An Automated System for Pedestrian Facility Data Collection from Aerial Images

Prioritized improving pedestrian facility inventory, particularly concerning crosswalks and sidewalks, is an important action item in state departments of transportation Strategic Highway Safety Plans. However, such information is not widely available at the state level.

The TRB IDEA (Innovations Deserving Exploratory Analysis) Program's Highway IDEA Final Report 209: An Automated System for Pedestrian Facility Data Collection from Aerial Images details the development of an innovative system using convolutional neural networks, an advanced machine learning method that uses deep learning, to process image data. These networks were used to automatically collect major pedestrian facility data, including sidewalk presence, crosswalk presence, and crosswalk length, from aerial images.