Embedded AI system for interactive vision screen based on human action recognition.

Abstract

In recent years, vision screening has emerged globally for employment (on a yearly basis) within primary and high schools since myopia heavily affects school-aged children. However, this is a laborious and time-consuming task. This article proposes an intelligent system for "self-service" vision screening. Individuals can accomplish this task independently-without any assistance by technical staff. The technical solution involved within this platform is human action recognition realized by pose estimation (real-time human joint localization in images, including detection, association, and tracking). The developed system is based on a compact and embedded artificial intelligence platform, aided by a red-green-blue-D sensor for ranging and pose extraction. A set of intuitive upper-limb actions was designed for unambiguous recognition and interaction. The deployment of this intelligent system brings great convenience for large-scale and rapid vision screening. Implementation details were extensively described, and the experimental results demonstrated efficiency for the proposed technique.