An infrared and visible image fusion method combining image saliency and non-downsampled contour transform

A non-subsampling contour and image fusion technology, applied in image enhancement, image analysis, image data processing, etc. Observation and computer processing, detailed information rich, multi-target information and the effect of detailed information

Active Publication Date: 2019-01-18
INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
View PDF9 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: infrared images usually have relatively low contrast and resolution, but since the acquisition of the image does not depend on external light, it can overcome the influence of the weather environment, etc., and obtain target information at night or in foggy conditions. , the detailed texture information of visible light images is usually relatively rich, but due to the influence of easy-to-conceal lighting, weather or target occlusion, sometimes the target information cannot be obtained well

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
  • An infrared and visible image fusion method combining image saliency and non-downsampled contour transform
  • An infrared and visible image fusion method combining image saliency and non-downsampled contour transform
  • An infrared and visible image fusion method combining image saliency and non-downsampled contour transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. This embodiment is carried out on the premise of the technical solution of the present invention, and the detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0054] Step 1. Determine whether the visible light image is a low-contrast image, and whether adaptive histogram equalization with limited contrast is required:

[0055] Image contrast calculation formula:

[0056]

[0057] Where δ is the possible gray difference between adjacent pixels, P δ is the distribution probability of pixels whose gray level difference between adjacent pixels is δ.

[0058] After calculating and testing multiple images, for an image with a gray scale range of [0, 255], the present invention judges the image as a low-contrast image when C≤3.8.

[0059] If the i...

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 infrared and visible light image fusion method combining image saliency and non-downsampled contour wave transform. Firstly, the contrast of visible light image is calculated. If the contrast of visible light image is low, the adaptive histogram equalization with limited contrast is carried out. The improved Frequency Tuned (FT) algorithm is used to extract the saliency region of infrared image, and then the background of the saliency image is suppressed. Then, non-down-sampled contour transform (NSCT) is performed on the infrared image and the processed visible imageto obtain low-frequency and high-frequency information, respectively. In the part of low frequency information, the saliency map is used for fusion, and in the part of high frequency information, thefusion rule of taking the large absolute value is used for fusion. At last, the fusion image is obtained by inverse NSCT with the low frequency coefficient and high frequency coefficient. The invention makes the fused image more abundant in detail information, more prominent in the target area, better in the visual effect of the fused image, and more suitable for human eye observation and computer processing.

Description

technical field [0001] The invention relates to an infrared and visible light image fusion method, in particular to an infrared and visible light image fusion method combining image saliency and non-subsampling contourlet transformation, which belongs to the field of digital image processing. Background technique [0002] Image sensors with different spectra sometimes have relatively good complementary characteristics. For example, the infrared image sensor is based on the difference in the infrared radiation of the object, reflecting the thermal radiation characteristics of the object. Since the acquisition of infrared images does not depend on external light, it has the characteristics of all-weather weather. The visible light image sensor is based on the different reflection capabilities of objects to visible light, which reflects the visible light reflection characteristics of the surface of the object. The acquisition of images is easily affected by factors such as illu...

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): G06T7/30
CPCG06T2207/10004G06T2207/10048G06T2207/20021G06T2207/20132G06T2207/20221G06T7/30
Inventor 林子慧徐智勇魏宇星张建林
Owner INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
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