Method and system for positioning a sphere in an image

Abstract

The invention discloses a method and system for positioning sphere in an image. The method comprises steps of: extracting, by converting the color space of a captured image and binarizing the captured image, the contours of a connected domain in the obtained binarized image; eliminating noncircular contours by using the geometric feature of a circle, acquiring the fitted ellipses of respective remaining contours, and screening out the contour of a circle, corresponding to the sphere, in the image according to the eccentricity of the fitted ellipses of the contours; and further positioning the sphere in the image according to the selected contours. The sphere positioning method and system firstly eliminate the contours which do not satisfy requirements and the non-circular contours by using the geometrical feature of the circle so as to avoid ellipse fitting operations for the irrelevant contours such as the non-circular contours in the subsequent ellipse fitting operation of the contours, thereby reducing computational amount, computational overhead, and memory consumption.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for locating a sphere in an image. Background technique [0002] As an isotropically symmetrical object, the projection imaging of the sphere in the plane image is also a figure with isotropically symmetrical geometric properties. Based on this feature of the sphere, in more and more applications, such as drones Positioning, all use the sphere to position in the image. [0003] In the prior art, the Hough circle transform is often used in the algorithm for recognizing circles in images. It uses the "voting" principle in the parameter space under the polar coordinate system to decide whether a pixel is located in a circle or not. On the circle, the pixel point with the highest voting value is finally selected as the point where the center of the circle is located. However, this method has the following disadvantages: In the case of unknown circle rad...

AI Technical Summary

Problems solved by technology

However, this method has the following disadvantages: In the case of unknown circle radius, this method needs to traverse the pixels in the image to obtain a voting map about the coordinates of the center of the circle and the size of the radius, so a large number of pixel calculations are required. A large amount will consume memory resources

Images