Target object positioning method and device and readable storage medium

Abstract

The embodiment of the invention provides a target object positioning method and device and a readable storage medium. The method comprises the following steps: obtaining a current video frame image ofthe surrounding environment of the target object from camera equipment, inputting the current video frame image into a target neural network; obtaining a first descriptor of the current video frame image; according to the first descriptor, determining a preset number of second descriptors from the visual map, visual map, determining a target key video frame image associated with the second descriptor, determining a first pose associated with the target key video frame image; and according to the first pose associated with the target key video frame image and the laser point cloud map, generating a simulation laser point cloud corresponding to the first pose, and according to the first pose associated with the target key video frame image and the simulation laser point cloud, determining the current pose of the target object. By performing coarse positioning and fine positioning on the current pose of the target object, the positioning precision of the current pose of the target objectis improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a target object positioning method, device and readable storage medium. Background technique [0002] With the continuous development of science and technology, the application of artificial intelligence in the fields of robots, drones, and unmanned driving is becoming more and more extensive. In order to ensure that robots, unmanned aerial vehicles, and unmanned vehicles can adapt to different and complex environments, higher requirements are put forward for the intelligence of robots, unmanned aerial vehicles, and unmanned vehicles. The autonomous navigation and positioning technology of robots, drones, and unmanned vehicles is the core, and the positioning is the primary problem to be solved, which has attracted the eager attention of many researchers. [0003] At present, the visual positioning method is adopted, and the visual positioning scheme is to extra...

AI Technical Summary

Problems solved by technology

[0004] However, the positioning accuracy of the current visual positioning method is not high enough. Therefore, how to improve the positioning accuracy of the target object needs to be solved urgently.

Images