Using Model Aircraft to Collect Vehicle Trajectory Data

Video data has been used more widely in the field of traffic engineering in recent years, especially in the vehicle trajectories extraction. However, the existing methods of collecting video data have many shortcomings, including the high cost and inflexibility. What's more, existing video data processing systems are complex and have some limitations, either highly influenced by traffic condition or time-consuming and laborious. This paper proposed a new method to collect video data and process the data to extract vehicle trajectories. A consumer-grade camera which can shoot high-quality video was installed on a fixed-wing model aircraft, designed specifically for traffic surveillance. Also, an image processing software was developed, which can process the image frames extracted from the video shot by camera on model aircraft. The proposed method only needs to know coordinates of several reference points (e.g., some certain pavement markings) in the first image, which can be easily obtained by measuring or other accessible methods. The software can calculate the time-dependent coordinates of vehicles in consecutive series of pictures and, then, draw the trajectory automatically. The whole system can collect trajectory data effectively and efficiently, the cost of which is lower than those of existing systems. The general accuracy of trajectory is of the order of 10cm with the observing height around 200m, in addition, it takes only 30 minutes around for an experienced operator to obtain an 100-meter-long trajectory of around 8 vehicles by using the proposed system.

• 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:
  • Wang, Hao
  • Duan, Songyao
  • Zheng, Yunzhuang
  • Liu, Shanwen
  • Dong, Changyin
  • Li, Ye
• 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: 18p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Data collection; Digital video; Drones; Image processing; Traffic surveillance; Vehicle trajectories
• Subject Areas: Data and Information Technology; Highways; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01517507
• Record Type: Publication
• Report/Paper Numbers: 14-2801
• Files: TRIS, TRB, ATRI
• Created Date: Mar 10 2014 9:23AM