Title: Integrating Vision Based Navigation with INS and GPS for Land Vehicle Navigation in Challenging GNSS Environments
Author(s): Yunlong Sun, Muhammed Tahsin Rahman, Tashfeen B. Karamat, Aboelmagd Noureldin, Yanbin Gao
Published in: Proceedings of the 29th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2016)
September 12 - 16, 2016
Oregon Convention Center
Portland, Oregon
Pages: 1312 - 1321
Cite this article: Sun, Yunlong, Rahman, Muhammed Tahsin, Karamat, Tashfeen B., Noureldin, Aboelmagd, Gao, Yanbin, "Integrating Vision Based Navigation with INS and GPS for Land Vehicle Navigation in Challenging GNSS Environments," Proceedings of the 29th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2016), Portland, Oregon, September 2016, pp. 1312-1321.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In
Abstract: The inertial navigation system (INS) and the global positioning systems (GPS) are the most popular methods of navigation. However, the INS is prone to severe drift errors, especially when dealing with commercial grade systems, and GPS may not always be available, such as indoors and in downtown canyons. This paper proposes a vision based navigation system with landmark matching to improve the overall navigation solution, particularly in the absence of GPS. Landmarks of known position need to be set in advance. As the landmark appears in the visual images, it is detected through a template matching algorithm, and the vehicle’s position and azimuth angle are determined, which are then fed to the extended Kalman filter (EKF) to integrate with the INS information. This method was applied to an indoor trajectory without GPS coverage and an outdoor portion in the presence of GPS, and the resulting solution was far more accurate when compared to an INS only solution.