Unlock instant, AI-driven research and patent intelligence for your innovation.
A kind of background extraction method and target discrimination method
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of background extraction and discrimination method, which is applied in the field of image processing, can solve problems such as poor applicability, inability to apply to all scenes, and inability to extract the initial background, etc., to achieve high accuracy, good applicability, and improved accuracy.
Active Publication Date: 2022-07-12
CHENGDU XGIMI TECH CO LTD
View PDF9 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] The current image processing technology will involve the need to judge whether an image contains a target, and the process of target judgment often involves background extraction and background update. The existing background extraction usually first directly extracts an image without a target as the initial background. , and then perform target discrimination on the images acquired in real time, because in many cases it is impossible to obtain images without targets or whether the acquired images contain targets, resulting in the inability to extract the initial background, poor applicability, and cannot be applied to all Scenes
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0049] like figure 1 As shown, this embodiment provides a background extraction method, including:
[0050] S1: collect several frames of images to obtain a first temperature matrix;
[0051] S2: set the first threshold T1 according to the first temperature matrix;
[0052] S3: determine whether there is an element value greater than the first threshold T1 in the first temperature matrix, if so, proceed to the next step, otherwise the obtained first temperature matrix is the background temperature matrix;
[0053] S4: Calculate the average value of all element values in the first temperature matrix that are less than the first threshold value T1;
[0054] S5: Update the element values of the first temperature matrix greater than the first threshold T1 to the average value to obtain a background temperature matrix;
[0055] Among them, one temperature matrix corresponds to one frame of image, and the element values in the temperature matrix are the temperature values...
Embodiment 2
[0070] like image 3 As shown, a target discrimination method that can use the background extraction method provided in Embodiment 1 to obtain the initial background temperature matrix in the target discrimination process, including:
[0071] P1: Extract the initial background temperature matrix;
[0072] P2: Collect real-time images and obtain real-time image temperature matrix;
[0073] P3: Calculate the difference between the real-time image temperature matrix and the initial background temperature matrix to obtain the foreground temperature matrix;
[0074] P4: Compare the element values in the foreground temperature matrix with the second threshold value T2 respectively, and determine the pixel point corresponding to the element value greater than the second threshold value T2 as the target point, otherwise it is determined as the background point, and then continue to carry out the real-time acquisition image, obtain a real-time image temperature matrix for this step...
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
Login to View More
Abstract
The invention discloses a background extraction method, comprising: collecting several frames of images to obtain a first temperature matrix; setting a first threshold T1 according to the first temperature matrix; judging whether there is an element value greater than the first threshold T1 in the first temperature matrix, If it exists, go to the next step, otherwise the obtained first temperature matrix is the background temperature matrix; average all the element values in the first temperature matrix that are less than the first threshold T1; The element values are updated to the average value to obtain a background temperature matrix; wherein, one temperature matrix corresponds to one frame of image, and the element values in the temperature matrix are the temperature values of different pixel points in the image respectively. In the present invention, the background points behind the target point and the directly acquired background points are respectively assigned, so that the extracted background has higher accuracy.
Description
technical field [0001] The invention relates to the field of image processing, in particular to a background extraction method and a target detection method. Background technique [0002] Image processing refers to the technology of using computers to analyze images to achieve the desired results, also known as image processing. Image processing generally refers to digital imageprocessing. Digital image refers to the use of industrial cameras, video cameras, scanners and other equipment to obtain a large image. The elements of the array become pixels, also called pixel points, and their values are called gray values. In the computer, images can be divided into binary images, gray images, index images and truecolor RGB images. [0003] The current image processing technology involves the need to judge whether an image contains a target, and the process of target judgment often involves background extraction and background update. The existing background extraction usually...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More