Crash Prediction and Avoidance by Identifying and Evaluating Risk Factors from Onboard Cameras

Motor vehicle crashes are a huge concern of roadway transportation safety, resulting in over 37,000 fatalities and $800 million losses annually. In recent years, the number of fatalities is growing. Risk factors that have been traditionally used no longer fully explain causes of the recent increase in fatalities. Human beings have bounded abilities in vision, cognition, making judgment, and simultaneously handling multiple tasks, particularly in complex, dynamic environments or in response to suddenly occurring situations. Therefore, assisting them in the cognition of risks and making the right decisions in a near real-time manner is a particular need in order to advance transportation toward zero fatalities. This project is motivated to developing a data-driven, computer-vision empowered, verifiable system that can predict crashes, and thereby improves drivers’ ability to avoid them. Pursuing a systematic approach, this project seamlessly integrates data analytics, deep learning, and computer vision technology to achieve the goal. Specifically, the project creates a crash report dataset trimmed from FARS, and analyzes the data to identify a set of risk factors that contribute to crashes and assess their significance levels. Provided with these, a Convolutional Neural Network (CNN) for scene segmentation and vehicle detection, and a Multi-tag Classification Network, are trained using the public KITTI dataset without crash accidents and the new dataset of crashes collected from YouTube. With the trained neural network models, videos captured from cameras mounted in vehicles can be analyzed in a near real-time manner, which infers the risk factor values for crash prediction and avoidance. For the purpose of crash prediction, a Long Short Term Memory (LSTM) model is developed to analyze the time-series data of risk factors in all frames along with their corresponding significance levels. The developed system, and the underlying technology and methods, are new capabilities for addressing motor vehicle crashes.

• Record URL:
  http://matc.unl.edu/research/research_project.php?researchID=560

Language

• English

Project

• Status: Completed
• Funding: $150000
• Contract Numbers:

  69A3551747107

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590

  Mid-America Transportation Center

  University of Nebraska-Lincoln
  2200 Vine Street, PO Box 830851
  Lincoln, NE  United States  68583-0851
• Managing Organizations:

  Mid-America Transportation Center

  University of Nebraska-Lincoln
  2200 Vine Street, PO Box 830851
  Lincoln, NE  United States  68583-0851
• Project Managers:

  Stearns, Amy

• Performing Organizations:

  Missouri University of Science & Technology, Rolla

  Department of Engineering
  202 University Center
  Rolla, MO    65409
• Principal Investigators:

  Qin, Ruwen

  Yin, Zhaozheng

• Start Date: 20190101
• Expected Completion Date: 20200930
• Actual Completion Date: 20200731
• USDOT Program: University Transportation Centers Program
• Source Data: 91994-41

Subject/Index Terms

• TRT Terms: Cameras; Crash data; Crash risk forecasting; Data analysis; Machine learning; Neural networks; Time series analysis
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01692384
• Record Type: Research project
• Source Agency: Mid-America Transportation Center
• Contract Numbers: 69A3551747107
• Files: UTC, RIP
• Created Date: Feb 6 2019 5:28PM