Real-time pose determination method, device and electronic equipment

Abstract

Embodiments of the present invention provide a real-time pose determination method, device and electronic equipment, which relate to the field of image technology. Wherein, the above real-time pose determination method estimates the output pose information when the unmanned device collects the image frame to be estimated according to the obtained image frame to be estimated and the map data; wherein, the map data is based on the acquisition time A map created by the historical image frame earlier than the image frame to be estimated and the positioning data of the historical image frame; according to the geographic reference model, converting the output pose information into real-time pose information in the world coordinate system; Wherein, the geographic reference model is a model used for data conversion between the visual coordinate system and the world coordinate system. Thereby improving the error caused by map drift and improving the accuracy of the obtained pose information.

Description

technical field [0001] The present invention relates to the field of image technology, in particular to a real-time pose determination method, device and electronic equipment. Background technique [0002] The emergence of simultaneous localization and mapping (SLAM) technology enables unmanned equipment (drones, robots, etc.) to achieve autonomous navigation in unknown environments, and further promotes the development of unmanned equipment. [0003] At present, monocular vision SLAM is widely used. It tracks each frame of image collected and then creates a map to facilitate pose determination. However, the map created based on the collected images has the problem of data drift. At the same time, the location information of the created map using monocular vision SLAM is relative coordinates rather than absolute coordinates in real space, which leads to The pose information determined by this map is not accurate enough. Contents of the invention [0004] In view of this,...

AI Technical Summary

Problems solved by technology

However, the map created based on the collected images has the problem of data drift. At the same time, the location information of the created map using monocular vision SLAM is relative coordinates rather than absolute coordinates in the real space, which leads to The pose information determined by the map is not accurate enough

Images