External cueing is a potentially effective strategy to reduce freezing of gait (FOG) in persons with Parkinson’s disease (PD). Case reports suggest that three-dimensional (3D) cues might be more effective in reducing FOG than two-dimensional cues. We investigate the usability of 3D augmented reality visual cues delivered by smart glasses in comparison to conventional 3D transverse bars on the floor and auditory cueing via a metronome in reducing FOG and improving gait parameters. In laboratory experiments, 25 persons with PD and FOG performed walking tasks while wearing custom-made smart glasses under five conditions, at the end-of-dose. For two conditions, augmented visual cues (bars/staircase) were displayed via the smart glasses. The control conditions involved conventional 3D transverse bars on the floor, auditory cueing via a metronome, and no cueing. The number of FOG episodes and percentage of time spent on FOG were rated from video recordings. The stride length and its variability, cycle time and its variability, cadence, and speed were calculated from motion data collected with a motion capture suit equipped with 17 inertial measurement units. A total of 300 FOG episodes occurred in 19 out of 25 participants. There were no statistically significant differences in number of FOG episodes and percentage of time spent on FOG across the five conditions. The conventional bars increased stride length, cycle time, and stride length variability, while decreasing cadence and speed. No effects for the other conditions were found. Participants preferred the metronome most, and the augmented staircase least. They suggested to improve the comfort, esthetics, usability, field of view, and stability of the smart glasses on the head and to reduce their weight and size. In their current form, augmented visual cues delivered by smart glasses are not beneficial for persons with PD and FOG. This could be attributable to distraction, blockage of visual feedback, insufficient familiarization with the smart glasses, or display of the visual cues in the central rather than peripheral visual field. Future smart glasses are required to be more lightweight, comfortable, and user friendly to avoid distraction and blockage of sensory feedback, thus increasing usability.

Remote photo-plethysmography (rPPG) uses a remotely placed camera to estimating a person's heart rate (HR). Similar to how heart rate can provide useful information about a person's vital signs, insights about the underlying physio/psychological conditions can be obtained from heart rate variability (HRV). HRV is a measure of the fine fluctuations in the intervals between heart beats. However, this measure requires temporally locating heart beats with a high degree of precision. We introduce a refined and efficient real-time rPPG pipeline with novel filtering and motion suppression that not only estimates heart rate more accurately, but also extracts the pulse waveform to time heart beats and measure heart rate variability. This method requires no rPPG specific training and is able to operate in real-time. We validate our method on a self-recorded dataset under an idealized lab setting, and show state-of-the-art results on two public dataset with realistic conditions (VicarPPG and PURE).

Remote photo-plethysmography (rPPG) uses a camera to estimate a person’s heart rate (HR). Similar to how heart rate can provide useful information about a person’s vital signs, insights about the underlying physio/psychological conditions can be obtained from heart rate variability (HRV). HRV is a measure of the fine fluctuations in the intervals between heart beats. However, this measure requires temporally locating heart beats with a high degree of precision. We introduce a refined and efficient real-time rPPG pipeline with novel filtering and motion suppression that not only estimates heart rates, but also extracts the pulse waveform to time heart beats and measure heart rate variability. This unsupervised method requires no rPPG specific training and is able to operate in real-time. We also introduce a new multi-modal video dataset, VicarPPG 2, specifically designed to evaluate rPPG algorithms on HR and HRV estimation. We validate and study our method under various conditions on a comprehensive range of public and self-recorded datasets, showing state-of-the-art results and providing useful insights into some unique aspects. Lastly, we make available CleanerPPG, a collection of human-verified ground truth peak/heart-beat annotations for existing rPPG datasets. These verified annotations should make future evaluations and benchmarking of rPPG algorithms more accurate, standardized and fair.

In face-to-face social interactions, blind and visually impaired persons (VIPs) lack access to nonverbal cues like facial expressions, body posture, and gestures, which may lead to impaired interpersonal communication. In this study, a wearable sensory substitution device (SSD) consisting of a head mounted camera and a haptic belt was evaluated to determine whether vibrotactile cues around the waist could be used to convey facial expressions to users and whether such a device is desired by VIPs for use in daily living situations. Ten VIPs (mean age: 38.8, SD: 14.4) and 10 sighted persons (SPs) (mean age: 44.5, SD: 19.6) participated in the study, in which validated sets of pictures, silent videos, and videos with audio of facial expressions were presented to the participant. A control measurement was first performed to determine how accurately participants could identify facial expressions while relying on their functional senses. After a short training, participants were asked to determine facial expressions while wearing the emotion feedback system. VIPs using the device showed significant improvements in their ability to determine which facial expressions were shown. A significant increase in accuracy of 44.4% was found across all types of stimuli when comparing the scores of the control (mean±SEM: 35.0±2.5%) and supported (mean±SEM: 79.4±2.1%) phases. The greatest improvements achieved with the support of the SSD were found for silent stimuli (68.3% for pictures and 50.8% for silent videos). SPs also showed consistent, though not statistically significant, improvements while supported. Overall, our study shows that vibrotactile cues are well suited to convey facial expressions to VIPs in real-time. Participants became skilled with the device after a short training session. Further testing and development of the SSD is required to improve its accuracy and aesthetics for potential daily use.

Background The development of treatments for freezing of gait (FOG) in Parkinson's disease (PD) requires experimental study setups in which FOG is likely to occur, and is amenable to therapeutic interventions. We explore whether the 'Auditory Stroop Task' (AST) can be used to increase cognitive load (and thereby elicit FOG), simultaneously with visual cues (as a therapeutic intervention for FOG). We additionally examined how these two contrasting effects might interact in affecting gait and FOG parameters. Objectives We investigated whether: (1) the 'Auditory Stroop Task' (AST) influences gait in healthy elderly and persons with PD who experience FOG, and increases the frequency of FOG events among PD patients; (2) the AST and visual cues interact; and (3) different versions of the AST exert different cognitive loads. Methods In 'Experiment 1', 19 healthy elderly subjects performed a walking task while performing a high and low load version of the AST. Walking with a random numbers task, and walking without cognitive load served as control conditions. In 'Experiment 2', 20 PD patients with FOG and 18 healthy controls performed a walking task with the AST, and no additional cognitive load as control condition. Both experiments were performed with and without visual PLOS ONE |

No 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 . 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.

Objective. Elucidating how cueing alleviates freezing of gait (FOG) in Parkinson's disease (PD) would enable the development of more effective, personalized cueing strategies. Here, we aimed to validate a visual cueing virtual environment (VE) paradigm for future use in e.g. neuroimaging studies and behavioral studies on motor timing and scaling in PD patients with FOG. Approach. We included 20 PD patients with FOG and 16 age-matched healthy control subjects. Supine participants were confronted with a VE displaying either no cues, bars or staircases. They navigated forward using alternate suppression of foot pedals. Motor arrests (as proxy for FOG), and measures of motor timing and scaling were compared across the three VE conditions for both groups. Main results. VE cues (bars and staircases) did not reduce motor arrests in PD patients and healthy control subjects. The VE cues did reduce pedal amplitude in healthy control subjects, without effects on other motor parameters. Conclusion. We could not validate a visual cueing VE paradigm to study FOG. The VE cues possibly failed to convey the necessary spatial and temporal information to support motor timing and scaling. We discuss avenues for future research.