CN106485742A - A kind of remote sensing images based on Arnold chaotic maps encrypt search method - Google Patents
A kind of remote sensing images based on Arnold chaotic maps encrypt search method Download PDFInfo
- Publication number
- CN106485742A CN106485742A CN201610590717.5A CN201610590717A CN106485742A CN 106485742 A CN106485742 A CN 106485742A CN 201610590717 A CN201610590717 A CN 201610590717A CN 106485742 A CN106485742 A CN 106485742A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing images
- encryption
- gray
- search method
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
- G06T2201/0052—Embedding of the watermark in the frequency domain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of remote sensing images based on Arnold chaotic maps encrypt search method, the method comprising the steps of：Step S1：Preprocessing of remote sensing images；Step S2：The extraction of Characteristics of The Remote Sensing Images vector；Step S3：The encipherment protection of remote sensing images；Step S4：The similitude coupling of remote sensing images；Step S5：The deciphering of remote sensing images and the inverse process of remote sensing images encryption.Its advantage shows：Applying to remote sensing images field based on Arnold chaotic maps encryption method; protect safety storage of the remote sensing images under cloud environment; by setting up the associate feature in plain text and between ciphertext, data consumer is enable directly to carry out safe retrieval by cloud computing to ciphertext remote sensing images.
Description
Technical field
The present invention relates to remote sensing images encryption and its retrieval process field, and in particular to a kind of based on Arnold chaotic maps
Remote sensing images encryption search method.
Background technology
Under the background of information globalization, remote sensing is with its visualization, globalization, networking and intelligentized feature, distant
Sense technology has shown the achievement except attracting people's attention in all trades and professions.Modern remote sensing technology in terms of acquisition of information
Big advantage and potentiality are shown, while its unique technology glamour is also show in terms of Data Analysis Services.Remote sensing
Technology can provide a large amount of abundant information for people.The remotely-sensed data that sensor can be obtained by remote sensing technology is changed into can profit
Information is simultaneously utilized by us.
Remote sensing is a kind of method of long-range detection object technology, by the imaging spectrometer acquisition figure being mounted on satellite
As information, the terrestrial object information for observing is obtained according to the electromagnetic wave of target reflection and radiation, and which is analyzed process.Become
As spectrometer is combined together by will determine the spectrum of atural object and the image of expression atural object space characteristics, produce one group can be simultaneously
Reflection atural object spatial information and its two dimensional image of spectral information, the data characteristicses with " collection of illustrative plates ", are combined well
Image and the advantage of spectroscopic data.Pixel in remote sensing image is mixed by the feedback information of several atural objects, seldom
Be made up of single atural object, reflection but the mixed information of several atural objects.Frequency spectrum, can be very used as one of the energy of material
It is used as well distinguishing the important evidence of terrain object attribute.The frequency spectrum of image reflects the spatial distribution of pixel energy, characterizes
The spatial frequency features of atural object, and close connection is all there is with space characteristics such as the tone of atural object, texture, edge and directions
System.
With the fast development of Spatial Information Technology, remotely-sensed data as a kind of important space-time data, in environment
The major areas such as monitoring, hazard forecasting, national defense safety play indispensable important function.The recall precision of remote sensing images and
Precision, directly affects popularity and the real-time of remote sensing image data application.
Chinese patent literature CN201410802048.4, applying date 2014.12.22, patent name is：One kind is supervised based on nothing
Remote sensing image retrieval method and the system of feature learning is superintended and directed, remote sensing image retrieval method based on unsupervised feature learning and is
System, including extracting notable figure respectively to retrieving each image in image library, and obtains corresponding two according to the segmentation threshold of notable figure
Value notable figure；To retrieving each image in image library, it is partitioned into significantly by mask computing according to corresponding binaryzation notable figure
Region；Equivalently-sized image block is extracted from salient region of image and training sample is constructed, and utilize unsupervised feature learning method
Sample is trained to learn the feature of image；Finally, image retrieval is carried out.The present invention extracts size from the marking area of image
Identical image block is configured to the training sample of unsupervised feature learning, compensate for traditional direct carry out on original image with
The defect of machine sampling, the vision attention feature for not only conforming with human eye and the Search Requirement that more can directly reflect people, are protecting
The characteristic extraction procedure of complexity is eliminated while card retrieval precision ratio.
However, above-mentioned with regard to remote Sensing Image Retrieval scheme only with regard to feature in picture material, mixed with regard to Arnold
The remote sensing images encryption retrieval of ignorant mapping is not then corresponding to be reported.
In sum, traditional images encryption be by the displacement of pixel and obscuring, wherein the scramble of pixel with obscure past
Toward being split as two relatively low isolated links of coupling, and the retrieval of ciphertext is all built upon on the basis of index,
Need badly a kind of safe, the possibility penetrated is lower, attack tolerant, set up relation in plain text and between ciphertext to be pacified
The remote sensing images based on Arnold chaotic maps of full search encrypt search method.
Content of the invention
The purpose of the present invention is for deficiency of the prior art, provides a kind of safe, and the possibility that is penetrated is more
Low, attack tolerant, set up relation in plain text and between ciphertext to carry out the remote sensing based on Arnold chaotic maps of safe search
Image encryption search method.
For achieving the above object, this technical scheme for adopting is：
A kind of remote sensing images based on Arnold chaotic maps encrypt search method, the method comprising the steps of：
Step S1：Preprocessing of remote sensing images；
Step S11：The process that carries out of border of the remote sensing images to encrypting, makes the length of remote sensing images and wide equal；
Step S12：Denoising is carried out to remote sensing images using the full variation denoising model of self adaptation, by combining impact filter
Ripple device and nonlinear anisotropic diffusion wave filter, and auto-adaptive parameter is chosen using edge detection operator, to the distant of Noise
Sense image carries out smoothing denoising and retains local edge；
Step S2：The extraction of Characteristics of The Remote Sensing Images vector, specially：Using the remotely-sensed data of 8 satellite of Landsat, will be per
The gray value of individual figure layer quantifies to 0～255, according to the spectral signature of remote sensing images and the threshold range of setting：[0,63], [64,
127], [128,191], [192,255], gray value is divided into 5*11 group space, counts the feature of every width remote sensing images
Vector；
Step S3：The encipherment protection of remote sensing images；
Step S31：Chaos sequence is generated, former remote sensing images is carried out with the unrest encryption of frequency domain, makes the gray value of remote sensing images
Confusion is able on the position in space；
Step S32：XOR, chaos matrix of the initial pictures with generation in above-mentioned steps S31 is carried out XOR,
Obtain the remote sensing images that encrypts；
Step S4：The similitude coupling of remote sensing images；
Step S5：The deciphering of remote sensing images and the inverse process of remote sensing images encryption.
Preferably, remote sensing images are encrypted in step S31, are mapped using the Arnold after delivery：
It is wherein the pixel value position of former remote sensing images, for carrying out the pixel value locus after gray chaos, p and q is
Positive integer, k are the number of times of encryption iteration, M be conversion process after the line number of remote sensing images and columns.
Preferably, in step S32 remote sensing images frequency domain encryption, specially：The method that is encrypted using XOR is to remote sensing figure
As carrying out obscuring for gray value：
For the gray scale value matrix of remote sensing images after encryption, it is and the equal-sized random matrix of remote sensing images, is corresponding
Gray matrix on locus, represents the gray scale interval maximum of remote sensing images.
Preferably, carry out corresponding process to convert to random matrix, make random matrix frequency domain computing be carried out with remote sensing images
Original characteristic vector can also be kept afterwards, convenient retrieval coupling can be carried out to the remote sensing images that encrypts.
Preferably, according to the extracting method of the characteristic vector of remote sensing images, the remote sensing figure before being encrypted in step S4
The characteristic vector of picture, if its corresponding characteristic vector of the remote sensing images after being encrypted is；When Minkowski distance most
In short-term, i.e.,Satisfactory ciphertext graph picture is retrieved, wherein P is a variable element, according to
The difference of parameter, can accurately navigate to target image.
Preferably, step S5 inverse mapping is：
It is wherein the pixel value position of original image, is the gray matrix of original image；For the pixel value position after change, for changing
Gray scale value matrix after change.
The invention has the advantages that：
1st, remote sensing images field is applied to based on Arnold chaotic maps encryption method, remote sensing images are protected in cloud ring
Safety storage under border, by setting up the associate feature in plain text and between ciphertext, enables data consumer directly by cloud meter
Calculate to carry out safe retrieval to ciphertext remote sensing images.
2nd, the chaos sequence for producing is mapped with respect to the chaos produced by 1 dimensional Logistic Map using Arnold transformation
Sequence has higher security and attack tolerant, has good attack tolerant for the method for exhaustion；
3rd, well using chaos sequence to the sensitive this characteristic of initial value, when initial value has very fine distinction, energy
Completely different chaos sequence is enough produced；
4th, in order to avoid the autocorrelation between chaos sequence, we are using the chaos sequence of 1000 iteration formation afterwards
Row, so as to improve the security of ciphertext；
5th, this programme employs the method that XOR and mould plus and minus calculation combine so that cracker effectively cannot obtain
Chaos sequence is taken, for this is with respect to the method only image being encrypted with XOR, security is higher, is cracked
Possibility is lower.
6th, the gray value and locus to image is all encrypted, directly to adding in the case of indexing without the need for foundation
Close remote sensing images carry out safe retrieval.
Description of the drawings
Accompanying drawing 1 is a kind of remote sensing images encryption search method FB(flow block) based on Arnold chaotic maps of the present invention.
Accompanying drawing 2 is remote sensing images border zero padding schematic diagram.
Accompanying drawing 3 is the quantized result figure of remote sensing images.
Accompanying drawing 4 is the characteristic vector pickup flow chart of remote sensing images.
Accompanying drawing 5 is the encryption and decryption flow chart based on Arnold chaotic maps.
Accompanying drawing 6 is the safe retrieval flow chart of remote sensing images.
Specific embodiment
Below in conjunction with the accompanying drawings the specific embodiment that the present invention is provided is elaborated.
Embodiment 1
Refer to a kind of remote sensing images encryption search method stream based on Arnold chaotic maps that Fig. 1, Fig. 1 are the present invention
Journey block diagram.A kind of remote sensing images based on Arnold chaotic maps encrypt search method, and described remote sensing images encrypt retrieval side
Method is comprised the following steps：
Step S1：Preprocessing of remote sensing images；
Remote sensing images can be affected by external environment condition during acquisition and transmission, obtain the quality of image following
Drop, the analysis to remote sensing images and identification bring certain difficulty.Therefore using front needing to carry out at noise reduction remote sensing images
Reason, is enhanced the spectral signature of remote sensing images, it is therefore an objective to improve the separability of remote sensing image, while also reducing to part
The requirement that noise data is processed.
Step S11：This programme adopts the AES based on Arnold chaotic maps, it is therefore desirable to the remote sensing figure that encrypts
The process that the border of picture is carried out, makes the length of remote sensing images and wide equal.
Step S12：Denoising is carried out to remote sensing images using self adaptation full variation (ATV) denoising model, by joint
Shock filter and nonlinear anisotropic diffusion wave filter, and auto-adaptive parameter is chosen using edge detection operator, to noisy
The remote sensing images of sound carry out smoothing denoising and retain local edge.
Step S2：The extraction of Characteristics of The Remote Sensing Images vector；
The initial data of remote sensing images is made up of DN value, is converted into actual physical meaning through radiation calibration
Reflectance value.The DN value scope of remote sensing images be by sensor quantization level determining, if the quantization of 8bit, then DN
The scope of value is 0～255.The remotely-sensed data of main 8 satellite of employing Landsat of this programme, by the gray value amount of each figure layer
Change to 0～255, then the gray space of whole remote sensing images has 25611 kinds of colors, with larger gray space value.For
Higher matching probability can be had, on the basis of many experiments, we choose following four threshold range, are respectively
[0,63], [64,127], [128,191], [192,255], gray value is divided into 5*11 group space, and (Landsat8 satellite is altogether
Have 11 wave bands), we can count the characteristic vector of often width remote sensing images on this basis.
Step S3：The encryption method of the remote sensing images mapped based on Arnold；
Step S31：When being encrypted to remote sensing images, we are using the Arnold mapping after delivery：
It is wherein the pixel value position of former remote sensing images, for carrying out the pixel value locus after gray chaos, p and q is
Positive integer, k are the number of times of encryption iteration, M be conversion process after the line number of remote sensing images and columns；
Step S32：The frequency domain encryption of remote sensing images；
The method that this programme is mainly encrypted using XOR carries out gray value to remote sensing images and obscures：
(2)
For the gray scale value matrix of remote sensing images after encryption, it is and the equal-sized random matrix of remote sensing images, is corresponding
Gray matrix on locus, represents the gray scale interval maximum of remote sensing images.
Convenient retrieval coupling is carried out in order to the remote sensing images to encrypting, it would be desirable to which random matrix is carried out accordingly
Process conversion, make random matrix and remote sensing images keep original characteristic vector after carrying out frequency domain computing.
Step 4：The similitude coupling of remote sensing images；
According to the extracting method of the characteristic vector of remote sensing images, we can be encrypted before remote sensing images feature
Vector, if its corresponding characteristic vector of the remote sensing images after we can be encrypted in the same manner is.
When Minkowski distance most in short-term, i.e.,Retrieve satisfactory ciphertext
Image.Wherein P is a variable element, according to the difference of parameter, can accurately navigate to target image.
Step 5：The deciphering of remote sensing images and the inverse process of remote sensing images encryption
According to the AES in step 3, it is known that its inverse mapping is：
It is wherein the pixel value position of original image, is the gray matrix of original image；For the pixel value position after change, for changing
Gray scale value matrix after change.
It is and the equirotal random matrix of artwork that the algorithm which obtains is as follows：
The interval section of stochastic variable be on the basis of many experiments determine, in order that characteristic vector be evenly distributed and
Set.
Embodiment 2
For more preferably vivid understanding technique scheme, 2- Fig. 6 is further illustrated below in conjunction with the accompanying drawings, and the one of the present invention
Plant the encryption of the remote sensing images based on Arnold chaotic maps search method to comprise the following steps：
Step S1：Preprocessing of remote sensing images
Step S11：By the Boundary filling 0 (black) to image, the remote sensing images length of encryption and width is made to be even number；
Step S12：Using shock filter and nonlinear anisotropic diffusion wave filter to preprocessing of remote sensing images, flat
Retain edge and the grain details characteristic of original image while sliding noise；
Step S13：Auto-adaptive parameter x_f is calculated using Image Edge-Detection operator effect pretreatment image；
Step S14：According to above-mentioned auto-adaptive parameter x_f, we can obtain corresponding self adaptation Total Variation
(ATV), the corresponding noise in image is removed.
Step S2：The extraction of Characteristics of The Remote Sensing Images vector
According to the spectral signature of remote sensing images and the threshold range of setting：[0,63], [64,127], [128,191],
[192,255], count the corresponding characteristic vector of remote sensing images.
Step S3：The encipherment protection of remote sensing images
Using a kind of remote sensing image encryption method based on Arnold chaotic maps, pixel permutation is being carried out to remote sensing images
While with obscuring, it is ensured that the characteristic vector of remote sensing images is constant.
Step S31：Chaos sequence is generated, former remote sensing images is carried out with the unrest encryption of frequency domain, makes the gray value of remote sensing images
Confusion is able on the position in space；
Step S32：XOR, chaos matrix of the initial pictures with generation in above-mentioned steps is carried out XOR, is obtained
Remote sensing images to encryption；
Step S4：The similitude coupling of remote sensing images
If encryption before remote sensing images characteristic vector Γ 1, its corresponding feature of the remote sensing images after encryption to
Measure as Γ 2, according to AES, when Minkowski distance most in short-term, target image can be retrieved.
Step S5：The deciphering of remote sensing images and the inverse process of remote sensing images encryption.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, on the premise of without departing from the inventive method, can also make some improvement and supplement, and these improve and supplement also should be regarded as
Protection scope of the present invention.
Claims (6)
1. a kind of remote sensing images based on Arnold chaotic maps encrypt search method, it is characterised in that methods described include with
Lower step：
Step S1：Preprocessing of remote sensing images；
Step S11：The process that carries out of border of the remote sensing images to encrypting, makes the length of remote sensing images and wide equal；
Step S12：Denoising is carried out to remote sensing images using the full variation denoising model of self adaptation, by combining shock filter
With nonlinear anisotropic diffusion wave filter, and using edge detection operator choose auto-adaptive parameter, the remote sensing figure to Noise
As carrying out smoothing denoising and retaining local edge；
Step S2：The extraction of Characteristics of The Remote Sensing Images vector, specially：Using the remotely-sensed data of 8 satellite of Landsat, by each figure
The gray value of layer quantifies to 0～255, according to the spectral signature of remote sensing images and the threshold range of setting：[0,63], [64,
127], [128,191], [192,255], gray value is divided into 5*11 group space, counts the feature of every width remote sensing images
Vector；
Step S3：The encipherment protection of remote sensing images；
Step S31：Chaos sequence is generated, and former remote sensing images is carried out with the unrest encryption of frequency domain, the gray value of remote sensing images is made in sky
Between position on be able to confusion；
Step S32：XOR, chaos matrix of the initial pictures with generation in above-mentioned steps S31 is carried out XOR, is obtained
The remote sensing images of encryption；
Step S4：The similitude coupling of remote sensing images；
Step S5：The deciphering of remote sensing images and the inverse process of remote sensing images encryption.
2. remote sensing images according to claim 1 encrypt search method, it is characterised in that to remote sensing images in step S31
It is encrypted, is mapped using the Arnold after delivery：
It is wherein the pixel value position of former remote sensing images, for carrying out the pixel value locus after gray chaos, p and q is just whole
Number, k is the number of times of encryption iteration, M be conversion process after the line number of remote sensing images and columns.
3. remote sensing images according to claim 1 encrypt search method, it is characterised in that remote sensing images in step S32
Frequency domain encryption, specially：The method that is encrypted using XOR is carried out gray value to remote sensing images and obscures：
For the gray scale value matrix of remote sensing images after encryption, it is and the equal-sized random matrix of remote sensing images, is corresponding space
Gray matrix on position, represents the gray scale interval maximum of remote sensing images.
4. remote sensing images according to claim 2 encrypt search method, it is characterised in that random matrix is carried out accordingly
Conversion is processed, and makes random matrix keep original characteristic vector after frequency domain computing being carried out with remote sensing images, can be to adding
Close remote sensing images carry out convenient retrieval coupling.
5. remote sensing images according to claim 1 encrypt search method, it is characterised in that according to remote sensing images in step S4
Characteristic vector extracting method, the characteristic vector of the remote sensing images before being encrypted, if, the remote sensing figure after being encrypted
As its corresponding characteristic vector is；
When Minkowski distance most in short-term, i.e.,Satisfactory ciphertext graph picture is retrieved,
Wherein P is a variable element, according to the difference of parameter, can accurately navigate to target image.
6. remote sensing images according to claim 1 encrypt search method, it is characterised in that the inverse mapping of step S5 is：
It is wherein the pixel value position of original image, is the gray matrix of original image；For the pixel value position after change, be change after
Gray scale value matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610590717.5A CN106485742B (en) | 2016-07-26 | 2016-07-26 | A kind of remote sensing images encryption search method based on Arnold chaotic maps |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610590717.5A CN106485742B (en) | 2016-07-26 | 2016-07-26 | A kind of remote sensing images encryption search method based on Arnold chaotic maps |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106485742A true CN106485742A (en) | 2017-03-08 |
| CN106485742B CN106485742B (en) | 2019-08-23 |
Family
ID=58273140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610590717.5A Active CN106485742B (en) | 2016-07-26 | 2016-07-26 | A kind of remote sensing images encryption search method based on Arnold chaotic maps |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106485742B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507254A (en) * | 2017-08-18 | 2017-12-22 | 济南大学 | Compression of images encryption method based on arithmetic coding |
| CN108665964A (en) * | 2018-05-14 | 2018-10-16 | 江西理工大学应用科学学院 | A kind of medical image wavelet field real-time encryption and decryption algorithm based on multi-chaos system |
| CN112214781A (en) * | 2020-11-11 | 2021-01-12 | 广东新禾道信息科技有限公司 | Remote sensing image big data processing method and system based on block chain |
| CN112383523A (en) * | 2020-11-02 | 2021-02-19 | 国网电子商务有限公司 | Image encryption method and related device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2682884A1 (en) * | 2012-07-05 | 2014-01-08 | Perennity SPRL-BVBA | Apparatus for securely transferring, sharing and storing of medical images |
| CN103744976A (en) * | 2014-01-13 | 2014-04-23 | 北京工业大学 | Secure image retrieval method based on homomorphic encryption |
| CN104751401A (en) * | 2015-04-16 | 2015-07-01 | 大连大学 | Novel piecewise linear chaotic mapping image encrypting and encoding method |
| CN105761198A (en) * | 2016-02-24 | 2016-07-13 | 陕西师范大学 | Image selective encryption and decryption method based on dynamic probability and space-frequency domain compositing |
-
2016
- 2016-07-26 CN CN201610590717.5A patent/CN106485742B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2682884A1 (en) * | 2012-07-05 | 2014-01-08 | Perennity SPRL-BVBA | Apparatus for securely transferring, sharing and storing of medical images |
| CN103744976A (en) * | 2014-01-13 | 2014-04-23 | 北京工业大学 | Secure image retrieval method based on homomorphic encryption |
| CN104751401A (en) * | 2015-04-16 | 2015-07-01 | 大连大学 | Novel piecewise linear chaotic mapping image encrypting and encoding method |
| CN105761198A (en) * | 2016-02-24 | 2016-07-13 | 陕西师范大学 | Image selective encryption and decryption method based on dynamic probability and space-frequency domain compositing |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507254A (en) * | 2017-08-18 | 2017-12-22 | 济南大学 | Compression of images encryption method based on arithmetic coding |
| CN107507254B (en) * | 2017-08-18 | 2018-11-23 | 济南大学 | Compression of images encryption method based on arithmetic coding |
| CN108665964A (en) * | 2018-05-14 | 2018-10-16 | 江西理工大学应用科学学院 | A kind of medical image wavelet field real-time encryption and decryption algorithm based on multi-chaos system |
| CN112383523A (en) * | 2020-11-02 | 2021-02-19 | 国网电子商务有限公司 | Image encryption method and related device |
| CN112383523B (en) * | 2020-11-02 | 2022-02-22 | 国网电子商务有限公司 | Image encryption method, related device and storage medium |
| CN112214781A (en) * | 2020-11-11 | 2021-01-12 | 广东新禾道信息科技有限公司 | Remote sensing image big data processing method and system based on block chain |
| CN112214781B (en) * | 2020-11-11 | 2021-06-11 | 广东新禾道信息科技有限公司 | Remote sensing image big data processing method and system based on block chain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106485742B (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145131B (en) | Infrared and visible light image fusion method based on multiscale generation type countermeasure network | |
| Combinido et al. | A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images | |
| Chen et al. | Spatiotemporal remote sensing image fusion using multiscale two-stream convolutional neural networks | |
| CN106485742A (en) | A kind of remote sensing images based on Arnold chaotic maps encrypt search method | |
| Pacifici et al. | Automatic change detection in very high resolution images with pulse-coupled neural networks | |
| CN103886106B (en) | Remote sensing image safe-retrieval method based on spectral feature protection | |
| CN105469098A (en) | Precise LINDAR data ground object classification method based on adaptive characteristic weight synthesis | |
| De Martinao et al. | Classification of optical high resolution images in urban environment using spectral and textural information | |
| Liu et al. | Unsupervised hierarchical spectral analysis for change detection in hyperspectral images | |
| CN106815852B (en) | Color image evidence collecting method based on the extremely humorous transformation of quaternary number | |
| CN105096234B (en) | A kind of high spectrum image encryption method based on hybrid domain | |
| Du et al. | Fusion and classification of Beijing-1 small satellite remote sensing image for land cover monitoring in mining area | |
| Hu et al. | SPNet: A spectral patching network for end-to-end hyperspectral image classification | |
| Manoharan et al. | Pixel value differencing method based on CMYK colour model | |
| Al Shibli et al. | Artificial intelligent drone-based encrypted machine learning of image extraction using pretrained Convolutional Neural Network (CNN) | |
| Singh et al. | Exploring the optimal combination of image fusion and classification techniques | |
| CN111985450A (en) | Hyperspectral remote sensing image integrity authentication method applying perceptual hashing | |
| Luo et al. | Fusion of high spatial resolution optical and polarimetric SAR images for urban land cover classification | |
| Adam et al. | The assessment of invasive alien plant species removal programs using remote sensing and GIS in two selected reserves in the eThekwini Municipality, KwaZulu-Natal | |
| CN104865572A (en) | Polarization synthesis method based on interested target enhancement | |
| Simin et al. | Band selection of hyperspectral images based on Bhattacharyya distance | |
| Wang et al. | Image Fusion and Evaluation of Geological Disaster Based on Remote Sensing. | |
| Denaro et al. | Nonlinear relative radiometric normalization for Landsat 7 and Landsat 8 imagery | |
| Deng et al. | Application of Improved Image Hash Algorithm in Image Tamper Detection | |
| Aghighi et al. | Improved adaptive Markov random field based super-resolution mapping for mangrove tree identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |