Underwater image enhancement method based on conditional generative adversarial network

An underwater image, conditional generation technology, applied in image enhancement, biological neural network model, image analysis, etc., can solve the problems of lack of details in synthetic images, poor practical generalization ability, color distortion, etc.

Active Publication Date: 2020-10-27
OCEAN UNIV OF CHINA
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides an underwater image enhancement method based on a conditional generative confrontation network, and the technical problem to be solved is: the existing image processing method based on a generative confrontation network has poor practical generalization ability, and there are also problems such as lack of details in the synthesized image, color distortion, Problems such as excessive introduction of noise

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 method based on conditional generative adversarial network
  • Underwater image enhancement method based on conditional generative adversarial network
  • Underwater image enhancement method based on conditional generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The embodiment of the present invention will be explained in detail below in conjunction with the accompanying drawings. The examples given are only for the purpose of illustration, and cannot be interpreted as limiting the present invention. The accompanying drawings are only for reference and description, and do not constitute the scope of patent protection of the present invention. limitations, since many changes may be made in the invention without departing from the spirit and scope of the invention.

[0046] (1) Method description

[0047] The purpose of the underwater image enhancement task is to process a low-quality underwater image (denoted as X) through a series of processes to obtain a high-quality and clear image (denoted as Y), which can be classified as from an image (turbid water quality) to Image translation issue for another image (clear water quality). The underwater image enhancement task can be seen as finding a way to learn a mapping relationship ...

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 relates to the technical field of underwater image processing, and specifically discloses an underwater image enhancement method based on a conditional generative adversarial network. Abasic image enhancement model is constructed; a step-by-step adversarial training strategy is provided; meanwhile, a pixel-level loss composed of a target loss function (formed by linearly combining an adversarial loss function, an L2 loss function and an angle loss function) is constructed in a training strategy; good robustness and effectiveness are realized; even if real underwater paired training data is lacked, the training precision is improved; artificially synthesized pairing data is used; enhancement of a real underwater image can still be effectively realized; the problem of atomization blurring in an underwater image is efficiently solved; image contrast is improved, problems of bluish and greenish color cast of the underwater image can be excellently solved, detail informationof the target object in the image can be enhanced, image visibility is improved, a farther target can be more clearly seen, and the generated image is promoted to be closer to a real scene.

Description

technical field [0001] The invention relates to the technical field of underwater image processing, in particular to an underwater image enhancement method based on a conditional generation confrontation network. Background technique [0002] Underwater image processing technology can quickly and effectively improve the quality of underwater images. Compared with expensive hardware support, its implementation cost is lower, so underwater image processing technology has received extensive attention. These technologies play an important role in many marine engineering and scientific research tasks, such as: underwater coral monitoring, marine biological migration monitoring, submarine cables and parameters detection, deep sea exploration, etc. The main reason for underwater image degradation is the strong absorption and scattering of light by water. Water contains a large number of suspended particles, such as microorganisms, dust, etc. When light propagates in water and coll...

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): G06T5/00G06T7/90G06N3/04G06N3/08
CPCG06T5/001G06T7/90G06N3/08G06T2207/10024G06T2207/20081G06T2207/20084G06N3/045
Inventor 俞智斌韩茹月
Owner OCEAN UNIV OF CHINA
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