Target and background contrast enhancement method based on multi-channel polarization distance model

A background contrast and multi-channel technology, which is applied in the field of target and background contrast enhancement based on multi-channel polarization distance model, can solve the problems of poor anti-environmental interference performance, and achieve less susceptible to noise, fast image processing speed, and computational complexity low effect

Active Publication Date: 2020-12-11
HEFEI UNIV OF TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing concepts of polarization distance are built on a two-channel polarization visual processing framework based on orthogonal adversarial interneurons, however, the limitation of the two-channel system is that it cannot always distinguish between two different polarization states, and there is polarization confusion state, poor anti-environmental interference performance

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
  • Target and background contrast enhancement method based on multi-channel polarization distance model
  • Target and background contrast enhancement method based on multi-channel polarization distance model
  • Target and background contrast enhancement method based on multi-channel polarization distance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In this embodiment, as figure 1As shown, a target and background contrast enhancement method based on a multi-channel polarization distance model is mainly used for target detection and other tasks in scenes with high target concealment and strong environmental interference. , based on the polarization distance, a new polarization characterization quantity, a four-channel polarization distance bionic model is proposed to enhance the contrast between the target and the background. Specifically, the process is as follows:

[0040] Step 1: Obtain the polarization image I with the target at the polarization angles of 0°, 45°, 90°, and 135°, respectively 0 , I 45 , I 90 , I 135 ;

[0041] Among the polarization-sensitive organisms, there are two groups of orthogonally oriented striated muscle microvilli in the compound eye structure of a few organisms, one of which exhibits a 45° deflection relative to the other, which can infer the polarization information collection o...

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 target and background contrast enhancement method based on a multi-channel polarization distance model. The method comprises the steps: 1, acquiring polarization images at different polarization angles; 2, selecting background areas in the polarization images; 3, separating out G channel images in all the RGB images; 4, calculating the activity value of a simulated photoreceptor R; and 5, calculating a polarization distance image by using the multi-channel polarization distance model. According to the method, the contrast between the target and the background can be well enhanced in a low-contrast scene, so that the visibility and the saliency of the target are improved.

Description

technical field [0001] The invention belongs to the research field of target detection, in particular to a target and background contrast enhancement method based on a multi-channel polarization distance model. Background technique [0002] The visual system often relies on features such as shape, size, color, and contrast. Contrast vision plays an important role in biological behaviors such as detection and recognition of prey, recognition of the environment and habitat, and visual communication. In addition to color vision in nature, there is another unique vision that humans do not have - polarization vision. Compared with unpolarized light, polarized light has characteristic information in more dimensions. Targets with different materials and textures can often capture differences and distinguish them through polarization information. Some organisms can detect or even generate polarized light and use them for related visual tasks. Therefore, the polarization contrast ...

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): G06T5/00
CPCG06T5/007G06T2207/10024
Inventor 王昕钟彬彬王大千杨天高隽
Owner HEFEI UNIV OF TECH
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