Access to high-quality data is an important barrier in the digital analysis of urban settings, including applications within computer vision and urban design. Diverse forms of data collected from sensors in areas of high activity in the urban environment, particularly at street intersections, are valuable resources for researchers interpreting the dynamics between vehicles, pedestrians, and the built environment. In this paper, we present a high-resolution audio, video, and LiDAR dataset of three urban intersections in Brooklyn, New York, totaling almost 8 unique hours. The data were collected with custom Reconfigurable Environmental Intelligence Platform (REIP) sensors that were designed with the ability to accurately synchronize multiple video and audio inputs. The resulting data are novel in that they are inclusively multimodal, multi-angular, high-resolution, and synchronized. We demonstrate four ways the data could be utilized — (1) to discover and locate occluded objects using multiple sensors and modalities, (2) to associate audio events with their respective visual representations using both video and audio modes, (3) to track the amount of each type of object in a scene over time, and (4) to measure pedestrian speed using multiple synchronized camera views. In addition to these use cases, our data are available for other researchers to carry out analyses related to applying machine learning to understanding the urban environment (in which existing datasets may be inadequate), such as pedestrian-vehicle interaction modeling and pedestrian attribute recognition. Such analyses can help inform decisions made in the context of urban sensing and smart cities, including accessibility-aware urban design and Vision Zero initiatives.

Climate change and the associated increase in heat-related hazards pose a pressing threat to urban residents’ health and well-being. People, when walking in particular, are at risk of experiencing heat stress as they navigate urban environments. This study proposes a novel heat risk assessment framework combining pedestrian mobility modeling with urban microclimate modeling. Using this framework, we assessed pedestrian heat-related exposure and risk in urban areas by integrating the Universal Thermal Climate Index (UTCI) as the hazard and pedestrian trips to critical destinations as exposure. We considered temporal variation, in both hazard and exposure, by examining different time periods during the day—morning peak, midday, and evening peak. In addition to hazard and exposure, we also considered vulnerability by focusing on young children and older adults. We contribute to improving the spatial resolution of heat risk assessment by analyzing the hazard for pedestrian trips between home locations and five critical destinations—bus stops, rail stations, parks, schools, and commercial amenities—at the address-point level and using a pedestrian network comprising sidewalks and crosswalks. Our framework helps identify sidewalks with high heat exposure levels as well as home locations with high cumulative heat risk, accounting for walking trips to critical destinations along feasible routes. We demonstrated the effectiveness of this framework by applying it to a 36-square-kilometer area of central Los Angeles, CA. Our findings offer valuable information to urban planners and policy-makers, supporting evidence-based prioritization of intervention sites, climate adaptation strategies, and policy decisions essential for climate-proof planning. By implementing targeted interventions in areas where heat hazard is expected to affect the most vulnerable pedestrians, planners can create heat-resilient, pedestrian-friendly environments while prioritizing the health and well-being of vulnerable groups. This study contributes to the growing knowledge of robust risk assessment methodologies for climate-proof planning, specifically with regard to addressing outdoor heat-related risks during extreme heat events.

We have entered a new era of computing—one where AI permeates every aspect of society from education to healthcare. In this workshop, we examine the emerging role of AI in the design of equitable and accessible cities, transportation systems, and interactive tools for mapping and navigation. We will solicit short papers around key Urban AI + disability themes, including autonomous vehicles, intelligent wheelchairs, assistive human-robotic interaction, assessing and navigating pedestrian pathways, indoor accessibility, and overarching challenges related to ethics, bias, and data privacy and security. We invite both traditional HCI and accessibility researchers as well as scholars and practitioners from other disciplines relevant to this workshop, including disability studies, gerontology, social work, community psychology, and law. Our overarching goal is to identify open challenges, share current work across disciplines, and spur new collaborations related to AI and urban accessibility.

Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environments, shadows can provide shaded places to stay during the hot seasons, mitigate heat island effect, and increase pedestrian comfort levels. Properly quantifying sunlight access and shadows in large urban environments is key in tackling some of the important challenges facing cities today. In this paper, we propose Deep Umbra, a novel computational framework that enables the quantification of sunlight access and shadows at a global scale. Our framework is based on a conditional generative adversarial network that considers the physical form of cities to compute high-resolution spatial information of accumulated sunlight access for the different seasons of the year. We use data from seven different cities to train our model, and show, through an extensive set of experiments, its low overall RMSE (below 0.1) as well as its extensibility to cities that were not part of the training set. Additionally, we contribute a set of case studies and a comprehensive dataset with sunlight access information for more than 100 cities across six continents of the world.

We examine the feasibility of using deep learning to infer 33 classes of sidewalk accessibility conditions in pre-cropped streetscape images, including bumpy, brick/cobblestone, cracks, height difference (uplifts), narrow, uneven/slanted, pole, and sign. We present two experiments: first, a comparison between two state-of-the-art computer vision models, Meta’s DINOv2 and OpenAI’s CLIP-ViT, on a cleaned dataset of ∼ 24k images; second, an examination of a larger but noisier crowdsourced dataset (∼ 87k images) on the best performing model from Experiment 1. Though preliminary, Experiment 1 shows that certain sidewalk conditions can be identified with high precision and recall, such as missing tactile warnings on curb ramps and grass grown on sidewalks, while Experiment 2 demonstrates that larger but noisier training data can have a detrimental effect on performance. We contribute an open dataset and classification benchmarks to advance this important area.