A Cloth Positioning Method in Complicated Environment

Abstract

The invention discloses a cloth surface positioning method in a complex environment, comprising: step 1, obtaining real-time cloth information of a loom through a built platform; step 2, adopting Gaussian filtering to eliminate the influence of noise; step 3, designing a new maximum The diffuse reflection chromaticity estimation formula eliminates the highlight problem caused by irregular lighting; step 4, extracts the edge information of the cloth, obtains the optical flow field, improves the instability of the optical flow, and proposes a new multi-frame optical flow fusion algorithm, combining edge information and optical flow The flow field information realizes the movement judgment and accurate positioning of the cloth surface. Obtain real-time images of loom cloth, and perform Gaussian filtering on the obtained images to eliminate noise caused by camera factors. This method removes overexposure and other problems in irregular environments, and at the same time improves the optical flow method combined with edge information to achieve motion judgment and accurate positioning of the cloth surface.

Description

technical field [0001] The invention loads an industrial camera module on a double-needle bed loom, and proposes a brand-new algorithm and platform for detecting cloth surface for intelligent production. A new algorithm for eliminating highlights is proposed to eliminate the overexposure problem in complex working environments, and at the same time, the improved optical flow algorithm combined with the edge algorithm is used to locate the cloth surface. Background technique [0002] With the development of technology, the scale of the textile industry has grown rapidly, and it has become an important economic pillar of my country's basic industry. With the advent of the Industry 4.0 era, the transformation and upgrading of traditional industries is imperative. Accurate positioning of the cloth surface can improve the operation accuracy of automation equipment, and can reduce the hardware cost of artificial intelligent detection equipment, thereby accelerating industrial tra...

AI Technical Summary

Problems solved by technology

[0003] In view of the different types of traditional looms and advanced looms, the production environment is not standardized, the lighting is not uniform, and equipment installation is not uniform, which causes inaccurate positioning, the invention uses optical flow combined with edge information to accurately locate the cloth surface

Images