CN107248149A - Methods on Multi-Sensors RS Image fusion method - Google Patents
Methods on Multi-Sensors RS Image fusion method Download PDFInfo
- Publication number
- CN107248149A CN107248149A CN201710399057.7A CN201710399057A CN107248149A CN 107248149 A CN107248149 A CN 107248149A CN 201710399057 A CN201710399057 A CN 201710399057A CN 107248149 A CN107248149 A CN 107248149A
- Authority
- CN
- China
- Prior art keywords
- image
- registration
- data
- decision
- information
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 9
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 230000000717 retained effect Effects 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 claims description 4
- 239000013589 supplement Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to Remote Sensing Data Processing technical field, more particularly to a kind of Methods on Multi-Sensors RS Image fusion method.The invention discloses the image co-registration based on pixel：Image co-registration based on pixel carries out basic geocoding, mutual geometrical registration is carried out to raster data, then uses its valuable complex data criterion, decision rule judges, recognized, classification, then by these valuable information fusions, the comprehensive result of decision is obtained；To data after above-mentioned three kinds of image co-registrations, again three kinds of results are compared with convergence analysis and show that the final result present invention can integrate and utilize the different qualities of a variety of data to greatest extent, the redundancy and contradiction existed between different sensors is eliminated, strengthens the transparency of image information.
Description
Technical field
The invention belongs to Remote Sensing Data Processing technical field, more particularly to a kind of Methods on Multi-Sensors RS Image fusion method.
Background technology
At present, with the development of remote sensing technology, multi-source Remote Sensing Images provide abundant information, different sensors for people
The remote sensing image data amount obtained to areal is increasing so that it is different that remote sensing system can provide the user areal
The mass data of time, spatially and spectrally resolution ratio.At present single sensing is typically employed in the acquisition of remote sensing image data
Device is obtained.The image information that single-sensor is obtained often is difficult to meet application, often relatively simple, so that the figure obtained
As relatively simple.
The content of the invention
It is an object of the invention to solve the problems, such as that techniques discussed above can be obtained more there is provided one kind by visual fusion
Many information, supplements the deficiency of single-sensor, can to greatest extent integrate and using the different qualities of a variety of data, eliminate
The redundancy and contradiction existed between different sensors, strengthen image information transparency, improve image information precision, improve and
The promptness of remote sensing information extraction and the Methods on Multi-Sensors RS Image fusion method of reliability are improved, its technical scheme is as follows：
Methods on Multi-Sensors RS Image fusion method, it is characterised in that：
Image co-registration based on pixel：Image co-registration based on pixel carries out basic geocoding, i.e., raster data is entered
The mutual geometrical registration of row, carries out the merging treatment of image picture elements level on the premise of each pixel is corresponded, to improve
The effect of image procossing, makes image segmentation, feature extraction work more accurately carry out；
The image co-registration of feature based：Correspondence between the image co-registration of feature based, structural information, sentences to characteristic attribute
Disconnected to have higher confidence level and accuracy, the image after fusion had both retained the structural information of former high-resolution remote sensing image,
The abundant spectral information of multispectral image has been merged again, and image category environment is improved, and Classification in Remote Sensing Image precision is improved；
Image co-registration based on decision-making level：Image co-registration based on decision-making level first pass through view data feature extraction and some
The participation of auxiliary information, then criterion is used its valuable complex data, decision rule judges, recognized, classification, so
Afterwards by these valuable information fusions, the comprehensive result of decision is obtained；
To data after above-mentioned three kinds of image co-registrations, then convergence analysis is compared to three kinds of results draws final result.
The Methods on Multi-Sensors RS Image fusion method that the present invention is provided, the image co-registration based on pixel can improve at image
The effect of reason, makes the work such as image segmentation, feature extraction more accurately carry out.The image co-registration of feature based is to characteristic attribute
Judgement there is higher confidence level and accuracy, and data processing amount greatly reduces, and is conducive to processing in real time.After fusion
Image had both retained the structural information of former high-resolution remote sensing image, and the abundant spectral information of multispectral image, figure have been merged again
As classification environment is improved, Classification in Remote Sensing Image precision is improved.Image co-registration based on decision-making level can obtain optimal having
The data of value.
The beneficial effects of the invention are as follows：More information can be obtained by visual fusion, supplement single-sensor is not
Foot, can integrate and using the different qualities of a variety of data to greatest extent, eliminate between different sensors the redundancy that exists with
Contradiction, strengthen image information transparency, improve image information precision, improve remote sensing information extraction promptness and
Reliability.
Embodiment
Embodiment is specifically described below：
Methods on Multi-Sensors RS Image fusion method, it is characterised in that：
Image co-registration based on pixel：Image co-registration based on pixel carries out basic geocoding, i.e., raster data is entered
The mutual geometrical registration of row, carries out the merging treatment of image picture elements level on the premise of each pixel is corresponded, to improve
The effect of image procossing, makes image segmentation, feature extraction work more accurately carry out；
The image co-registration of feature based：Correspondence between the image co-registration of feature based, structural information, sentences to characteristic attribute
Disconnected to have higher confidence level and accuracy, the image after fusion had both retained the structural information of former high-resolution remote sensing image,
The abundant spectral information of multispectral image has been merged again, and image category environment is improved, and Classification in Remote Sensing Image precision is improved；
Image co-registration based on decision-making level：Image co-registration based on decision-making level first pass through view data feature extraction and some
The participation of auxiliary information, then criterion is used its valuable complex data, decision rule judges, recognized, classification, so
Afterwards by these valuable information fusions, the comprehensive result of decision is obtained；
To data after above-mentioned three kinds of image co-registrations, then convergence analysis is compared to three kinds of results draws final result.
Analyzed according to the fusion for classification of different images different qualities, it can be deduced that more accurate image information, to not
Image information with classification is compared global analysis and obtains final having more characteristics；More accurately graphical information.
Claims (1)
1. Methods on Multi-Sensors RS Image fusion method, it is characterised in that：
Image co-registration based on pixel：Image co-registration based on pixel carries out basic geocoding, i.e., raster data is entered
The mutual geometrical registration of row, carries out the merging treatment of image picture elements level on the premise of each pixel is corresponded, to improve
The effect of image procossing, makes image segmentation, feature extraction work more accurately carry out；
The image co-registration of feature based：Correspondence between the image co-registration of feature based, structural information, sentences to characteristic attribute
Disconnected to have higher confidence level and accuracy, the image after fusion had both retained the structural information of former high-resolution remote sensing image,
The abundant spectral information of multispectral image has been merged again, and image category environment is improved, and Classification in Remote Sensing Image precision is improved；
Image co-registration based on decision-making level：Image co-registration based on decision-making level first pass through view data feature extraction and some
The participation of auxiliary information, then criterion is used its valuable complex data, decision rule judges, recognized, classification, so
Afterwards by these valuable information fusions, the comprehensive result of decision is obtained；
To data after above-mentioned three kinds of image co-registrations, then convergence analysis is compared to three kinds of results draws final result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710399057.7A CN107248149A (en) | 2017-05-31 | 2017-05-31 | Methods on Multi-Sensors RS Image fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710399057.7A CN107248149A (en) | 2017-05-31 | 2017-05-31 | Methods on Multi-Sensors RS Image fusion method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107248149A true CN107248149A (en) | 2017-10-13 |
Family
ID=60018457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710399057.7A Withdrawn CN107248149A (en) | 2017-05-31 | 2017-05-31 | Methods on Multi-Sensors RS Image fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107248149A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228900A (en) * | 2018-02-06 | 2018-06-29 | 国网山西省电力公司电力科学研究院 | Power equipment multispectral data center model method for building up based on layered structure |
| CN114254568A (en) * | 2022-02-28 | 2022-03-29 | 浙江国遥地理信息技术有限公司 | GPS remote sensing flood early warning method based on artificial intelligence decision tree |
-
2017
- 2017-05-31 CN CN201710399057.7A patent/CN107248149A/en not_active Withdrawn
Non-Patent Citations (2)
| Title |
|---|
| 杨长保 等: "多源遥感数据融合方法的新探索" * |
| 王帅;: "多元遥感影像数据融合研究" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228900A (en) * | 2018-02-06 | 2018-06-29 | 国网山西省电力公司电力科学研究院 | Power equipment multispectral data center model method for building up based on layered structure |
| CN108228900B (en) * | 2018-02-06 | 2021-12-24 | 国网山西省电力公司电力科学研究院 | Power equipment multispectral data center model building method based on hierarchical structure |
| CN114254568A (en) * | 2022-02-28 | 2022-03-29 | 浙江国遥地理信息技术有限公司 | GPS remote sensing flood early warning method based on artificial intelligence decision tree |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392964B (en) | The indoor SLAM method combined based on indoor characteristic point and structure lines | |
| CN105069746B (en) | Video real-time face replacement method and its system based on local affine invariant and color transfer technology | |
| CN101996407B (en) | Colour calibration method for multiple cameras | |
| CN110555412B (en) | End-to-end human body gesture recognition method based on combination of RGB and point cloud | |
| CN107481315A (en) | A kind of monocular vision three-dimensional environment method for reconstructing based on Harris SIFT BRIEF algorithms | |
| CN101673396B (en) | Image fusion method based on dynamic object detection | |
| CN104167016B (en) | A kind of three-dimensional motion method for reconstructing based on RGB color and depth image | |
| CN105930795A (en) | Walking state identification method based on space vector between human body skeleton joints | |
| CN108898063A (en) | A kind of human body attitude identification device and method based on full convolutional neural networks | |
| CN110443898A (en) | A kind of AR intelligent terminal target identification system and method based on deep learning | |
| CN103530599A (en) | Method and system for distinguishing real face and picture face | |
| CN103425967A (en) | Pedestrian flow monitoring method based on pedestrian detection and tracking | |
| CN104361314A (en) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion | |
| CN109086668A (en) | Based on the multiple dimensioned unmanned aerial vehicle remote sensing images road information extracting method for generating confrontation network | |
| CN102214291A (en) | Method for quickly and accurately detecting and tracking human face based on video sequence | |
| CN106874884A (en) | Human body recognition methods again based on position segmentation | |
| CN109758756B (en) | Gymnastics video analysis method and system based on 3D camera | |
| CN106156714A (en) | The Human bodys' response method merged based on skeletal joint feature and surface character | |
| CN102855621A (en) | Infrared and visible remote sensing image registration method based on salient region analysis | |
| CN105678735A (en) | Target salience detection method for fog images | |
| CN106529432A (en) | Hand area segmentation method deeply integrating significance detection and prior knowledge | |
| CN101908153A (en) | Method for estimating head postures in low-resolution image treatment | |
| CN111160291A (en) | Human eye detection method based on depth information and CNN | |
| CN108021857B (en) | Building detection method based on unmanned aerial vehicle aerial image sequence depth recovery | |
| CN107248149A (en) | Methods on Multi-Sensors RS Image fusion method |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171013 |