Algorithm of Vehicle Speed Detection in Unmanned Aerial Vehicle Videos

The use of Unmanned Aerial Vehicles (UAVs) for traffic surveillance applications has been steadily growing by their unique advantages over the past few years. But at present the method which can extract traffic information from UAV videos still has many challenges, including camera motion, high object distance, varying object background or multiple objects near to each other. In this paper, an algorithm is proposed to track vehicle and extract its speed from the UAV videos. Firstly, detect feature points in the frames and match them, then choose the inner points from the matched points. Use the inner points to calibrate affine model and complete image registration by the model. Secondly, select the target by the way of human-computer interaction and use Camshift algorithm to track the target. Then a series of position coordinates about the moving target are extracted. Thirdly, use the affine model to calibrate the position coordinates obtained in the second step, then use the calibrated position coordinates and time interval to calculate the tracked target speed. Experiments have shown the results that the algorithm for different speed vehicles has good detection accuracy all above 92.4%.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ50 Information Systems and Technology.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Xin, Zhang
  • Chang, Yuntao
  • Li, Li
  • Jia-ning, Guo
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References;
• Pagination: 17p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Algorithms; Drones; Image processing; Speed detectors; Traffic surveillance
• Subject Areas: Data and Information Technology; Highways; I71: Traffic Theory; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01518167
• Record Type: Publication
• Report/Paper Numbers: 14-2616
• Files: TRIS, TRB, ATRI
• Created Date: Mar 12 2014 9:33AM