Pose estimation method and device based on binocular vision inertial odometer and processor

Abstract

The invention provides a pose estimation method and device based on a binocular vision inertial odometer, a storage medium and a processor. The method comprises steps: obtaining a first attitude angle, a second attitude angle and displacement, wherein the first attitude angle is an attitude angle of a carrier acquired through an inertia measurement unit, and the second attitude angle and displacement are acquired from multiple frames of images corresponding to the carrier acquired by the binocular vision odometer; obtaining a weighted average value of the first attitude angle and the second attitude angle, wherein the weighted average value is a fusion attitude angle of the carrier; and updating the displacement according to the fusion attitude angle. The attitude angles acquired by the inertial measurement unit and the binocular vision odometer are fused, so that the robustness of the fusion system is improved, the operation time of the fusion algorithm is shortened, the fusion algorithm is more flexible to debug, the precision of the attitude angles of the visual odometer is obviously improved, and the positioning precision of a pure visual positioning algorithm is improved through fusion of the two.

Description

technical field [0001] The present application relates to the field of robotics, in particular, to a method, device, storage medium and processor for estimating pose based on binocular visual-inertial odometer. Background technique [0002] At present, with the vigorous development of miniaturized, low-power, and economical mobile robots and drones, it is urgent to solve the realization of positioning functions under low-power platforms. Visual positioning methods, as a way of autonomous positioning, can Effectively solve the error caused by the slipping of wheeled odometers in harsh environments (such as construction sites). At the same time, in the development of construction robots, there are some wheels or motion models that are difficult to model. At this time, only visual odometry can be used to achieve rough positioning. Features. [0003] The traditional visual positioning algorithm based on nonlinear optimization requires too much computing resources and pose outpu...

AI Technical Summary

Problems solved by technology

[0006] The main purpose of this application is to provide a method, device, storage medium and processor for estimating pose based on binocular visual inertial odometer, so as to solve the problem of low positioning accuracy of visual positioning algorithm in the prior art

Images