Automobile night vision anti-halo image segmentation and evaluation method based on infrared and visible light fusion

A fusion image and image segmentation technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as poor evaluation results and inconsistent visual effects of human eyes, and achieve a reasonable evaluation effect
CN109166131AActive Publication Date: 2019-01-08XIAN TECH UNIV
4 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIAN TECH UNIV
Publication Date
2019-01-08

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides an automobile night vision anti-halo image evaluation method based on infrared and visible light. The method automatically determines a halo threshold gray value of a visible light gray image according to halo degree of visible light image by designing adaptive iterative threshold method, and automatically divides the fused image into a halo region and a non-halo region. Aiming at the difference between halo region and non-halo region, the halo elimination degree is designed to evaluate the effect of halo elimination in halo region, and the enhancement effect of color detail information in non-halo region is evaluated from multiple angles. This method solves the problem that the evaluation result of infrared and visible fusion image is inconsistent with human visualeffect when it is used to evaluate automobile night vision anti-halo fusion image, and the halo elimination of fusion image is more thorough and the evaluation result is worse.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of automobile anti-halation technology, and in particular relates to a car night vision anti-halation image segmentation method and an image evaluation method after segmentation by combining infrared and visible light. The degree of elimination and the quality of image details are suitable for judging the fusion algorithm of automobile anti-halation image combining infrared and visible light. Background technique

[0002] The image fusion anti-halation technology, which combines the advantages of no halo in infrared images and rich color detail information in visible light images, provides a new way to solve the problem of halo in night driving, and has a good application prospect.

[0003] In order to judge the halo elimination degree and detail information enhancement effect of automobile night vision anti-halation fusion images, as well as to judge the pros and cons of different image fusion algorithms, the evaluat...

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