Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Self-adapting image compressive sampling method based on multi-dimension saliency map

An image compression, multi-scale technology, applied in the field of image processing, can solve the problem of waste of sampling resources, to avoid the effect of reducing the size

Active Publication Date: 2012-03-28
XIDIAN UNIV
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

They use the same sampling rate for each block, so the sampling resources allocated to the "visually significant" area are not enough to achieve the required level. On the contrary, for the "non-visually significant" area, it will cause a waste of sampling resources. There is no Effective use of limited sampling resources

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
  • Self-adapting image compressive sampling method based on multi-dimension saliency map
  • Self-adapting image compressive sampling method based on multi-dimension saliency map
  • Self-adapting image compressive sampling method based on multi-dimension saliency map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] refer to figure 1 , the present invention is an adaptive image compression sampling method based on a multi-scale saliency map, which can be used in a single-pixel image acquisition system, and the method includes the following steps:

[0050] (1) Obtain a low-resolution sampling image P through acquisition by a low-resolution sensor;

[0051] (2) Perform SVT transformation on the low-resolution sampling image P. When the decomposition level is set to 3, a low-frequency image P is obtained. 1 and three high-frequency support value images S 1 , S 2 , S 3 ;

[0052] Among them, the SVT transformation is carried out as follows:

[0053] 2a) Given the size of the rectangular neighborhood of the mapped input vector space, that is, the rectangular neighborhood of N×N size, given the parameter γ of the least squares vector machine and the parameter σ of the Gaussian radial basis (RBF) kernel function, the above The values ​​of the parameters are all empirical values. Th...

Embodiment 2

[0079] The adaptive image compression sampling method based on the multi-scale saliency map is the same as that in Embodiment 1. In order to describe the method of the present invention in detail, the implementation steps and conditions of the method are fused together and explained as follows:

[0080] Step 1. Low resolution sampling:

[0081] A low-resolution image P obtained by a low-resolution sensor.

[0082]Step 2. Use SVT to transform the low-resolution sampled image P to obtain a saliency map:

[0083] 2a) Given a rectangular neighborhood of N×N size mapped to the input vector space, given the parameter γ of the least squares vector machine and the parameter σ of the Gaussian Radial Basis (RBF) kernel function, all of the above are empirical parameters. The mathematical expression of the RBF kernel function is:

[0084] K(x,x i )=exp(-‖x-x i ‖ 2 / 2σ 2 )

[0085] Where x is the position vector of the image pixel, x i is the position vector of the i-th pixel of t...

Embodiment 3

[0110] The adaptive image compression sampling method based on the multi-scale saliency map is the same as the embodiment 1-2, and the effect of the present invention can be further illustrated by the following experiments:

[0111] 1) Experimental conditions

[0112] This experiment uses natural images, SAR images, and visible light remote sensing images as experimental data, and uses software MATLAB 7.9.0 as a simulation tool, and the computer configuration is Intel Core2 / 2.13G / 2G.

[0113] 2) Experimental content

[0114] Firstly, the saliency map generation model is used to obtain the saliency map for the low-resolution image, the "visually salient" area and the "non-visually salient" area of ​​the image are determined, and then the number of measurements is allocated. Through the OMP reconstruction algorithm, the reconstructed image is finally obtained.

[0115] In this experiment, a random Gaussian matrix is ​​selected as the observation matrix, the average sampling rat...

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 self-adapting image compressive sampling method based on a multi-dimension saliency map, and is used for solving the problem of sampling resource waste due to the average allocation of the sampling rate to the image during compressive sampling. The method mainly comprises the steps of: carrying out support value transformation (SVT) on an sampled image and calculating toobtain a saliency map of the image; determining a vision salient region and a vision non-salient region according to the saliency map; allocating measurement data, allocating more sampling resources to the vision salient region; and reconstructing the measurement data obtained by self-adapting sampling through a nonlinear reconstructing algorithm to finally obtain an reconstructed image. Comparedwith the prior art, the method has the advantages that: when the compressive measurement of the image is carried out, according to the difference in people vision attention regions, self-adapting sampling resource allocation can be achieved based on different attention regions, thus the utilization rate of the sampling resources is increased and the quality of the recovered image is improved simultaneously. The method can be used for self-adapting compressive sampling of natural images, remote sensing images and the like, and has broad application prospects in low-cost imaging equipment.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to an adaptive image compression sampling method, in particular to an adaptive image compression sampling method based on a multi-scale saliency map. Background technique [0002] The traditional signal sampling theory is based on the Nyquist sampling theorem. In order to ensure that the signal can be recovered from the sampled signal without distortion, the sampling frequency should be at least twice the cutoff frequency of the signal. This results in a high hardware cost when the signal bandwidth is large. Compressed Sampling (CS) is a new theoretical framework for signal acquisition and processing proposed to overcome this problem. The basic idea is: assuming that the original signal is compressible, that is, it can be sparsely represented under a certain dictionary, then by constructing an observation system that is not related to the dictionary, and using the obs...

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): G06T9/00
Inventor 杨淑媛焦李成吴赟刘芳王爽侯彪马文萍左第俊周宇刘帆
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com