Focusing method based on quantum particle swarm optimization algorithm

Abstract

The invention provides a focusing method based on a quantum particle swarm optimization algorithm for focusing an image during image shooting. The method comprises the following steps: step 1: using aplurality of particles located in a three-dimensional space to respectively represent gray values of pixel points in the image, and randomly setting the gray values represented by the particles; step2, performing average distribution on the initial positions of the particles in a quantum particle swarm according to a position formula; step 3, calculating fitness values of the particles by usingan average gray value variance function of a foreground image and a background image of the image, and obtaining an optimal segmentation threshold by using the quantum particle swarm optimization algorithm in combination with a domain search method; step 4, segmenting the image into the foreground image and the background image according to the optimal segmentation threshold; step 5, selecting a focusing area according to the center of gravity of the gray value of the foreground image; and step 6, using a gray level difference method as an image definition evaluation function, and determiningthe position of a lens according to a function value calculated by the image definition evaluation function so as to complete the focusing.

Description

technical field [0001] The invention relates to the technical field of image focusing, in particular to a focusing method based on a quantum particle swarm optimization algorithm. Background technique [0002] Focusing mainly includes three basic parts, namely focusing area selection, image definition evaluation, and search algorithm. Traditional image focusing techniques include ranging method, focus detection method, and phase focusing method. Commonly used focusing area selection algorithms include center windowing. , multi-point windowing, non-uniform sampling windowing, pupil tracking method and skin detection method, the central windowing does not have the ability to adapt to the imaging position of the main target; multi-point windowing introduces more background, and the calculation amount is larger , the focusing speed slows down; non-uniform sampling windowing also does not have the ability to adapt, and a large number of floating-point calculations affect the focu...

AI Technical Summary

Problems solved by technology

[0002] Focusing mainly includes three basic parts, namely focusing area selection, image definition evaluation, and search algorithm. Traditional image focusing techniques include ranging method, focus detection method, and phase focusing method. Commonly used focusing area selection algorithms include center windowing. , multi-point windowing, non-uniform sampling windowing, pupil tracking method and skin detection method, center windowing does not have the ability to adapt to the imaging position of the main target; multi-point windowing introduces more background, and the calculation amount is larger , the focusing speed slows down; non-uniform sampling windowing also does not have adaptive capabilities, and a large number of floating-point operations affect the focusing speed; the pupil tracking rule requires that the pupil information of the photographer must be obtained, and the scope of use of skin detection is even smaller.

Images