Analysis of Lane Departure Crashes with Emerging Data, Machine Learning and Field Evaluation

Details

• Creators:
  Li, Jia
• Corporate Creators:
  University of Washington. Washington State Transportation Center (TRAC) ; Washington State University. Department of Civil and Environmental Engineering
• Corporate Contributors:
  Washington (State). Department of Transportation ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Traffic lanes
  • Crash causes
  • Road markings
  • Machine vision
  • Data analysis
  • Field tests
  • Advanced driver information systems
  • Evaluation
  • Driver support systems
  • Machine learning
  More +
• Publication/ Report Number:
  WA-RD 947.1
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  Washington (State). Department of Transportation
• Description:
  This study develops a technical framework to characterize and quantify the contributing factors of lane departure crashes in the State of Washington. The technical framework consists of machine learning models for route- and event-level lane departure risk prediction leveraging different sources of emerging data. Field study is also conducted to assess lane marking conditions and how well lane detection function works using ADAS (Advanced Driver Assistance System) technology. Using the proposed framework and data from 2020 to 2022, we identify that driver age, driving speed, lighting condition, and surface condition are consistently the top factors contributing to lane departure crashes on state routes in Washington. Field study shows that though weak spots exist, overall lane marking conditions on the surveyed segments are compatible with the lane detection function of ADAS.
• Format:
  PDF
• Funding:
  T1462 Task 39
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/94019/dot_94019_DS1.pdf
• File Type:
  [PDF - 5.43 MB]
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:bbf3fa7a772dbc37e3a1bd11e82c48b95480b112c46997bd16906987e6487de5d01cffe5a68895afa740f21721b0db2c16706876a474bcb14c04a968feb0500b