Research of Vehicle Detection Algorithm in Infrared Thermal Imaging Videos

Abstract

This paper proposes a new algorithm for counting vehicle information in the infrared thermal imaging video sequences. First, the characteristics of the adjacent frames in video sequences has been analyzed, together with the modeling for the background information and updating background model according to the inter-frame variation. Second, the information of the moving target in the current frame is preliminarily extracted adopting the background subtraction algorithm, it achieves image segmentation and the division of the best detection area according to the imaging features of vehicles in different lanes by using morphological filtering and setting up the detection window. Then, model classification is done using the connected domain tags and template matching for vehicles in detection region. Finally, vehicle information each frame detects is counted by lanes. The experimental results present that the algorithm for dividing the best detection region segmentation image can reduce the miss rate and the false detection rate to the maximum extent. Meanwhile, the algorithm also has good detection accuracy for statistics of the traffic flow and classification of vehicles in video sequences. ©, 2015, Journal of Information and Computational Science. All right reserved.