CN108109125A - Information extracting method and device based on remote sensing images - Google Patents
Information extracting method and device based on remote sensing images Download PDFInfo
- Publication number
- CN108109125A CN108109125A CN201810004262.3A CN201810004262A CN108109125A CN 108109125 A CN108109125 A CN 108109125A CN 201810004262 A CN201810004262 A CN 201810004262A CN 108109125 A CN108109125 A CN 108109125A
- Authority
- CN
- China
- Prior art keywords
- thematic
- remote sensing
- sample
- sensing images
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000008569 process Effects 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000001228 spectrum Methods 0.000 claims abstract description 20
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000003595 spectral effect Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000015654 memory Effects 0.000 description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 238000003860 storage Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06T5/80—Geometric correction
-
- 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
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the present invention provides a kind of information extracting method and device based on remote sensing images, and this method includes obtaining remote sensing images and the remote sensing images are pre-processed to obtain pretreatment image;It determines special topic sample, and band math is carried out to the pretreatment image according to the wave band feature of the special topic sample and obtains data to be analyzed;Calculate the similarity of the spectrum form and each spectrum form in the data to be analyzed of the thematic sample;The spectroscopic data and mark for being less than predetermined threshold value with the similarity of the thematic sample are chosen from the data to be analyzed;According to mark result extracted from the pretreatment image with the corresponding original image information of each mark, and it is clustered and iterative processing is to obtain thematic image information;Vectorized process is carried out to the thematic image information to obtain thematic data and preserve.The embodiment of the present invention can effectively improve the extraction rate of thematic information, while ensure to extract the reliability of result.
Description
Technical field
The present invention relates to Remote Sensing Data Processing technical fields, are carried in particular to a kind of information based on remote sensing images
Take method and apparatus.
Background technology
The development of satellite imagery technology, data processing speed are much lagged behind to the research of satellite image cutting techniques at present
The remote rhythm for not catching up with remote sensing satellite and obtaining data becomes an arduousness so as to cause the quick identification of various Natural resources informations
Work, especially obtain large area vector quantization information.
The content of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of information extracting method and dress based on remote sensing images
It puts, to improve the above problem.
Present pre-ferred embodiments provide a kind of information extracting method based on remote sensing images, including:
It obtains remote sensing images and the remote sensing images is pre-processed to obtain pretreatment image;
It determines special topic sample, and band math is carried out to the pretreatment image according to the wave band feature of the special topic sample and is obtained
To data to be analyzed;
Calculate the similarity of the spectrum form and each spectrum form in the data to be analyzed of the thematic sample;
It is chosen from the data to be analyzed and is less than the spectroscopic data of predetermined threshold value simultaneously with the similarity of the thematic sample
Mark;
According to mark result extracted from the pretreatment image with the corresponding original image information of each mark, and to its into
Row cluster and iterative processing are to obtain thematic image information;
Vectorized process is carried out to the thematic image information to obtain thematic data and preserve.
Further, which is pre-processed to obtain pretreatment image, including:
Color enhancement and resolution ratio fusion are carried out to the remote sensing image data, obtains high-precision remote sensing images;
Geographical location registration and geometric correction carry out the high-precision remote sensing images based on default map and elevation model
To obtain the pretreatment image.
Further, if the special topic sample is woods body sample, according to the wave band feature of the special topic sample to described pre-
Processing image, which carries out the step of band math obtains data to be analyzed, to be included:
Obtain corresponding with woods body sample infrared band and red spectral band, and ask for the difference between the two and the two it
With;
Obtain vegetation index using the difference between the two divided by sum of the two, and the vegetation index is amplified processing using as
Data to be analyzed.
Further, the original image information includes multiple scattered figure spots and multiple clear areas, it is clustered
And iterative processing to obtain thematic image information the step of include:
The multiple scattered figure spot is connected to form classification patch, and the blank that preset value will be less than in multiple clear areas
Area gives up, and obtains including the thematic image information of the classification patch.
Further, the spectrum form of the thematic sample and each spectrum form in the data to be analyzed are being calculated
The realization of Spectral angle mapper algorithm can be used during similarity.
Further, carrying out vectorized process to the thematic image information to obtain thematic data and the step of preserve
Afterwards, the method further includes:
Mask process carries out the thematic sample for having completed classification based on the pretreatment image, and will complete at mask
Pretreatment image after reason carries out pretreatment image during information extraction as next thematic sample.
Present pre-ferred embodiments also provide a kind of information extracting device based on remote sensing images, including:
Preprocessing module, for obtaining remote sensing images and being pre-processed to obtain pretreatment image to the remote sensing images;
Band math module, for determining thematic sample, and according to the wave band feature of the special topic sample to the pretreatment
Image carries out band math and obtains data to be analyzed;
Similarity calculation module, for calculating the spectrum form of the thematic sample and each light in the data to be analyzed
Compose the similarity of form;
Mark module, the similarity for being chosen from the data to be analyzed with the thematic sample are higher than predetermined threshold value
Spectroscopic data and mark;
Information extraction modules are corresponding original with each mark for being extracted according to mark result from the pretreatment image
Image information, and it is clustered and iterative processing is to obtain thematic image information;
Vectorized process module, for the thematic image information progress vectorized process to be obtained thematic data and protected
It deposits.
Further, the preprocessing module includes:
For the remote sensing images to be carried out with color enhancement and resolution ratio fusion, it is distant to obtain high-precision for pretreatment unit
Feel image;
Unit is corrected, high-precision remote sensing images progress geographical location is matched somebody with somebody for being based on default map and elevation model
Accurate and geometric correction is to obtain the pretreatment image.
Further, the original image information includes multiple scattered figure spots and multiple clear areas, described information extraction
Module is additionally operable to connect to form classification patch by the multiple scattered figure spot, and the sky that will be less than preset value in multiple clear areas
White area is given up, and obtains including the thematic image information of the classification patch.
Further, described device further includes:
Mask process module, for based on the pretreatment image to having completed the thematic sample of classification at line mask
Reason, and using the pretreatment image after completion mask process as pretreatment figure during next thematic sample progress information extraction
Picture.
Compared with prior art, the embodiment of the present invention provides a kind of information extracting method and device based on remote sensing images,
Wherein, according to classification and extraction of the pop feature of thematic sample to the thematic information in remote sensing images, letter can be effectively improved
Cease extraction efficiency and reliability.Also effective guarantee of embodiment of the present invention information extraction process is intelligent and efficient simultaneously,
Reduce cost of processing information.
For the above objects, features and advantages of the present invention is enable to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
It in order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of scope, for those of ordinary skill in the art, without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the box of the electronic equipment of the application information extracting device provided in an embodiment of the present invention based on remote sensing images
Structure diagram.
Fig. 2 is the flow diagram of the information extracting method provided in an embodiment of the present invention based on remote sensing images.
Fig. 3 is the sub-process schematic diagram of step S110 shown in Fig. 2.
Fig. 4 is the frame structure schematic diagram of the information extracting device provided in an embodiment of the present invention based on remote sensing images.
Fig. 5 is the frame structure schematic diagram of the preprocessing module shown in Fig. 4.
Icon:10- electronic equipments;Information extracting devices of the 100- based on remote sensing images;110- preprocessing modules;111- is pre-
Processing unit;112- corrects unit;120- band math modules;130- similarity calculation modules;140- mark modules;150- believes
Cease extraction module;160- vectorized process modules;170- mask process modules;200- memories;300- storage controls;400-
Processor.
Specific embodiment
Classification, the extraction of traditional thematic information based on remote sensing images depend primarily on human-computer interaction visual interpretation,
It is such as picked up by artificial experience into row bound, low so as to cause information extraction efficiency, the result of different people processing exists in addition
Difference so that many valuable information can not interpret out at the first time, while will also result in data waste.
Through inventor the study found that same atural object all has different Spectral Characteristics in the same band or different-waveband, because
This, can carry out the classification and extraction of the different thematic informations in remote sensing images according to the pop feature of atural object.
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Usually
The component for the embodiment of the present invention being described and illustrated herein in the accompanying drawings can configure to arrange and design with a variety of.Cause
This, the detailed description of the embodiment of the present invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Go out all other embodiments obtained on the premise of creative work, belong to the scope of protection of the invention.
It should be noted that:Similar label and letter represents similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent attached drawing in a attached drawing.
As shown in Figure 1, it is the information extracting method based on remote sensing images provided using present pre-ferred embodiments
With the frame structure schematic diagram of the electronic equipment 10 of device, which includes the information extracting device based on remote sensing images
100th, memory 200, storage control 300 and processor 400.Wherein, the memory 200, storage control 300 and place
Reason 400 each element of device is directly or indirectly electrically connected between each other, to realize the transmission of data or interaction.For example, these yuan
It is realized and is electrically connected by one or more communication bus or signal wire between part.The information extraction dress based on remote sensing images
Putting 100 includes at least one the electronics can be stored in the memory 200 or be solidificated in the form of software or firmware setting
Software function module in standby 10 operating system.The processor 400 accesses institute under the control of the storage control 300
Memory 200 is stated, for performing the executable module stored in the memory 200, for example (,) it is described based on remote sensing images
Software function module and computer program included by information extracting device 100 etc., and then realize matching somebody with somebody in the embodiment of the present invention
Put method.Optionally, the electronic equipment 10 may be, but not limited to, smart mobile phone, IPAD, computer, server etc..
It should be appreciated that structure shown in FIG. 1 is only to illustrate.The electronic equipment 10 can have it is more more than shown in Fig. 1 or
The less component of person has the configuration different from shown in Fig. 1.Wherein, each component shown in FIG. 1 can be by software, hardware
Or a combination thereof realization.
Further, as shown in Fig. 2, being the information extracting method based on remote sensing images that present pre-ferred embodiments provide
Flow diagram, the information extracting method based on remote sensing images be applied to Fig. 1 shown in electronic equipment 10.It ties below
Fig. 2 is closed the idiographic flow and step of the information extracting method based on remote sensing images is described in detail.
Step S110 obtains remote sensing images and the remote sensing images is pre-processed to obtain pretreatment image.
Wherein, there are many acquisition modes of the remote sensing images, for example, can directly be issued by national correlation department, again
For example, it can be obtained in a manner that oneself actual measurement is obtained or bought.In addition, in the present embodiment, as shown in figure 3,
The remote sensing image data can be pre-processed by following step S111 and step S112, it is specific as follows.
Step S111 carries out the remote sensing images color enhancement and resolution ratio fusion to obtain high-precision remote sensing figure
Picture.
Wherein, can color enhancement be carried out to the remote sensing image data by professional image software, resolution ratio merges
Deng, the existing high spatial resolution of image that makes that treated, and have abundant color.Optionally, the professional image is soft
Part can be but not limited to ENVI (The Environment for Visualizing Images) remote sensing image processing such as and put down
Platform etc., the present embodiment are not limited herein.
Step S112, the high-precision remote sensing images are carried out based on default map and elevation model geographical location registration and
Geometric correction is to obtain the pretreatment image.
In the present embodiment, the default map can flexibly be chosen according to actual demand.For example, the default map can
To be but not limited to hypsographic map, layer colours topographic map, topographical profile graph etc..
Step S120 determines special topic sample, and the pretreatment image is carried out according to the wave band feature of the special topic sample
Band math obtains data to be analyzed.
Wherein, the thematic sample can be but not limited to forest land sample, water body sample, sand ground sample etc..The present embodiment
In, it is described special topic sample selection can be by artificial experience carry out, for example, can be completely dependent on naked eyes or field investigation come
The pixel in remote sensing images is specified as classification samples, then the similarity by analyzing each pixel and thematic sample in sample,
To judge to sort out.Such as by taking the sample of forest land as an example, local delineation is carried out in remote sensing images based on the forest land sample, and by delineation
Forest land is as standard, i.e., thematic sample.
Further, since the corresponding wave band of different thematic samples is different, to the wave bands of different thematic samples into
Row computing can obtain the new wave band that can be protruded and reflect the thematic information difference, and then the information that notes abnormalities, to complete follow-up point
Class.
For example, when the special topic sample is forest land sample, according to the wave band feature of thematic sample to the pretreatment image
Carrying out the step of band math obtains data to be analyzed includes:The corresponding wave band of forest land sample is obtained as infrared band and feux rouges
Wave band, then ask for changing the difference between the two and sum of the two in infrared band and red spectral band, utilize the difference between the two divided by the two
The sum of obtain vegetation index, and processing is amplified to the vegetation index using as data to be analyzed (new wave band), this is treated point
Analysis data can reflect the difference of vegetation.
In another example when the special topic sample is water body sample, the pretreatment is schemed according to the wave band feature of thematic sample
Include as carrying out the step of band math obtains data to be analyzed:The corresponding wave band of water body sample is obtained as green light band and red
Wave section, then green light band and infrared band the difference between the two and sum of the two are asked for, utilize the difference between the two divided by sum of the two
It obtains water body index, and processing is amplified to the water body index using as data to be analyzed (new wave band), the number to be analyzed
According to the difference that can reflect water body.
It should be noted that vegetation index or water body index due to being directly calculated etc. both less than 1, far smaller than its all band
Therefore pixel value, in actual implementation, can obtain 1000 times obtained of such as vegetation index or water body index expansion to be analyzed
Data, then matching operation is carried out with the pixel value of its all band, to reflect that thematic sample is believed with other special topics from spectral characteristic
The difference of breath.
Step S130 calculates the phase of the spectrum form and each spectrum form in the data to be analyzed of the thematic sample
Like degree.
In the present embodiment, the spectrum form of the thematic sample and each spectrum form in the data to be analyzed are being calculated
Similarity when can be used but be not limited to Spectral angle mapper algorithm realization.
Step S140 chooses the light for being less than predetermined threshold value with the similarity of the thematic sample from the data to be analyzed
Modal data simultaneously marks.
In the present embodiment, the similarity is the corresponding spectrum form of data to be analyzed light corresponding with the special topic sample
The spectral modeling difference between form is composed, when the spectral modeling difference is less than predetermined threshold value (spectral modeling threshold value), then can assert the light
It is same class that corresponding testing data, which is composed, with the thematic sample, and is marked.
Optionally, the predetermined threshold value can carry out flexible design according to actual demand, for example, being forest land for thematic sample
Sample, the predetermined threshold value can be 0.01 or so;It is desert sample for thematic sample, the predetermined threshold value can be 0.03
Left and right.It should be noted that in the present embodiment, the predetermined threshold value, which crosses conference, causes classification results more than actual conditions, and presets threshold
Be worth it is too small can cause classification results less than actual conditions, and the corresponding classification results of different classifications threshold value are different.
Step S150 extracts original image corresponding with each mark according to mark result from the pretreatment image and believes
Breath, and it is clustered and iterative processing is to obtain thematic image information.
Wherein, due to carrying out that in sorted remote sensing image data a series of tiny classification can be generated based on thematic information
Figure spot and clear area (no class area) therefore, cluster it and can be with the step of iterative processing is to obtain thematic image information
Including:The multiple scattered figure spot is connected to form classification patch, and the clear area that preset value will be less than in multiple clear areas
Give up, obtain including the thematic image information of the classification patch.
Wherein, cluster analysis is a kind of filling relation, and multiple scattered small figure classes are connected and are classified as one kind, such as may be used
To provide the filtering box of a 3*3, it will be bonded to less than the clear area of the numerical value in the figure spot that connection has been completed in classification, be polymerized to one
Class.Meanwhile then cast out for the classification patch of not upper enough the area of pictural surface.In addition, iterative analysis gives up merging for one kind, it can be according to special
Figure spot less than some pixel number threshold value is integrated into close region by the purposes of topic sample, for example, by taking the sample of forest land as an example, it is assumed that
Pixel number threshold value is 500 in advance, then rejecting is ignored in the forest land that automatic classification results can be less than to 500 pixels, is integrated into phase
Neighbouring region.
Step S160 carries out vectorized process to obtain thematic data and preserve to the thematic image information.
Wherein, since the classification results after being extracted by data are that raster data cannot be directly used to statistical analysis and fortune
It calculates, therefore, in the present embodiment, it is necessary to which the thematic information obtained after handling classification carries out grid and vector processing.
Step S170 carries out the thematic sample for having completed classification mask process based on the pretreatment image, and will
Complete the pretreatment image when pretreatment image after mask process carries out information extraction as next thematic sample.
Wherein, due to carrying out data classification, extraction based on a kind of thematic sample every time, to avoid a upper special topic
Sample impacts data classification, the extraction of next special topic sample, in the present embodiment, can be to having completed extraction and having divided
The thematic sample of class carries out mask process, and the image that will have completed classification is covered or directly scratched, it is made no longer to join
With classification.
Further, as shown in figure 4, being the information extracting device based on remote sensing images that present pre-ferred embodiments provide
100 frame structure schematic diagram, the electronics that the information extracting device 100 based on remote sensing images is applied to shown in Fig. 1 are set
Standby 10.Wherein, the information extracting device 100 based on remote sensing images include preprocessing module 110, band math module 120,
Similarity calculation module 130, mark module 140, information extraction modules 150, vectorized process module 160 and mask process module
170。
The preprocessing module 110, for obtaining remote sensing images and being pre-processed to the remote sensing images
Image.In the present embodiment, the description as described in the preprocessing module 110 specifically refers to the detailed description of above-mentioned steps S110,
That is, the step S110 can be performed by the preprocessing module 110, thus do not illustrate more herein.Optionally, as schemed
Shown in 5, the preprocessing module 110 includes pretreatment unit 111 and correction unit 112.
The pretreatment unit 111 merges to obtain for carrying out the remote sensing images color enhancement and resolution ratio
High-precision remote sensing images.In the present embodiment, the description as described in the pretreatment unit 111 specifically refers to above-mentioned steps S111
It is described in detail, that is, the step S111 can be performed by pretreatment unit 111, thus does not illustrate more herein.
The correction unit 112 carries out ground for being based on default map and elevation model to the high-precision remote sensing images
Position registration and geometric correction are managed to obtain the pretreatment image.In the present embodiment, the description as described in the correction unit 112
The detailed description of above-mentioned steps S112 is specifically referred to, that is, the step S112 can be performed by correction unit 112, thus
Do not illustrate more herein.
The band math module 120, for determining thematic sample, and according to the wave band feature of the special topic sample to described
Pretreatment image carries out band math and obtains data to be analyzed.In the present embodiment, the description as described in the band math module 120
The detailed description of above-mentioned steps S120 is specifically referred to, that is, the step S120 can be performed by band math module 120,
Do not illustrate more herein thus.
The similarity calculation module 130, for calculating the spectrum form of the thematic sample and the data to be analyzed
In each spectrum form similarity.In the present embodiment, the description as described in the similarity calculation module 130 specifically refers to
The detailed description of step S130 is stated, that is, the step S130 can be performed by similarity calculation module 130, thus herein not
Make more explanations.
The mark module 140, the similarity for being chosen from the data to be analyzed with the thematic sample are higher than
The spectroscopic data and mark of predetermined threshold value.In the present embodiment, the description as described in the mark module 140 specifically refers to above-mentioned step
The detailed description of rapid S140, that is, the step S140 can be performed by mark module 140, thus does not illustrate more herein.
Described information extraction module 150, for being extracted according to mark result from the pretreatment image and each mark pair
The original image information answered, and it is clustered and iterative processing is to obtain thematic image information.In the present embodiment, on institute
The description for stating information extraction modules 150 specifically refers to the detailed description of above-mentioned steps S150, that is, the step S150 can be with
It is performed by information extraction modules 150, thus not illustrated more herein.
The vectorized process module 160, for obtaining special topic to the thematic image information progress vectorized process
Data simultaneously preserve.In the present embodiment, the description as described in the vectorized process module 160 specifically refers to above-mentioned steps S160
It is described in detail, that is, the step S160 can be performed by vectorized process module 160, thus does not illustrate more herein.
The mask process module 170, for based on the pretreatment image to completed classification thematic sample into
Line mask processing, and using the pretreatment image after completion mask process as pre- during next thematic sample progress information extraction
Handle image.In the present embodiment, the description as described in the mask process module 170 specifically refers to the detailed of above-mentioned steps S170
Description, that is, the step S170 can be performed by mask process module 170, thus does not illustrate more herein.
In conclusion the embodiment of the present invention provides a kind of information extracting method and device based on remote sensing images, wherein, root
According to classification and extraction of the pop feature of thematic sample to the thematic information in remote sensing images, information extraction effect can be effectively improved
Rate and reliability.Also effective guarantee of embodiment of the present invention information extraction process is intelligent and efficient simultaneously, reduces letter
Cease processing cost.
In the several embodiments provided in the embodiment of the present invention, it should be understood that disclosed apparatus and method also may be used
To realize by another way.Apparatus and method embodiment described above is only schematical, for example, in attached drawing
Flow chart and block diagram show the device of multiple embodiments according to the present invention, the possibility of method and computer program product is realized
Architectural framework, function and operation.In this regard, each box in flow chart or block diagram can represent module, a program
A part for section or code, a part for the module, program segment or code are used to implement defined patrol comprising one or more
Collect the executable instruction of function.It should also be noted that at some as the function of in the realization method replaced, being marked in box
It can be occurred with being different from the order marked in attached drawing.For example, two continuous boxes can essentially be held substantially in parallel
Row, they can also be performed in the opposite order sometimes, this is depending on involved function.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and/or flow chart can use function or dynamic as defined in performing
The dedicated hardware based system made is realized or can realized with the combination of specialized hardware and computer instruction.
In addition, each function module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contribute to the prior art or the part of the technical solution can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, is used including some instructions so that a computer equipment (can be
People's computer, electronic equipment or network equipment etc.) perform all or part of step of each embodiment the method for the present invention
Suddenly.And foregoing storage medium includes:USB flash disk, mobile hard disk, are deposited at read-only memory (ROM, Read-Only Memory) at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic disc or CD.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain so that process, method, article or equipment including a series of elements not only include those elements, but also including
It other elements that are not explicitly listed or further includes as elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, also there are other identical elements in article or equipment.
The foregoing is merely the alternative embodiments of the present invention, are not intended to limit the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of information extracting method based on remote sensing images, which is characterized in that including:
It obtains remote sensing images and the remote sensing images is pre-processed to obtain pretreatment image;
It determines special topic sample, and band math is carried out to the pretreatment image according to the wave band feature of the special topic sample and is treated
Analyze data;
Calculate the similarity of the spectrum form and each spectrum form in the data to be analyzed of the thematic sample;
The spectroscopic data and mark for being less than predetermined threshold value with the similarity of the thematic sample are chosen from the data to be analyzed;
According to mark result extracted from the pretreatment image with the corresponding original image information of each mark, and it is gathered
Class and iterative processing are to obtain thematic image information;
Vectorized process is carried out to the thematic image information to obtain thematic data and preserve.
2. the information extracting method according to claim 1 based on remote sensing images, which is characterized in that the remote sensing images number
The step of according to being pre-processed to obtain pretreatment image, including:
The remote sensing images are carried out with color enhancement and resolution ratio fusion, obtains high-precision remote sensing images;
Geographical location registration and geometric correction carry out the high-precision remote sensing images based on default map and elevation model to obtain
To the pretreatment image.
3. the information extracting method according to claim 1 based on remote sensing images, which is characterized in that if the special topic sample
For woods body sample, then band math is carried out to the pretreatment image according to the wave band feature of the special topic sample and obtain number to be analyzed
According to the step of, including:
Infrared band corresponding with the woods body sample and red spectral band are obtained, and asks for the difference between the two and sum of the two;
Vegetation index is obtained using the difference between the two divided by sum of the two, and processing is amplified to the vegetation index using as treating point
Analyse data.
4. the information extracting method according to claim 1 based on remote sensing images, which is characterized in that the original image letter
Breath includes multiple scattered figure spots and multiple clear areas, it is clustered and iterative processing is to obtain the step of thematic image information
Suddenly, including:
The multiple scattered figure spot is connected to form classification patch, and the clear area for being less than preset value in multiple clear areas is given up
It abandons to obtain the thematic image information for including the classification patch.
5. the information extracting method according to claim 1 based on remote sensing images, which is characterized in that calculating the special topic
Spectral angle mapper algorithm reality can be used during the similarity of the spectrum form of sample and each spectrum form in the data to be analyzed
It is existing.
6. the information extracting method according to claim 1 based on remote sensing images, which is characterized in that the thematic map
As information carry out vectorized process with obtain thematic data and the step of preserve after, the method further includes:
Mask process carries out the thematic sample for having completed classification based on the pretreatment image, and will be after completion mask process
Pretreatment image of pretreatment image when carrying out information extraction as next thematic sample.
7. a kind of information extracting device based on remote sensing images, which is characterized in that including:
Preprocessing module, for obtaining remote sensing images and being pre-processed to obtain pretreatment image to the remote sensing images;
Band math module, for determining thematic sample, and according to the wave band feature of the special topic sample to the pretreatment image
It carries out band math and obtains data to be analyzed;
Similarity calculation module, for calculating the spectrum form of the thematic sample and each spectrum shape in the data to be analyzed
The similarity of state;
Mark module, for choosing the light for being higher than predetermined threshold value with the similarity of the thematic sample from the data to be analyzed
Modal data simultaneously marks;
Information extraction modules, for being extracted according to mark result from the pretreatment image and the corresponding original image of each mark
Information, and it is clustered and iterative processing is to obtain thematic image information;
Vectorized process module, for the thematic image information progress vectorized process to be obtained thematic data and preserved.
8. the information extracting device according to claim 7 based on remote sensing images, which is characterized in that the preprocessing module
Including:
Pretreatment unit for the remote sensing images to be carried out with color enhancement and resolution ratio fusion, obtains high-precision remote sensing figure
Picture;
Correct unit, carry out for being based on default map and elevation model to the high-precision remote sensing images geographical location registration and
Geometric correction is to obtain the pretreatment image.
9. the information extracting device according to claim 7 based on remote sensing images, which is characterized in that the original image letter
Breath includes multiple scattered figure spots and multiple clear areas, and described information extraction module is additionally operable to connect the multiple scattered figure spot
It connects to form classification patch, and the clear area for being less than preset value in multiple clear areas is given up, obtain comprising the classification patch
Thematic image information.
10. the information extracting device according to claim 7 based on remote sensing images, which is characterized in that described device is also wrapped
It includes:
Mask process module, for carrying out mask process to the thematic sample for having completed classification based on the pretreatment image,
And using the pretreatment image after completion mask process as pretreatment image during next thematic sample progress information extraction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810004262.3A CN108109125A (en) | 2018-01-03 | 2018-01-03 | Information extracting method and device based on remote sensing images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810004262.3A CN108109125A (en) | 2018-01-03 | 2018-01-03 | Information extracting method and device based on remote sensing images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108109125A true CN108109125A (en) | 2018-06-01 |
Family
ID=62218799
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810004262.3A Pending CN108109125A (en) | 2018-01-03 | 2018-01-03 | Information extracting method and device based on remote sensing images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108109125A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109063605A (en) * | 2018-07-16 | 2018-12-21 | 中国水产科学研究院南海水产研究所 | A kind of oyster row's oyster frame cultivation measuring method, system and device for aquaculture |
CN109542062A (en) * | 2018-11-20 | 2019-03-29 | 四川省宇行规划设计有限公司 | Resource environment dynamic digital monitor control system and method, information data processing terminal |
CN110276254A (en) * | 2019-05-17 | 2019-09-24 | 恒锋信息科技股份有限公司 | No peddler region street pedlar's automatic identification method for early warning based on unmanned plane |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1791082A1 (en) * | 2005-11-23 | 2007-05-30 | Leica Geosystems AG | Feature extraction using pixel cues and object cues |
CN101950361A (en) * | 2010-09-06 | 2011-01-19 | 中国科学院遥感应用研究所 | Adaptive extraction method of remote sensing image thematic information based on spectrum matching degree |
CN103093233A (en) * | 2012-12-03 | 2013-05-08 | 中国环境科学研究院 | Forest classification method based on object-oriented high-resolution remote sensing image |
CN105372672A (en) * | 2015-12-07 | 2016-03-02 | 广州地理研究所 | Time sequence data-based southern winter crop planting area extraction method |
CN106950177A (en) * | 2016-11-16 | 2017-07-14 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method of the satellite remote-sensing images of GF 4 |
-
2018
- 2018-01-03 CN CN201810004262.3A patent/CN108109125A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1791082A1 (en) * | 2005-11-23 | 2007-05-30 | Leica Geosystems AG | Feature extraction using pixel cues and object cues |
CN101950361A (en) * | 2010-09-06 | 2011-01-19 | 中国科学院遥感应用研究所 | Adaptive extraction method of remote sensing image thematic information based on spectrum matching degree |
CN103093233A (en) * | 2012-12-03 | 2013-05-08 | 中国环境科学研究院 | Forest classification method based on object-oriented high-resolution remote sensing image |
CN105372672A (en) * | 2015-12-07 | 2016-03-02 | 广州地理研究所 | Time sequence data-based southern winter crop planting area extraction method |
CN106950177A (en) * | 2016-11-16 | 2017-07-14 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method of the satellite remote-sensing images of GF 4 |
Non-Patent Citations (7)
Title |
---|
包蕾: "基于RS与GIS的城中村与山地居民点现状研究", 《中国优秀硕士学位论文全文数据库_经济与管理科学辑J辑》 * |
华中农学院土化系: "《土壤专业图件的卫片编绘技术 中》", 30 September 1984, 华中农学院土化系出版发行 * |
周宇津: "基于决策树的多分类器遥感影像分层分类研究与系统实现", 《中国优秀硕士学位论文全文数据库_信息科技辑I辑》 * |
尹海华: "《城市与区域规划空间分析实验教程》", 28 February 2014, 东南大学出版社 * |
杜培军等: "高光谱遥感数据光谱特征的提取与应用", 《中国矿业大学学报》 * |
樊彦国等: "基于多波段分析的无阈值自动光谱角制图分类法", 《地理与地理信息科学》 * |
许鹏: "《草地资源调查规划学》", 31 October 2000, 中国农业出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109063605A (en) * | 2018-07-16 | 2018-12-21 | 中国水产科学研究院南海水产研究所 | A kind of oyster row's oyster frame cultivation measuring method, system and device for aquaculture |
CN109542062A (en) * | 2018-11-20 | 2019-03-29 | 四川省宇行规划设计有限公司 | Resource environment dynamic digital monitor control system and method, information data processing terminal |
CN110276254A (en) * | 2019-05-17 | 2019-09-24 | 恒锋信息科技股份有限公司 | No peddler region street pedlar's automatic identification method for early warning based on unmanned plane |
CN110276254B (en) * | 2019-05-17 | 2024-06-07 | 恒锋信息科技股份有限公司 | Unmanned aerial vehicle-based automatic recognition and early warning method for bootlegged area bootlegged |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109800736B (en) | Road extraction method based on remote sensing image and deep learning | |
Ke et al. | A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing | |
Tian et al. | Optimization in multi‐scale segmentation of high‐resolution satellite images for artificial feature recognition | |
EP2801951B1 (en) | Aerial image segmentation for refineries | |
CN109241871A (en) | A kind of public domain stream of people's tracking based on video data | |
US20100272357A1 (en) | Method of image segmentation | |
CN111986099A (en) | Tillage monitoring method and system based on convolutional neural network with residual error correction fused | |
CN108596102B (en) | RGB-D-based indoor scene object segmentation classifier construction method | |
CN109711288A (en) | Remote sensing ship detecting method based on feature pyramid and distance restraint FCN | |
CN107016403B (en) | A method of completed region of the city threshold value is extracted based on nighttime light data | |
Hormese et al. | Automated road extraction from high resolution satellite images | |
CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
CN110133443B (en) | Power transmission line component detection method, system and device based on parallel vision | |
CN113537180B (en) | Tree obstacle identification method and device, computer equipment and storage medium | |
CN109635811A (en) | The image analysis method of spatial plant | |
CN108109125A (en) | Information extracting method and device based on remote sensing images | |
CN110986889A (en) | High-voltage substation panoramic monitoring method based on remote sensing image technology | |
CN115019163A (en) | City factor identification method based on multi-source big data | |
CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
Chang et al. | A visual basic program for ridge axis picking on DEM data using the profile-recognition and polygon-breaking algorithm | |
Lizarazo et al. | Segmentation of remotely sensed imagery: moving from sharp objects to fuzzy regions | |
CN113723833B (en) | Method, system, terminal equipment and storage medium for evaluating quality of forestation actual results | |
KR102416714B1 (en) | System and method for city-scale tree mapping using 3-channel images and multiple deep learning | |
CN110826394A (en) | Reservoir identification method and device based on convolutional neural network algorithm | |
Jovanović et al. | Object based image analysis in forestry change detection |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180601 |
|
RJ01 | Rejection of invention patent application after publication |