Vehicle detection and tracking in airborne videos by multi-motion layer analysis

  • Authors:

  • Xianbin Cao;Jinhe Lan;Pingkun Yan;Xuelong Li

  • Affiliations:

  • University of Science and Technology of China, 230026, Hefei, People’s Republic of China and BeiHang University, 100083, Beijing, People’s Republic of China;University of Science and Technology of China, 230026, Hefei, People’s Republic of China;Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Phot ...;Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Phot ...

  • Venue:
  • Machine Vision and Applications
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Airborne vehicle detection and tracking systems equipped on unmanned aerial vehicles (UAVs) are receiving more and more attention due to their advantages of high mobility, fast deployment and large surveillance scope. However, such systems are difficult to develop because of factors like UAV motion, scene complexity, and especially the partial occlusion of targets. To address these problems, a new framework of multi-motion layer analysis is proposed to detect and track moving vehicles in airborne platform. After motion layers are constructed, they are maintained over time for tracking vehicles. Most importantly, since the vehicle motion layers can be maintained even when the vehicles are only partially observed, the proposed method is robust to partial occlusion. Our experimental results showed that (1) compared with other previous algorithms, our method can achieve better performance in terms of higher detection rate and lower false positive rate; (2) it is more efficient and more robust to partial occlusion; (3) it is able to meet the demand of real time application due to its computational simplicity.