A simple target recognition method based on yuv color space

A simple and targeted technology, applied in the field of simple target recognition based on YUV color space, it can solve the problems of complex operation, high requirements on target information, calibration method, and difficulty in implementation, and achieves rapid calibration, simplified target calibration algorithm, and satisfactory accuracy. Effect

Active Publication Date: 2022-02-11
ROCKET FORCE UNIV OF ENG
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no general feature calibration method that can solve the problem of target calibration in various types of images
Among them, the feature calibration method of contour and shape is based on image color information, and this kind of method has high requirements on target information and calibration method, it is difficult to realize, the operation is complicated, and it is not convenient to perform feature calibration on targets with simple color features

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 simple target recognition method based on yuv color space
  • A simple target recognition method based on yuv color space
  • A simple target recognition method based on yuv color space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 2 The sample pattern of , the front of the clothes with blue background color is "Superman logo", that is, there is a red S in the red polygonal frame, the fill color in the polygonal frame is yellow, the target pattern is the polygonal frame and the S in the polygonal frame, then The color feature of the target pattern is red. In the VC++ software, read the sample pattern to obtain the Y, U, and V component values ​​of all pixels in the sample pattern, and generate a UV distribution map as shown in image 3 . Then perform coarse calibration and fine calibration respectively, the specific process is as follows:

[0031] Coarse calibration scheme: Find the pixel point area representing the target pattern feature on the generated UV distribution map, click the feature area with the mouse, and compare the U and V component values ​​of the pixel points containing the target feature area point by point to obtain the U and V component values The maximum and ...

Embodiment 2

[0038] Applying the identification method of the present invention to the field of robots can enable the robot to acquire the ability to distinguish colors, thereby laying the foundation for realizing higher intelligence of the robot.

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 simple target recognition method based on YUV color space, belonging to the technical field of image processing. Based on the YUV color space distribution information of the target image, the pixel geometric configuration and the pixel geometric position relationship are used to simplify the target calibration algorithm. When it is applied to identify targets with simple color features, it can quickly perform calibration and recognition, and the recognition accuracy can be achieved. Meet the use requirements.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a simple target recognition method based on a YUV color space. Background technique [0002] In the field of robot vision, the feature calibration of the target image mainly includes methods such as color, contour and shape. However, there is no general feature labeling method that can solve the problem of object labeling in various types of images. Among them, the feature calibration method of contour and shape is based on image color information, and this kind of method has high requirements on target information and calibration method, it is difficult to realize, the operation is complicated, and it is not convenient to perform feature calibration on targets with simple color features. Contents of the invention [0003] In order to solve the defects in the above-mentioned prior art, the object of the present invention is to provide a simple target recog...

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): G06V20/20G06V10/56
CPCG06V20/20G06V10/56G06V2201/07
Inventor 宋海涛张合新姚二亮田琦王夏复夏朝辉郭杨
Owner ROCKET FORCE UNIV OF ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap