Single-vidicon equivalent binocular stereoscopic vision model based foam stereoscopic feature extraction method

Abstract

The invention discloses a single-vidicon equivalent binocular stereoscopic vision model based foam stereoscopic feature extraction method. Two frame images of flowing foams, shot by one vidicon in one orientation at different moments, serve as two foam images, shot by two vidicons in different orientations at the same moment in the same scene on the basis of acquiring a foam video of the flotation production field by single vidicon and by utilizing difference information generated by two adjacent images in the video due to foam flowing, the binocular stereoscopic vision model simulating eye imaging process is equivalently built, depth information of foams in the foam image is acquired, foam stereoscopic features are further extracted, the nonferrous metal flotation working condition is effectively recognized and the optimized control of the nonferrous metal flotation process is realized.

Description

technical field [0001] The invention relates to a method for extracting foam stereoscopic features based on the principle of single-camera equivalent binocular stereo vision in the non-ferrous metal beneficiation process, specifically a method for extracting key features of flotation foam images, and belongs to the fields of image processing technology and pattern recognition. Background technique [0002] People mainly acquire, process and understand external information through the visual system. The mineral flotation production process is mainly to judge the working conditions by observing the characteristics of the foam on the surface of the flotation tank with the naked eye, and carry out the flotation process operation. At present, although researchers at home and abroad have proposed many features to describe the apparent structure of foam images, such as color, texture, size, etc., the extraction of these features is based on two-dimensional image processing methods,...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the traditional non-ferrous metal foam flotation feature extraction methods are all based on two-dimensional images, and it is difficult to fully characterize the characteristics of human stereo vision; The existing equipment provides a method for extracting foam stereoscopic features based on the principle of single-camera equivalent binocular stereo vision. The image analysis and index prediction in the selection process provide more comprehensive and effective information, combined with the three-dimensional characteristics of the flotation foam for intelligent identification of working conditions, can quickly and accurately identify the category of working conditions at the flotation site

Images