Image detection method of thick line type cross ring mark

An image detection and thick-line technology, which is applied in image analysis, image data processing, instruments, etc., can solve problems such as detection methods of thick-line cross circle marks that have not yet been seen.

Active Publication Date: 2013-07-10
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing detection methods, the marking symbols processed are generally single cir...

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
  • Image detection method of thick line type cross ring mark
  • Image detection method of thick line type cross ring mark
  • Image detection method of thick line type cross ring mark

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0168] Example 1: if Figure 5 As shown, after the thick line is single-pixelized, there are two intersection points on one side of the detection frame, and the distance between the two intersection points and the central axis is different. After turning into a single-pixel straight line according to step 3, there is an intersection point with each side of the detection frame. For example, the solid point on the left of the upper line is the selected reserved intersection point, and the hollow point on the right is the elimination point, and then identify it as the cross center point according to step 4.1. , and finally detect the cross circle mark according to step five.

example 2

[0169] Example 2: if Image 6 As shown, after the thick line is single-pixelized, there are two intersection points on the four sides of the detection frame, and the distance between the two intersection points and the central axis is the same. According to step 3, it becomes a single-pixel straight line and there are two intersections with each side of the detection frame. According to step 4, 2 is identified as the cross center point, and finally the cross circle mark is detected according to step 5.

example 3

[0170] Example 3: if Figure 7 As shown, after the thick line is single-pixelized, the distance between the intersection point of the detection frame in the horizontal direction and the central axis is the same, and the distance between the two intersection points in the vertical direction is different from the central axis. After turning into a single-pixel straight line according to 2 in step 3, there are two intersection points with the horizontal side of the detection frame, and one intersection point with the vertical side of the detection frame (the solid point is the selected reserved intersection point, and the hollow point is the elimination point), press step 3 2. The detected pixel identified as the center of the detection frame is not the center point of the cross, which is correct.

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 provides an image detection method of a thick line type cross ring mark. The method includes the following steps: firstly conducting single pixelate on linear lines with different thicknesses in a mark; then using a detection frame to identify central points of all the cross intersections, namely, the cross intersection central points; finally according to number ratio of black pixels and white pixels inside the detection frame, selecting a cross ring mark, and therefore deciding an accurate position of a central point of the cross ring mark. The image detection method of the thick line type cross ring mark is not influenced by variation of thicknesses of lines after imaging of the marked lines, almost not influenced by illumination variation, has certain robustness to noise, and achieves good detection effect when horizontal shift, revolving and zooming of a detected object after imaging happen.

Description

technical field [0001] The invention relates to an image detection technology, in particular to an automatic image detection of a thick-line cross-circle mark in a video image of a moving object. Background technique [0002] The detection and tracking of moving objects has important research value in science and engineering, and has broad application prospects in many fields such as intelligent monitoring, intelligent robots, human-computer interaction, medical diagnosis, video compression, and military affairs. Image detection is one of the key technologies. [0003] The current motion analysis methods are roughly divided into three categories: frequency domain-based methods, feature-based methods and pixel-based methods. The method based on the frequency domain performs Fourier transform on the collected image sequence, and calculates the phase angle difference between adjacent frames by calculating the phase angle difference between adjacent frames through the character...

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
IPC IPC(8): G06T7/00G06T7/20
Inventor 齐敏王强樊养余侯晓琴王毅吕国云李珂
Owner NORTHWESTERN POLYTECHNICAL UNIV
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