Tracking-based deer vehicle collision detection using thermal imaging

  • Authors:

  • Debao Zhou;Matt Dillon;Eil Kwon

  • Affiliations:

  • Department of Mechanical and Production Engineering, University of Minnesota, Duluth, MN;Department of Mechanical and Production Engineering, University of Minnesota, Duluth, MN;Department of Civil Engineering, University of Minnesota, Duluth, MN

  • Venue:
  • ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Deer vehicle collision (DVC) is constantly a major safety issue for the driving on rural road. It is estimated that there are over 35,000 DVCs yearly in the US resulting in about 200 deaths and close to 4,000 reported property damages of one thousand dollars or more. This justifies many attempts trying to detect deer on road. However, very little success has been achieved. In order to reduce the number of DVCs, this work focused on the study of using an infrared thermal camera with tracking system to detect the presence of deer to avoid DVCs. The prototype consists of an infrared thermal temperature image grabbing and processing system, which includes an infrared thermal camera, a frame grabber, an image processing system and a motion tracking system, which includes two motors with their motion control system. By analyzing the infrared thermal images which are independent of visible light, the presence of an animal can be determined in either night or day time through pattern recognition and matching.