Unlock instant, AI-driven research and patent intelligence for your innovation.

A nighttime image enhancement method based on multi-pass decomposition

An image enhancement and multi-channel technology, applied in the field of image processing, can solve the problem of not being able to remove noise well, and achieve the effect of removing noise interference at night

Active Publication Date: 2021-07-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since image noise is amplified in the process of brightness enhancement, existing denoising algorithms cannot remove noise 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
  • A nighttime image enhancement method based on multi-pass decomposition
  • A nighttime image enhancement method based on multi-pass decomposition
  • A nighttime image enhancement method based on multi-pass decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to facilitate those skilled in the art to understand the technical content of the present invention, the content of the present invention will be further explained below in conjunction with the accompanying drawings.

[0019] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0020] Select a night image (number: N-002-0) from the currently public low-quality image library PKU-EAQA (download address: https: / / pkuml.org / resources / pku-eaqa.html) as the implementation object, The size of the image is 400×300×3, and the format is a 24-bit bmp image. The specific calculation process is as follows figure 1 As shown, the specific process is as follows:

[0021] S1. Based on the estimation of the global noise level of the image, decompose the image into the base layer and the detail layer: extract the three color channels of red (R), green (G) and blue (B) of the image to be processed, and an...

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 nighttime image enhancement method based on multi-path decomposition, which is applied in the technical field of image processing. Aiming at the problem that the prior art cannot remove noise well during nighttime image processing, the invention first bases on the global noise of the nighttime image to be processed To estimate the level, decompose the nighttime image to be processed into the base layer image and the detail layer image; then perform brightness adaptation calculation on the base layer image; secondly correct the color of the base layer brightness adaptation image; perform edge protection and detail layer image again Noise suppression; finally, the color-corrected base layer image is fused with the edge-protected and noise-suppressed detail layer image to obtain an enhanced nighttime image; the method of the present invention can well remove the noise interference of the nighttime image.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a technology for enhancing nighttime images. Background technique [0002] In image processing, images acquired in night scenes often have problems such as low brightness, uneven illumination, and large noise interference. Low-quality night images often affect the performance of computing systems based on image information, such as night surveillance systems. Therefore, it is of great significance to perform visual enhancement preprocessing (such as denoising, brightness enhancement, detail enhancement, etc.) on the low-quality nighttime images collected by the device. A typical image enhancement method at night or in low brightness is the image enhancement method based on light source estimation (LIME), see the literature "X.Guo, Y.Li, and H.Ling, "LIME:Low-light imageenhancement via illumination map estimation, "IEEE Trans. Image Processing, vol. 26, no. 2, pp. 982–993, 2017."...

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 Patents(China)
IPC IPC(8): G06T5/00
Inventor 杨开富张显石李永杰
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA