Flotation broken froth detection method based on rapid retina feature point matching and multi-scale segmentation

Abstract

The invention relates to a flotation broken froth detection method based on rapid retina feature point matching and multi-scale segmentation. The flotation broken froth detection method comprises the following steps: firstly, collecting two continuous frames of flotation froth images, carrying out NSST decomposition on the two frames of froth images, carrying out froth edge detection and fusion on a multi-scale high-frequency sub-band, and extracting a central point of each segmented froth in a next frame of image; secondly, carrying out feature point description and matching on the two frames of images by adopting an improved FREAK sampling model, and extracting candidate broken froths according to the distribution density of matching points around the previous frame of segmented froths; finally, mapping the central point of each segmented froth in the next frame of image into the previous frame of segmented image, counting the central point number contained in the candidate broken froths; and judging the candidate broken froths containing a plurality of center points or without center points as broken froths. For the flotation broken froth detection method based on rapid retina feature point matching and multi-scale segmentation, the improved FREAK algorithm is high in matching effect and real-time performance, and the broken froth detection method is less influenced by illumination and motion changes, and the broken froths can be effectively extracted.

Description

technical field [0001] The invention relates to the technical field of flotation bubble detection, in particular to a flotation broken bubble detection method based on fast retinal feature point matching and multi-scale segmentation. Background technique [0002] The stability of flotation bubbles affects the performance of production indicators such as recovery rate and concentrate grade. Accurately extracting broken bubbles is crucial to the establishment of a prediction model for flotation production indicators, but bubbles are constantly changing, such as displacement, deformation, and rupture. Moreover, the collected images are affected by light, which makes it difficult to detect broken bubbles. At present, there are mainly two detection methods at home and abroad: frame difference and feature point matching: the frame difference method first performs displacement correction on adjacent image frames and then calculates the difference, judges the highlighted area in the...

AI Technical Summary

Problems solved by technology

[0002] The stability of flotation bubbles affects the performance of production indicators such as recovery rate and concentrate grade. Accurately extracting broken bubbles is crucial to the establishment of a prediction model for flotation production indicators, but bubbles are constantly changing, such as displacement, deformation, and rupture. Moreover, the collected images are affected by light, which makes it difficult to detect broken bubbles.

At present, there are mainly two detection methods at home and abroad: frame difference and feature point matching: the frame difference method first performs displacement correction on adjacent image frames and then calculates the difference, judges the highlighted area in the difference image as the corresponding collapse bubble, and detects The accuracy is affected by the bubble deformation and illumination, and the bright spots and highlighted edges of deformed bubbles are easy to be misdetected; the feature point matching method is to apply the SIFT matching algorithm to the broken bubble detection, and estimate the broken rate through the matching results of two frames of images, but The accuracy is limited by the selection of the judgment threshold, there is a certain error, and the real-time performance of the SIFT algorithm is not strong

[0003] In 2012, Alahi et al. proposed the Fast Retinal Keypoint (FREAK) algorithm at the CVPR conference, using a binary descriptor similar to the human retina. The advantages of this algorithm's high positioning accuracy and fast calculation make it widely used in occasions with high real-time requirements. application, FREAK can solve the real-time deficiencies of SIFT, but the accuracy of the feature point matching method is not high

Images