Deriving Bearing Measurements from Video Images using Haar-like Features for Vehicle-to-Vehicle Navigation

Elmira Amirloo Abolfathi and Kyle O'Keefe

Abstract:	In this paper Vehicle-to-Vehicle navigation is reviewed and the augmentation of between vehicles moving base stations differential GPS (DGPS) with vision derived bearing measurements is proposed. A method for deriving bearing measurements from video data is introduced theoretically and then demonstrated. A real data set collected with two vehicles driving on a city street in Calgary, Alberta, Canada is then used to demonstrate the method. The initial results show small errors in vision derived bearing measurements. The integration of vision derived bearing measurements and moving base station DGPS show an improvement in the across-track positioning solution.
Published in:	Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014) September 8 - 12, 2014 Tampa Convention Center Tampa, Florida
Pages:	888 - 895
Cite this article:	Abolfathi, Elmira Amirloo, O'Keefe, Kyle, "Deriving Bearing Measurements from Video Images using Haar-like Features for Vehicle-to-Vehicle Navigation," Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014), Tampa, Florida, September 2014, pp. 888-895.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In