Image defogging method and system based on meta-assisted learning
A meta-learning and image technology, applied in the field of image dehazing methods and systems based on meta-assisted learning, can solve problems such as poor dehazing performance, achieve consistent data distribution, and improve dehazing performance.
Pending Publication Date: 2022-03-15
NANJING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide an image defogging method and system based on meta-assisted lea
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0058] The purpose of the present invention is to provide an image defogging method and system based on meta-assisted learning to solve the problem of slightly poor defogging performance of image defogging methods in the prior art.
[0059] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and spec...
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
Login to View More Abstract
The invention relates to an image defogging method and system based on meta-assisted learning. The method comprises the following steps: constructing a data set; the data set comprises an artificially synthesized fog image data set and a natural fog image data set; the natural fog image data set comprises a plurality of real foggy day images; constructing a convolutional network model; the convolutional network model comprises an encoder, a decoder, a meta learning unit and an auxiliary learning unit; performing feature extraction on the synthesized fog image and the real fog day image by using a convolutional network model to obtain image feature data; optimizing the convolutional network model by using the image feature data and the clear image to obtain an optimized convolutional network model; and carrying out defogging processing on a to-be-measured fog image by using the optimized convolutional network model. According to the method, the auxiliary learning unit is introduced, so that the data distribution of the synthesized fog image and the real fog image is consistent, and the defogging performance of the convolutional network model is improved.
Description
technical field [0001] The present invention relates to the field of image defogging, in particular to an image defogging method and system based on meta-assisted learning. Background technique [0002] Image dehazing is one of the core research issues in the field of image enhancement. The purpose is to restore blurred and hazy images into clear images and improve the performance of other computer vision tasks. Image defogging is an underlying task of computer vision. It has a wide range of application scenarios and can assist other computer vision tasks, such as object detection, pedestrian re-identification, image segmentation, image classification and other fields. Therefore, the research on image defogging technology is imminent . [0003] Existing image defogging techniques are mainly divided into two categories, one is machine learning methods based on statistical priors, and the other is end-to-end deep learning methods. Methods based on statistical priors mainly i...
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
Login to View More IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06T5/003G06N3/084G06T2207/20081G06T2207/20084G06N3/045
Inventor 项欣光陈卓鹏金露
Owner NANJING UNIV OF SCI & TECH