Itzamná: A Prototype for Accessible Mobility Analysis with AI Using Sensor Data
摘要
This paper presents Itzamná, a prototype designed to improve pedestrian accessibility in urban environments through the integration of sensor data, Artificial Intelligence (AI), and citizen participation. Focused on Mexico City’s aging population and infrastructure challenges, the methodology combines LiDAR and RGB imagery with a participatory platform to detect and classify sidewalk conditions. Deep Learning models analyze surface irregularities and obstacles, generating georeferenced insights to support inclusive urban planning. Preliminary results from the Zacatenco campus reveal that 87.4% of detected issues are uneven surfaces, underscoring the need for targeted interventions. By merging low-cost technologies with community engagement, Itzamná offers a replicable framework for assessing and visualizing pedestrian mobility risks, contributing to urban well-being strategies in emerging cities.