CN107274441A - The wave band calibration method and system of a kind of high spectrum image - Google Patents
The wave band calibration method and system of a kind of high spectrum image Download PDFInfo
- Publication number
- CN107274441A CN107274441A CN201710447441.XA CN201710447441A CN107274441A CN 107274441 A CN107274441 A CN 107274441A CN 201710447441 A CN201710447441 A CN 201710447441A CN 107274441 A CN107274441 A CN 107274441A
- Authority
- CN
- China
- Prior art keywords
- image
- registration
- wave band
- point
- characteristic point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001228 spectrum Methods 0.000 title claims abstract description 24
- 230000009466 transformation Effects 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims abstract description 11
- 239000000284 extract Substances 0.000 claims abstract description 11
- 238000005070 sampling Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 238000003384 imaging method Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- 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
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of waveband registration method of high spectrum image, including：Some wave band is chosen as benchmark wave band, new image is generated and is used as benchmark image；Characteristic point is extracted on band image subject to registration, template window is extracted centered on characteristic point；Selection extracts search window, thick match point is obtained using template matching method with characteristic point identical coordinate as center on benchmark image；The thick transformation relation of band image subject to registration and benchmark image is set up, match point of the characteristic point on benchmark image is calculated, search window is extracted centered on the match point, smart match point is obtained using template matching method；The smart transformation relation of band image subject to registration and benchmark image is set up, the correction of band image subject to registration is completed.Using technical scheme, the wave band registration of unmanned plane high spectrum image can be automatically performed, makes all wave bands of unmanned plane high spectrum image that there is Space Consistency, processing speed is fast, and registration accuracy is high.
Description
Technical field
The invention belongs to Hyperspectral imagery processing technical field, it is related to a kind of unmanned plane high spectrum image waveband registration method
And system.
Background technology
Unmanned plane has the advantages that mobility is high, cost is low, in recent years small range large scaled cartography, emergency disaster relief,
It is widely used in terms of resource environment investigation, precision agriculture, one as satellite remote sensing and traditional air remote sensing important
Arbitrary way.Unmanned plane high-spectrum remote-sensing is compared with satellite high-spectrum remote-sensing its advantageous advantage, due to unmanned plane
Flying height is low, the existing abundant spectral information of high spectrum image of acquisition, also there is very high spatial resolution, spatial discrimination
Rate can reach a centimetre rank, and can apply to environmental monitoring, precision agriculture, (crop growing state judgement, agricultural output assessment, pest and disease damage are pre-
It is alert) in terms of.
The characteristics of due to unmanned plane itself and the imaging mode for the hyperspectral imager being mounted on unmanned plane, unmanned plane
The processing of high spectrum image is a no small challenge.The traditional hyperspectral imager being mounted on satellite has optical splitter, wave band
Between all be alignment, it is not necessary to carry out the registration between wave band.Unmanned plane particularly rotor type unmanned plane is limited due to load,
Generally several kilograms, it is impossible to carry traditional hyperspectral imager.The hyperspectral imager mostly frame carried on current unmanned plane
Width formula imager, using the imaging mode of continuous exposure, obtains multiwave high spectrum image.Unmanned plane exists during due to exposure
Motion, therefore between same scape image different-waveband alignd, it is necessary to carry out the registration between wave band.
The content of the invention
In view of this, the invention provides a kind of waveband registration method of high spectrum image, including：
Step S100, chooses some wave band as benchmark wave band, then respectively expands the image of the wave band up and down
Several pixels, generate new image and are used as benchmark image；
Step S200, characteristic point is extracted on band image subject to registration, and each characteristic point is extracted centered on characteristic point
Template window；
Step S300, to each characteristic point, selection and the characteristic point identical coordinate are on benchmark image
The heart, extracts search window, thick match point is obtained using template matching method；
Step S400, the thick transformation relation of band image subject to registration and benchmark image is set up based on the thick match point, right
Each characteristic point, calculates match point of the characteristic point on benchmark image, with described according to the thick transformation relation
With search window is extracted centered on point, smart match point is obtained using template matching method；
Step S500, the smart transformation relation of band image subject to registration and benchmark image is set up based on the smart match point, so
The correction of band image subject to registration is completed using the smart transformation relation afterwards；
Step S600, repeat step S200~S500, complete the registration of next wave band.
Further, before characteristic point is extracted, the enhancing that band image subject to registration protrude contrast is operated.
Further, the thick match point described in step S400 is to use stochastical sampling coherence method and least square method
Reject the later thick match point of Mismatching point, the smart match point described in step S500 be using stochastical sampling coherence method and
Least square method rejects the later smart match point of Mismatching point.
Further, after per registering a wave band, offset of the wave band relative to benchmark wave band is calculated, in step
In S300 to next wave band using characteristic point coordinate add offset after coordinate centered on extract search window.
Further, in step s 200, useOr SIFT or Harris or SURF is used as extraction characteristic point
Operator.
The present invention also provides a kind of wave band registration system of high spectrum image, including：
Benchmark image generation module, for choosing some wave band as benchmark wave band, then by the image of the wave band
Several pixels are respectively expanded in lower left and right, generate new image and are used as benchmark image；
Template window extraction module, for extracting characteristic point on band image subject to registration, is extracted centered on characteristic point
The template window of each characteristic point；
Thick matching module, for each characteristic point, being selected and the characteristic point identical coordinate on benchmark image
As center, search window is extracted, thick match point is obtained using template matching method；
Smart matching module, the thick conversion for being set up band image subject to registration and benchmark image based on the thick match point is closed
System, to each characteristic point, calculates match point of the characteristic point on benchmark image, with institute according to the thick transformation relation
State and extract search window centered on match point, smart match point is obtained using template matching method
Geometric correction module, the essence conversion for setting up band image subject to registration and benchmark image based on the smart match point
Relation, then completes the correction of band image subject to registration using the smart transformation relation；
Further, above-mentioned wave band registration system also includes image enhancement module, for before characteristic point is extracted, treating
Registering band image protrude the enhancing operation of contrast.
Further, above-mentioned wave band registration system also includes Mismatching point rejecting module, for consistent using stochastical sampling
Property method and least square method reject Mismatching point.
Further, above-mentioned wave band registration system also includes offset computing module, for after a registering wave band,
Calculate offset of the wave band relative to benchmark wave band.
Using above-mentioned technical proposal, the wave band registration of unmanned plane high spectrum image can be automatically performed, makes unmanned plane bloom
All wave bands of spectrogram picture have Space Consistency, and processing speed is fast, and registration accuracy is high.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to limited in any way.Except foregoing description
Schematical aspect, embodiment and feature outside, by reference to accompanying drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature would is that what is be readily apparent that.
Brief description of the drawings
In the accompanying drawings, unless specified otherwise herein, otherwise represent same or analogous through multiple accompanying drawing identical references
Part or element.What these accompanying drawings were not necessarily to scale.It should be understood that these accompanying drawings depict only according to the present invention
Some disclosed embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is the waveband registration method flow chart of the high spectrum image of the embodiment of the present invention.
Fig. 2 is the wave band registration system construction drawing of the high spectrum image of the embodiment of the present invention.
Embodiment
Hereinafter, some exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be changed by various different modes.
Therefore, accompanying drawing and description are considered essentially illustrative rather than restrictive.
As shown in figure 1, the waveband registration method of the high spectrum image of the present embodiment, comprises the following steps：
Step S100, chooses some wave band as benchmark wave band, the image of the wave band is respectively then expanded into M up and down
Individual pixel, generates new image and is used as benchmark image.
Wave band registration is on the basis of some wave band of high spectrum image, to carry out registration.Therefore, elder generation is needed before registration
Suitable wave band is selected as benchmark wave band, the principle of selection be the registering success rate and accuracy rate of other wave bands and the wave band more
Height, choosing method can be analyzed by each spectral range, actual progress determines that this is common knowledge, no longer with quasi-experiment etc.
Repeat.
Original high spectrum image is the same in the size of each wave band, according to practical application needs, after registration, each wave band
Image size also must be the same.But, because imaging time is inconsistent, cause the areas imaging of benchmark wave band and other wave bands not
Unanimously, if be directly registrable, and ensure that images after registration size is constant, the missing image partial data after registration can be caused, because
This, chooses after benchmark wave band, the image of benchmark wave band is respectively expanded into M pixel up and down, forms new image and makees
On the basis of image.M value determines that M values are more than maximum by the maximum offset between other wave bands and benchmark wave band
Offset.
Step S200, characteristic point is extracted on band image subject to registration, and each characteristic point is extracted centered on characteristic point
Template window.
Before characteristic point is extracted, enhancing operation is carried out to band image subject to registration, prominent contrast makes the spy of extraction
Levy a little more.
In this step, it can be usedOr SIFT (Scale-invariant feature transform, yardstick
Invariant features are changed) or Harris or SURF (Speeded-Up Robust Features accelerate robust feature) conduct extraction
The operator of characteristic point, the present embodiment is preferredOperator, by the Robert ladders for calculating each pixel of band image subject to registration
The gray scale covariance matrix of degree and a window centered on pixel (c, r), finds as far as possible in band image subject to registration
The point of the error ellipse of small and close circle is used as characteristic point.
Step S300, to each characteristic point, selection and the characteristic point identical coordinate are on benchmark image
The heart, extracts search window, and then completing thick matching using normalizated correlation coefficient obtains thick match point.
After thick matching is completed, there may be some Mismatching points, use stochastical sampling coherence method (Random
Sample Consensus, RANSAC) and least square method rejecting Mismatching point, obtain correct thick match point.
Step S400, the thick conversion for setting up band image subject to registration and benchmark image based on above-mentioned correct thick match point is closed
System, to each characteristic point, calculates match point of the characteristic point on benchmark image, with institute according to the thick transformation relation
State and extract search window centered on match point, completing essence matching using normalizated correlation coefficient obtains smart match point.
Compared to thick matching, essence matching uses smaller search window, and higher normalizated correlation coefficient threshold value is found more smart
True smart match point.After the completion of accurate matching, Mismatching point is rejected using RANSAC and least square method, correct essence is obtained
With point.
Step S500, the essence conversion for setting up band image subject to registration and benchmark image based on above-mentioned correct smart match point is closed
System, then completes the correction of band image subject to registration using the smart transformation relation.
Calibration model uses multinomial model, the exponent number of multinomial model according to match point quantity and anamorphose situation come
It is determined that.Multinomial model needs match point distribution than more uniform.Match point is homogenized before correction, specific method
For：Mesh generation is pressed to image, match point is assigned to different grids, for there is the grid of match point, retains matching degree most
A big control point, then builds model using the match point after homogenization.
Step S600, repeat step S200~S500, complete the registration of next wave band.
In order to improve registering efficiency, after one wave band of registration, offset of the wave band relative to benchmark wave band is calculated,
In step S300 to next wave band using characteristic point coordinate add offset after coordinate centered on extract search window.
As shown in Fig. 2 the present embodiment also provides a kind of system of the waveband registration method for above-mentioned high spectrum image, bag
Include：
Benchmark image generation module 100, for choosing some wave band as benchmark wave band, then by the image of the wave band
Respectively expand several pixels up and down, generate new image and be used as benchmark image；
Template window extraction module 200, for extracting characteristic point on band image subject to registration, is carried centered on characteristic point
Take the template window of each characteristic point；
Thick matching module 300, for each characteristic point, selection to be sat with the characteristic point identical on benchmark image
Centered on being denoted as, search window is extracted, thick match point is obtained using template matching method；
Smart matching module 400, the thick change for setting up band image subject to registration and benchmark image based on the thick match point
Relation is changed, to each characteristic point, match point of the characteristic point on benchmark image is calculated according to the thick transformation relation,
Search window is extracted centered on the match point, smart match point is obtained using template matching method
Geometric correction module 500, the essence for setting up band image subject to registration and benchmark image based on the smart match point
Transformation relation, then completes the correction of band image subject to registration using the smart transformation relation.
The wave band registration system of the present embodiment, in addition to image enhancement module, for before characteristic point is extracted, treating and matching somebody with somebody
Quasi- band image protrude the enhancing operation of contrast.
The wave band registration system of the present embodiment, in addition to Mismatching point reject module, for using stochastical sampling uniformity
Method and least square method reject Mismatching point.
The wave band registration system of the present embodiment, in addition to offset computing module, for after a registering wave band, counting
Calculate offset of the wave band relative to benchmark wave band.
The wave band calibration method and system for the high spectrum image that the present embodiment is provided can be automatically performed unmanned plane EO-1 hyperion
The wave band registration of image, makes all wave bands of unmanned plane high spectrum image have Space Consistency, and processing speed is fast, registration accuracy
It is high.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, its various change or replacement can be readily occurred in,
These should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
Shield scope is defined.
Claims (9)
1. a kind of waveband registration method of high spectrum image, it is characterised in that including：
Step S100, chooses some wave band as benchmark wave band, the image of the wave band is respectively then expanded to some up and down
Individual pixel, generates new image and is used as benchmark image；
Step S200, characteristic point is extracted on band image subject to registration, and the template of each characteristic point is extracted centered on characteristic point
Window；
Step S300, to each characteristic point, selection is carried with the characteristic point identical coordinate as center on benchmark image
Search window is taken, thick match point is obtained using template matching method；
Step S400, the thick transformation relation of band image subject to registration and benchmark image is set up based on the thick match point, to each
Individual characteristic point, calculates match point of the characteristic point on benchmark image, with the match point according to the thick transformation relation
Centered on extract search window, obtain smart match point using template matching method；
Step S500, the smart transformation relation of band image subject to registration and benchmark image is set up based on the smart match point, is then made
The correction of band image subject to registration is completed with the smart transformation relation；
Step S600, repeat step S200~S500, complete the registration of next wave band.
2. waveband registration method according to claim 1, it is characterised in that before characteristic point is extracted, to ripple subject to registration
Section image protrude the enhancing operation of contrast.
3. waveband registration method according to claim 1, it is characterised in that the thick match point described in step S400 is to make
The later thick match point of Mismatching point, the essence described in step S500 are rejected with stochastical sampling coherence method and least square method
Match point is to reject the later smart match point of Mismatching point using stochastical sampling coherence method and least square method.
4. waveband registration method according to claim 1, it is characterised in that after one wave band of registration, calculate the ripple
Section uses next wave band the coordinate of characteristic point plus after offset relative to the offset of benchmark wave band in step S300
Coordinate centered on extract search window.
5. waveband registration method according to claim 1, it is characterised in that in step s 200, is usedOr
SIFT or Harris or SURF is used as the operator for extracting characteristic point.
6. a kind of wave band registration system of high spectrum image, it is characterised in that including：
Benchmark image generation module, for choosing some wave band as benchmark wave band, then by bottom left on the image of the wave band
Respectively expand several pixels on the right side, generates new image and is used as benchmark image；
Template window extraction module, for extracting characteristic point on band image subject to registration, extracts each centered on characteristic point
The template window of characteristic point；
Thick matching module, for each characteristic point, being selected and the characteristic point identical coordinate conduct on benchmark image
Center, extracts search window, thick match point is obtained using template matching method；
Smart matching module, the thick transformation relation for setting up band image subject to registration and benchmark image based on the thick match point,
To each characteristic point, match point of the characteristic point on benchmark image is calculated according to the thick transformation relation, with described
Search window is extracted centered on match point, smart match point is obtained using template matching method
Geometric correction module, the essence conversion for being set up band image subject to registration and benchmark image based on the smart match point is closed
System, to each characteristic point, according to the smart transformation relation, geometric correction is carried out using multinomial model.
7. wave band registration system according to claim 6, it is characterised in that also including image enhancement module, for carrying
Take before characteristic point, the enhancing that band image subject to registration protrude contrast is operated.
8. wave band registration system according to claim 6, it is characterised in that also reject module including Mismatching point, be used for
Mismatching point is rejected using stochastical sampling coherence method and least square method.
9. wave band registration system according to claim 6, it is characterised in that also including offset computing module, for
After a registering wave band, offset of the wave band relative to benchmark wave band is calculated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710447441.XA CN107274441B (en) | 2017-06-14 | 2017-06-14 | Wave band calibration method and system for hyperspectral image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710447441.XA CN107274441B (en) | 2017-06-14 | 2017-06-14 | Wave band calibration method and system for hyperspectral image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107274441A true CN107274441A (en) | 2017-10-20 |
| CN107274441B CN107274441B (en) | 2020-07-03 |
Family
ID=60066739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710447441.XA Active CN107274441B (en) | 2017-06-14 | 2017-06-14 | Wave band calibration method and system for hyperspectral image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107274441B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493298A (en) * | 2018-11-13 | 2019-03-19 | 中国国土资源航空物探遥感中心 | A kind of airborne sweep type high-spectral data fast geometric bearing calibration |
| CN110285870A (en) * | 2019-07-22 | 2019-09-27 | 深圳市卓城科技有限公司 | Vehicle spindle-type and wheel number determination method and its system |
| CN111915582A (en) * | 2020-07-28 | 2020-11-10 | 南京工业大学浦江学院 | Image tampering detection method based on brightness characteristic coupling information quantity restriction |
| CN112288009A (en) * | 2020-10-29 | 2021-01-29 | 西安电子科技大学 | R-SIFT chip hardware Trojan horse image registration method based on template matching |
| CN112598717A (en) * | 2020-12-14 | 2021-04-02 | 珠海欧比特宇航科技股份有限公司 | Full-spectrum registration method and medium for hyperspectral satellite images |
| CN113658063A (en) * | 2021-07-28 | 2021-11-16 | 中国科学院西安光学精密机械研究所 | Automatic data correction method and system for AOTF type spectral imager |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101281645A (en) * | 2008-05-23 | 2008-10-08 | 哈尔滨工程大学 | Method for registration of multispectral image based on small component and noise component |
| CN101509782A (en) * | 2009-03-09 | 2009-08-19 | 华中科技大学 | Small-sized ground marker capturing and positioning method |
| CN101950419A (en) * | 2010-08-26 | 2011-01-19 | 西安理工大学 | Quick image rectification method in presence of translation and rotation at same time |
| US9245201B1 (en) * | 2013-03-15 | 2016-01-26 | Excelis Inc. | Method and system for automatic registration of images |
| CN105701830A (en) * | 2016-01-18 | 2016-06-22 | 武汉大学 | LASIS waveband image registration method and system based on geometric model |
| CN106204601A (en) * | 2016-07-15 | 2016-12-07 | 华东师范大学 | A kind of live body parallel method for registering of EO-1 hyperion sequence image based on wave band scanning form |
-
2017
- 2017-06-14 CN CN201710447441.XA patent/CN107274441B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101281645A (en) * | 2008-05-23 | 2008-10-08 | 哈尔滨工程大学 | Method for registration of multispectral image based on small component and noise component |
| CN101509782A (en) * | 2009-03-09 | 2009-08-19 | 华中科技大学 | Small-sized ground marker capturing and positioning method |
| CN101950419A (en) * | 2010-08-26 | 2011-01-19 | 西安理工大学 | Quick image rectification method in presence of translation and rotation at same time |
| US9245201B1 (en) * | 2013-03-15 | 2016-01-26 | Excelis Inc. | Method and system for automatic registration of images |
| CN105701830A (en) * | 2016-01-18 | 2016-06-22 | 武汉大学 | LASIS waveband image registration method and system based on geometric model |
| CN106204601A (en) * | 2016-07-15 | 2016-12-07 | 华东师范大学 | A kind of live body parallel method for registering of EO-1 hyperion sequence image based on wave band scanning form |
Non-Patent Citations (2)
| Title |
|---|
| 张过，李凡: "LASIS 影像波段配准", 《红外与毫米波学报》 * |
| 徐丽燕: "基于特征点的遥感图像配准方法及应用研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493298A (en) * | 2018-11-13 | 2019-03-19 | 中国国土资源航空物探遥感中心 | A kind of airborne sweep type high-spectral data fast geometric bearing calibration |
| CN110285870A (en) * | 2019-07-22 | 2019-09-27 | 深圳市卓城科技有限公司 | Vehicle spindle-type and wheel number determination method and its system |
| CN111915582A (en) * | 2020-07-28 | 2020-11-10 | 南京工业大学浦江学院 | Image tampering detection method based on brightness characteristic coupling information quantity restriction |
| CN111915582B (en) * | 2020-07-28 | 2024-03-08 | 南京工业大学浦江学院 | Image tampering detection method based on brightness characteristic coupling information quantity constraint |
| CN112288009A (en) * | 2020-10-29 | 2021-01-29 | 西安电子科技大学 | R-SIFT chip hardware Trojan horse image registration method based on template matching |
| CN112598717A (en) * | 2020-12-14 | 2021-04-02 | 珠海欧比特宇航科技股份有限公司 | Full-spectrum registration method and medium for hyperspectral satellite images |
| CN112598717B (en) * | 2020-12-14 | 2024-05-17 | 珠海欧比特卫星大数据有限公司 | Full spectrum registration method and medium for hyperspectral satellite images |
| CN113658063A (en) * | 2021-07-28 | 2021-11-16 | 中国科学院西安光学精密机械研究所 | Automatic data correction method and system for AOTF type spectral imager |
| CN113658063B (en) * | 2021-07-28 | 2023-05-26 | 中国科学院西安光学精密机械研究所 | Automatic data correction method and system for AOTF type spectrum imager |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107274441B (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107274441A (en) | The wave band calibration method and system of a kind of high spectrum image | |
| Zhao et al. | A robust adaptive spatial and temporal image fusion model for complex land surface changes | |
| Ponti et al. | Precision agriculture: Using low-cost systems to acquire low-altitude images | |
| US20240193938A1 (en) | System and method for vegetation detection from aerial photogrammetric multispectral data | |
| CN110929944A (en) | Wheat scab disease severity prediction method based on hyperspectral image and spectral feature fusion technology | |
| CN110647932B (en) | Planting crop structure remote sensing image classification method and device | |
| CN112308152A (en) | Hyperspectral image ground object classification method based on spectrum segmentation and homogeneous region detection | |
| Ye et al. | An image-based approach for automatic detecting tasseling stage of maize using spatio-temporal saliency | |
| Zhang et al. | Two-step ResUp&Down generative adversarial network to reconstruct multispectral image from aerial RGB image | |
| Jiang et al. | Unmixing-based spatiotemporal image fusion accounting for complex land cover changes | |
| CN112329733B (en) | Winter wheat growth monitoring and analyzing method based on GEE cloud platform | |
| CN114092804A (en) | Method and device for identifying remote sensing image | |
| CN115641444B (en) | Wheat lodging detection method, device, equipment and medium | |
| CN115564808B (en) | Multi-resolution hyperspectral/SAR image registration method based on public space-spectrum subspace | |
| CN116379935A (en) | Island shallow sea water depth prediction method, device and equipment based on multispectral image | |
| CN116307105A (en) | Winter wheat yield prediction method, device and equipment based on multi-mode canopy image | |
| CN115311336A (en) | Image registration method, device and equipment of multiple cameras and storage medium | |
| CN114782274A (en) | Unmanned aerial vehicle multispectral image radiation correction method based on illumination estimation | |
| CN113496505B (en) | Image registration method and device, multispectral camera, unmanned equipment and storage medium | |
| Malczewska et al. | Challenges in Preparing Datasets for Super-Resolution on the Example of SENTINEL-2 and Planet Scope Images | |
| Deng et al. | A paddy field segmentation method combining attention mechanism and adaptive feature fusion | |
| Yang et al. | Cropland mapping in fragmented agricultural landscape using modified pyramid scene parsing network | |
| López et al. | Multi-Spectral Imaging for Weed Identification in Herbicides Testing | |
| Han et al. | TemPanSharpening: A multi-temporal Pansharpening solution based on deep learning and edge extraction | |
| Silva et al. | Non-linear Distortion Recognition in UAVs' Images using Deep Learning. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 |