Estimation of spatial-temporal hand motion parameters in rehabilitation using a low-cost noncontact measurement system

A hand motion capture method based on infrared thermography for measuring fine motor skills in biomedicine

Many biomedical applications require fine motor skill assessments; however, real-time and contactless fine motor skill assessments are not typically implemented. In this study, we followed the 2D-to-3D pipeline principle and proposed a transformer-based spatial-temporal network to accurately regress 3D hand joint locations by inputting infrared thermal video for eliminating need of multiple cameras or RGB-D devices. We also developed a dataset composed of infrared thermal videos and ground truth annotations for training. The label represents a set of 3D joint locations from infrared optical trackers, which is considered the gold standard for clinical applications. To demonstrate their potential, the proposed method was used to measure the finger motion angle, and we investigated its accuracy by comparing the proposal with the Azure Kinect system and Leap Motion system. On the proposed dataset, the proposed method achieved a 3D hand pose mean error of less than 14 mm and outperforms the other deep learning methods. When the error thresholds were larger than approximately 35 mm, our method first to achieved excellent performance (>80%) in terms of the fraction of good frames. For the finger motion angle calculation task, the proposed and commercial systems had comparable inter-system reliability (ICC_2,1 ranging from 0.81 to 0.83) and excellent validity (Pearson's r-values ranging from 0.82 to 0.86). We believe that the proposed approaches can capture hand motion and measure finger motion angles and can be used in different biomedicine scenarios as an effective evaluation tool for fine motor skills.

Analysis of the Leap Motion Controller's Performance in Measuring Wrist Rehabilitation Tasks Using an Industrial Robot Arm Reference

The Leap Motion Controller (LMC) is a low-cost markerless optical sensor that performs measurements of various parameters of the hands that has been investigated for a wide range of different applications. Research attention still needs to focus on the evaluation of its precision and accuracy to fully understand its limitations and widen its range of applications. This paper presents the experimental validation of the LMC device to verify the feasibility of its use in assessing and tailoring wrist rehabilitation therapy for the treatment of physical disabilities through continuous exercises and integration with serious gaming environments. An experimental set up and analysis is proposed using an industrial robot as motion reference. The high repeatability of the selected robot is used for comparisons with the measurements obtained via a leap motion controller while performing the basic movements needed for rehabilitation exercises of the human wrist. Experimental tests are analyzed and discussed to demonstrate the feasibility of using the leap motion controller for wrist rehabilitation.

Restricted Kinematics in Children With Autism in the Execution of Complex Oscillatory Arm Movements

Restricted and repetitive behavior is a core symptom of autism spectrum disorder (ASD) characterized by features of restrictedness, repetition, rigidity, and invariance. Few studies have investigated how restrictedness is manifested in motor behavior. This study aimed to address this question by instructing participants to perform the utmost complex movement. Twenty children with ASD and 23 children with typical development (TD) performed one-dimensional, left-right arm oscillations by demonstrating varying amplitudes and frequencies. The entropy of amplitude and velocity was calculated as an index of kinematic complexity. Results showed that the velocity entropy, but not the amplitude entropy, was significantly lower in ASD than in TD (p < 0.01), suggesting restricted kinematics. Further analysis demonstrated that a significantly higher proportion of the velocity values was allocated at a low-speed level in the children with ASD (p < 0.01). A qualitative comparison of the complex movement with movement at preferred frequency suggested that the children with ASD might be less likely to shift away from the preferred movement. However, our study can be improved in terms of recruiting a larger sample of participants, measuring the level of motivation, and collecting both complex and preferred movements of the same participant.