Search

There is a lack of data on the location, condition, and accessibility of sidewalks across the world, which not only impacts where and how people travel but also fundamentally limits interactive mapping tools and urban analytics. In this paper, we describe initial work in semi-automatically building a sidewalk network topology from satellite imagery using hierarchical multi-scale attention models, inferring surface materials from street-level images using active learning-based semantic segmentation, and assessing sidewalk condition and accessibility features using Crowd+AI. We close with a call to create a database of labeled satellite and streetscape scenes for sidewalks and sidewalk accessibility issues along with standardized benchmarks., CVPR 2022 AVA (Accessibility, Vision, and Autonomy Meet) Workshop

Research on how socioeconomic status interacts with neighbourhood characteristics to influence disparities in obesity outcomes is currently limited by residential segregation-induced structural confounding, a lack of empirical studies outside the U.S. and other 'Western' contexts, and an over-reliance on cross-sectional analyses. This study addresses these challenges by examining how socioeconomic status modifies the effect of accumulated exposures to obesogenic neighbourhood environments on children and mothers' BMI, drawing from a longitudinal mother-child birth cohort study in Singapore, an Asian city-state with relatively little residential segregation. We find that increased access to park connectors was associated with a decrease in BMI outcomes for mothers with higher socioeconomic status, but an increase for those with lower socioeconomic status. We also find that increased access to bus stops was associated with an increase in BMIz of children with lower socioeconomic status, but with a decrease in BMIz of children with higher socioeconomic status, while increased access to rail stations was associated with a decrease in BMIz of children with lower socioeconomic status only. Our results suggest that urban interventions might have heterogeneous effects by socioeconomic status.

City governments and planners alike commonly seek to increase pedestrian activity on city streets as part of broader sustainability, community building, and economic development strategies. Though walkability has received ample attention in planning literature, most planners still lack practical methods for predicting how development proposals could affect pedestrian activity on specific streets or public spaces at different times of the day. Cities typically require traffic impact assessments (TIAs) but not pedestrian impact assessments. In this study I present a methodology for estimating pedestrian trip generation and distribution between detailed origins and destinations in both existing and proposed built environments. Using the betweenness index from network analysis, I introduce a number of methodological improvements that allow the index to model pedestrian trips with parameters and constraints to account for pedestrian behavior in different settings. I demonstrate its application in the Kendall Square area of Cambridge (MA), where estimated foot traffic is compared during lunch and evening peak periods with observed pedestrian counts. The proposed approach can be particularly useful for TIAs, neighborhood plans, and large-scale development projects, where pedestrian flow estimates can be used to guide pedestrian infrastructure and safety improvements and public space investments or for locating pedestrian priority streets during the COVID-19 pandemic.

Recent developments in vehicle automation, connectivity, electro-mobility and ridesharing platforms are expected to transform urban mobility patterns and consequently reshape urban form. Historically we have seen that introduction of new transportation technologies has influenced new urban models and altered development patterns. An often-cited example in this regard is the rise of the private automobile which brought about a rise in suburban development. Urban form and transport flows have a complex two-way relationship where changes in one has repercussions on the other. Given this interdependency, the impacts of the recent technological developments, collectively termed as the ‘technological shift in transportation’, must be investigated within urban design and planning disciplines. There is enormous uncertainty surrounding how the technological shift in transportation may impact cities, and urban design and planning can play a decisive role in steering these impacts. The efficiencies and safety benefits of vehicle automation have been widely stated in support of its widespread implementation. At the same time, critics warn against dire environmental and social consequences of reckless implementations that do not take into consideration the complex interdependencies of the technology with the broader social, economic and physical context. This research examines the impacts of the technological shift in transportation on cities and urban form and searches for appropriate methods to conduct urban design in this context. The interplay of urban form and transport flows is investigated by integrating multi-agent simulations within the urban design workflow, through a series of ‘Design Experiments’. Singapore’s residential New Town model is chosen as a test site to conduct these design experiments, which aim to understand what design strategies can help us maximise the benefits of the technological shift and minimise its potential risks. Piecemeal design strategies are assessed through simulations to understand changes in transport flows over time and study emergent patterns. These insights inform a set of urban design and planning strategies in response to the technological shift in transportation a new structural model of the Singapore New Town for the short, mid and long term future. These proposals range from retrofitting the New Town in the short term to modifying the model structurally in the mid-term, moving towards a radically different ‘Post-Road City’ in the long term.