Stereoscopic vision identification method of non-smooth sphere-like target, positioning clamping detection device and application thereof

Abstract

The invention discloses a stereoscopic vision identification method of a non-smooth sphere-like target, a positioning clamping detection device and an application thereof. According to the method, through camera calibration, monocular correction, binocular correction, segmentation of a non-smooth sphere target and background and binocular distance measurement, the three-dimensional pose of the non-smooth sphere target is calculated and fitted. The device comprises a visual inspection mechanism, an industrial personal computer and a clamping mechanism. The visual detection mechanism identifiesand detects the non-smooth sphere target by adopting the three-dimensional visual identification method to obtain the positioning information of the non-smooth sphere target, and then transmits the positioning information to the industrial personal computer, so that the non-smooth sphere target is clamped by the clamping mechanism. The stereoscopic vision recognition method is high in precision, and the positioning clamping detection device is stable in clamping, has a fault-tolerant function and is suitable for positioning and clamping a target in a complex environment.

Description

technical field [0001] The invention relates to the technical field of detection, in particular to a stereoscopic vision recognition method of a non-smooth spherical object, a positioning and clamping detection device and its application. Background technique [0002] At present, in engineering, non-smooth, irregular and complex objects such as spheres are mainly classified, positioned and sorted manually by visual inspection. But artificial classification is imprecise, and location is inaccurate, and sorting labor intensity is big, and the thorn of non-smooth spheroid sometimes also can injure people's skin as pineapple fruit surface. Vision robots can replace manual work, and stereo vision has the advantage of detecting three-dimensional objects, but there are still problems in vision positioning and mechanism clamping. When the target is a biological flexible body, the mechanism clamping the flexible body may cause the flexible body to deform under force; when the target...

AI Technical Summary

Problems solved by technology

However, manual classification is imprecise, positioning is inaccurate, sorting labor intensity is high, and sometimes non-smooth spheroids such as thorns on the surface of pineapple fruit can also hurt people's skin

Vision robots can replace manual operations, and stereo vision has the advantage of detecting three-dimensional objects, but there are still problems in vision positioning and mechanism clamping

When the target is a biological flexible body, the mechanism clamping the flexible body may cause the flexible body to deform under force; when the target is an irregularly shaped fruit, the mechanism needs to distinguish the top and bottom of the fruit for positioning. Visual positioning and three-dimensional reconstruction are more difficult, which makes it difficult for the mechanism to accurately clamp irregularly shaped targets

Images