Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method of Adaptive Background Subtraction Applicable to Industrial Inspection

An adaptive background and industrial technology, applied in image enhancement, instrumentation, computing, etc., can solve problems such as unreachable, unsatisfactory, and image quality impacts of cameras, and achieve the effect of removing a small amount of noise, low image noise, and high stability

Active Publication Date: 2021-03-23
珠海博明视觉科技有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the working conditions of the camera are never ideal, such as light leakage from the black box, the camera has not reached the working temperature or exceeded the working temperature, air humidity and other environmental factors will make the dark current too high or too low, and finally affect the quality of the generated image, resulting in noise too much or the image is too dark
In the quality test items, the requirements for image clarity and authenticity are particularly strict, and this algorithm cannot meet the needs of most test items.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method of Adaptive Background Subtraction Applicable to Industrial Inspection
  • A Method of Adaptive Background Subtraction Applicable to Industrial Inspection
  • A Method of Adaptive Background Subtraction Applicable to Industrial Inspection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as figure 1 Shown, in this embodiment, the present invention comprises the following steps:

[0023] A. Input image;

[0024] B. Fit the image on a plane, regard all the pixels of the image as a set of discrete points, and then fit these discrete points to the plane, that is, find the minimum value of the sum of distances from these points to the plane;

[0025] C. Homogenize the image, by setting the minimum value as the threshold, and then remove the points greater than the threshold, so as to achieve the effect of uniform image plane;

[0026] D. Do image pyramid processing on the homogenized image. The image pyramid is a form of multi-scale representation of images. It is an effective but conceptually simple structure to explain images with multiple resolutions. The pyramid of an image It is a series of image collections arranged in a pyramid shape with gradually reduced resolution. All the images come from the same original image and are obtained through ste...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for adaptive background subtraction applicable to industrial detection, and aims to provide a method for adaptive background subtraction applicable to industrial detection in order to improve the adaptability and stability of background subtraction to the environment in industrial measurement and guarantee the precision. The method includes following steps: A, inputting an image; B, performing planar fitting on the image; C, uniformizing the image; D, performing image pyramid processing; E, searching an object; F, subtracting a background outside a circle and calculating a background mean value; G, subtracting the background mean value by the whole image; and I, outputting the image. The method is applied to the technical field of industrial intelligent manufacture.

Description

technical field [0001] The invention relates to an adaptive background subtraction method suitable for industrial detection. Background technique [0002] The basic principle of traditional background subtraction is to take a real-time image of the black box every time the camera is turned on as a dark current image. After the camera starts working, the dark current image is subtracted from the image of the object captured to obtain a denoised image. However, the working conditions of the camera are never ideal, such as light leakage from the black box, the camera has not reached the working temperature or exceeded the working temperature, air humidity and other environmental factors will make the dark current too high or too low, and finally affect the quality of the generated image, resulting in noise Too much or the image is too dark. In the quality test items, the requirements for image clarity and authenticity are particularly strict, and this algorithm cannot meet the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
Inventor 王晓城车镇兵
Owner 珠海博明视觉科技有限公司