CN104778665A - Compressed ghost imaging reconstruction method based on natural image block prior driving and system - Google Patents
Compressed ghost imaging reconstruction method based on natural image block prior driving and system Download PDFInfo
- Publication number
- CN104778665A CN104778665A CN201510173941.XA CN201510173941A CN104778665A CN 104778665 A CN104778665 A CN 104778665A CN 201510173941 A CN201510173941 A CN 201510173941A CN 104778665 A CN104778665 A CN 104778665A
- Authority
- CN
- China
- Prior art keywords
- image
- natural
- image block
- natural image
- expression dictionary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003384 imaging method Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000006835 compression Effects 0.000 claims description 35
- 238000007906 compression Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000007634 remodeling Methods 0.000 abstract 1
- 230000000452 restraining effect Effects 0.000 abstract 1
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a compressed ghost imaging reconstruction method based on natural image block prior driving and a compressed ghost imaging reconstruction system. The method comprises the following steps: extracting a plurality of image blocks from each natural image of a natural image database; learning over-complete expression dictionary base of the natural images by the image blocks, and enabling the natural image blocks to achieve the sparse characteristic on projection coefficients of the over-complete expression dictionary base; according to the incidence relation among the over-complete expression dictionary base, the image blocks and the natural images, remodeling the compressed sensing reconstructing algorithm of ghost imaging, and restraining the sparsity of the whole situation of the image under a gradient domain or two-dimensional discrete cosine transform and the sparsity of the local image blocks under the over-complete expression dictionary base, so as to reconstruct the natural image. The compressed ghost imaging reconstruction method disclosed by the embodiment of the invention effectively reduces the acquisition frequency for the compressed ghost imaging technology and promotes the quality of the compressed ghost imaging reconstructed image.
Description
Technical field
The present invention relates to the compression ghost technical field of imaging calculated in shooting, particularly a kind of compression ghost image reconstruction method and system driven based on natural image block priori.
Background technology
In recent years, calculate shooting and learn and become the international forward position hot research in the fields such as intersecting sight, graphics, shooting, signal transacting, how to make full use of computing method and constantly promote new imaging device and cause and pay close attention to widely.The imaging that ghost is imaged as in the serious environment of illumination condition complexity, noise provides a kind of formation method flexibly newly, utilizes fully to calculate the performance tool that means that shooting learns promote this imaging and be of great significance.
The development of ghost imaging technique is substantially through three main stages, there is the optical imaging device blank of its correspondence: the terrible imaging technique that first Bennink et.al proposed in 2002, this imaging technique is a kind of two-photon relevance imaging technology based on quantum strength fluctuation relevance theory, the conjunction coupling of the information that this imaging technique utilizes two-way light path to collect, achieve utilize non-space to resolve detector to the collection of scene and reconstruct, the terrible imaging device at this initial stage is also known as the imaging of quantum ghost; The people such as Gatti et.al proposed this formation method theoretical foundation in 2004 is not only confined to quantum optics theory, and classical optical theory is suitable for too.They propose to utilize pseudo-thermal light source substitution amount sub-light source in quantum ghost imaging device, and successfully achieve the relevance imaging technology approximate with quantum light source effect, this is the second stage of terrible imaging progress, classical terrible imaging; In order to promote the application potential of terrible imaging technique further, 2009, the people such as J.Shapiroet.al propose to replace the high-resolution imaging in reference path, and the terrible imaging technique utilizing the spatial light modulator can remembering and store light illumination mode, that is: calculate terrible imaging.In the terrible imaging of calculating, single pixel harvester is very flexible, is easy to be expanded in different collection dimensions, such as during three-dimensional terrible imaging in the expansion of attitude dimension, and multispectral section of terrible imaging is expansion ghost being imaged on to spectral coverage dimension.
In theory, terrible imaging technique is the associated light theory based on being different from traditional optical theory.Traditional optical directly observes the distribution of distribution of light intensity and measure, and association optics is then correlation measurement to the intensity of light field and observation.The single order related information (intensity and position phase) of light field that what existing imaging technique mainly utilized is, and ' ghost ' imaging mainly utilizes the double velocity correlation information of light field, essentially, double velocity correlation is a kind of measurement of statistical correlation of strength fluctuation.This statistical correlation is measured can the noise introduced due to optical environment disturbance in optic path process of the minimizing of high degree, for the imaging in the terrible imaging device optical environment such as complicated and noise is serious at optical condition provides theoretical foundation, the terrible imaging of such as remote sensing.
Summary of the invention
Object of the present invention is intended at least solve one of above-mentioned technological deficiency.
For this reason, one object of the present invention is to propose a kind of compression ghost image reconstruction method driven based on natural image block priori.The method effectively reduces the times of collection of compression required for terrible imaging technique, and improves the quality compressing terrible image reconstruction image.
Another object of the present invention is to propose a kind of compression ghost image reconstruction system driven based on natural image block priori.
To achieve these goals, the embodiment of a first aspect of the present invention discloses a kind of compression ghost image reconstruction method driven based on natural image block priori, comprises the following steps: extract multiple image block from each natural image of natural image database; By the mistake complete expression dictionary base of described multiple image block Learning from Nature image, the projection coefficient of natural image block on described mistake complete expression dictionary base is made to have sparse characteristic; According to described mistake complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness under described mistake complete expression dictionary base of openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained, thus realize the reconstruct to natural image.
According to the compression ghost image reconstruction method driven based on natural image block priori of the embodiment of the present invention, analyze redundancy and the similarity of natural scene image block, sparse coding technological learning is utilized to have the excessively complete dictionary of sparse projection coefficient, introduce the mistake complete expression base of image local under based on the terrible image reconstruction algorithm frame of compressive sensing theory and retrain the openness again modeling that complete terrible imaging of image block under this expression base, thus the quality reconstruction of terrible image reconstruction image under improving again same times of collection.Embodiments of the invention utilize the prior imformation of the local of natural image, and combine the restructing algorithm based on the terrible imaging technique of compressive sensing theory, realize the efficient of terrible imaging technique and high-quality reconstruct.
In addition, the compression ghost image reconstruction method driven based on natural image block priori according to the above embodiment of the present invention can also have following additional technical characteristic:
In some instances, described each natural image from natural image database extracts multiple image block, comprises further: according to sparse coding algorithm, and from each natural image of natural image database, image block is extracted in multiple random position.
In some instances, described mistake complete expression dictionary base source analysis, comprise: the set being obtained the primitive structure base of natural scene by sparse coding training study, the set of described primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
In some instances, also comprise: according to the prior imformation of natural scene, train described mistake complete expression dictionary base.
In some instances, described prior imformation comprises the classification of natural scene.
The embodiment of second aspect present invention discloses a kind of compression ghost image reconstruction system driven based on natural image block priori, comprising: extraction module, extracts multiple image block for each natural image from natural image database; Training module, for the mistake complete expression dictionary base by described multiple image block Learning from Nature image, makes the projection coefficient of natural image block on described mistake complete expression dictionary base have sparse characteristic; Reconstructed module, for according to described mistake complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness under described mistake complete expression dictionary base of openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained, thus realize the reconstruct to natural image.
According to the compression ghost image reconstruction system driven based on natural image block priori of the embodiment of the present invention, analyze redundancy and the similarity of natural scene image block, sparse coding technological learning is utilized to have the excessively complete dictionary of sparse projection coefficient, introduce the mistake complete expression base of image local under based on the terrible image reconstruction algorithm frame of compressive sensing theory and retrain the openness again modeling that complete terrible imaging of image block under this expression base, thus the quality reconstruction of terrible image reconstruction image under improving again same times of collection.Embodiments of the invention utilize the prior imformation of the local of natural image, and combine the restructing algorithm based on the terrible imaging technique of compressive sensing theory, realize the efficient of terrible imaging technique and high-quality reconstruct.
In addition, the compression ghost image reconstruction system driven based on natural image block priori according to the above embodiment of the present invention can also have following additional technical characteristic:
In some instances, described extraction module is used for: according to sparse coding algorithm, and from each natural image of natural image database, image block is extracted in multiple random position.
In some instances, described mistake complete expression dictionary base source analysis, comprise: the set being obtained the primitive structure base of natural scene by sparse coding training study, the set of described primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
In some instances, described training module is used for: according to the prior imformation of natural scene, trains described mistake complete expression dictionary base.
In some instances, described prior imformation comprises the classification of natural scene.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein,
Fig. 1 is according to an embodiment of the invention based on the process flow diagram of the compression ghost image reconstruction method of natural image block priori driving;
Fig. 2 is the extraction schematic diagram of the natural image blocks of data of the embodiment of the present invention;
Fig. 3 is the mistake complete expression dictionary base schematic diagram of the natural scene image of the embodiment of the present invention;
Fig. 4 is the image block of the embodiment of the present invention and the relationship map figure of integral image;
Fig. 5 is that the natural image of the embodiment of the present invention is crossing the sparse expression schematic diagram under complete expression dictionary base; And
Fig. 6 is according to an embodiment of the invention based on the structured flowchart of the compression ghost image reconstruction system of natural image block priori driving.
Embodiment
Be described below in detail embodiments of the invention, the example of embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.
In describing the invention, it will be appreciated that, term " " center ", " longitudinal direction ", " transverse direction ", " on ", D score, " front ", " afterwards ", " left side ", " right side ", " vertically ", " level ", " top ", " end ", " interior ", orientation or the position relationship of the instruction such as " outward " are based on orientation shown in the drawings or position relationship, only the present invention for convenience of description and simplified characterization, instead of indicate or imply that the device of indication or element must have specific orientation, with specific azimuth configuration and operation, therefore limitation of the present invention can not be interpreted as.In addition, term " first ", " second " only for describing object, and can not be interpreted as instruction or hint relative importance.
In describing the invention, it should be noted that, unless otherwise clearly defined and limited, term " installation ", " being connected ", " connection " should be interpreted broadly, and such as, can be fixedly connected with, also can be removably connect, or connect integratedly; Can be mechanical connection, also can be electrical connection; Can be directly be connected, also indirectly can be connected by intermediary, can be the connection of two element internals.For the ordinary skill in the art, concrete condition above-mentioned term concrete meaning in the present invention can be understood.
Below in conjunction with accompanying drawing, the compression ghost image reconstruction method and system driven based on natural image block priori according to the embodiment of the present invention are described.
Fig. 1 is according to an embodiment of the invention based on the process flow diagram of the compression ghost image reconstruction method of natural image block priori driving.As shown in Figure 1, according to an embodiment of the invention based on the compression ghost image reconstruction method that natural image block priori drives, comprise the steps:
S101: extract multiple image block from each natural image of natural image database.
In one embodiment of the invention, can according to sparse coding algorithm, from each natural image of natural image database, image block is extracted in multiple random position.Such as: for each image in natural image storehouse, determined the position of the image block that will extract by random mode, the image block of 8*8 size picture of publishing picture is intercepted from this position.
Specifically, as shown in Figure 2, the extraction of natural image block, by gathering the position of image block to random the choosing of each image in natural data storehouse, 300 high-quality natural images altogether, often open image zooming-out 250 image blocks, image block position choose completely random, obtain the study of 75000 image blocks for the complete base of mistake of natural scene image block.
S102: by the mistake complete expression dictionary base of multiple image block Learning from Nature image, makes the projection coefficient of natural image block on the complete expression dictionary base of mistake have sparse characteristic.
Wherein, for the source analysis crossing complete sparse expression base (that is: crossing complete expression dictionary base), consider that the natural scene image block of low-dimensional is compared to global scene image, there is redundancy and the similarity of height more, obtained the set of the primitive structure base of natural scene by efficient sparse coding training study, the set of this primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
As shown in Figure 3, by learning complete expression dictionary base to the natural image block after stochastic sampling in step S101, make natural image block cross on complete expression dictionary base and can high precision rebuild, its projection coefficient only has the nonzero element of minimum ratio simultaneously, namely has sparse characteristic.The study of crossing complete expression dictionary base will learn from dissimilar natural scene image, thus makes its sparse reconstruct for natural scene image block have universality.Specifically, crossing the study of complete expression dictionary base, by learning complete base to the natural image block after stochastic sampling in previous step, making natural image block cross on complete base and can high precision rebuild, its projection coefficient only has the nonzero element of minimum ratio simultaneously, namely has sparse characteristic.The study of crossing complete expression dictionary base will learn from dissimilar natural scene image, thus makes its sparse reconstruct for natural scene image block have universality.
In one embodiment of the invention, also comprise: according to the prior imformation of natural scene, trained complete expression dictionary base.Wherein, prior imformation includes but not limited to: the classification of natural scene.
S103: according to crossing complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained to cross under complete expression dictionary base openness, thus realize the reconstruct to natural image.
As shown in Figure 4, relation between natural image and natural image block can be converted by a positive and negative linear mapping, by this transformation relation, can combine, to the algorithm modeling again of terrible imaging based on the compression ghost restructing algorithm of imaging of whole scene and the fast priori of natural scene image.
As shown in Figure 5, training under mistake complete expression dictionary base out, the image block of natural scene can realize sparse Its Sparse Decomposition, that namely trains out is excessively completely expressed base, can realize high precision and the sparse expression to scene image block, this is also the origin of the modeling again of the embodiment of the present invention.
The restructing algorithm of the compression ghost imaging that natural image block priori drives, the image block of main local projects sparse attribute with overall structural information as prior-constrained excessively complete being expressed on base, thus can reconstruct high-quality terrible imaging from less sampled data.
According to the compression ghost image reconstruction method driven based on natural image block priori of the embodiment of the present invention, analyze redundancy and the similarity of natural scene image block, sparse coding technological learning is utilized to have the excessively complete dictionary of sparse projection coefficient, introduce the mistake complete expression base of image local under based on the terrible image reconstruction algorithm frame of compressive sensing theory and retrain the openness again modeling that complete terrible imaging of image block under this expression base, thus the quality reconstruction of terrible image reconstruction image under improving again same times of collection.Embodiments of the invention utilize the prior imformation of the local of natural image, and combine the restructing algorithm based on the terrible imaging technique of compressive sensing theory, realize the efficient of terrible imaging technique and high-quality reconstruct.
Fig. 6 is according to an embodiment of the invention based on the structured flowchart of the compression ghost image reconstruction system of natural image block priori driving.As shown in Figure 6, according to an embodiment of the invention based on the compression ghost image reconstruction system 600 that natural image block priori drives, comprising: extraction module 610, training module 620 and reconstructed module 630.
Wherein, extraction module 610 extracts multiple image block for each natural image from natural image database.Training module 620, for the mistake complete expression dictionary base by multiple image block Learning from Nature image, makes the projection coefficient of natural image block on the complete expression dictionary base of mistake have sparse characteristic.Reconstructed module 630 is for according to crossing complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained to cross under complete expression dictionary base openness, thus realize the reconstruct to natural image.
In one embodiment of the invention, extraction module 610 is for according to sparse coding algorithm, and from each natural image of natural image database, image block is extracted in multiple random position.
In one embodiment of the invention, cross complete expression dictionary base source analysis, comprise: the set being obtained the primitive structure base of natural scene by sparse coding training study, the set of described primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
In one embodiment of the invention, training module 620, for the prior imformation according to natural scene, trains described mistake complete expression dictionary base.Further, prior imformation comprises the classification of natural scene.
According to the compression ghost image reconstruction system driven based on natural image block priori of the embodiment of the present invention, analyze redundancy and the similarity of natural scene image block, sparse coding technological learning is utilized to have the excessively complete dictionary of sparse projection coefficient, introduce the mistake complete expression base of image local under based on the terrible image reconstruction algorithm frame of compressive sensing theory and retrain the openness again modeling that complete terrible imaging of image block under this expression base, thus the quality reconstruction of terrible image reconstruction image under improving again same times of collection.Embodiments of the invention utilize the prior imformation of the local of natural image, and combine the restructing algorithm based on the terrible imaging technique of compressive sensing theory, realize the efficient of terrible imaging technique and high-quality reconstruct.
It should be noted that, the specific implementation of the terrible image reconstruction method of compression driven based on natural image block priori of the specific implementation of the compression ghost image reconstruction system driven based on natural image block priori of the embodiment of the present invention and the embodiment of the present invention is similar, specifically refer to the description of method part, in order to reduce redundancy, do not repeat.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, those of ordinary skill in the art can change above-described embodiment within the scope of the invention when not departing from principle of the present invention and aim, revising, replacing and modification.
Claims (10)
1., based on the compression ghost image reconstruction method that natural image block priori drives, it is characterized in that, comprise the following steps:
Multiple image block is extracted from each natural image of natural image database;
By the mistake complete expression dictionary base of described multiple image block Learning from Nature image, the projection coefficient of natural image block on described mistake complete expression dictionary base is made to have sparse characteristic;
According to described mistake complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness under described mistake complete expression dictionary base of openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained, thus realize the reconstruct to natural image.
2. the compression ghost image reconstruction method driven based on natural image block priori according to claim 1, it is characterized in that, described each natural image from natural image database extracts multiple image block, comprises further:
According to sparse coding algorithm, from each natural image of natural image database, image block is extracted in multiple random position.
3. the compression ghost image reconstruction method driven based on natural image block priori according to claim 1, it is characterized in that, described mistake complete expression dictionary base source analysis, comprise: the set being obtained the primitive structure base of natural scene by sparse coding training study, the set of described primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
4. the compression ghost image reconstruction method driven based on natural image block priori according to any one of claim 1-3, is characterized in that, also comprise: according to the prior imformation of natural scene, train described mistake complete expression dictionary base.
5. the compression ghost image reconstruction method driven based on natural image block priori according to claim 4, it is characterized in that, described prior imformation comprises the classification of natural scene.
6., based on the compression ghost image reconstruction system that natural image block priori drives, it is characterized in that, comprising:
Extraction module, extracts multiple image block for each natural image from natural image database;
Training module, for the mistake complete expression dictionary base by described multiple image block Learning from Nature image, makes the projection coefficient of natural image block on described mistake complete expression dictionary base have sparse characteristic;
Reconstructed module, for according to described mistake complete expression dictionary base, incidence relation between image block and natural image, again modeling is carried out to the restructing algorithm of the compressed sensing of terrible imaging, and openness under described mistake complete expression dictionary base of openness, the topography block of image overall under gradient field or two-dimension discrete cosine transform is retrained, thus realize the reconstruct to natural image.
7. the compression ghost image reconstruction system driven based on natural image block priori according to claim 6, it is characterized in that, described extraction module is used for: according to sparse coding algorithm, and from each natural image of natural image database, image block is extracted in multiple random position.
8. the compression ghost image reconstruction system driven based on natural image block priori according to claim 6, it is characterized in that, described mistake complete expression dictionary base source analysis, comprise: the set being obtained the primitive structure base of natural scene by sparse coding training study, the set of described primitive structure base was the block image of complete sparse expression natural scene that also can be pervasive.
9. the compression ghost image reconstruction system driven based on natural image block priori according to any one of claim 6-8, it is characterized in that, described training module is used for: according to the prior imformation of natural scene, trains described mistake complete expression dictionary base.
10. the compression ghost image reconstruction system driven based on natural image block priori according to claim 9, it is characterized in that, described prior imformation comprises the classification of natural scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173941.XA CN104778665B (en) | 2015-04-14 | 2015-04-14 | Compression ghost image reconstruction method and system based on the driving of natural image block priori |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173941.XA CN104778665B (en) | 2015-04-14 | 2015-04-14 | Compression ghost image reconstruction method and system based on the driving of natural image block priori |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104778665A true CN104778665A (en) | 2015-07-15 |
| CN104778665B CN104778665B (en) | 2018-12-11 |
Family
ID=53620113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510173941.XA Expired - Fee Related CN104778665B (en) | 2015-04-14 | 2015-04-14 | Compression ghost image reconstruction method and system based on the driving of natural image block priori |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104778665B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570876A (en) * | 2016-10-24 | 2017-04-19 | 南京理工大学 | Ghost imaging image edge extracting method |
| CN107730451A (en) * | 2017-09-20 | 2018-02-23 | 中国科学院计算技术研究所 | A kind of compressed sensing method for reconstructing and system based on depth residual error network |
| CN109073777A (en) * | 2018-07-25 | 2018-12-21 | 合刃科技（深圳）有限公司 | A kind of hidden substance detecting system and method |
| CN109342462A (en) * | 2018-10-12 | 2019-02-15 | 贵州民族大学 | Neutron ghost imager |
| CN110646810A (en) * | 2019-09-27 | 2020-01-03 | 北京理工大学 | Speckle optimization compressed sensing ghost imaging method and system |
| CN112203089A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Image compression method, system and device based on code rate control of sparse coding |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708576A (en) * | 2012-05-18 | 2012-10-03 | 西安电子科技大学 | Method for reconstructing partitioned images by compressive sensing on the basis of structural dictionaries |
| CN102724020A (en) * | 2012-06-13 | 2012-10-10 | 华为技术有限公司 | Signal processing method, system and communication device based on sparse degree estimation |
| CN103247034A (en) * | 2013-05-08 | 2013-08-14 | 中国科学院光电研究院 | Sparse-spectrum-dictionary hyperspectral image reconstruction method by using compressed sensing |
| CN103440675A (en) * | 2013-07-30 | 2013-12-11 | 湖北工业大学 | Overall situation reconstitution optimization model construction method for image block compressed sensing |
| CN103530863A (en) * | 2013-10-30 | 2014-01-22 | 广东威创视讯科技股份有限公司 | Multistage reconstruction image super resolution method |
| CN103903261A (en) * | 2014-03-24 | 2014-07-02 | 西安电子科技大学 | Spectrum image processing method based on partition compressed sensing |
-
2015
- 2015-04-14 CN CN201510173941.XA patent/CN104778665B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708576A (en) * | 2012-05-18 | 2012-10-03 | 西安电子科技大学 | Method for reconstructing partitioned images by compressive sensing on the basis of structural dictionaries |
| CN102724020A (en) * | 2012-06-13 | 2012-10-10 | 华为技术有限公司 | Signal processing method, system and communication device based on sparse degree estimation |
| CN103247034A (en) * | 2013-05-08 | 2013-08-14 | 中国科学院光电研究院 | Sparse-spectrum-dictionary hyperspectral image reconstruction method by using compressed sensing |
| CN103440675A (en) * | 2013-07-30 | 2013-12-11 | 湖北工业大学 | Overall situation reconstitution optimization model construction method for image block compressed sensing |
| CN103530863A (en) * | 2013-10-30 | 2014-01-22 | 广东威创视讯科技股份有限公司 | Multistage reconstruction image super resolution method |
| CN103903261A (en) * | 2014-03-24 | 2014-07-02 | 西安电子科技大学 | Spectrum image processing method based on partition compressed sensing |
Non-Patent Citations (2)
| Title |
|---|
| JIANCHAO YANG ET AL: "Image super-resolution as sparse representation of raw image patches", 《IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
| JIANCHAO YANG ET AL: "Image Super-Resolution via Sparse Representation", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570876A (en) * | 2016-10-24 | 2017-04-19 | 南京理工大学 | Ghost imaging image edge extracting method |
| CN106570876B (en) * | 2016-10-24 | 2019-05-07 | 南京理工大学 | A method of extracting terrible image edge |
| CN107730451A (en) * | 2017-09-20 | 2018-02-23 | 中国科学院计算技术研究所 | A kind of compressed sensing method for reconstructing and system based on depth residual error network |
| CN107730451B (en) * | 2017-09-20 | 2020-06-05 | 中国科学院计算技术研究所 | Compressed sensing reconstruction method and system based on depth residual error network |
| CN109073777A (en) * | 2018-07-25 | 2018-12-21 | 合刃科技（深圳）有限公司 | A kind of hidden substance detecting system and method |
| WO2020019204A1 (en) * | 2018-07-25 | 2020-01-30 | 合刃科技（深圳）有限公司 | System and method for detecting stealthy object |
| CN109073777B (en) * | 2018-07-25 | 2020-07-31 | 合刃科技（深圳）有限公司 | Stealth object detection system and method |
| CN109342462A (en) * | 2018-10-12 | 2019-02-15 | 贵州民族大学 | Neutron ghost imager |
| CN109342462B (en) * | 2018-10-12 | 2021-10-01 | 贵州民族大学 | Neutron ghost imager |
| CN110646810A (en) * | 2019-09-27 | 2020-01-03 | 北京理工大学 | Speckle optimization compressed sensing ghost imaging method and system |
| CN112203089A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Image compression method, system and device based on code rate control of sparse coding |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104778665B (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778665A (en) | Compressed ghost imaging reconstruction method based on natural image block prior driving and system | |
| CN101794440B (en) | Weighted adaptive super-resolution reconstructing method for image sequence | |
| CN103729853B (en) | High score remote sensing image building under three-dimension GIS auxiliary damages detection method | |
| CN105654492A (en) | Robust real-time three-dimensional (3D) reconstruction method based on consumer camera | |
| CN105335929B (en) | A kind of depth map ultra-resolution method | |
| CN108389226A (en) | A kind of unsupervised depth prediction approach based on convolutional neural networks and binocular parallax | |
| CN104156957B (en) | Stable and high-efficiency high-resolution stereo matching method | |
| CN103227888B (en) | A kind of based on empirical mode decomposition with the video stabilization method of multiple interpretational criteria | |
| CN106930770B (en) | Shield machine shield gap estimation method based on convolutional neural networks | |
| CN103268629B (en) | Unmarked some real time restoration method of 3 D human body form and attitude | |
| CN103077511A (en) | Image super-resolution reconstruction method based on dictionary learning and structure similarity | |
| CN103279935A (en) | Method and system of thermal infrared remote sensing image super-resolution reconstruction based on MAP algorithm | |
| CN101299235A (en) | Method for reconstructing human face super resolution based on core principle component analysis | |
| CN103871087B (en) | The mixed compression sensing method of EO-1 hyperion solution based on three-dimensional total variation sparse prior | |
| CN105139339A (en) | Polarization image super-resolution reconstruction method based on multi-level filtering and sample matching | |
| CN116258658B (en) | Swin transducer-based image fusion method | |
| Dal Poz et al. | Dynamic programming approach for semi-automated road extraction from medium-and high-resolution images | |
| CN103020939A (en) | Method for removing large-area thick clouds for optical remote sensing images through multi-temporal data | |
| CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection | |
| CN105634498A (en) | Observation matrix optimization method | |
| CN104091364B (en) | Single-image super-resolution reconstruction method | |
| Jiang et al. | Efficient match pair selection for oblique UAV images based on adaptive vocabulary tree | |
| CN106203269A (en) | A kind of based on can the human face super-resolution processing method of deformation localized mass and system | |
| CN103839075A (en) | SAR image classification method based on united sparse representation | |
| CN107590782A (en) | A kind of spissatus minimizing technology of high-resolution optical image based on full convolutional network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181211 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |