Map the spatial distribution of human heat stress levels using LiDAR data, remote sensing, and local meteorological data.
Using historical Google Street View images and deep learning investigating the temporal change and inequities of street tree canopies in New York City.
Examine the environmental inequities in terms of different types of urban green spaces using satellite imagery, Google Street View, and land use/cover map.
Investigate associations between changes in human mobility from Google Mobility Data and the rate of new daily COVID-19 diagnoses in the US across the urban-rural gradient.
Using Google Street View, machine learning, sunlight exposure model, and network routing to provide a pedestrian level stratege to get rid of too much sunlight exposure.
Using Google Street View and geometrical transform to estimate the sky view factor (openness of street canyons) and understand streetscape in a upside-down view.
Street trees provide shade in hot summers. Using Google Street View and building height model, we can quantify and map the amount of shade provided by street trees.
Remote sensing doen't have to be overhead view. Using hemispheircal images generated from panoramas to understand the urban environment from a bottom-up view.
Analyzing the drivers of pedestrian activity in dense urban environment using massively collected human GPS trace and Google Street View data.
Have you been annoyied by the dazzling sunlight driving? This project will help you out using Google Street View and machine learning.
High-resolution remotely sensed data provide a rapid, overhead view of urban space. It make urban environment monitoring and mapping efficient.
Mapping the street greenery for cities around the world using geo-tagged Google Street View and computer vision.