Super-resolution graph recovery method for simultaneously enhancing underwater images

A technology of super resolution and restoration method, which is applied in the field of image processing and can solve problems such as underwater image distortion.

Inactive Publication Date: 2020-11-03
NORTHEAST GASOLINEEUM UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these models report good results, they do

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
  • Super-resolution graph recovery method for simultaneously enhancing underwater images
  • Super-resolution graph recovery method for simultaneously enhancing underwater images
  • Super-resolution graph recovery method for simultaneously enhancing underwater images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention is specifically described below in conjunction with accompanying drawing, as Figure 1-7 As shown, the inventive point of this application is that it refers to a method of using a low-resolution distorted image as an input, and then learning a network to enhance perception and restore an image at a high resolution. Our method formulates the problem as learning a pixel-to-pixel mapping from a low-resolution distorted image source domain X to an enhanced high-resolution image target domain Y, and our method expresses this mapping as a generator function G:X→Y. Consider learning the saliency prediction on the shared feature space, and then learn the enhanced super-resolution recovery method (SESR) task. This method adopts an extended expression here: the enhanced super-resolution recovery method (SESR) learns the generation function G:X→S, E, Y, S and E of the additional output denote the predicted saliency map and the low-resolution enhanced image (s...

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 super-resolution graph recovery method for simultaneously enhancing underwater images, which is based on a generation model of a residual network, recovers a perception imagewith spatial resolution of 2 times, 3 times or 4 times through a learning algorithm, and supervises the training of the perception image by formulating a multi-mode target function. The objective function can solve the problems of color degradation, insufficient image definition and loss of advanced feature representation in a chrominance-specific underwater environment, and can also supervise and learn a significant foreground region in an image, thereby guiding network learning to enhance the global contrast. The invention has the beneficial effects that the performance is better, and meanwhile, the UIQM score is better.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a super-resolution graphic restoration method for simultaneous enhancement of underwater images. Background technique [0002] Underwater image enhancement and restoration is an important research problem. Correct and restore distorted optical images to preserve pixel intensity. Classical methods use hand-crafted filters to improve local contrast and enhance color stability, especially for dehazing, color Calibration, water removal, etc. These methods are inspired by the theory of human visual perception, and mainly focus on restoring background illumination and brightness reproduction. However, these methods are often computationally too demanding for real-time robotic deployment, and intensive depth-of-field and optical measurements are not always feasible for practical applications. Another class of physics-based methods uses atmospheric dehazing models to estimate the true t...

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
IPC IPC(8): G06T5/00G06T3/40G06N3/04G06N3/08
CPCG06T5/001G06T5/007G06T3/4053G06T3/4046G06N3/08G06T2207/10024G06T2207/20081G06T2207/30168G06N3/045
Inventor 赵慧岩
Owner NORTHEAST GASOLINEEUM UNIV
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