CN112101388A - Hyperspectral image end member extraction method and system - Google Patents
Hyperspectral image end member extraction method and system Download PDFInfo
- Publication number
- CN112101388A CN112101388A CN202011217803.4A CN202011217803A CN112101388A CN 112101388 A CN112101388 A CN 112101388A CN 202011217803 A CN202011217803 A CN 202011217803A CN 112101388 A CN112101388 A CN 112101388A
- Authority
- CN
- China
- Prior art keywords
- module
- color
- abundance
- end member
- image
- 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- Withdrawn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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The embodiment of the invention discloses a hyperspectral image end member extraction method and a hyperspectral image end member extraction system in the technical field of spectrum processing. The hyperspectral image end member extraction method comprises the following steps: s1, collecting a spectral image, and dividing colors in the spectral image into an end member pure color area and a pixel element gradual change color area; and S2, calculating abundance values of corresponding end members according to the areas of the pure color areas of the end members, and storing the abundance values in a classified manner. The method comprises the steps of dividing a collected spectral image into pure colors and gradient colors, dividing the spectral colors into pixels consisting of single end members corresponding to the pure colors and multiple end members corresponding to the gradient hues, calculating the area of the pure colors, converting the area into abundance values, searching various end member information contained in gradient color pixel points and abundance values corresponding to the end members through an image contrast technology, and superposing the end member abundance values obtained by the pure colors and the gradient colors, so that the end members are accurately extracted from the spectral image.
Description
Technical Field
The embodiment of the invention relates to the technical field of spectrum processing, in particular to a hyperspectral image end member extraction method and system.
Background
The end members only contain one type of ground feature information, the general image elements are all mixed image elements and comprise various types of ground features, when the mixed image elements are decomposed, the end members in one image element can be quantitatively described, and the area percentage of the end members in each image element in the image element, namely the abundance of the end members, can be obtained.
In the existing spectral image end member extraction process, due to the limitation of processing means, the corresponding end member information in the spectral image and the abundance value information corresponding to each end member are difficult to calculate quickly, and certain images are brought to end member extraction.
Based on the above, the invention designs a hyperspectral image end member extraction method and a hyperspectral image end member extraction system, so as to solve the problems.
Disclosure of Invention
The embodiment of the invention provides a hyperspectral image end member extraction method and a hyperspectral image end member extraction system, which are used for solving the technical problems mentioned in the background technology.
The embodiment of the invention provides a hyperspectral image end member extraction method. In one possible embodiment, the method comprises the following steps:
s1, collecting a spectral image, and dividing colors in the spectral image into an end member pure color area and a pixel element gradual change color area;
s2, calculating abundance values of corresponding end members according to the areas of the pure color areas of the end members and storing the abundance values in a classified manner;
and S3, collecting pixel points of the pixel gradual change color region, comparing the similarity of all the pixel points with a color pixel point database, searching for end members and abundance value data of the end members contained in the pixel reaching the specified similarity, and storing the end members and the abundance value data of the end members in the S2.
The embodiment of the invention also provides a hyperspectral image end member extraction system. In one feasible scheme, the system comprises a spectrum acquisition module, a color division module, an abundance measurement and calculation module, an end member abundance storage module, a gradual color processing module and a gradual abundance measurement and calculation module;
the spectrum acquisition module is used for acquiring spectrum image data information;
the color division module is used for dividing colors in the spectral image into an end member pure color part and a gradual change color pixel part;
the abundance measuring and calculating module is used for calculating the abundance of the pure color end member part;
the end member abundance storage module is used for storing abundance data information of each end member;
the gradual change color processing module is used for extracting the information of each pixel point of the gradual change color pixel part;
and the gradual change abundance measuring and calculating module is used for measuring and calculating the end member information and the end member abundance data information contained in each gradual change pixel point according to the color pixel point big data.
The embodiment of the invention provides a hyperspectral image end member extraction system. In one possible scheme, the color dividing module comprises a spectrum scanning module, a pure color identification module and an image intercepting module;
the spectrum scanning module is used for scanning the collected spectrum image color information;
the pure color identification module is used for scanning pure color partial areas in the spectral images corresponding to various end members;
and the image intercepting module is used for automatically intercepting the pure color part in the spectral image and sending the pure color part to the abundance measuring and calculating module.
The embodiment of the invention provides a hyperspectral image end member extraction system. In one possible scheme, the abundance measuring module comprises an area measuring module and an abundance value conversion module;
the area measuring and calculating module is used for measuring and calculating the area data information of the pure color areas of various end members;
and the abundance value conversion module is used for converting abundance value data information according to the area data of each end member.
The embodiment of the invention provides a hyperspectral image end member extraction system. In one possible solution, the gradient color processing module includes a gradient image extraction module and a pixel point extraction module;
the gradual change image extraction module is used for extracting the gradual change color partial images divided by the color division module;
and the pixel point extraction module is used for extracting pixel point images in the gradient color images.
The embodiment of the invention provides a hyperspectral image end member extraction system. In a feasible scheme, the gradual change abundance measuring and calculating module comprises a color comparison module, a color pixel point database module and an abundance extraction module;
the color pixel point database module is used for storing various color pixel points and corresponding end members and end member abundance data;
and the color comparison module is used for searching the end members and the end member abundance data information which reach the specified similarity in the color pixel point database module according to the extracted pixel point image comparison, and sending the end member abundance data information to the end member abundance storage module to stack the abundance value of the specified end members.
Based on the scheme, the collected spectral image is divided into the single end member corresponding to the pure color and the pixel consisting of the multiple end members corresponding to the gradient hue according to the pure color and the gradient color, the area of the pure color part is converted into the abundance value after being calculated, various end member information contained in the gradient color pixel point and abundance values corresponding to the end members are searched through an image contrast technology, and the end member abundance values obtained by the pure color and the gradient color are superposed, so that the end members are accurately extracted from the spectral image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a block flow diagram of the extraction method of the present invention;
FIG. 2 is a system architecture diagram of the extraction system of the present invention;
FIG. 3 is a system diagram of a color partitioning module and an abundance measuring module according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," "circumferential," and the like are used in the indicated orientations and positional relationships based on the drawings for convenience in describing and simplifying the description, but do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
In the present invention, unless otherwise specifically stated or limited, the terms "mounted," "connected," "fixed," and the like are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally formed; the connection can be mechanical connection, electrical connection or communication connection; either directly or indirectly through intervening media, either internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
FIG. 1 is a hyperspectral image end member extraction method in a first embodiment of the invention; the method comprises the following steps:
s1, collecting a spectral image, and dividing colors in the spectral image into an end member pure color area and a pixel element gradual change color area;
s2, calculating abundance values of corresponding end members according to the areas of the pure color areas of the end members and storing the abundance values in a classified manner;
and S3, collecting pixel points of the pixel gradual change color region, comparing the similarity of all the pixel points with a color pixel point database, searching for end members and abundance value data of the end members contained in the pixel reaching the specified similarity, and storing the end members and the abundance value data of the end members in the S2.
It should be noted that in the process of extracting end members in a spectral image by using the hyperspectral image end member extraction method of the invention, the collected spectral image is divided into a pure color area part of a single end member and a pixel gradient color area containing a plurality of end members by color division; in the pure color area, the abundance value information of each pure color area can be directly converted by identifying the area information of the pure color area, in the gradient color area, the contrast analysis is carried out by utilizing the large pixel point database, various end member information corresponding to each pixel point and the abundance value information corresponding to each end member can be quickly found, so that the abundance value of the gradient color end member is sequentially added into the abundance value of the end member of the pure color area, and the extraction work of the spectrogram image end member is realized.
Fig. 2-3 are a hyperspectral image end member extraction system in an embodiment two, which is an improved scheme based on the embodiment one and includes a spectrum collection module, a color division module, an abundance measurement module, an end member abundance storage module, a gradient color processing module, and a gradient abundance measurement module;
the spectrum acquisition module is used for acquiring spectrum image data information;
the color division module is used for dividing colors in the spectral image into an end member pure color part and a gradual change color pixel part;
the abundance measuring and calculating module is used for calculating the abundance of the pure color end member part;
the end member abundance storage module is used for storing abundance data information of each end member;
the gradual change color processing module is used for extracting the information of each pixel point of the gradual change color pixel part;
and the gradual change abundance measuring and calculating module is used for measuring and calculating the end member information and the end member abundance data information contained in each gradual change pixel point according to the color pixel point big data.
When the hyperspectral image end member extraction system is used for extracting a hyperspectral image end member, spectral image data are collected through a spectrum collection module, a pure color area and a gradient color area in a spectral image are divided through a color division module, an abundance value of the pure color area is measured and calculated through an abundance calculation module and then stored in an end member abundance storage module, a gradient color processing module is used for extracting pixel points in the image of the gradient color image, end member information contained in each pixel point and abundance values corresponding to each end member are extracted through the gradient abundance measurement module, and finally the end member information and the abundance values are superposed into each end member storage submodule in the end member abundance storage module.
Optionally, the color division module includes a spectrum scanning module, a pure color identification module and an image interception module;
the spectrum scanning module is used for scanning the collected spectrum image color information;
the pure color identification module is used for scanning pure color partial areas in the spectral images corresponding to various end members;
and the image intercepting module is used for automatically intercepting the pure color part in the spectral image and sending the pure color part to the abundance measuring and calculating module. It should be noted that, in this embodiment, when the spectral image is further color-divided, the spectral image is scanned to collect the pure color regions corresponding to the colors of the end members, and the image of the end member is automatically captured to the abundance measuring module to calculate the abundance value.
In addition, the abundance measuring and calculating module comprises an area measuring and calculating module and an abundance value conversion module;
the area measuring and calculating module is used for measuring and calculating the area data information of the pure color areas of various end members;
the abundance value conversion module is used for converting abundance value data information according to the area data of each end member; and when the abundance value of the pure color region is measured and calculated, the abundance value information of the end member is calculated according to the corresponding end member by measuring and calculating the area of the pure color region.
More specifically, the gradient color processing module comprises a gradient image extraction module and a pixel point extraction module;
the gradual change image extraction module is used for extracting the gradual change color partial images divided by the color division module;
the pixel point extracting module is used for extracting pixel point images in the gradient color images; when the pixel points in the gradient color area are obtained, the residual gradient color area is divided by the extraction color dividing module, and then the pixel points in the area are searched.
Further, the gradual change abundance measuring and calculating module comprises a color comparison module, a color pixel point database module and an abundance extraction module;
the color pixel point database module is used for storing various color pixel points and corresponding end members and end member abundance data;
the color comparison module is used for searching the end members and the abundance data information of the end members which reach the specified similarity in the color pixel point database module according to the extracted pixel point image comparison, and sending the end members and the abundance data information to the abundance storage module of the end members to stack the abundance values of the specified end members; when the abundance value of the gradual-change color pixel point is measured and calculated, the extracted pixel point is searched for the corresponding end member information and the abundance value corresponding to each end member in the pixel point database.
In the present invention, unless otherwise explicitly specified or limited, the first feature "on" or "under" the second feature may be directly contacting the first feature and the second feature or indirectly contacting the first feature and the second feature through an intermediate.
Also, a first feature "on," "above," and "over" a second feature may mean that the first feature is directly above or obliquely above the second feature, or that only the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lower level than the second feature.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example" or "some examples," or the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A hyperspectral image end member extraction method is characterized by comprising the following steps:
s1, collecting a spectral image, and dividing colors in the spectral image into an end member pure color area and a pixel element gradual change color area;
s2, calculating abundance values of corresponding end members according to the areas of the pure color areas of the end members and storing the abundance values in a classified manner;
and S3, collecting pixel points of the pixel gradual change color region, comparing the similarity of all the pixel points with a color pixel point database, searching for end members and abundance value data of the end members contained in the pixel reaching the specified similarity, and storing the end members and the abundance value data of the end members in the S2.
2. A hyperspectral image end member extraction system is characterized by comprising a spectrum acquisition module, a color division module, an abundance measurement module, an end member abundance storage module, a gradient color processing module and a gradient abundance measurement module;
the spectrum acquisition module is used for acquiring spectrum image data information;
the color division module is used for dividing colors in the spectral image into an end member pure color part and a gradual change color pixel part;
the abundance measuring and calculating module is used for calculating the abundance of the pure color end member part;
the end member abundance storage module is used for storing abundance data information of each end member;
the gradual change color processing module is used for extracting the information of each pixel point of the gradual change color pixel part;
and the gradual change abundance measuring and calculating module is used for measuring and calculating the end member information and the end member abundance data information contained in each gradual change pixel point according to the color pixel point big data.
3. The hyperspectral image end member extraction system according to claim 2, wherein the color division module comprises a spectrum scanning module, a pure color identification module and an image interception module;
the spectrum scanning module is used for scanning the collected spectrum image color information;
the pure color identification module is used for scanning pure color partial areas in the spectral images corresponding to various end members;
and the image intercepting module is used for automatically intercepting the pure color part in the spectral image and sending the pure color part to the abundance measuring and calculating module.
4. The hyperspectral image end member extraction system according to claim 2, wherein the abundance measuring and calculating module comprises an area measuring and calculating module and an abundance value conversion module;
the area measuring and calculating module is used for measuring and calculating the area data information of the pure color areas of various end members;
and the abundance value conversion module is used for converting abundance value data information according to the area data of each end member.
5. The hyperspectral image end member extraction system according to claim 2, wherein the gradient color processing module comprises a gradient image extraction module and a pixel point extraction module;
the gradual change image extraction module is used for extracting the gradual change color partial images divided by the color division module;
and the pixel point extraction module is used for extracting pixel point images in the gradient color images.
6. The hyperspectral image end-member extraction system according to claim 2, wherein the gradient abundance measurement module comprises a color contrast module, a color pixel database module and an abundance extraction module;
the color pixel point database module is used for storing various color pixel points and corresponding end members and end member abundance data;
and the color comparison module is used for searching the end members and the end member abundance data information which reach the specified similarity in the color pixel point database module according to the extracted pixel point image comparison, and sending the end member abundance data information to the end member abundance storage module to stack the abundance value of the specified end members.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011217803.4A CN112101388A (en) | 2020-11-04 | 2020-11-04 | Hyperspectral image end member extraction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011217803.4A CN112101388A (en) | 2020-11-04 | 2020-11-04 | Hyperspectral image end member extraction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101388A true CN112101388A (en) | 2020-12-18 |
Family
ID=73784567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011217803.4A Withdrawn CN112101388A (en) | 2020-11-04 | 2020-11-04 | Hyperspectral image end member extraction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101388A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715455A (en) * | 2015-01-09 | 2015-06-17 | 青岛市光电工程技术研究院 | Spectral imaging handprint enhancing method |
| CN111141698A (en) * | 2019-12-30 | 2020-05-12 | 中国地质大学（北京） | Lithology classification method based on thermal infrared emissivity |
-
2020
- 2020-11-04 CN CN202011217803.4A patent/CN112101388A/en not_active Withdrawn
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715455A (en) * | 2015-01-09 | 2015-06-17 | 青岛市光电工程技术研究院 | Spectral imaging handprint enhancing method |
| CN111141698A (en) * | 2019-12-30 | 2020-05-12 | 中国地质大学（北京） | Lithology classification method based on thermal infrared emissivity |
Non-Patent Citations (3)
| Title |
|---|
| 唐晓燕: "《高光谱图像混合像元非线性分解技术》", 31 March 2019, 电子科技大学出版社 * |
| 孔祥兵: "《高光谱影像同质区分析及稀疏性解混》", 31 December 2018, 黄河水利出版社 * |
| 杨可明 等: "基于端元提取的高光谱影像特定目标识别", 《金属矿山》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446004B (en) | Digital pathological full-section image retrieval method | |
| CN109374537B (en) | Urban black and odorous water body identification method and device | |
| CN110120046B (en) | Potential landslide identification method integrating DEM (digital elevation model), optical remote sensing and deformation information | |
| CN110196892B (en) | Comprehensive protective land monitoring platform based on Internet of things and method thereof | |
| JP5557091B2 (en) | Image processing apparatus, image reading apparatus, image processing method, and image processing program | |
| CN101964293B (en) | Metallographical microstructural image processing method | |
| CN105224961B (en) | A kind of infrared spectrum feature extracting and matching method of high resolution | |
| CN106228186A (en) | Classification hyperspectral imagery apparatus and method | |
| CN106951863A (en) | A kind of substation equipment infrared image change detecting method based on random forest | |
| Kalinicheva et al. | Neural network autoencoder for change detection in satellite image time series | |
| CN114639012A (en) | Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing | |
| Tullis et al. | Expert system house detection in high spatial resolution imagery using size, shape, and context | |
| CN112101388A (en) | Hyperspectral image end member extraction method and system | |
| CN110929690B (en) | Remote sensing image road network extraction method based on deep neural network | |
| Chen et al. | Fusion of LIDAR data and high resolution images for forest canopy modelling | |
| CN115372281A (en) | Monitoring system and method for physical structure and chemical composition of soil | |
| Wallace et al. | Analysis of remotely sensed data | |
| CN112033537B (en) | Spectrum extraction method and device of hyperspectral acquisition system | |
| Weber et al. | Towards efficient satellite image time series analysis: Combination of dynamic time warping and quasi-flat zones | |
| Desclée et al. | Object-based method for automatic forest change detection | |
| CN111583121A (en) | Unmanned aerial vehicle hyperspectral image splicing method for vegetation | |
| JP6329651B1 (en) | Image processing apparatus and image processing method | |
| Khorrami et al. | A new multistep approach to identify leaf-off poplar plantations using airborne imagery | |
| CN111122447B (en) | Multispectral wave band correction method for unmanned aerial vehicle | |
| CN117766061B (en) | Artificial intelligence-based tomato extract purity detection method and system |
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 |
Application publication date: 20201218 |
|
| WW01 | Invention patent application withdrawn after publication |