Browsing by Subject "Thermal imagery"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Infrared Thermal Camera-Based Real-Time Identification and Tracking of Large Animals to Prevent Animal-Vehicle Collisions (AVCs) on Roadways
    (Intelligent Transportation Systems Institute, Center for Transportation Studies, University of Minnesota, 2012-05) Zhou, Debao
    Animal vehicle collision (AVC) is constantly a major safety issue for the driving on roadways. It is estimated that there are over 35,000 AVCs yearly resulting in 3 to 11 deaths, over 400 personal injuries, and close to 4,000 reported property damages of $1,000 or more. This justifies the many attempts that have been tried to detect large animals on road. However, very little success has been achieved. To reduce the number of AVCs, this research used an infrared (IR) thermal imaging method to detect the presence of large animals and to track their locations so drivers could avoid AVCs. The system consists of an infrared-thermal-image grabbing and processing system and a motion control system to track the objects. By analyzing the infrared thermal images, the presence of deer in surrounding areas have been identified, and thus tracked. Since the IR thermal imaging is independent of visible light, the system can work both day and night, even in bad weather. The system can cover a circle area up to 1,000 feet in radius for the identification of an object the size of an adult human being.
  • Thumbnail Image
    Item
    Thermal Image-Based Deer Detection to Reduce Accidents Due to Deer-Vehicle Collisions
    (Intelligent Transportation Systems Institute, Center for Transportation Studies, University of Minnesota, 2013-01) Zhou, Debao
    Deer-vehicle collision (DVC) is one of the most serious traffic issues in the Unite States. To reduce DVCs, this research developed a system using a contour-based histogram of oriented gradients algorithm (CNT-HOG) to identify deer through the processing of images taken by thermographic cameras. The system is capable of detecting deer in low visibility. Two motors are applied to enlarge the detection range and make the system capable of tracking deer by providing two degrees of freedom. The main assumption in the CNT-HOG algorithm is that the deer are brighter than their background in a thermo image. The brighter areas are defined as the regions of interest, or ROIs. ROIs were identified based on the contours of brighter areas. HOG features were then collected and certain detection frameworks were applied to the image portions in the ROIs instead of the whole image. In the detection framework, a Linear Support Vector Machine classifier was applied to achieve identification. The system has been tested in various scenarios, such as a zoo and roadways in different weather conditions. The influence of the visible percentage of a deer body and the posture of a deer on detection accuracy has been measured. The results of the applications on roadside have shown that this system can achieve high detection accuracy (up to 100%) with fast computation speed (10 Hz). Achieving such a goal will help to decrease the occurrence of DVCs on roadsides.