Related Experiment Video
Updated: Apr 26, 2026
Eye Tracking Young Children with Autism
Published on: March 27, 2012
Computer vision tools for low-cost and noninvasive measurement of autism-related behaviors in infants
Jordan Hashemi1, Mariano Tepper1, Thiago Vallin Spina2
1Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA.
Insights
Early detection of autism spectrum disorder (ASD) is crucial. This study introduces low-cost computer vision tools to identify behavioral signs in infants, aiding early risk detection and clinical assessment.
Area of Science:
- Developmental Psychology
- Computer Vision
- Pediatric Neurology
Background:
- Early detection of developmental disorders, including autism spectrum disorder (ASD), significantly improves child outcomes.
- Traditional behavioral observation methods for identifying early ASD signs are time-intensive and require specialized training.
- Existing methods pose challenges for large-scale research and routine clinical practice.
Purpose of the Study:
- To develop non-invasive, low-cost computer vision tools for early detection of ASD behavioral signs in infants.
- To create algorithms for measuring behavioral responses relevant to ASD risk assessment using the Autism Observation Scale for Infants (AOSI).
- To provide tools that can augment clinical assessments for neurodevelopmental disorders.
Main Methods:
- Utilizing computer vision to track facial features and analyze visual attention in infants.
- Developing algorithms based on components of the Autism Observation Scale for Infants (AOSI).
- Comparing computer vision-derived observations with assessments from expert and nonexpert clinicians.
Main Results:
- The developed computer vision tools can effectively capture critical behavioral observations indicative of ASD risk.
- The system demonstrates the potential to measure visual attention and responses to specific developmental tasks.
- Results show promise in augmenting traditional clinical observations for early ASD detection.
Conclusions:
- Computer vision offers a scalable and cost-effective approach to early ASD behavioral sign detection.
- These tools can support clinicians in identifying infants at risk for neurodevelopmental disorders.
- This work represents a significant step towards non-invasive, technology-assisted early developmental disorder screening.
Abstract:
The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral signs can be observed late in the first year of life. Many of these studies involve extensive frame-by-frame video observation and analysis of a child's natural behavior. Although nonintrusive, these methods are extremely time-intensive and require a high level of observer training; thus, they are burdensome for clinical and large population research purposes. This work is a first milestone in a long-term project on non-invasive early observation of children in order to aid in risk detection and research of neurodevelopmental disorders. We focus on providing low-cost computer vision tools to measure and identify ASD behavioral signs based on components of the Autism Observation Scale for Infants (AOSI). In particular, we develop algorithms to measure responses to general ASD risk assessment tasks and activities outlined by the AOSI which assess visual attention by tracking facial features. We show results, including comparisons with expert and nonexpert clinicians, which demonstrate that the proposed computer vision tools can capture critical behavioral observations and potentially augment the clinician's behavioral observations obtained from real in-clinic assessments.
More Related Videos
05:10Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
Published on: March 17, 2023
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015