Design and Development of Eye Tracking System for Children with Autism

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition impacting communication and social interaction in children. Eye-tracking technology has emerged as a valuable tool to investigate visual attention patterns in children with ASD. This paper presents the design and development of an eye-tracking system for children with ASD, employing a Raspberry Pi 4, Noir camera, gaze tracker, and LED display to create an immersive virtual reality (VR) environment for precise visual attention measurement. The hardware implementation involves integrating the Raspberry Pi circuitry and AMOLED screen into a VR box, with the Noir camera capturing eye images. A meticulous calibration process maps pupil coordinates to screen coordinates accurately. The system's software, employing OpenCV for image processing and Firebase for data storage, is rigorously tested on adults to ensure reliable gaze tracking prior to assessing children with autism. Successful tracking of gaze coordinates during stimulus display indicates its potential for accurate data collection. However, minor reading errors from the sensor slightly hinder accuracy, suggesting improvements via camera sensor and microcontroller upgrades. The eye-tracking system offers a promising avenue for early and accurate ASD diagnosis, offering critical insights into visual attention patterns, and facilitating effective interventions to enhance social and communication skills in children with ASD.