Fusion of vision, GPS and 3D gyro data in solving camera registration problem for direct visual navigation

This paper presents a precise and robust camera registration solution for the novel vision-based road navigation system - VICNAS, which superimposes virtual 3D navigation indicators and traffic signs upon the real road view in an Augmented Reality (AR) space. Traditional vision based or inertial sensor based solutions of registration problem are mostly designed for well-structured environment, which is however unavailable in a wide-open uncontrolled road environment for navigation purposes. This paper proposed a hybrid system that combines computer vision, GPS and 3D inertial gyroscope technologies to provide precise and robust camera pose estimation. The fusion approach is based on our PMM (parameterized model matching) algorithm, in which the road shape model is derived from the digital map data, and matched with road features extracted from real images. Inertial data estimates the initial possible motion, and also serves as relative tolerance to stable the pose output. The algorithms proposed in this paper are validated with the experimental results of real road tests under different road conditions.

• Authors:
  • HU, Z
  • UCHIMURA, K
• Publication Date: 2006

Language

• English

Media Info

• Pagination: 3-12
• Serial:
  • INTERNATIONAL JOURNAL OF ITS RESEARCH
  • Volume: 4
  • Issue Number: 1

Subject/Index Terms

• TRT Terms: Calculation; Data collection; Fusion; Global Positioning System; Information display systems; Intelligent transportation systems; Mathematical models; Methodology; Route guidance; Video cameras
• Uncontrolled Terms: Visual display
• ITRD Terms: 6464: Calculation; 6750: Camera; 8623: Data acquisition; 5270: Fusion; 9126: Global positioning system; 8735: Intelligent transport system; 9102: Method; 8771: Route guidance; 9080: Three dimensional; 8630: Visual display
• Subject Areas: Operations and Traffic Management; I70: Traffic and Transport;

Filing Info

• Accession Number: 01109614
• Record Type: Publication
• Source Agency: Transport Research Laboratory
• Files: ITRD
• Created Date: Aug 25 2008 8:48AM