United States Department of Transportation
i
Deep Learning Methods to Leverage Traffic Monitoring Cameras for Pedestrian Data Applications
-
2019-05-01
-
[PDF-1.59 MB]
Details:
-
Alternative Title:Transit Policy in the Context of New Transportation Paradigms [Project Title from Cover]
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Corporate Publisher:
-
Abstract:Transportation agencies often own extensive networks of monocular traffic cameras, which are typically used for traffic monitoring by officials and experts. While the information captured by these cameras can also be of great value in transportation planning and operations, such applications are less common due to the lack of scalable methods and tools for data processing and analysis. This paper exemplifies how the value of existing traffic camera networks can be augmented using the latest computing techniques. We use traffic cameras owned by the City of Austin to study pedestrian road use and identify potential safety concerns. Our approach automatically analyzes the content of video data from existing traffic cameras using a semi-automated processing pipeline powered by the state-of-art computing hardware and algorithms. The method also extracts a background image at analyzed locations, which is used to visualize locations where pedestrians are present, and display their trajectories. We also propose quantitative metrics of pedestrian activity which may be used to prioritize the deployment of pedestrian safety solutions, or evaluate their performance.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
