Building Smart Transportation Hubs with 3D Vision and Video Technologies to Improve Servicesto People with Disabilities

1 Large transportation hubs are difficult to navigate, especially for people with disabilities such as those 2 with visual or mobility impairment, Autism Spectrum Disorder (ASD), or simply those with navigation 3 challenges. The primary objective of this research is to design and develop a novel cyber-physical 4 infrastructure that can effectively and efficiently transform existing transportation hubs into smart 5 facilities capable of providing better location-aware services (e.g. finding terminals, improving travel 6 experience, obtaining security alerts). We investigated the integration of a number of novel Internet of 7 Things elements, including video analytics, low-cost Bluetooth beacons, mobile computing, and LiDAR8 scanned 3D semantic models, to provide reliable indoor navigation services to people with traveling 9 challenges, yet requiring minimum infrastructure changes since our approach leverages existing 10 cyberinfrastructures such as surveillance cameras, facility models, and mobile phones, and incorporates a 11 minimum number of new and small devices such as beacons to achieve reliable navigation services. We 12 choose two groups of people for our initial study– those with visual impairment and ASD since both 13 groups face difficulties in a crowded and complex 3D environment. Thus two unique features of our 14 solution are the use of 3D digital semantic models and crowd analysis with surveillance cameras for 15 providing the best available paths. We have started a pilot test with people with disabilities at a multi16 floor building in New York City to demonstrate the effectiveness of our proposed framework. 17 18 19 20 Glossary of Terms: 21 ASD: Autism Spectrum Disorder 22 BLE: Bluetooth Low Energy 23 BoW: Bag of Words 24 BVI: Blind and Visual Impairment 25 CNN: Convolutional Neural Network 26 ConvNet: Convolutional Neural Network 27 DCT: Discrete Cosine Transform 28 GIST: a low dimensional representation of the scene, which does not require any form of segmentation 29 IoT: Internet of things 30 Lidar: Light Detection and Ranging 31 SfM: Structure from Motion 32 33 34 35 36