Tightly-Coupled GNSS/Vision Using a Sky-Pointing Camera for Vehicle Navigation in Urban Areas

Abstract

This paper presents a method of fusing the ego-motion of a robot or a land vehicle estimated from an upward-facing camera with Global Navigation Satellite System (GNSS) signals for navigation purposes in urban environments. A sky-pointing camera is mounted on the top of a car and synchronized with a GNSS receiver. The advantages of this configuration are two-fold: firstly, for the GNSS signals, the upward-facing camera will be used to classify the acquired images into sky and non-sky (also known as segmentation). A satellite falling into the non-sky areas (e.g., buildings, trees) will be rejected and not considered for the final position solution computation. Secondly, the sky-pointing camera (with a field of view of about 90 degrees) is helpful for urban area ego-motion estimation in the sense that it does not see most of the moving objects (e.g., pedestrians, cars) and thus is able to estimate the ego-motion with fewer outliers than is typical with a forward-facing camera. The GNSS and visual information systems are tightly-coupled in a Kalman filter for the final position solution. Experimental results demonstrate the ability of the system to provide satisfactory navigation solutions and better accuracy than the GNSS-only and the loosely-coupled GNSS/vision, 20 percent and 82 percent (in the worst case) respectively, in a deep urban canyon, even in conditions with fewer than four GNSS satellites.

Tightly Coupled GNSS/INS Integration via Factor Graph and Aided by Fish-Eye Camera

“…NLOS receptions could be detected with the detected sky views and decent improvements were obtained. Similar researches [43,44] were conducted recently and the improved GNSS positioning was integrated with visual simultaneous localization and mapping [45]. However, these methods tended to exclude the NLOS receptions from further GNSS positioning which was not applicable in the dense urban areas.…”

Integration of Low-Cost GNSS and Monocular Cameras for Simultaneous Localization and Mapping

“…In a tightly coupled visual-GNSS navigation system, the carrier phase or pseudo-range is measured directly and is fused with visual information. In the tightly coupled system, even if only one satellite is tracked, the system can still make use of the GNSS information [ 34 , 35 ]. In a loosely coupled system, the position calculated by the GNSS receiver is fused with visual measurements.…”

Tackling the Scale Factor Issue in a Monocular Visual Odometry Using a 3D City Model

“…The global scale factor is thus computed as: frames. The relative scale factor is estimated based in the actual and previous estimated platform position (Gakne and O'Keefe, 2018). This is given as:…”

“…An experiment consisting on a monocular system rigidly mounted on the top of the car driven in downtown Calgary, AB, Canada was conducted to test this other method (and is the same as used in Gakne and O'Keefe (2018)). A sky-pointing camera and a reference system (a SPAN LCI from NovAtel) are both mounted on the vehicle roof as depicted in Figure 8.…”