VIS4ION-Thailand (Visually Impaired Smart Service System for Spatial Intelligence and Onboard Navigation) - Resub - 1

项目总结/文摘

PROJECT SUMMARY/ABSTRACT Visual impairment engenders mobility losses, debility, illness and premature mortality. These mobility losses have been associated with unemployment rates that reach 80% globally and to severe compromises in quality of life (QoL). In many cases, health and wellbeing are ‘attacked’ by vision loss in any form factor and psychosocial barriers such as anxiety and depression are compounding influences that increase as deficits scale. The fear of falling is a threat that contributes to this downward ‘spiral’ and often goes unchecked; this fear is alarmingly justified, as visual impairment precipitates substantial increases in mechanical trips, falls and long-bone factures. This perfect storm leaves considerable swaths of the population poor, disenfranchised, and experiencing adverse health outcomes. These startling facts, although true in almost every high-income country, are even more severe in low- and middle-income countries, such as Thailand. When considered at a basic functional level, visual impairment destroys access to information about our three-dimensional world and the objects in it, leading to poor spatial cognition and an inability to navigate successfully, whether that be to a place of employment or a grocery store. Advanced wearables provide a potential solution to close this gap and provide consistent and reliable access to the information needed for mobility and orientation during navigation. Our team was instrumental in developing a novel wearable - VIS4ION (Visually Impaired Smart Service System for Spatial Intelligence and Onboard Navigation), a personal mobility solution that serves as a customizable, human-in-the- loop, sensing-to-feedback platform to deliver functional assistance in real-time. Our central hypothesis is that wearables support spatial cognition in visually impaired (VI) populations, augmenting personal freedom and agency, and promoting health and wellbeing. We seek to enhance this technology with next-generation mapping and localization software fashioned into a microservice to support spatial cognition in the VI. We will assess the performance of this new approach (e.g., mapping) as well as its impact on function (e.g., navigation efficiency), health (e.g., falls), and wellness (e.g., QoL) metrics. The proposal has five aims in two phases focused on validating this approach in a global setting. First, we will implement semantic segmentation and image-query- based localization networks in a small Thai campus to operate independently of both environmental (sensor- based) and Wi-Fi/cell infrastructure. We will then deploy this augmented platform with VI students. Third, we will assess for acceptability, appropriateness, and feasibility, focusing on experiences with VIS4ION. If milestones are met for this first phase (R21), we will progress to the second phase (R33). Fourth, we will test the effectiveness of the improved system over an extended-use period. Lastly, an additional urban area in Bangkok will be selected and 3D environmental map built for generalizability testing, ensuring that VIS4ION is able to handle multiple locations with disparate contextual elements. Given this foundation and planned advances, we predict the platform will substantially mitigate fall and immobility risks and associated adverse health outcomes.