of breathing and heart beat is possible. In addition sleeping positions and the activity of the patient will be evaluated using an inertial measurement unit (IMU). The device is easy to set up and offers the possibility to use it independently at home. Initial experiments have shown that volunteers were able to set up the device on their own. Furthermore several overnight recordings revealed the capability to monitor breathing, heart rate, sleeping position as well as movements of the patient.

Embodied learning of a generative neural model for biological motion perception and inference

Although an action observation network and mirror neurons for understanding the actions and intentions of others have been under deep, interdisciplinary consideration over recent years, it remains largely unknown how the brain manages to map visually perceived biological motion of others onto its own motor system. This paper shows how such a mapping may be established, even if the biologically motion is visually perceived from a new vantage point. We introduce a learning artificial neural network model and evaluate it on full body motion tracking recordings. The model implements an embodied, predictive inference approach. It first learns to correlate and segment multimodal sensory streams of own bodily motion. In doing so, it becomes able to anticipate motion progression, to complete missing modal information, and to self-generate learned motion sequences. When biological motion of another person is observed, this self-knowledge is utilized to recognize similar motion patterns and predict their progress. Due to the relative encodings, the model shows strong robustness in recognition despite observing rather large varieties of body morphology and posture dynamics. By additionally equipping the model with the capability to rotate its visual frame of reference, it is able to deduce the visual perspective onto the observed person, establishing full consistency to the embodied self-motion encodings by means of active inference. In further support of its neuro-cognitive plausibility, we also model typical bistable perceptions when crucial depth information is missing. In sum, the introduced neural model proposes a solution to the problem of how the human brain may establish correspondence between observed bodily motion and its own motor system, thus offering a mechanism that supports the development of mirror neurons.

Sensor fusion for complex articulated body tracking applied in rowing

This paper presents a sensor fusion model for integrating wearable inertial measures with sensors in the environment. This approach is designed and tested to support body motion tracking of rowing in indoor and outdoor environments. This paper presents the approach based on a complex kinematic model and Unscented Kalman filtering. The approach is validated in an indoor setup based on the SPRINT rowing system by comparison against results obtained from a commercial motion capture system, thus providing future directions for the assessment of rowers’ performance on an instrumented boat.

Automatic Bird Species Filtering Using a Multimodel Approach

We report a filtering algorithm for bird species detection using videos captured by uncalibrated moving cameras, a typical characteristic of crowd sourced videos. The algorithm tracks both body and wing motion dimensions of a flying bird to form signatures for species filtering. In the body model, we consider both cases when background motion introduced by the camera can and cannot be directly recognized using key point matching. We are also able to recover intrinsic camera parameters in the body motion tracking. In the wing model, we consider both periodic wing flapping and gliding motion patterns. These models are combined to form a multimodel framework. We have tested the algorithm and compared its performance with single model approaches in physical experiments. Results show that the new algorithm significantly reduces the false positive rate, while maintaining a low false negative rate. The area under ROC curve is 92.86%.

Towards photorealistic and immersive virtual-reality environments for simulated prosthetic vision: integrating recent breakthroughs in consumer hardware and software.

Simulated prosthetic vision (SPV) in normally sighted subjects is an established way of investigating the prospective efficacy of visual prosthesis designs in visually guided tasks such as mobility. To perform meaningful SPV mobility studies in computer-based environments, a credible representation of both the virtual scene to navigate and the experienced artificial vision has to be established. It is therefore prudent to make optimal use of existing hardware and software solutions when establishing a testing framework. The authors aimed at improving the realism and immersion of SPV by integrating state-of-the-art yet low-cost consumer technology. The feasibility of body motion tracking to control movement in photo-realistic virtual environments was evaluated in a pilot study. Five subjects were recruited and performed an obstacle avoidance and wayfinding task using either keyboard and mouse, gamepad or Kinect motion tracking. Walking speed and collisions were analyzed as basic measures for task performance. Kinect motion tracking resulted in lower performance as compared to classical input methods, yet results were more uniform across vision conditions. The chosen framework was successfully applied in a basic virtual task and is suited to realistically simulate real-world scenes under SPV in mobility research. Classical input peripherals remain a feasible and effective way of controlling the virtual movement. Motion tracking, despite its limitations and early state of implementation, is intuitive and can eliminate between-subject differences due to familiarity to established input methods.

Computer Simulation of Lower Extremities Movement during Stair Climbing

Tracking of human body motion is applied in many fields, such as virtual reality, clinical biomechanics, the study of man-machine-environment relationship, the analysis of sports movements, etc. Nowadays, the preferred approach to tracking human body motion is based on the use of appropriate optical or magnetic markers, which are placed on specific landmark points, and real-time estimating of their spatial coordinates. With the improvements introduced in computerized monitoring of human motion kinematics, it is important to emphasize the significance of combining motion capture data with commercial CAD packages. The aim of this research was to develop new interactive methods in creating virtual models within the highly sophisticated CAD computer technologies, as well as computer simulations for analyzing the various forms of human locomotion. Within this research, special attention is focused on the study of locomotion when climbing stairs, as an activity that requires large amount of metabolic energy, and thus represents great difficulty in performing daily activities for people with disorders of the musculoskeletal system, and particularly for people with lower limb amputation.

User Experiences While Playing Dance-Based Exergames and the Influence of Different Body Motion Sensing Technologies

Dance Dance Revolution is a pioneering exergame which has attracted considerable interest for its potential to promote regular exercise and its associated health benefits. The advent of a range of different consumer body motion tracking video game console peripherals raises the question whether their different technological affordances (i.e., variations in the type and number of body limbs that they can track) influence the user experience while playing dance-based exergames both in terms of the level of physical exertion and the nature of the play experience. To investigate these issues a group of subjects performed a total of six comparable dance routines selected from commercial dance-based exergames (two routines from each game) on three different consoles. The subjects’ level of physical exertion was assessed by measuring oxygen consumption and heart rate. They also reported their perceived level of exertion, difficulty, and enjoyment ratings after completing each dance routine. No differences were found in the physiological measures of exertion between the peripherals/consoles. However, there were significant variations in the difficulty and enjoyment ratings between peripherals. The design implications of these results are discussed including the tension between helping to guide and coordinate player movement versus offering greater movement flexibility.

Performance Evaluation of LDA and RADON in GAIT Recognition

Gait is an emergent biometric aimed essentially to recognize people by the way they walk. Gait’s advantages are that it requires no contact like automatic face recognition, and that it is less likely to be obscured than other biometrics. Gait has allied subjects including medical studies, psychology, human body modeling and motion tracking. These lend support to view that gait has clear potential as a biometric. To identify a person using their distinct Gait, the publicly available database is being taken in the video sequence format. By applying PCA analysis the gait points are extracted and trained. To obtain the false positive points LDA and a combined approach of LDA and Radon is used. The performance of the usage of LDA separately and LDARadon are being compared and the results are being produced as the graph..

A Fast ICP Algorithm for 3-D Human Body Motion Tracking

Iterative closest point (ICP) algorithm has been widely used for registering the geometry, shape and color of the 3-D meshes. However, ICP requires a long computation time to find the corresponding closest points between the model points and the data points. To overcome this problem, we propose a fast ICP algorithm that consists of two acceleration techniques: hierarchical model point selection (HMPS) and logarithmic data point search (LDPS). HMPS accelerates the search by reducing the search region of the data points corresponding to a model point effectively: it selects the model points in a coarse-to-fine manner and employs the four neighboring closest data points in the upper layer to make the search region for finding the closest data point corresponding to a model point in the lower layer. LDPS accelerates the search by visiting the data points within the search region using 2-D logarithm search. The HMPS method and the LDPS method can be operating separately or together. To evaluate the speed of the proposed ICP, we apply it to the 3-D human body motion tracking. The proposed fast ICP is about 3.17 times faster than the existing ICP such as the K-D tree.

SU-FF-J-116: On the Development of Intra-Fraction Whole Body Motion Tracking During Total Body Irradiation

Purpose: The feasibility of total marrow irradiation (TMI) using highly conformal image‐guided Tomotherapy is recently being explored as a radiation dose escalation pre‐conditioning TMI regimen for high risk hematological malignancies. Though, initial trial shows potential of this technology, treatment procedure is at present an open loop. This is a concern for safety as well as accuracy of the treatment delivery. The primary objective of this study is to develop a real time optical tracking system (OTS) which will offer better understanding of intra‐fraction whole body motion and develop a closed loop feedback approach to treatment that will enhance the safety of this new treatment.Method and Materials: A stereoscopic camerasystem is utilized to track near‐infrared reflective markers placed on the Rando phantom. The cameras were calibrated to determine the 3D location of each detected marker. The entire stereoscopic marker detection system returns a set of 3D marker locations at a rate of 60 Hz. Five criteria for evaluating motion capture technology are considered for selection of the optical detection system — accuracy, bandwidth, frame rate, capture volume, and real time performance. The translational motion detection uncertainties in OTS are measured and compared with onboard three dimensional megavoltage CT (MVCT) scanning system for pre‐treatment setup verification. Results: The preliminary work has shown : (i) the translational motion with better than 4mm accuracy, (ii) the vision‐based acquisition can be performed very quickly (in second) compared to the MVCT scan (5–10 minutes) method currently used for initial patient positioning; (iii) bony portions of the body can be accurately tracked in three dimensions. Conclusion: The proposed method entices the effectiveness of vision‐based whole body patient motion tracking for use with the helical tomotherapy treatment.