For this project, supported by the Ford Motor Company, we are developing a library of posture and gesture data that can help us to better understand potential interactions between vehicles and pedestrians. The work is motivated, in particular, with the increasing sophistication with which vehicle-based sensor platforms can image and tag signals of human activity as they traverse urban spaces. In building the data-set, we will rely on motion capture of body language data, which allows us to acquire very high-resolution positions for key sequences of body language, which we can then process and map to synthetic computational rigs. In this way, these data can be subsumed into our other modeling platforms for what-if simulation and visualization.

Motion capture data for pedestrian movement, retargeted to a synthetic character rig for body language analysis and tagging of activities.

Ford Research and Innovation Center

Capturing body language

Massive ice CA

Spatiotemporal GIS

Urban simulation in GIS

Big data movement analytics

Land indicators of climate

High-performance computing and networking for geosimulation

Earthquake models

Ice-sheet modeling

Dynamic physics for built infrastructure

Moving agents through space and time

Validating agent-based models

Machine-learning behavioral geography

Accelerating agent-based models

Megacity futures

Immersive modeling

Space-time GIS and analysis

A toolkit for measuring sprawl

Modeling time, space, and behavior