Vehicle matching in smart camera networks using image projection profiles at multiple instances
作者：
Highlights：
• We propose a novel method for vehicle appearance modeling and matching.
• A key novelty is automatic collection of good observations for matching.
• Our method is robust in real-world scenarios.
• Our method outperforms more complex object matching methods.
• Our method is data and computationally efficient, deployable on smart cameras.
摘要
•We propose a novel method for vehicle appearance modeling and matching.•A key novelty is automatic collection of good observations for matching.•Our method is robust in real-world scenarios.•Our method outperforms more complex object matching methods.•Our method is data and computationally efficient, deployable on smart cameras.
论文关键词：Multi-camera tracking,Feature extraction,Appearance modeling,Object recognition,Traffic surveillance
论文评审过程：Received 31 August 2012, Revised 8 April 2013, Accepted 19 June 2013, Available online 3 July 2013.
论文官网地址：https://doi.org/10.1016/j.imavis.2013.06.007
