Cabin image instance segmentation method and device, electronic equipment and storage medium

Abstract

The invention discloses a cabin image instance segmentation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-assembled cabin image which comprises a first RGB image and a first depth image, inputting the to-be-assembled cabin image to a trained image instance segmentation model, obtaining extraction results of areas corresponding to different cabin sections in the to-be-assembled cabin section image; wherein the trained image instance segmentation model is obtained by training different cabin images and real mask images corresponding to the different cabin images. According to the method, through the image instance segmentation model, the recognition robustness of the corresponding area of the cabin in the image and the recognition precision of the cabin in complex interference environments such as high brightness and high darkness are greatly improved, coarse positioning of the outer contour of the cabin is realized, and the automation level of cabin pose measurement is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method, a device, an electronic device and a storage medium for segmenting cabin image instances. Background technique [0002] The production capacity of large-scale ships, aircraft, rockets and missiles, etc., reflects the comprehensive strength of the country's high-end equipment manufacturing industry, and is also an important manifestation of comprehensive national strength. These large-scale equipment are generally broken down into multiple cabins for modular production, and finally assembled through docking. The assembly technology of large compartments largely determines the manufacturing cost, production cycle time and final quality of these systems. The docking technology of large cabins based on multi-robot coordination has been gradually applied to the assembly of large cabins in shipbuilding, aerospace and weapon manufacturing, which greatly improves the assembl...

AI Technical Summary

Problems solved by technology

However, the visual recognition system based on RGB images generated by traditional visual sensors is easily affected by irrelevant factors such as target background changes and illumination changes, resulting in low recognition accuracy.

Images