Zero-sample unsupervised image defogging method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An unsupervised, image-based technology, applied in the field of image processing, can solve the problems of unsupervised, shortening the inference time of a single image, etc., to reduce the inference time, improve the dehazing performance, and solve the effect of excessive inference time
Pending Publication Date: 2022-07-01
JINAN UNIVERSITY
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to overcome the defects and deficiencies of the existing technology, the present invention provides a zero-sample unsupervised image defogging method and system. The present invention only uses a single foggy image for training, and introduces a variety of priors for the loss function. Optimizing the loss function and training parameters, on the one hand, solves the dependence of the defogging method on prior knowledge and large-scale paired real data sets; Single image inference time
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0069] like figure 1 As shown, this embodiment provides a zero-sample unsupervised image dehazing method, including the following steps:
[0070] Get a foggy image and use it directly as an input image;
[0071] Construct a zero-sample unsupervised dehazing neural network. The zero-sample unsupervised dehazing neural network includes the atmospheric illumination image prediction branch, the transmission image prediction branch and the haze-free image prediction branch, which are used to realize the layer de-separation of the input fog image and obtain the atmosphere. Light intensity image information, transmission image information, and fog-free image information, which can be continuously updated to obtain the best dehazing image by reconstructing the fog image and calculating constraints;
[0072] The zero-sample unsupervised dehazing neural network is trained as follows: the input required for model training is the learning rate, loss function parameters, the number of ite...
Embodiment 2
[0120] like Figure 5 As shown, this embodiment provides a zero-sample unsupervised image dehazing system, including: a hazy image acquisition module, a zero-sample unsupervised dehazing neural network building module, a zero-sample unsupervised dehazing neural network training module, a loop Iteration module and output module;
[0121] In this embodiment, the foggy image acquisition module is used to acquire a foggy image as an input image;
[0122] In this embodiment, the zero-sample unsupervised dehazing neural network building module is used to construct a zero-sample unsupervised dehazing neural network, and the zero-sample unsupervised dehazing neural network includes an atmospheric illumination image prediction branch, a transmission image prediction branch and a haze-free neural network. image prediction branch;
[0123] In this embodiment, the atmospheric illumination image prediction branch adopts a variational autoencoder structure;
[0124] In this embodiment, t...
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 discloses a zero-sample unsupervised image defogging method and a zero-sample unsupervised image defogging system. The zero-sample unsupervised image defogging method comprises the following steps: acquiring a foggy image; the constructed zero-sample unsupervised defogging neural network comprises an atmosphere illumination image prediction branch, a transmission image prediction branch and a fogless image prediction branch; the foggy image is subjected to atmospheric image and transmission image prediction branches to obtain an atmospheric light value image and a transmission image, and regularization loss is calculated; calculating the atmospheric light loss of the atmospheric image prediction branch through the variational auto-encoder loss and the atmospheric light value constraint loss; the foggy image is processed by a fogless image prediction branch to obtain a fogless image, and the loss of the defogged image is calculated based on prior knowledge of statistical characteristics; calculating a reconstructed fog image and calculating reconstruction loss; the total loss is the sum of reconstruction loss, defogged image loss, atmospheric light loss and regularization loss; and network parameters are updated through loop iteration, network training is completed, and a final defogging result is obtained. According to the method, the inference speed of unsupervised defogging is improved, and the defogging effect is better.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a zero-sample unsupervised image dehazing method and system. Background technique [0002] Smog refers to smoke, dust or moisture in the atmosphere. With the intensification of environmental pollution, haze weather becomes more and more frequent. The presence of haze can significantly reduce image quality, resulting in poor performance in various image processing tasks such as image recognition and detection, remote sensing, and video surveillance. Therefore, image dehazing has attracted much attention as a key technique to restore degraded images captured in severe weather. [0003] Currently, image dehazing algorithms are mainly divided into two categories: prior-based methods and learning-based methods. Prior-based methods introduce reasonable prior knowledge as a constraint, which has the effect of naturalness and high fidelity. However, the effect of such methods ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more