Abstract
In this paper, we address the problem of recovering the intrinsic and extrinsic parameters of a camera or a group of cameras in a setting overlooking a traffic scene. Unlike many other settings, conventional camera calibration techniques are not applicable in this case. We present a method that uses certain geometric primitives commonly found in traffic scenes in order to recover calibration parameters. These primitives provide needed redundancy and are weighted depending on the significance of their corresponding image features. We show experimentally that these primitives are capable of achieving accurate results suitable for most traffic monitoring applications.
Original language | English (US) |
---|---|
Title of host publication | 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
Pages | 1878-1883 |
Number of pages | 6 |
State | Published - 2004 |
Event | 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Sendai, Japan Duration: Sep 28 2004 → Oct 2 2004 |
Publication series
Name | 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
---|---|
Volume | 2 |
Other
Other | 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
---|---|
Country/Territory | Japan |
City | Sendai |
Period | 9/28/04 → 10/2/04 |
Bibliographical note
Funding Information:This work has been supported in part by the National Science Foundation through Grants #IIS-0219863, #CMS-0127893, #CNS-0324864, and #CNS-0224363, the Minnesota Department of Transportation, and the ITS Institute at the University of Minnesota. We would also like to thank the anonymous reviewers for their valuable comments.
Keywords
- Application systems
- Calibration
- Multi-view reconstruction
- Multi-view stereo
- Traffic monitoring