Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Weak and small target detection method based on Gaussian Markov random field motion direction estimation

A technology of Gauss Markov random field and direction of motion, applied in computing, computer components, instruments, etc., can solve problems such as small size and difficulty in detecting small targets, so as to ensure accuracy, improve overall detection rate, and speed up calculation The effect of the process

Active Publication Date: 2022-03-08
INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The detection of infrared weak and small target images is widely used in science and technology, but due to the influence of atmospheric radiation, operating distance, photoelectric interference and other factors, the target is small in size on the image, showing point shape, without any contour texture features, and sometimes It will be submerged in the complex background, heavy noise, clutter, etc. will also affect the judgment of the algorithm, making it very difficult to detect small targets

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
  • Weak and small target detection method based on Gaussian Markov random field motion direction estimation
  • Weak and small target detection method based on Gaussian Markov random field motion direction estimation
  • Weak and small target detection method based on Gaussian Markov random field motion direction estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] like figure 1 As shown, the present invention provides a method for detecting weak and small targets based on Gauss Markov random field motion direction estimation, comprising the following steps:

[0035] 1. Adaptive Gaussian weighted Markov random field filter model

[0036] The traditional first-order GMRF model is difficult to adapt to dynamically changing scene data due to the use of fixed filtering weight parameters. In order to obtain a difference image that can effectively retain the target signal and suppress most of the background information, the present invention proposes an adaptive Gaussian weighted Markov random field filtering model, which fully integrates the spatial information of the pixel coordinates and the similarity of the pixel values The information is weighted to better describe the joint probability distribut...

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 weak and small target detection method based on Gaussian Markov random field motion direction estimation, which comprises the following steps of: firstly, establishing a new self-adaptive Gaussian weighted Markov random field filtering model to obtain a difference image of an image, and then, constructing a target Markov transition probability model according to an established motion model; in this way, the motion direction of the target is estimated, and the target signal is enhanced in a transition probability weighting mode along the motion direction. Compared with similar algorithms, the algorithm has good advancement, and a better detection effect is obtained.

Description

technical field [0001] The present invention relates to object tracking, the field of object tracking. It specifically involves a weak target detection method based on Gauss Markov random field motion direction estimation, mainly for tracking and detection of weak targets, and accurately extracting real small targets in various complex photoelectric noises. It also involves computers Areas of vision algorithm improvement. Background technique [0002] The detection of infrared weak and small target images is widely used in science and technology. However, due to the influence of atmospheric radiation, operating distance, photoelectric interference and other factors, the target is small in size on the image, showing point shape, without any contour texture features, and sometimes It will be submerged in the complex background, heavy noise, clutter, etc. will also affect the judgment of the algorithm, making small target detection very difficult. [0003] The improvement of ...

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): G06V20/00G06V10/44G06V10/84G06K9/62
CPCG06F18/295Y02D30/70
Inventor 闵雷樊香所
Owner INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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