Image Compressive Sensing Reconstruction System and Method for Learning Sampling and Grouping
A reconstruction system and image compression technology, applied in image enhancement, image analysis, graphics and image conversion, etc., can solve the problems of high computational complexity and large parameter scale, so as to improve the system reconstruction performance and reduce the complexity of the reconstruction system degree of effect
Active Publication Date: 2022-08-05
SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the reconstruction end of the traditional block-based compressed sensing scheme uses a measurement matrix of the same size as the encoding end to perform image reconstruction, which still has the disadvantages of requiring a large number of parameters and high computational complexity.
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
[0058] Describe in detail below in conjunction with accompanying drawing and embodiment:
[0059] 1. System
[0060] 1. Overall
[0061] like figure 1 , the system includes the input image measurement value Y, and is provided with a non-overlapping grouping module 10, a multi-channel parallel block image dimensionality reduction and reconstruction module 20, a block image stitching module 30, an image upsampling and reconstruction module 40 and an image depth reconstruction module module 50;
[0062] The input image measurement value Y, the non-overlapping grouping module 10, the multi-channel parallel block image dimensionality reduction and reconstruction module 20, the block image stitching module 30, the image upsampling and reconstruction module 40 and the image depth reconstruction module 50 interact in sequence, and the system The output is the reconstructed image X R .
[0063] In detail: the non-overlapping grouping module 10 has one input terminal and L output 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 an image compression sensing reconstruction system and a method for learning sampling and grouping, and relates to the technical field of image imaging and reconstruction. The system is: an input image measurement value (Y), a non-overlapping grouping module (10), a multi-channel parallel block image dimensionality reduction and reconstruction module (20), a block image stitching module (30), and an image upsampling and reconstruction module (40) interacts with the image depth reconstruction module (50) in turn, and the system outputs the reconstructed image (X R ). The method includes: ① non-overlapping grouping; ② multi-channel parallel block image dimensionality reduction and reconstruction; ③ block image stitching; ④ image upsampling reconstruction; ⑤ image depth reconstruction; ⑥ image block compression sampling; ⑦ measurement Joint optimization of matrices and reconfiguration systems. While effectively reducing the complexity of the reconstruction system, the present invention can further improve the reconstruction performance of the system, and is suitable for applications such as compression imaging.
Description
technical field [0001] The invention relates to the technical field of image imaging and reconstruction, in particular to an image compressive sensing reconstruction system and a method for learning sampling and grouping; A high-performance image compressed sensing reconstruction system and method with reduced complexity of reconstruction technology. Background technique [0002] Compressed sensing is a new signal sampling theory. Compared with traditional Shannon sampling, compressed sensing proves that it can achieve accurate reconstruction of sparse signal dimensionality reduction sampling, so it can greatly reduce the amount of data sampled, thereby effectively reducing data storage space and data transmission bandwidth. Compressed sensing has been widely used in image imaging. Image compressed sensing reconstruction is the core problem involved in compressed sensing imaging, and it has been a research hotspot in this field since the theory of compressed sensing was pr...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/50G06T3/40
CPCG06T5/50G06T3/4038G06T2207/20081G06T2207/20084
Inventor 熊承义刘川鄂高志荣秦鹏飞
Owner SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES