Quick pose detection method based on geometric features of inside and outside contours of workpiece

Abstract

The invention discloses a quick pose detection method based on geometric features of inside and outside contours of a workpiece. The method comprises the following steps of (1) obtaining a workpiece image; (2) performing preprocessing operation on the obtained workpiece image; (3) performing geometric feature acquisition on the preprocessed workpiece image; and (4) performing pose identification according to the obtained geometric features. According to the method, a compartment in a closed state during transport is transformed to be in a position state that drawers in a box body are all outward through rotation, so that cargos can be conveniently taken under the condition of ensuring cargo transport safety. Compared with the prior art, the method has the advantages that the detection precision is relatively high, relatively little time is consumed, timeliness requirements of automated production can be met, the detection speed and the detection precision are better considered, and very good robustness in a practical application environment is achieved.

Description

technical field [0001] The invention relates to a fast pose detection method based on geometric features of inner and outer contours of workpieces, and belongs to the technical fields of image processing and visual target detection. Background technique [0002] At present, many workpiece pose detection methods have been proposed, mainly including detection methods based on feature matching, detection methods based on geometric parameters and detection methods based on color space. In the above method, the extraction of features has high requirements on lighting conditions, and many false features will be generated in the case of unsatisfactory lighting, and the recognition rate is low. In addition, the above methods generally need to establish a template database, and then perform complex calculations to match with known templates, which not only increases storage space, but also consumes a lot of time for matching, which often cannot meet the real-time requirements of auto...

AI Technical Summary

Problems solved by technology

In the above method, the extraction of features has high requirements on the lighting conditions. When the lighting is not ideal, many false features will be generated, and the recognition rate is low.

In addition, the above methods generally need to establish a template database, and then perform complex calculations to match with known templates, which not only increases storage space, but also consumes a lot of time for matching, which often cannot meet the real-time requirements of automated production

Images