CN106228553B - High-resolution remote sensing image shadow Detection apparatus and method - Google Patents
High-resolution remote sensing image shadow Detection apparatus and method Download PDFInfo
- Publication number
- CN106228553B CN106228553B CN201610573898.0A CN201610573898A CN106228553B CN 106228553 B CN106228553 B CN 106228553B CN 201610573898 A CN201610573898 A CN 201610573898A CN 106228553 B CN106228553 B CN 106228553B
- Authority
- CN
- China
- Prior art keywords
- image
- remote sensing
- shadow
- resolution remote
- space characteristics
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06T2207/20076—Probabilistic image processing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of high-resolution remote sensing image shadow Detection apparatus and method, are related to field of image processing.The high-resolution remote sensing image shadow Detection apparatus and method are by converting space characteristics image for a high-resolution remote sensing image；Primary segmentation is carried out to the space characteristics image, and obtains shadow region and non-hatched area；Processing result is handled shadow region and non-hatched area and obtained again, and vector machine classification is supported to the high-resolution remote sensing image according to the processing result, and obtain probability image array；Processing is optimized to the probability image array according to extension random walk algorithm, and obtains shadow image matrix of consequence.The finally obtained shadow image of high-resolution remote sensing image shadow Detection apparatus and method has the characteristics that robustness is high, noise spot is few and is not necessarily to handmarking, and improves the precision of the shadow image detected.
Description
Technical field
The present invention relates to field of image processings, in particular to a kind of high-resolution remote sensing image shadow Detection device
With method.
Background technique
In recent years, with the rapid development of satellite sensing technology, high-resolution remote sensing image spatial resolution is greatly improved,
Part satellite remote sensing date spatial resolution has reached sub-meter grade.However, the presence of shade very great Cheng in high-resolution remote sensing image
The characteristic information that image is weakened on degree has obscured the spatial detail of important object, gives subsequent image procossing, analysis and target
Identification brings very big difficulty.
In the prior art, the shadow region of the method detection high-resolution remote sensing image of adaptive feature selection is usually utilized
Domain.Concrete mode to be first that RGB color image or Pan full-colour image differentiate to input picture, choose by hand labeled
Then partial phantom region out is sought local threshold using using each section of fixed-size window to label, is then calculated
Global average threshold, detects image shade with this threshold value.But adaptive feature selection method includes multiple in processing
When the high-resolution remote sensing image of miscellaneous scene, the detection method performance based on threshold value can be remarkably decreased, and algorithm robustness is not high.
Summary of the invention
In view of this, the embodiment of the present invention be designed to provide a kind of high-resolution remote sensing image shadow Detection device with
Method.
In a first aspect, the embodiment of the invention provides a kind of high-resolution remote sensing image shadow Detection device, the high score
Resolution remote sensing image shade detection device includes:
Image conversion unit, for converting space characteristics image for a high-resolution remote sensing image；
Territorial classification unit for carrying out primary segmentation to the space characteristics image, and obtains shadow region and non-yin
Shadow zone domain；
Probability image array obtaining unit, for shadow region and non-hatched area to be handled and handled
As a result, being simultaneously supported vector machine classification to the high-resolution remote sensing image according to the processing result, and obtain initial general
Rate image array；
Shadow image matrix of consequence obtaining unit, according to extension random walk algorithm to the probability image array into
Row optimization processing, and obtain shadow image matrix of consequence.
Second aspect, the embodiment of the invention also provides a kind of high-resolution remote sensing image shadow detection method, the height
Resolution remote sensing images shadow detection method includes:
Space characteristics image is converted by a high-resolution remote sensing image；
Primary segmentation is carried out to the space characteristics image, and obtains shadow region and non-hatched area；
Processing result is handled shadow region and non-hatched area and is obtained, and according to the processing result to described
High-resolution remote sensing image is supported vector machine classification, and obtains probability image array；
Processing is optimized to the probability image array according to extension random walk algorithm, and obtains shadow image
Matrix of consequence.
Compared with prior art, high-resolution remote sensing image shadow Detection apparatus and method provided by the invention, pass through by
One high-resolution remote sensing image is converted into space characteristics image；Primary segmentation is carried out to the space characteristics image, and obtains yin
Shadow zone domain and non-hatched area；Processing result is handled shadow region and non-hatched area and obtained again, and according to described
Processing result is supported vector machine classification to the high-resolution remote sensing image, and obtains probability image array；Foundation
Extension random walk algorithm optimizes processing to the probability image array, and obtains shadow image matrix of consequence.It should
The finally obtained shadow image of high-resolution remote sensing image shadow Detection apparatus and method have that robustness is high, noise spot is few and
The characteristics of without handmarking, and improve the precision of the shadow image detected.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.Therefore, below to the reality of the invention provided in the accompanying drawings
The detailed description for applying example is not intended to limit the range of claimed invention, but is merely representative of selected implementation of the invention
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Fig. 1 is the block diagram of server provided in an embodiment of the present invention；
Fig. 2 is the functional unit schematic diagram of high-resolution remote sensing image shadow Detection device provided in an embodiment of the present invention；
Fig. 3 is the flow chart of high-resolution remote sensing image target shadow detection method provided in an embodiment of the present invention.
Wherein, the corresponding relationship between appended drawing reference and component names is as follows: high-resolution remote sensing image shadow Detection dress
Set 100, server 101, processor 102, memory 103, storage control 104, Peripheral Interface 105, image conversion unit
201, territorial classification unit 202, probability image array obtaining unit 203, shadow image matrix of consequence obtaining unit 204.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
The high-resolution remote sensing image shadow Detection apparatus and method that the embodiment of the present invention proposes, provide a kind of remote sensing mesh
Method for detecting area is marked, which is applicable to server 101.The server 101 can be, but not
It is limited to, network server, database server, cloud server etc..
As shown in Figure 1, being the block diagram of the server 101.The server 101 includes high-definition remote sensing figure
As shadow Detection device 100, processor 102, memory 103, storage control 104 and Peripheral Interface 105.
The memory 103, storage control 104 and processor 102, each element are directly or indirectly electrical between each other
Connection, to realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or letter between each other
Number line, which is realized, to be electrically connected.The high-resolution remote sensing image shadow Detection device 100 includes that at least one can be with software or solid
The form of part (firmware) is stored in the memory 103 or is solidificated in the operating system of the server 101
Software function module in (operating system, OS).The processor 102 is used to execute to store in memory 103
Executable module, for example, software function module or computer that the high-resolution remote sensing image shadow Detection device 100 includes
Program.
Wherein, memory 103 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 103 is for storing program, and the processor 102 executes described program after receiving and executing instruction, aforementioned
Method performed by the server 101 that the stream process that any embodiment of the embodiment of the present invention discloses defines can be applied to processor
In 102, or realized by processor 102.
Processor 102 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 102 can
To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
It can be microprocessor or the processor be also possible to any conventional processor etc..
Various input/output devices are couple processor and memory 103 by the Peripheral Interface 105.In some realities
It applies in example, Peripheral Interface 105, processor 102 and storage control 104 can be realized in one single chip.Some other
In example, they can be realized by independent chip respectively.
Referring to Fig. 2, the present invention implements a kind of high-resolution remote sensing image shadow Detection device 100 provided, the height
Resolution remote sensing images shadow Detection device 100 includes image conversion unit 201, territorial classification unit 202, probability image
Matrix obtaining unit 203 and shadow image matrix of consequence obtaining unit 204.
Described image conversion unit 201 is used to convert space characteristics image for a high-resolution remote sensing image.
Specifically, 201 formula of described image conversion unitBy one
High-resolution remote sensing image is converted into space characteristics image, whereinR, G, B are respectively the high-definition remote sensing figure
Red figure layer, green figure layer and the blueprint layer of picture, I, H, S are respectively the brightness figure layer of the space characteristics image, saturation degree figure layer
And coloration figure layer, V1、V2For interim intermediate variable, f indicates that the space characteristics image, i, j indicate that the space of pixel is sat
Mark.It is converted by image conversion unit by space and first converts original RGB image to the color space IHS, numeral system is recycled to turn
It changes and acquires space characteristics image f.
The territorial classification unit 202 is used to carry out primary segmentation to the space characteristics image, and obtains shadow region
With non-hatched area.
Specifically, the territorial classification unit 202 is used to carry out threshold value point to the space characteristics image using Da-Jin algorithm
It cuts, and obtains shadow region and non-hatched area.
Probability image array obtaining unit 203, for shadow region and non-hatched area to be handled and obtained
Processing result, and vector machine classification is supported to the high-resolution remote sensing image according to the processing result, and obtain just
Beginning probabilistic image matrix.
Specifically, the probability image array obtaining unit is used to carry out form to shadow region and non-hatched area
Filtering corrosion is learned, and extracts the sub-pixel point of shadow region and non-hatched area respectively, and according to the high-definition remote sensing
Image, the space characteristics image and the sub-pixel point extracted are supported vector to the high-resolution remote sensing image
Machine classification, and obtain probability image array.
Specifically, the acquisition pattern of probability image array can be with are as follows: given training sample set, that is, the seed picture obtained
Vegetarian refreshments collection (xi,yi), i=1,2..., l, x ∈ Rn, y ∈ { ± 1 }, wherein l indicates the number of sub-pixel point, RnIndicate seed
The feature set of pixel, (in present invention implementation, the classification of sub-pixel point is shadow region to the classification of y expression sub-pixel point
Seed point or non-hatched area seed point).The hyperplane of support vector machines is denoted as (wx)+b=0, wherein w is required initial
Probabilistic image matrix, b are the free values that can be arranged according to environment.Keep support vector cassification correct in face of all training samples
Classify and have class interval, it is desirable to which the hyperplane of support vector machines is met into constraint: yi[(w·xi)+b] >=1i=1,
2 ..., l, to calculate class interval and beTherefore the problem of construction optimal hyperlane, is converted under constraint formula
It asks:In the present embodiment, Lagrange function can be introduced, solves constrained optimization
Problem, to obtain probability image array w.
Shadow image matrix of consequence obtaining unit 204, according to extension random walk algorithm to the probability image moment
Battle array optimizes processing, and obtains shadow image matrix of consequence.
Specifically, the shadow image matrix of consequence obtaining unit 204 is used for according to formulaObtain shadow image matrix of consequence Pn, whereinPn is shadow image
Matrix of consequence, L are joint Laplace operator, and
Indicate the intensity of the connection between two neighbor pixels ii, jj, vi、vjIt respectively indicates
The pixel value of pixel i, j, β is one, and for the free values that environment is different and is changed, Pq is probability image array,
∧qFor diagonal matrix, and diagonal matrix ∧qDiagonal line on element representation node random walk probability.
In view of the shade in actual high-resolution remote sensing image always at connected domain state occur, each pixel it
Between relevance just seem there is critically important Decision-making Function to shadow Detection.In the present embodiment, by utilizing shadow image knot
Fruit matrix obtaining unit 204 optimizes processing to the probability image array according to extension random walk algorithm, and obtains
Shadow image matrix of consequence, simple shadow Detection and actual conditions can be connected, uses with spatial coherence for according to
According to extension random walk, shadow image matrix of consequence more highly accurately can be obtained, while can also effectively remove and detect
Shadow image matrix of consequence existing for salt-pepper noise.Therefore, detection, which obtains shadow image matrix of consequence, can not only reach fine
Required precision, moreover it is possible to so that detection flush edge and closer to reality.
Referring to Fig. 3, being needed the embodiment of the invention also provides a kind of high-resolution remote sensing image shadow detection method
It is bright, high-resolution remote sensing image shadow detection method provided by the present embodiment, the technology effect of basic principle and generation
Fruit is identical with above-described embodiment, and to briefly describe, the present embodiment part does not refer to place, can refer to corresponding in above-described embodiment
Content.The high-resolution remote sensing image shadow detection method includes:
Step S301: space characteristics image is converted by a high-resolution remote sensing image.
Space characteristics image is converted by a high-resolution remote sensing image by image conversion unit 201.Specifically, step
S301 may include formulaObtain space characteristics image, whereinR, G, B are respectively the high-definition remote sensing figure
Red figure layer, green figure layer and the blueprint layer of picture, I, H, S are respectively the brightness figure layer of the space characteristics image, saturation degree figure layer
And coloration figure layer, V1、V2For interim intermediate variable, f indicates that the space characteristics image, i, j indicate that the space of pixel is sat
Mark.
Step S302: primary segmentation is carried out to the space characteristics image, and obtains shadow region and non-hatched area.
By territorial classification unit 202 to the space characteristics image carry out primary segmentation, and obtain shadow region with it is non-
Shadow region.Specifically, step S302 may include carrying out Threshold segmentation to the space characteristics image using Da-Jin algorithm, and obtain
Obtain shadow region and non-hatched area.
Step S303: processing result is handled shadow region and non-hatched area and is obtained, and according to the processing
As a result vector machine classification is supported to the high-resolution remote sensing image, and obtains probability image array.
Shadow region and non-hatched area are handled and located by probability image array obtaining unit 203
Reason is as a result, be simultaneously supported vector machine classification to the high-resolution remote sensing image according to the processing result, and obtain initial
Probabilistic image matrix.Specifically, step S303 may include carrying out morphologic filtering corrosion to shadow region and non-hatched area,
And the sub-pixel point of shadow region and non-hatched area is extracted respectively, and according to the high-resolution remote sensing image, the sky
Between characteristic image and the sub-pixel extracted point vector machine classification is supported to the high-resolution remote sensing image, and obtain
Obtain probability image array.
Step S304: processing is optimized to the probability image array according to extension random walk algorithm, and is obtained
Obtain shadow image matrix of consequence.
By shadow image matrix of consequence obtaining unit 204 according to extension random walk algorithm to the probability image
Matrix optimizes processing, and obtains shadow image matrix of consequence.Specifically, step S304 may include according to formulaObtain shadow image matrix of consequence Pn, wherein PnFor shadow image
Matrix of consequence, L are joint Laplace operator, and Pq is probability image array, ∧qFor diagonal matrix, and diagonal matrix ∧q
Diagonal line on element representation node random walk probability.
It is tested through inventor, having obtained result shown in table 1, (wherein, the percentage in table 1 indicates the echo detected
The precision of picture).Table 1 lists two width figures (figure A, figure B) respectively in 1, adaptive feature selection method；2, it is based on support vector machines
The method of classification；3, the method based on stingy picture；4, high-resolution remote sensing image shadow detection method provided in an embodiment of the present invention
Processing under the obtained precision of shadow image, it will be apparent that, precision is higher, shows that effect is better.As it can be seen from table 1 this hair
The precision highest of the shadow image of the high-resolution remote sensing image shadow Detection apparatus and method of bright proposition.
Table 1
To sum up, high-resolution remote sensing image shadow Detection apparatus and method provided by the invention, by by a high-resolution
Remote sensing images are converted into space characteristics image；To the space characteristics image carry out primary segmentation, and obtain shadow region with it is non-
Shadow region；Processing result is handled shadow region and non-hatched area and obtained again, and according to the processing result pair
The high-resolution remote sensing image is supported vector machine classification, and obtains probability image array；According to extension random row
It walks algorithm and processing is optimized to the probability image array, and obtain shadow image matrix of consequence.The high-resolution is distant
Feeling the finally obtained shadow image of image shadow Detection apparatus and method has robustness height, noise spot few and is not necessarily to artificial mark
The characteristics of note, and improve the precision of the shadow image detected.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for 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, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Claims (6)
1. a kind of high-resolution remote sensing image shadow Detection device, which is characterized in that the high-resolution remote sensing image shade inspection
Surveying device includes:
Image conversion unit, for converting space characteristics image for a high-resolution remote sensing image；
Territorial classification unit for carrying out primary segmentation to the space characteristics image, and obtains shadow region and nonshaded area
Domain；
Probability image array obtaining unit, for being handled shadow region and non-hatched area and being obtained processing knot
Fruit, and vector machine classification is supported to the high-resolution remote sensing image according to the processing result, and obtain probability
Image array；
Shadow image matrix of consequence obtaining unit carries out the probability image array according to extension random walk algorithm excellent
Change processing, and obtain shadow image matrix of consequence；
The probability image array obtaining unit is used to carry out morphologic filtering corrosion to shadow region and non-hatched area,
And the sub-pixel point of shadow region and non-hatched area is extracted respectively, and according to the high-resolution remote sensing image, the sky
Between characteristic image and the sub-pixel extracted point vector machine classification is supported to the high-resolution remote sensing image, and obtain
Obtain probability image array；
Described image conversion unit formulaSpace characteristics image is obtained,
In,R, G, B are respectively that the high-resolution is distant
Feel red figure layer, green figure layer and the blueprint layer of image, I, H, S are respectively brightness figure layer, the saturation degree of the space characteristics image
Figure layer and coloration figure layer, V1、V2For interim intermediate variable, f indicates that the space characteristics image, i, j indicate the space of pixel
Coordinate.
2. high-resolution remote sensing image shadow Detection device according to claim 1, which is characterized in that the territorial classification
Unit is used to carry out Threshold segmentation to the space characteristics image using Da-Jin algorithm, and obtains shadow region and non-hatched area.
3. high-resolution remote sensing image shadow Detection device according to claim 1, which is characterized in that the shadow image
Matrix of consequence obtaining unit is used for according to formulaObtain shadow image result square
Battle array Pn, whereinPn
For shadow image matrix of consequence, L is joint Laplace operator, PqFor probability image array, ∧qFor diagonal matrix, and it is right
Angular moment battle array ∧qDiagonal line on element representation node random walk probability.
4. a kind of high-resolution remote sensing image shadow detection method, which is characterized in that the high-resolution remote sensing image shade inspection
Survey method includes:
Space characteristics image is converted by a high-resolution remote sensing image；
Primary segmentation is carried out to the space characteristics image, and obtains shadow region and non-hatched area；
Processing result is handled shadow region and non-hatched area and is obtained, and according to the processing result to the high score
Resolution remote sensing images are supported vector machine classification, and obtain probability image array；
Processing is optimized to the probability image array according to extension random walk algorithm, and obtains shadow image result
Matrix；
It is described to be handled shadow region and non-hatched area and obtained processing result, and according to the processing result to described
High-resolution remote sensing image by support vector cassification obtain probability image array the step of include:
Morphologic filtering corrosion is carried out to shadow region and non-hatched area, and extracts shadow region and non-hatched area respectively
Sub-pixel point, and according to the high-resolution remote sensing image, the space characteristics image and the sub-pixel point extracted
Vector machine classification is supported to the high-resolution remote sensing image, and obtains probability image array；
Described the step of converting space characteristics image for a high-resolution remote sensing image includes: formulaSpace characteristics image is converted by a high-resolution remote sensing image, whereinR, G, B are respectively the high-definition remote sensing figure
Red figure layer, green figure layer and the blueprint layer of picture, I, H, S are respectively the brightness figure layer of the space characteristics image, saturation degree figure layer
And coloration figure layer, V1、V2For interim intermediate variable, f indicates that the space characteristics image, i, j indicate that the space of pixel is sat
Mark.
5. high-resolution remote sensing image shadow detection method according to claim 4, which is characterized in that obtained to conversion
Space characteristics image carries out primary segmentation, and obtains shadow region with the step of non-hatched area and include:
Threshold segmentation is carried out to the space characteristics image using Da-Jin algorithm, and obtains shadow region and non-hatched area.
6. high-resolution remote sensing image shadow detection method according to claim 4, which is characterized in that described according to extension
Random walk algorithm optimizes processing to the probability image array, and the step of obtaining shadow image matrix of consequence packet
It includes:
According to formulaObtain shadow image matrix of consequence Pn, whereinPnFor shadow image
Matrix of consequence, L are joint Laplace operator, PqFor probability image array, ∧qFor diagonal matrix, and diagonal matrix ∧q
Diagonal line on element representation node random walk probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610573898.0A CN106228553B (en) | 2016-07-20 | 2016-07-20 | High-resolution remote sensing image shadow Detection apparatus and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610573898.0A CN106228553B (en) | 2016-07-20 | 2016-07-20 | High-resolution remote sensing image shadow Detection apparatus and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106228553A CN106228553A (en) | 2016-12-14 |
| CN106228553B true CN106228553B (en) | 2019-07-23 |
Family
ID=57531530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610573898.0A Active CN106228553B (en) | 2016-07-20 | 2016-07-20 | High-resolution remote sensing image shadow Detection apparatus and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228553B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108269262B (en) * | 2017-12-01 | 2021-04-30 | 兰州交通大学 | High-resolution remote sensing image shadow automatic extraction algorithm based on polynomial fitting |
| CN109886193B (en) * | 2019-02-21 | 2020-11-20 | 电子科技大学 | Volume cloud detection method and device and computer readable storage medium |
| CN116188496B (en) * | 2023-04-25 | 2023-07-07 | 牧马人(山东)勘察测绘集团有限公司 | Remote sensing image self-adaptive segmentation method based on land utilization type |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147920A (en) * | 2011-03-02 | 2011-08-10 | 上海大学 | Shadow detection method for high-resolution remote sensing image |
| CN103295013A (en) * | 2013-05-13 | 2013-09-11 | 天津大学 | Pared area based single-image shadow detection method |
| CN105528596A (en) * | 2016-02-03 | 2016-04-27 | 长江大学 | High-resolution remote sensing image building automatic extraction method and system by using shadow |
| CN105590316A (en) * | 2015-12-11 | 2016-05-18 | 中国测绘科学研究院 | Object-oriented high-resolution remote-sensing image shadow extraction method |
-
2016
- 2016-07-20 CN CN201610573898.0A patent/CN106228553B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147920A (en) * | 2011-03-02 | 2011-08-10 | 上海大学 | Shadow detection method for high-resolution remote sensing image |
| CN103295013A (en) * | 2013-05-13 | 2013-09-11 | 天津大学 | Pared area based single-image shadow detection method |
| CN105590316A (en) * | 2015-12-11 | 2016-05-18 | 中国测绘科学研究院 | Object-oriented high-resolution remote-sensing image shadow extraction method |
| CN105528596A (en) * | 2016-02-03 | 2016-04-27 | 长江大学 | High-resolution remote sensing image building automatic extraction method and system by using shadow |
Non-Patent Citations (2)
| Title |
|---|
| "Object Shadow Detection From Remote Sensing Images";Atul A. Kolge et al;《International Journal on Recent and Innovation Trends in Computing and Communication》;20150228;第3卷(第2期);第251-253页 |
| "高光谱遥感影像空谱特征提取与分类方法研究";康旭东;《中国博士学位论文全文数据库 信息科技辑》;20150915(第9期);论文第74-79页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106228553A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gevaert et al. | Informal settlement classification using point-cloud and image-based features from UAV data | |
| Guindon et al. | Landsat urban mapping based on a combined spectral–spatial methodology | |
| CN108596055B (en) | Airport target detection method of high-resolution remote sensing image under complex background | |
| Guan et al. | Integration of orthoimagery and lidar data for object-based urban thematic mapping using random forests | |
| Zhou | An object-based approach for urban land cover classification: Integrating LiDAR height and intensity data | |
| Van der Linden et al. | Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines | |
| CN106339674B (en) | The Hyperspectral Image Classification method that model is cut with figure is kept based on edge | |
| Munawar et al. | Mining multispectral aerial images for automatic detection of strategic bridge locations for disaster relief missions | |
| CN106228553B (en) | High-resolution remote sensing image shadow Detection apparatus and method | |
| CN105809673B (en) | Video foreground dividing method based on SURF algorithm and the maximum similar area of merging | |
| US11804025B2 (en) | Methods and systems for identifying topographic features | |
| Tang et al. | A multiple-point spatially weighted k-NN method for object-based classification | |
| Baluyan et al. | Novel approach for rooftop detection using support vector machine | |
| CN109829426A (en) | Railway construction temporary building monitoring method and system based on high score remote sensing image | |
| Li et al. | 3DCentripetalNet: Building height retrieval from monocular remote sensing imagery | |
| Recky et al. | Window detection in complex facades | |
| CN114283343A (en) | Map updating method, training method and equipment based on remote sensing satellite image | |
| CN105631849B (en) | The change detecting method and device of target polygon | |
| Azeez et al. | Urban tree classification using discrete-return LiDAR and an object-level local binary pattern algorithm | |
| Koc-San et al. | Support vector machines classification for finding building patches from IKONOS imagery: the effect of additional bands | |
| Musleh et al. | Shadow detection of the satellite images of earth using ratio image pixels | |
| Wang et al. | Utilizing parallel networks to produce sub-pixel shifted images with multiscale spatio-spectral information for soft-then-hard sub-pixel mapping | |
| Gevaert | Unmanned aerial vehicle mapping for settlement upgrading | |
| Chen et al. | Detecting and Enumerating New Building Structures Utilizing Very‐High Resolution Imaged Data and Image Processing | |
| Chu et al. | A new regional shape index for classification of high resolution remote sensing images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |