Stereo 3D tracking of infants in natural play conditions

Towards an AI-driven soft toy for automatically detecting and classifying infant-toy interactions using optical force sensors

Introduction: It is crucial to identify neurodevelopmental disorders in infants early on for timely intervention to improve their long-term outcomes. Combining natural play with quantitative measurements of developmental milestones can be an effective way to swiftly and efficiently detect infants who are at risk of neurodevelopmental delays. Clinical studies have established differences in toy interaction behaviors between full-term infants and pre-term infants who are at risk for cerebral palsy and other developmental disorders. Methods: The proposed toy aims to improve the quantitative assessment of infant-toy interactions and fully automate the process of detecting those infants at risk of developing motor delays. This paper describes the design and development of a toy that uniquely utilizes a collection of soft lossy force sensors which are developed using optical fibers to gather play interaction data from infants laying supine in a gym. An example interaction database was created by having 15 adults complete a total of 2480 interactions with the toy consisting of 620 touches, 620 punches-"kick substitute," 620 weak grasps and 620 strong grasps. Results: The data is analyzed for patterns of interaction with the toy face using a machine learning model developed to classify the four interactions present in the database. Results indicate that the configuration of 6 soft force sensors on the face created unique activation patterns. Discussion: The machine learning algorithm was able to identify the distinct action types from the data, suggesting the potential usability of the toy. Next steps involve sensorizing the entire toy and testing with infants.

Infant movement classification through pressure distribution analysis

BACKGROUND

Aiming at objective early detection of neuromotor disorders such as cerebral palsy, we propose an innovative non-intrusive approach using a pressure sensing device to classify infant general movements. Here we differentiate typical general movement patterns of the "fidgety period" (fidgety movements) vs. the "pre-fidgety period" (writhing movements).

METHODS

Participants (N = 45) were sampled from a typically-developing infant cohort. Multi-modal sensor data, including pressure data from a pressure sensing mat with 1024 sensors, were prospectively recorded for each infant in seven succeeding laboratory sessions in biweekly intervals from 4 to 16 weeks of post-term age. 1776 pressure data snippets, each 5 s long, from the two targeted age periods were taken for movement classification. Each snippet was pre-annotated based on corresponding synchronised video data by human assessors as either fidgety present or absent. Multiple neural network architectures were tested to distinguish the fidgety present vs. fidgety absent classes, including support vector machines, feed-forward networks, convolutional neural networks, and long short-term memory networks.

RESULTS

Here we show that the convolution neural network achieved the highest average classification accuracy (81.4%). By comparing the pros and cons of other methods aiming at automated general movement assessment to the pressure sensing approach, we infer that the proposed approach has a high potential for clinical applications.

CONCLUSIONS

We conclude that the pressure sensing approach has great potential for efficient large-scale motion data acquisition and sharing. This will in return enable improvement of the approach that may prove scalable for daily clinical application for evaluating infant neuromotor functions.

Infants at risk for physical disability may be identified by measures of postural control in supine

BACKGROUND

Early detection of delay or impairment in motor function is important to guide clinical management and inform prognosis during a critical window for the development of motor control in children. The purpose of this study was to investigate the ability of biomechanical measures of early postural control to distinguish infants with future impairment in motor control from their typically developing peers.

METHODS

We recorded postural control from infants lying in supine in several conditions. We compared various center of pressure metrics between infants grouped by birth status (preterm and full term) and by future motor outcome (impaired motor control and typical motor control).

RESULTS

One of the seven postural control metrics-path length-was consistently different between groups for both group classifications and for the majority of conditions.

CONCLUSIONS

Quantitative measures of early spontaneous infant movement may have promise to distinguish early in life between infants who are at risk for motor impairment or physical disability and those who will demonstrate typical motor control. Our observation that center of pressure path length may be a potential early marker of postural instability and motor control impairment needs further confirmation and further investigation to elucidate the responsible neuromotor mechanisms.

IMPACT

The key message of this article is that quantitative measures of infant postural control in supine may have promise to distinguish between infants who will demonstrate future motor impairment and those who will demonstrate typical motor control. One of seven postural control metrics-path length-was consistently different between groups. This metric may be an early marker of postural instability in infants at risk for physical disability.

Motivating Spontaneous Infant Kicking Motions through Long Term Learning Utilizing a Robotic Mobile System

Our research investigates methods and systems to allow for early detection of motor impairment in infants and innovative interventions with the goal of improving longterm outcomes. A robotic baby mobile is utilized to motivate spontaneous kicking motions, which is used as a marker for predicting the potential of motor development delays. Our previous work investigated how the different stimuli modalities of a baby mobile can encourage infant kicking. We utilized a 3D camera system to detect the kicking motions, as well as recorded specific metrics of each kicking episode. In this work, we investigate the possibility of an infant having a preference of baby mobile stimuli that results in increased and sustained kicking motions. This preference is learned over multiple sessions with one infant and utilizes a Markov Decision Process to develop a policy.

Computer Vision to Automatically Assess Infant Neuromotor Risk

An infant's risk of developing neuromotor impairment is primarily assessed through visual examination by specialized clinicians. Therefore, many infants at risk for impairment go undetected, particularly in under-resourced environments. There is thus a need to develop automated, clinical assessments based on quantitative measures from widely-available sources, such as videos recorded on a mobile device. Here, we automatically extract body poses and movement kinematics from the videos of at-risk infants (N = 19). For each infant, we calculate how much they deviate from a group of healthy infants (N = 85 online videos) using a Naïve Gaussian Bayesian Surprise metric. After pre-registering our Bayesian Surprise calculations, we find that infants who are at high risk for impairments deviate considerably from the healthy group. Our simple method, provided as an open-source toolkit, thus shows promise as the basis for an automated and low-cost assessment of risk based on video recordings.

Computer Vision to Automatically Assess Infant Neuromotor Risk

An infant's risk of developing neuromotor impairment is primarily assessed through visual examination by specialized clinicians. Therefore, many infants at risk for impairment go undetected, particularly in under-resourced environments. There is thus a need to develop automated, clinical assessments based on quantitative measures from widely-available sources, such as videos recorded on a mobile device. Here, we automatically extract body poses and movement kinematics from the videos of at-risk infants (N = 19). For each infant, we calculate how much they deviate from a group of healthy infants (N = 85 online videos) using a Naïve Gaussian Bayesian Surprise metric. After pre-registering our Bayesian Surprise calculations, we find that infants who are at high risk for impairments deviate considerably from the healthy group. Our simple method, provided as an open-source toolkit, thus shows promise as the basis for an automated and low-cost assessment of risk based on video recordings.