Visual-inertial UAV attitude estimation using urban scene regularities

Abstract

Abstract-We present a drift-free attitude estimation method that uses image line segments for the correction of accumulated errors in integrated gyro rates when an unmanned aerial vehicle (UAV) operates in urban areas. Since man-made environments generally exhibit strong regularity in structure, a set of line segments that are either parallel or orthogonal to the gravitational direction can provide visual measurements for the absolute attitude from a calibrated camera.Line segments are robustly classified with the assumption that a single vertical vanishing point or multiple horizontal vanishing points exist. In the fusion with gyro angles, we introduce a new Kalman update step that directly uses line segments rather than vanishing points. The simulation and experiment based on urban images at distant views are provided to demonstrate that our method can serve as a robust visual attitude sensor for aerial robot navigation.

Indoor Manhattan spatial layout recovery from monocular videos via line matching

“…The rotation matrix representing the orientation of the frame of reference of the first camera with respect to the second one is denoted by R. Previous work has shown how to reconstruct the orientation of a camera from a single picture of a Manhattan world, using the location of the three vanishing points of the visible lines [31]. This estimation can be made more robust by measuring the gravity vector using a 3-axis accelerometer, a sensor that is present in any modern smartphones [32]. We will assume that the characteristic calibration matrices K 1 , K 2 of the cameras have been obtained offline, and that the orientation of each cameras with respect to the canonical reference system ( n 1 , n 2 , n 3 ) has been estimated (and, consequently, that R is known).…”

“…Following [32], we assume that one canonical direction is aligned with the gravity vector v Z , which can be found using the smartphone's accelerometers. The segments in the image that converge towards the associated vanishing point are removed.…”

Vision Based UAV Attitude Estimation: Progress and Insights

“…All vanishing point can be considered in a Gaussian sphere representation even those at infinity. For more details on representing vanishing points on a Gaussian sphere from a calibrated camera (see figure (6)), the reader is referred to [33,34,8]. Figure 6: Gaussian Sphere adapted from [34] The Gaussian sphere is a unit sphere which shares the same optical center of the pinhole camera.…”

“…In [8], their approach is based on vanishing points detection using raw line measurements directly to refine the attitude. They do not require any line tracking.…”

“…For example in [7], using an EFK, the candidate horizon lines are propagated and tracked through successive image frames, with statistically unlikely horizon candidates eliminated. In [8], they followed the EKF framework to combine inertial and visual sensor for real time attitude estimation. They have designed a KF for image line measurements.…”