Pose determination method and device based on depth information, medium and electronic equipment

Abstract

The invention provides a pose determination method and device based on depth information, a storage medium and electronic equipment, and belongs to the technical field of computer vision. The pose determination method comprises the following steps: acquiring a current frame image about a scene through a camera, and acquiring depth information of the current frame image; extracting feature points from the current frame image, determining the feature points with effective depth information as three-dimensional feature points, and determining the feature points with ineffective depth informationas two-dimensional feature points; matching the two-dimensional feature points and the three-dimensional feature points with local map points of a scene respectively, wherein the first error functioncomprises a two-dimensional error term and a three-dimensional error term, and the two-dimensional error term is an error between the successfully matched two-dimensional feature point and the local map point, and the three-dimensional error term is an error between the successfully matched three-dimensional feature point and the local map point; and determining the pose parameter of the camera inthe current frame by calculating the minimum value of the first error function. According to the invention, the tracking precision in the SLAM can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, and in particular to a method for determining a pose based on depth information, a device for determining a pose based on depth information, a computer-readable storage medium, and electronic equipment. Background technique [0002] SLAM (Simultaneous Localization And Mapping, simultaneous positioning and mapping) is a method that uses terminal devices to move in the scene and collect images of the scene, and at the same time determine the pose of the device itself and model the scene. It is AR (Augmented Reality, enhanced reality), robotics and other fields. [0003] In the existing SLAM methods, most of the alignment of the visual signal unit (such as a camera) and the IMU (InertiaMeasurement Unit, inertial measurement unit) determines the pose of the camera in real time, thereby restoring the scene picture captured by the camera to a scene model. However, this method is limit...

AI Technical Summary

Problems solved by technology

[0005] The present disclosure provides a pose determination method based on depth information, a pose determination device based on depth information, a computer-readable storage medium, and an electronic device, thereby improving the low tracking accuracy of the existing SLAM method at least to a certain extent The problem

Images