SPR-4855: Anomaly Detection in Traffic Patterns Using INDOT Camera System

INDOT cameras at each highway location can provide lane-level traffic flow data from TASI’s previous project. The primary goal for this project is to identify anomalies in traffic data patterns using a trained Neural Network, and store short video recordings of these anomalies as they are detected for review. The Neural Network can be trained using previously obtained week, month, or year traffic flow data and be used to distinguish in-distribution from out-of-distribution by comparing new data to the previous data.

Language

• English

Project

• Status: Active
• Funding: $146453
• Contract Numbers:

  SPR-4855

• Sponsor Organizations:

  Purdue University/Indiana Department of Transportation JHRP

  Purdue University
  1284 Civil Engineering Building, Room 4154
  West Lafayette, IN  United States  47907-1284
• Principal Investigators:

  Christopher, Lauren

  Chien, Stanley

  Chen, Yaobin

• Start Date: 20230801
• Expected Completion Date: 20241130
• Actual Completion Date: 0

Subject/Index Terms

• TRT Terms: Data analysis; Neural networks; Traffic data; Traffic flow
• Identifier Terms: Indiana Department of Transportation
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01890964
• Record Type: Research project
• Source Agency: Indiana Department of Transportation
• Contract Numbers: SPR-4855
• Files: RIP, STATEDOT
• Created Date: Aug 24 2023 3:22PM