Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Gray scale and gradient segmentation-based infrared target detection method

A technology of infrared targets and detection methods, applied in image analysis, image data processing, instruments, etc., can solve the problems of lower target detection accuracy, poor target detection ability, poor scene adaptability, etc., and achieve easy real-time implementation and image segmentation accuracy The effect of high and small algorithm calculation

Active Publication Date: 2016-03-23
NANJING LES ELECTRONICS EQUIP CO LTD
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing target detection technology has the following disadvantages: (1) Most detection algorithms have poor scene adaptability, and if the scene changes greatly, the accuracy of target detection will be reduced; (2) The target detection ability in complex scenes is poor; (3) Most algorithms use Single feature detection, poor robustness

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
  • Gray scale and gradient segmentation-based infrared target detection method
  • Gray scale and gradient segmentation-based infrared target detection method
  • Gray scale and gradient segmentation-based infrared target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] This embodiment discloses an infrared target detection method based on grayscale and gradient segmentation, which includes the following steps:

[0040] (1) Using the original image F org Compute the gradient image

[0041] (2 pairs Perform non-maximum suppression to obtain an image

[0042] (3) use Perform edge connection and edge closure judgments, and calculate the candidate target area Pos 1 ;

[0043] (4) According to Pos 1 Select a partial image F loc , for F loc Carry out segmentation to obtain the candidate target area Pos 2 ;

[0044] (5) According to Pos=Pos 1 ∩ Pos 2 Calculate the optimal target area Pos.

[0045] In step (1), use the Sobel operator to calculate the gradient image

[0046] In step (2), Perform "non-maximum suppression" and define the gradient direction as the AA connection direction (ie AA-data-AA), the BB connection direction (ie BB-data-BB), and the CC connection direction (ie CC-data-CC ), DD connection direction (tha...

Embodiment 2

[0054] combine figure 1 , the following examples are used to illustrate the infrared target detection method based on grayscale and gradient segmentation of the present invention. The number of pixels of the infrared image is 640×512, and the frame rate is 50HZ. The digital signal is transmitted to the special image processing board of FPGA+DSP architecture through optical fiber, and the infrared target detection method based on grayscale and gradient segmentation is realized in the DSP processor, and the processing time is less than 20ms, which meets the needs of real-time processing. The specific implementation steps are as follows:

[0055] (1) Get the original image F org , use the Sobel operator to calculate the gradient image

[0056] f org It is a 14-bit digital image, and the gradient image is obtained through the Sobel operator

[0057] (2 pairs Perform non-maximum suppression to obtain an image

[0058] (3) Calculate the closure degree in the row directi...

Embodiment 3

[0070] In Figure 2, Figure 2a represents the original image, Figure 2b Indicates the gradient segmentation result, Figure 2c is the grayscale segmentation result, Figure 2d for the final test result. The images show that the infrared target detection method proposed by the present invention based on gray scale and gradient segmentation has high target detection accuracy.

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 gray scale and gradient segmentation-based infrared target detection method. The method comprises the following steps: 1) calculating a gradient image Phi(x, y) by utilizing an original image Forg; 2) carrying out non-maximum value inhibition on the Phi(x, y) to obtain an image Phi1(x, y); 3) carrying out edge linking and edge closing judgement by utilizing the Phi1(x, y), and calculating a candidate target area Pos1; 4) selecting a local image Floc according to the Pos1 and segmenting the Floc to obtain a candidate target area Pos2; and 5) calculating an optimum target area Pos according to a formula (as shown in the specification).

Description

technical field [0001] The present invention relates to the field of infrared image processing, in particular to an infrared target detection method based on grayscale and gradient segmentation suitable for hardware real-time implementation Background technique [0002] As an important supplementary method of radar system, infrared imaging has the characteristics of passive detection, not easy to be found, and all-weather work, and has been widely used in military and civilian fields. In recent years, infrared imaging detection has become the focus and focus of research by scholars at home and abroad, and many valuable detection methods have been proposed. Zhang Qiang et al. proposed infrared weak and small target segmentation based on local maxima, and enhanced processing of the image to be detected through Gaussian templates; in view of the shortcomings of the traditional filtering method in fixed-size filter check weak and small target detection, Gong Junliang proposed a ...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T2207/10048
Inventor 白俊奇杜瀚宇
Owner NANJING LES ELECTRONICS EQUIP CO LTD
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com