Adaptive video-based vehicle classification technique for monitoring traffic.

Details

• Creators:
  Wei, Heng ; Abrishami, Hedayat ; Xiao, Xinhua ; Karteek, Allam
• Corporate Creators:
  University of Cincinnati. Dept. of Civil/Architectural Enginerring and Construction Management
• Corporate Contributors:
  United States. Federal Highway Administration
• Subject/TRT Terms:
  Automatic Vehicle Identification Axles Image Processing Machine Vision Traffic Surveillance Vehicle Classification Vehicle Length Video
• Publication/ Report Number:
  FHWA/OH-2015/20
• Resource Type:
  Tech Report
• Geographical Coverage:
  Ohio
• Corporate Publisher:
  Ohio. Dept. of Transportation. Office of Statewide Planning and Research
• Abstract:
  This report presents a methodology for extracting two vehicle features, vehicle length and number of axles in order
  
  to classify the vehicles from video, based on Federal Highway Administration (FHWA)’s recommended vehicle
  
  classification scheme. There are two stages regarding this classification. The first stage is the general classification
  
  that basically classifies vehicles into 4 categories or bins based on the vehicle length (i.e., 4-Bin length-based vehicle
  
  classification). The second stage is the axle-based group classification that classifies vehicles in more detailed
  
  classes of vehicles such as car, van, buses, based on the number of axles. The Rapid Video-based Vehicle
  
  Identification System (RVIS) model is developed based on image processing technique to enable identifying the
  
  number of vehicle axles. Also, it is capable of tackling group classification of vehicles that are defined by axles and
  
  vehicle length based on the FHWA’s vehicle classification scheme and standard lengths of 13 categorized vehicles.
  
  The RVIS model is tested with sample video data obtained on a segment of I-275 in the Cincinnati area, Ohio. The
  
  evaluation result shows a better 4-Bin length–based classification than the axle-based group classification. There
  
  may be two reasons. First, when a vehicle gets misclassified in 4-Bin classification, it will definitely be misclassified
  
  in axle-based group classification. The error of the 4-Bin classification will propagate to the axle-based group
  
  classification. Second, there may be some noises in the process of finding the tires and number of tires. The project
  
  result provides solid basis for integrating the RVIS that is particularly applicable to light traffic condition and the
  
  Vehicle Video-Capture Data Collector (VEVID), a semi-automatic tool to be particularly applicable to heavy traffic
  
  conditions, into a “hybrid” system in the future. Detailed framework and operation scheme for such an integration
  
  effort is provided in the project report.
  
  
• Format:
  PDF
• Funding:
  SJN 134874
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha256:43ce4d2e3cd649457e397c34cca8dac9f535da8b96c8450c60e20d5e03f5a938
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/29363/dot_29363_DS1.pdf
• File Type:
  [PDF - 3.16 MB ]