Integrating Vision Derived Bearing Measurements with Differential GPS for Vehicle-to-Vehicle Relative Navigation
Date
2015-03-11
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Vehicle positioning is an important component of intelligent transportation systems. Due to the relative low cost and low complexity of Global Navigation Satellite Systems (GNSS), the automotive industry has adopted this technology to provide vehicle position. GNSSs solution are reliable in open sky environments. However, position solutions are needed in the areas where there is poor GNSS accuracy or availability and other sensors may be required
This thesis presents the integration of vision-derived bearing measurements with between vehicle GNSS relative navigation. Two methods: target detection and machine learning based vehicle recognition, have been developed to obtain bearing measurements from the images. The resulting bearings are then integrated with a GNSS solution resulting in improved position accuracy and availability. The usefulness of the GNSS solution to improve the vehicle recognition algorithm is also investigated.
Description
Keywords
Engineering
Citation
Amirloo Abolfathi, E. (2015). Integrating Vision Derived Bearing Measurements with Differential GPS for Vehicle-to-Vehicle Relative Navigation (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/26582