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

Underwater image enhancement and restoration method based on convolutional neural network

A convolutional neural network and underwater image technology, applied in the field of underwater image enhancement and restoration, can solve problems such as artifacts, unnatural chromatic aberration, and a large amount of environmental data, and achieve the effect of improving quality

Active Publication Date: 2020-07-28
CHONGQING UNIV OF TECH
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have a certain effect on the color correction of underwater images and the improvement of texture clarity, but there are still subjective unnatural color differences and texture distortions.
Ancuti et al. proposed to fuse the parameters of the underwater images processed by the three methods of color improvement, gamma correction and texture enhancement, but this kind of algorithm is complex and the image is prone to artifacts caused by over-enhancement
In addition, traditional methods require a large amount of environmental data such as water scattering coefficients, scene depth, etc., which are difficult to obtain from a single image

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
  • Underwater image enhancement and restoration method based on convolutional neural network
  • Underwater image enhancement and restoration method based on convolutional neural network
  • Underwater image enhancement and restoration method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0039] Such as figure 1 As shown, a convolutional neural network-based underwater image enhancement and restoration method includes the following steps:

[0040]Step 1. Input an underwater image to be processed and multiple conventional images, and use the underwater image to degrade multiple conventional images to obtain multiple degraded conventional images, among which multiple conventional images are in the atmosphere The underwater image to be processed is taken underwater, and the size and pixels of the underwater image to be processed are the same as all conventional images;

[0041] Specifically, the specific steps for degrading any conventional image using the underwater image to be processed are:

[0042] Step 1-1, divide the underwater image to be processed and any conventional image into M×N small blocks of the same size, and the...

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 an underwater image enhancement and restoration method based on a convolutional neural network, and the method comprises the steps: degrading a plurality of conventional imagesthrough a to-be-processed underwater image, forming a training set through the plurality of conventional images and the corresponding degraded conventional images, and sequentially inputting the training set into the convolutional neural network for training; then, inputting the underwater image to be processed into the trained convolutional neural network, and outputting a first image; carryingout CIELAB color space transformation on the image, and extracting an L brightness channel, an A color channel and a B color channel of the image; and finally, performing texture enhancement on the to-be-processed underwater image, replacing the L brightness channel of the first image with the image after texture enhancement, and combining the image after texture enhancement with the A color channel and the B color channel in the first image to obtain a final image. According to the method, the problem of missing of underwater image training data is solved, complex calculation of a traditionalunderwater imaging model is avoided, and the quality of underwater images is well improved.

Description

technical field [0001] The invention relates to the field of underwater image enhancement and restoration, in particular to an underwater image enhancement and restoration method based on a convolutional neural network. Background technique [0002] Obtaining underwater images is of great significance to the detection and development of underwater environments. In the process of shooting underwater images, due to the rapid attenuation of red light during propagation, and the light scattering caused by particles in the water, the collected underwater images usually have low contrast, uneven brightness, unclear texture and chromatic aberration. Serious and other shortcomings. Therefore, people usually perform enhancement and restoration processing on underwater images to ensure the smooth development of underwater environmental operations. [0003] In recent years, underwater image processing technology has attracted more and more attention from scholars, and various underwa...

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): G06T5/00G06T5/40G06T7/90G06N3/04G06N3/08
CPCG06T5/40G06T7/90G06N3/08G06N3/045G06T5/92Y02A90/30
Inventor 陈芬童欣彭宗举蒋东荣
Owner CHONGQING UNIV OF TECH
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