Feature extraction method and device for super-resolution image reconstruction and storage medium
A super-resolution image and feature extraction technology, which is applied in the direction of image conversion, image data processing, neural learning methods, etc., can solve the problems of driver’s parking safety hazards, vulnerability to external interference, and blurred images of central control screens. , to achieve the effects of enhancing clarity and resolution, increasing attention, and suppressing environmental feature information
Pending Publication Date: 2022-05-17
ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The reversing image of the car is easily disturbed by the outside world due to the complexity of the external environment information, and the video transmitted to the central control screen is blurred and has low resolution, which brings safety hazards to the driver's parking
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
[0018] The application describes a number of embodiments, but the description is illustrative rather than restrictive, and it will be obvious to those of ordinary skill in the art that within the scope of the embodiments described in the application, There are many more embodiments and implementations. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Except where expressly limited, any feature or element of any embodiment may be used in combination with, or substituted for, any other feature or element of any other embodiment.
[0019] This application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The disclosed embodiments, features and elements of this application can also be combined with any conventional feature or element to form unique inventive solutions as defined by the append...
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 feature extraction method for super-resolution image reconstruction. The method comprises the following steps: constructing a convolutional neural network model; the model comprises an input module, a basic convolutional layer module, an attention mechanism cyclic feedback convolution module, an up-sampling module, a feature fusion module and an output module. Performing feature extraction on an original image by using the model; receiving original image data by an input module; the basic convolutional layer module extracts features from the original image data to obtain a first feature map; the attention mechanism cyclic feedback convolution module extracts features from the original image data by using a space attention mechanism, a channel attention mechanism and a cyclic feedback convolution unit to obtain a second feature map; an up-sampling module performs up-sampling on the first feature map and the second feature map to obtain a third feature map and a fourth feature map; the feature fusion module carries out feature fusion on the third feature map and the fourth feature map to obtain a fifth feature map; and the output module outputs the fifth feature map. According to the scheme, the definition and resolution of the image can be enhanced.
Description
technical field [0001] The embodiments of the present application relate to the field of machine vision, and in particular to a feature extraction method, device and storage medium for super-resolution image reconstruction. Background technique [0002] With the user's demand for driving environment safety and driving convenience and the development of computer science and technology, cars are becoming increasingly intelligent. The driver's perception of the surrounding complex environment is very important in the process of parking. In order to obtain high-quality parking assistance functions, the existing car is equipped with a reversing imaging device, and the road scene during parking is obtained in real time through an external camera sensor device. And transmit it to the central control display to provide the driver with driving safety information in real time. [0003] The reversing image of the car is easily disturbed by the outside world due to the complexity of th...
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): G06T3/40G06N3/08G06N3/04G06K9/62G06V10/80G06V10/82
CPCG06T3/4053G06N3/08G06N3/045G06F18/253
Inventor 李双双缪继树辛海同陈勇李志成
Owner ZHEJIANG GEELY HLDG GRP CO LTD