Geometric matching in visual navigation systems

Abstract

A first map comprising local features and 3D locations of the local features is generated, the local features comprising visible features in a current image and a corresponding set of covisible features. A second map comprising prior features and 3D locations of the prior features may be determined, where each prior feature: was first imaged at a time prior to the first imaging of any of the localfeatures, and lies within a threshold distance of at least one local feature. A first subset comprising previously imaged local features in the first map and a corresponding second subset of the prior features in the second map is determined by comparing the first and second maps, where each local feature in the first subset corresponds to a distinct prior feature in the second subset. A transformation mapping a subset of local features to a subset of prior features is determined.

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of and priority to U.S. Non-Provisional Application Serial No. 15 / 178,505, filed June 9, 2016, entitled "Geometric Matching In Visual Navigation Systems." The above applications are all assigned to the assignee of the present case, and all of them are incorporated herein by reference. technical field [0003] The subject matter disclosed herein relates generally to visual navigation systems, and in particular, to systems and methods for maintaining accuracy and precision in visual navigation systems. Background technique [0004] Smartphones and other mobile devices are increasingly used for visual navigation. In a visual navigation (VN) system (VNS), visual-inertial odometry (VIO) or vision-based localization (VBP) system (collectively referred to herein as "VNS") images captured by cameras are combined with other sensors or wireless measurements for Determine and / or estimate the...

AI Technical Summary

Problems solved by technology

However, as the length of time increases, the search space for feature points that need to be visually matched to determine whether a loop closure event has occurred increases significantly, thus limiting the applicability

Furthermore, because the appearance of features can change based on viewpoint and / or lighting, loop closure based solely on vision- or appearance-based feature matching can be challenging.

Images