WO2018192023A1

WO2018192023A1 - Method and device for hyperspectral remote sensing image classification

Info

Publication number: WO2018192023A1
Application number: PCT/CN2017/083766
Authority: WO
Inventors: 贾森; 邓琳; 沈琳琳
Original assignee: 深圳大学
Priority date: 2017-04-21
Filing date: 2017-05-10
Publication date: 2018-10-25
Also published as: CN107256407A; CN107256407B

Abstract

A method and device for hyperspectral remote sensing image classification. The method comprises: acquiring N preset Gabor filters (S101); acquiring N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of a hyperspectral remote sensing image on the basis of the N preset Gabor filters (S102); and utilizing a feature fusion algorithm to perform feature fusion with respect to the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features so as to determine the type of terrain in the hyperspectral remote sensing image (S103). The method, by fusing the three-dimensional Gabor amplitude features and the three-dimensional Gabor phase features of the hyperspectral remote sensing image for determining the type of terrain in the hyperspectral remote sensing image, increases the accuracy of terrain classification with respect to the hyperspectral remote sensing image.

Description

Hyperspectral remote sensing image classification method and device

This application is required to be submitted to the State Intellectual Property Office on April 21, 2017, the application number is 201710266000.X, and the title of the invention is “Priority of Hyperspectral Remote Sensing Image Classification Method and Apparatus”. The citations are incorporated herein by reference.

Technical field

The invention relates to the field of image processing, and in particular to a method and a device for classifying hyperspectral remote sensing images.

Background technique

Hyperspectral remote sensing image refers to the hyperspectral image data obtained by imaging the sensor in different wavelengths in the visible, near-infrared, mid-infrared and thermal infrared bands of the electromagnetic spectrum. Therefore, hyperspectral remote sensing images contain a wealth of spatial, radiation and spectral triple information, which provides a possibility for the fine classification and identification of surface materials.

At present, when classifying surface materials, since the amplitude information of three-dimensional Gabor features has good stability, it is usually used directly for classification, but for hyperspectral remote sensing images, the three-dimensional Gabor features are rich. The phase characteristics, so using only the amplitude characteristics of the Gabor feature to classify the surface features will make the classification accuracy low.

Summary of the invention

The embodiment of the invention provides a method and a device for classifying hyperspectral remote sensing images, so as to improve the classification accuracy of the features.

In a first aspect, an embodiment of the present invention provides a method for classifying a hyperspectral remote sensing image, where the method includes:

Obtaining N preset Gabor filters, where N is a positive integer;

Acquiring N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters;

The N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features are feature-fused by a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.

In a second aspect, an embodiment of the present invention provides a hyperspectral remote sensing image classification device, wherein the device includes:

An acquiring module, configured to acquire N preset Gabor filters, where N is a positive integer;

An extracting module, configured to acquire N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters;

And a determining module, configured to perform feature fusion on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.

It can be seen that, in the technical solution provided by the embodiment of the present invention, N preset Gabor filters are first acquired, and then N three-dimensional Gabor amplitude features of the hyperspectral remote sensing image are acquired based on the N preset Gabor filters. N three-dimensional Gabor phase features, and finally feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a category of the features in the hyperspectral remote sensing image . Since the phase feature of the hyperspectral remote sensing image includes rich phase features, and the three-dimensional Gabor amplitude feature is complementary to the three-dimensional Gabor phase feature, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor are merged by the hyperspectral remote sensing image in the embodiment of the present invention. The phase feature is used to determine the feature categories in hyperspectral remote sensing images and improve the accuracy of feature classification for hyperspectral remote sensing images.

Further, since the three-dimensional Gabor phase information has extremely high sensitivity to the spatial position of the ground object, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase feature of the hyperspectral remote sensing image are used for classification, which reduces the classification robustness.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without paying any creative work.

1 is a schematic flow chart of a first embodiment of a hyperspectral remote sensing image classification method according to an embodiment of the present invention;

2 is a schematic diagram of a frequency domain relationship of a three-dimensional Gabor feature according to an embodiment of the present invention;

3 is a three-dimensional Gabor filter parallel to the spectral dimension direction observed from three different viewing angles according to an embodiment of the present invention;

FIG. 4-a is a hyperspectral remote sensing image according to an embodiment of the present invention;

Figure 4-b is a three-dimensional Gabor amplitude feature set provided by an embodiment of the present invention;

Figure 4-c is a phase feature set and a coding feature set of a hyperspectral remote sensing image according to an embodiment of the present invention;

FIG. 5 is a schematic diagram showing classification of a hyperspectral remote sensing image provided by an embodiment of the present invention; FIG.

6 is a schematic flow chart of a second embodiment of a hyperspectral remote sensing image classification method according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a first embodiment of a hyperspectral remote sensing image classification apparatus according to an embodiment of the present invention; FIG.

FIG. 8 is a schematic structural diagram of a second embodiment of a hyperspectral remote sensing image classification apparatus according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is an embodiment of the invention, but not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of the present invention.

The terms "first", "second" and "third" and the like in the specification and claims of the present invention and the above drawings are used to distinguish different objects, and are not intended to describe a specific order. Moreover, the term "comprise" and any variants thereof are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units not listed, or alternatively For these processes, methods, production Other steps or units inherent to the item or device.

A method for classifying hyperspectral remote sensing images provided by an embodiment of the present invention includes:

Acquiring N preset Gabor filters, wherein the N is a positive integer; acquiring N Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters; using preset features A fusion algorithm performs feature fusion on the N Gabor amplitude features and the N three-dimensional Gabor phase features to determine a feature category in the hyperspectral remote sensing image.

Referring to FIG. 1, FIG. 1 is a schematic flowchart diagram of a first embodiment of a hyperspectral remote sensing image classification method according to an embodiment of the present invention. As shown in FIG. 1, the hyperspectral remote sensing image classification method provided by the embodiment of the present invention includes the following steps:

S101. Acquire N preset Gabor filters.

Wherein, the N is a positive integer, and the N preset Gabor filters are used for subsequent extraction of amplitude features and phase features of the hyperspectral remote sensing image.

Optionally, in an embodiment of the invention, the N preset Gabor filters are Gabor filters that are parallel to the spectral dimension direction of the hyperspectral remote sensing image.

It can be understood that due to the sensitivity of the phase information to the spatial position, the Gabor phase characteristics obtained by different Gabor filters have great differences in the classification ability of the features, and cannot be used for the subsequent encoding and classification processes, and if not used selectively. All Gabor filters are used for the classification of hyperspectral remote sensing images, which will make the calculation amount very large. Therefore, only the features extracted by the Gabor filter parallel to the spectral dimension direction of the hyperspectral remote sensing image are used for the classification of hyperspectral remote sensing images. Earth improves the computational efficiency of the algorithm.

Specifically, in one embodiment of the present invention, N Gabor filters parallel to the spectral dimension direction of the hyperspectral remote sensing image can be obtained by the following formula

Where f is the frequency of the preset Gabor filter,

Is the angle between the preset Gabor filter and the ω axis, and θ is the angle between the preset Gabor filter and the uv plane.

Indicates the direction of the Gabor filter, (x, y, b) represents the x coordinate, y coordinate, and spectral coordinate of the pixel of the hyperspectral remote sensing image, respectively, and σ is the width of the Gaussian envelope.

Specifically, in an example of the present invention, if

θ=π/2, see FIG. 2, FIG. 2 is a schematic diagram of a frequency domain relationship of a three-dimensional Gabor feature according to an embodiment of the present invention. As can be seen from FIG. 2, the direction indicated by the frequency f is a spectrum of a hyperspectral remote sensing image. Dimension direction.

Specifically, in an example of the present invention, if the frequency f _j = [0.5, 0.25, 0.125, 0.0625] is set, four three-dimensional Gabor filters parallel to the hyperspectral remote sensing image can be obtained {Ψ _i , i=1 ,...,4} for subsequent 3D Gabor feature extraction. For details, refer to FIG. 3. FIG. 3 is a three-dimensional Gabor filter parallel to the spectral dimension direction observed from three different perspectives according to an embodiment of the present invention.

Optionally, in some embodiments of the invention, the Gabor filter may be a Log-Gabor filter, a haar-Gabor filter.

S102. Extract N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters.

Optionally, in one embodiment of the present invention, a three-dimensional Gabor feature is obtained by convoluting a hyperspectral remote sensing image with N preset Gabor filters, and then encoding each pixel of the hyperspectral image to further obtain a high Amplitude and phase characteristics of the spectral image.

Specifically, firstly, the hyperspectral remote sensing image is convoluted with N three-dimensional Gabor filters to obtain i three-dimensional Gabor features.

Where R represents the hyperspectral remote sensing image, and G _i represents the i-th three-dimensional Gabor feature, where i is an arbitrary integer between 1 and N.

After obtaining N three-dimensional Gabor features, the amplitude characteristics M _i (x, y, b) and phase characteristics F _i (x, y, b) of the hyperspectral remote sensing image are calculated by the following formula:

M _i (x, y, b) = abs(G _i (x, y, b));

Where Re(G _i (x, y, b)) and Im(G _i (x, y, b)) are the real and imaginary parts of the Gabor feature, respectively.

For example, in an example of the present invention, if the value of N is 4, the four three-dimensional Gabor filters shown in FIG. 3 are first acquired, and the hyperspectral remote sensing image and the generated four three-dimensional Gabor filters are further performed. After the convolution operation, four three-dimensional Gabor filter features are obtained, and four three-dimensional Gabor amplitude features G _i (x, y, b) and three-dimensional Gabor phase features F _i (x, y, b) are further obtained by the above formula. ), where i takes any integer between 1 and 4. For details, refer to FIG. 4-a, FIG. 4-b, and FIG. 4-c. FIG. 4-a is a hyperspectral remote sensing image according to an embodiment of the present invention, and two Gabor filters in four three-dimensional Gabor filters are taken as For example, the three-dimensional Gabor amplitude feature set of Figure 4-b and the three-dimensional Gabor phase feature set of Figure 4-c are obtained. 4b is a three-dimensional Gabor amplitude feature set provided by an embodiment of the present invention; FIG. 4-c is a phase feature set and a coding feature set of the hyperspectral remote sensing image provided by the embodiment of the present invention. In Figure 4-c, the first column represents the three-dimensional Gabor phase features obtained by the two three-dimensional Gabor filters; the second column represents the features obtained when the real part of the first column of the three-dimensional Gabor features is encoded; A feature obtained by encoding an imaginary part of a first column of three-dimensional Gabor features.

It can be understood that the above three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase feature do not require the participation of training samples in the calculation process, so the practicability of the scheme can be improved.

Optionally, in other embodiments of the present invention, other methods may also be used to acquire the three-dimensional Gabor phase features, for example, based on a fusion coding method or a contention based coding method.

S103. Perform feature fusion on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.

The preset feature fusion algorithm refers to an algorithm for combining three-dimensional Gabor amplitude features and phase features to simultaneously use three-dimensional Gabor amplitude features and three-dimensional Gabor phase features for classification of remote sensing images.

Optionally, in an embodiment of the present invention, the N-dimensional Gabor amplitude feature and the N three-dimensional Gabor phase features are feature-fused by a preset feature fusion algorithm to determine the hyperspectral remote sensing. The feature categories in the image, including:

Based on any of the N-dimensional Gabor amplitude characteristic of a Gabor amplitude characteristic M _i acquires the image sensing confidence P belongs to any one category of the category p

And a category similarity measure p based on a Gabor phase characteristics from any of the N-dimensional Gabor phase characteristics of the acquired remote sensing images F _i and any of the categories of P

P is a positive integer;

Determining the confidence in the p categories

Measure distance from the similarity

The category in which the sum of the squared differences under the N Gabor filters is the largest is the feature class in the hyperspectral remote sensing image.

Among them, confidence

The value is between 0 and 1, which is used to reflect the probability that the hyperspectral remote sensing image belongs to the p-th category, thus the confidence level

The larger the probability that the hyperspectral remote sensing image belongs to the p-th class, the Hamming distance

The value is between 0 and 1, which is used to reflect the matching degree between the hyperspectral remote sensing image and the category p, when the Hamming distance

The smaller the smaller, the greater the probability that the hyperspectral remote sensing image belongs to the p-class.

Alternatively, in one embodiment of the present invention, the basis of any of the N-dimensional Gabor amplitude characteristic of a three-dimensional Gabor amplitude characteristic M _i acquires the image sensing P belongs to any one of categories category p Confidence

include:

Acquiring the confidence that the hyperspectral remote sensing image belongs to any of the P categories based on any of the three three-dimensional Gabor amplitude features M _i using the following formula

The D is a decision matrix of the remote sensing image acquired by the support vector machine, and the n _p is the number of non-zero elements of the p-th row in the decision matrix D.

Specifically, in an embodiment of the present invention, the decision matrix P can be obtained by assuming that there is a P-type feature, and for each test sample t, P×(P-1) are established by using a one-to-one strategy. Support vector machine classifier. Among them, for any two categories C1 and C2, the decision value δ can be obtained by voting; further, the decision matrix D is established, wherein when δ>0, DC1C2=δ, otherwise DC1C2=-δ, the other elements in the decision matrix D are zero. Since the support vector machine is good for classification, the support vector machine is used to determine the confidence.

Effectively improve the accuracy of the fusion decision.

It can be seen that the confidence

The value is between 0 and 1, and when the confidence is

The larger the larger, the greater the probability that the hyperspectral remote sensing image belongs to category p.

Optionally, in other embodiments of the present invention, the addition and multiplication can also be used to calculate the confidence.

Optionally, in an embodiment of the invention, the similarity measure distance

For Hamming distance, the acquiring a similarity metric distance between the hyperspectral remote sensing image and any one of the P categories based on any of the N three-dimensional Gabor phase features F _i

include:

The similarity measure between the hyperspectral remote sensing image t and any training sample s in the training set A is obtained by the following formula:

Where B is the spectral dimension of the hyperspectral image;

Obtaining a similarity measure distance between the hyperspectral remote sensing image t and any of the categories p

for:

It can be seen that the Hamming distance

The value is between 0 and 1, and when Hamming distance

The smaller the time, the greater the probability that the hyperspectral remote sensing image belongs to the category p, and the Hamming distance for the optimal matching of the hyperspectral remote sensing image and the category p

Zero.

Optionally, in other embodiments of the present invention, the foregoing Hamming distance may also be calculated by using a classification based on sparse representation, K-inline classification, and the like.

Optionally, in other embodiments of the present invention, the similarity metric distance may also be other distances, such as a Levinstein distance and a Li distance.

Understandably, the above confidence

Distance from Hamming

The parameters in the calculation formula are all determined parameters, so when using the above formula to calculate, no parameter estimation is needed, which will make the calculation more accurate.

It can be seen that if the fusion feature value is defined as E ^p , the E ^{p is} defined as the confidence

Distance from the Hamming

The sum of the squared differences under the N Gabor filters, ie

Because of confidence

The larger the probability, the higher the probability that the hyperspectral remote sensing image belongs to the category p, when the Hamming distance

The smaller the hyperspectral imagery greater probability of belonging to the category p, whereby when the three-dimensional integration and three-dimensional Gabor Gabor phase amplitude characteristic feature, the larger E ^p, the hyperspectral imagery greater probability of belonging to the category p, and finally The category corresponding to the value at which E ^{p is the} largest is the feature type in the hyperspectral remote sensing image. It can be understood that, by the above manner, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase feature of the hyperspectral remote sensing image can be simultaneously used in determining the feature category in the hyperspectral remote sensing image, thereby making the determined category more accurate.

Optionally, in other embodiments of the present invention, the fusion feature value E ^p may also be defined in other forms, such as a square form, an exponential form, and the like.

Specifically, in an embodiment of the present invention, if N=4, the four three-dimensional Gabor filters shown in FIG. 3 are first obtained, and then the three-dimensional Gabor amplitudes shown in FIG. 4-b are calculated by using step S102. Features and three-dimensional Gabor phase features as shown in Figure 4-c. Further, if the Gabor amplitude features shown in FIG. 4-b are classified by the support vector machine, the hyperspectral remote sensing image 4-a is obtained as the confidence level of each class.

By normalizing the Hamming distance, using the nearest neighbor strategy to classify the Gabor phase encoding features shown in Figure 4-c, the hyperspectral remote sensing image is obtained for each class of Hamming distance.

Then use E ^p fusion confidence

Distance from Hamming

The hyperspectral remote sensing image is classified to determine which feature category the hyperspectral remote sensing image belongs to. Referring to FIG. 5, FIG. 5 is a schematic diagram showing classification of hyperspectral remote sensing images according to an embodiment of the present invention.

It can be seen that, in the solution of the embodiment, N preset Gabor filters are first acquired, and then N three-dimensional Gabor amplitude features and N three-dimensional Gabors of the hyperspectral remote sensing image are acquired based on the N preset Gabor filters. Phase features, and finally feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features using a preset feature fusion algorithm to determine feature categories in the hyperspectral remote sensing image. Since the phase feature of the hyperspectral remote sensing image includes rich phase features, and the three-dimensional Gabor amplitude feature is complementary to the three-dimensional Gabor phase feature, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase are obtained by fusing the hyperspectral remote sensing image in the embodiment of the present invention. The feature is used to determine the classification of the features in the hyperspectral remote sensing image and improve the accuracy of the classification of the features of the hyperspectral remote sensing image.

Referring to FIG. 6, FIG. 6 is a schematic flowchart diagram of a second embodiment of a hyperspectral remote sensing image classification method according to an embodiment of the present invention. For the method shown in FIG. 6, the same or similar content as the method shown in FIG. 1 can be referred to the detailed description in FIG. 1, and details are not described herein again. As shown in FIG. 6, the hyperspectral remote sensing image classification method provided by the embodiment of the present invention includes the following steps:

S601. Acquire N preset Gabor filters.

Specifically, four Gabor filters parallel to the spectral dimension direction of the hyperspectral remote sensing image can be acquired.

S602. Acquire N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters.

S603, based on any of the N-dimensional Gabor amplitude characteristic of a Gabor amplitude characteristic M _i acquires the image sensing confidence P belongs to any one category of the category p

S604, based on a Gabor phase characteristics according to any of the N-dimensional Gabor phase characteristics of Hamming distance F _i acquired image with any of the remote sensing of the P categories in a category p

S605. Determine the confidence level in the p categories.

Measure distance from the similarity

It should be noted that there is no strict sequence between the above steps S603 and S604.

It can be seen that, in the solution of the embodiment, acquiring the target image, first acquiring N preset Gabor filters, and then acquiring N three-dimensional Gabor amplitude features of the hyperspectral remote sensing image based on the N preset Gabor filters N three-dimensional Gabor phase features, and finally feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a category of the features in the hyperspectral remote sensing image . Since the phase feature of the hyperspectral remote sensing image includes rich phase features, and the three-dimensional Gabor amplitude feature is complementary to the three-dimensional Gabor phase feature, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase are obtained by fusing the hyperspectral remote sensing image in the embodiment of the present invention. The features are used to determine the feature categories in hyperspectral remote sensing images and improve the accuracy of feature classification for hyperspectral remote sensing images.

The embodiment of the invention further provides a hyperspectral remote sensing image classification device, comprising:

An extracting module, configured to acquire a hyperspectral remote sensing image based on the N preset Gabor filters Three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features;

Specifically, please refer to FIG. 7. FIG. 7 is a schematic structural diagram of a first embodiment of a hyperspectral remote sensing image classification device according to an embodiment of the present invention, which is used to implement a hyperspectral remote sensing image classification disclosed in an embodiment of the present invention. method. As shown in FIG. 7, a hyperspectral remote sensing image classification device 700 according to an embodiment of the present invention may include:

The acquisition module 710, the extraction module 720, and the determination module 730.

The obtaining module 710 is configured to acquire N preset Gabor filters, where the N is a positive integer.

Where f is the frequency of the preset Gabor filter,

Specifically, in an example of the present invention, if

The extracting module 720 is configured to acquire N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters.

Specifically, first, a hyperspectral remote sensing image is convoluted with N three-dimensional Gabor filters by the following formula to obtain i three-dimensional Gabor features Gi(x, y, b),

M _i (x, y, b) = abs(G _i (x, y, b));

The determining module 730 is configured to perform feature fusion on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.

Optionally, in an embodiment of the present invention, the determining module 730 includes:

An acquisition unit 731, based on any of the N-dimensional Gabor amplitude characteristic of a Gabor amplitude characteristic M _i of the remote sensing image acquiring a category belongs to the confidence of P p to any category

P is a positive integer;

a determining unit 732, configured to determine the confidence level in the p categories

Measure distance from the similarity

Among them, confidence

Optionally, in an embodiment of the present invention, the obtaining unit 731 is specifically configured to:

Effectively improve the accuracy of the fusion decision.

It can be seen that the confidence

The value is between 0 and 1, and when the confidence is

Optionally, in an embodiment of the present invention, if the similarity metric distance includes a Hamming distance, the acquiring unit 731 is specifically configured to:

Where B is the spectral dimension of the original hyperspectral data;

Obtaining a Hamming distance between the hyperspectral remote sensing image t and any of the categories p

for:

It can be seen that the Hamming distance

The value is between 0 and 1, and when Hamming distance

Zero.

Understandably, the above confidence

Distance from Hamming

Distance from the Hamming

The sum of the squared differences under the N Gabor filters, ie

Because of confidence

Then use E ^p fusion confidence

Distance from Hamming

It can be seen that, in the solution of the embodiment, the hyperspectral remote sensing image classification device 700 first acquires N preset Gabor filters, and then acquires N three-dimensional Gabor amplitudes of the hyperspectral remote sensing image based on the N preset Gabor filters. Value feature and N three-dimensional Gabor phase features, and finally feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine features in the hyperspectral remote sensing image The category of the category. Since the phase feature of the hyperspectral remote sensing image includes rich phase features, and the three-dimensional Gabor amplitude feature is complementary to the three-dimensional Gabor phase feature, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase are obtained by fusing the hyperspectral remote sensing image in the embodiment of the present invention. The features are used to determine the feature categories in hyperspectral remote sensing images and improve the accuracy of feature classification for hyperspectral remote sensing images.

In the present embodiment, the hyperspectral remote sensing image classification device 700 is presented in the form of a unit. A "unit" herein may refer to an application-specific integrated circuit (ASIC), a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and/or other devices that provide the functionality described above. .

It is to be understood that the functions of the functional units of the hyperspectral remote sensing image classification device 700 of the present embodiment may be specifically implemented according to the method in the foregoing method embodiments. For the specific implementation process, reference may be made to the related description of the foregoing method embodiments, where No longer.

Referring to FIG. 8, FIG. 8 is a schematic structural diagram of a second embodiment of a hyperspectral remote sensing image classification apparatus according to an embodiment of the present invention, which is used to implement a hyperspectral remote sensing image classification method disclosed in an embodiment of the present invention. The hyperspectral remote sensing image classification device 800 may include at least one bus 801, at least one processor 802 connected to the bus 801, and at least one memory 803 connected to the bus 801.

The processor 802 calls, by using the bus 801, code stored in the memory for acquiring N preset Gabor filters, where N is a positive integer; acquiring hyperspectral remote sensing images based on the N preset Gabor filters N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features; feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features using a preset feature fusion algorithm to determine the hyperspectral remote sensing The feature category in the image.

Optionally, in some possible implementation manners of the present invention, the N preset Gabor filters are Gabor filters that are parallel to a spectral dimension direction of the hyperspectral remote sensing image.

Optionally, in some possible implementation manners of the present invention, the processor 802 performs feature fusion on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine The feature categories in the hyperspectral remote sensing image include:

P is a positive integer;

Determining the confidence in the p categories

Measure distance from the similarity

Alternatively, in some possible embodiments of the invention, the processor 802 based on any of the N-dimensional Gabor amplitude characteristic of a three-dimensional Gabor amplitude characteristic M _i of the remote sensing images acquired categories in P Confidence in any category p

include:

Optionally, in some possible implementation manners of the present invention, if the similarity metric distance is a Hamming distance, the processor 802 is based on any three-dimensional Gabor phase feature F of the N three-dimensional Gabor phase features. _i acquires the similarity Hyperspectral image P with any of the categories in a category of distance measure p

include:

Where B is the spectral dimension of the original hyperspectral data;

for:

It can be seen that, in the solution of the embodiment, the hyperspectral remote sensing image classification device 800 first acquires N preset Gabor filters, and then acquires N three-dimensional Gabor amplitudes of the hyperspectral remote sensing image based on the N preset Gabor filters. Value feature and N three-dimensional Gabor phase features, and finally feature fusion of the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine features in the hyperspectral remote sensing image The category of the category. Since the phase feature of the hyperspectral remote sensing image includes rich phase features, and the three-dimensional Gabor amplitude feature is complementary to the three-dimensional Gabor phase feature, the three-dimensional Gabor amplitude feature and the three-dimensional Gabor phase are obtained by fusing the hyperspectral remote sensing image in the embodiment of the present invention. The features are used to determine the feature categories in hyperspectral remote sensing images and improve the accuracy of feature classification for hyperspectral remote sensing images.

In the present embodiment, the hyperspectral remote sensing image classification device 800 is presented in the form of a unit. A "unit" herein may refer to an application-specific integrated circuit (ASIC), a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and/or other devices that provide the functionality described above. .

It can be understood that the functions of the functional units of the hyperspectral remote sensing image classification device 800 of the present embodiment can be specifically implemented according to the method in the foregoing method embodiments. For the specific implementation process, reference may be made to the related description of the foregoing method embodiments, where No longer.

The embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all of the steps of any hyperspectral remote sensing image classification method described in the foregoing method embodiments.

It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should understand that the present invention is not limited by the described action sequence. Because certain steps may be performed in other sequences or concurrently in accordance with the present invention. In addition, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

In the above embodiments, the descriptions of the various embodiments are different, and the details that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essential or the part contributing to the prior art or the entire technical solution. The portion or portion may be embodied in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, server or network device, etc.) to perform various embodiments of the present invention. All or part of the steps of the method described. The foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that The technical solutions described in the embodiments are modified, or some of the technical features are replaced by equivalents; and the modifications or substitutions do not deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

A method for classifying hyperspectral remote sensing images, characterized in that the method comprises:

Obtaining N preset Gabor filters, where N is a positive integer;

Extracting N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters;

The N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features are feature-fused by a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.
The method of claim 1 wherein said N predetermined Gabor filters are Gabor filters parallel to the spectral dimension of said hyperspectral remote sensing image.
The method according to claim 2, wherein the feature fusion is performed on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine the hyperspectral remote sensing The feature categories in the image, including:

Obtaining a confidence that the hyperspectral remote sensing image belongs to any of the P categories based on any of the N three-dimensional Gabor amplitude features M i
And a category similarity measure p based on a Gabor phase characteristics from any of the N-dimensional Gabor phase characteristics of the acquired remote sensing images F i and any of the categories of P
P is a positive integer;

Determining the confidence in the p categories
Measure distance from the similarity
The category in which the sum of the squared differences under the N Gabor filters is the largest is the feature class in the hyperspectral remote sensing image.
The method according to claim 3, wherein the acquiring the remote sensing image belongs to any one of P categories based on any one of the N three-dimensional Gabor amplitude features M i Confidence
include:

Acquiring the confidence that the hyperspectral remote sensing image belongs to any of the P categories based on any of the three three-dimensional Gabor amplitude features M i using the following formula

The D is a decision matrix of the remote sensing image acquired by the support vector machine, and the n p is the number of non-zero elements of the p-th row in the decision matrix D.
The method of claim 3, wherein the similarity metric distance comprises a Hamming distance, the hyperspectral acquisition of the hyperspectral based on any one of the N three-dimensional Gabor phase features F i The similarity measure distance between the remote sensing image and any of the P categories
include:

The similarity measure between the hyperspectral remote sensing image t and any training sample s in the training set A is obtained by the following formula:

Wherein B is a spectral dimension of the hyperspectral image;

Obtaining a Hamming distance between the hyperspectral remote sensing image t and any of the categories p
for:
A hyperspectral remote sensing image classification device, characterized in that the device comprises:

An acquiring module, configured to acquire N preset Gabor filters, where N is a positive integer;

An extracting module, configured to acquire N three-dimensional Gabor amplitude features and N three-dimensional Gabor phase features of the hyperspectral remote sensing image based on the N preset Gabor filters;

And a determining module, configured to perform feature fusion on the N three-dimensional Gabor amplitude features and the N three-dimensional Gabor phase features by using a preset feature fusion algorithm to determine a feature category in the hyperspectral remote sensing image.
The apparatus according to claim 6, wherein said N preset Gabor filters are Gabor filters parallel to a spectral dimension direction of said hyperspectral remote sensing image.
The apparatus according to claim 7, wherein the determining module comprises:

Obtaining unit, based on any of the N-dimensional Gabor amplitude characteristic of a Gabor amplitude characteristic M i acquires the image sensing confidence P belongs to any one category of the category p
And a category similarity measure p based on a Gabor phase characteristics from any of the N-dimensional Gabor phase characteristics of the acquired remote sensing images F i and any of the categories of P
P is a positive integer;

a determining unit, configured to determine the confidence level in the p categories
Measure distance from the similarity
The category in which the sum of the squared differences under the N Gabor filters is the largest is the feature class in the hyperspectral remote sensing image.
The device according to claim 8, wherein the obtaining unit is specifically configured to:

Acquiring the confidence that the hyperspectral remote sensing image belongs to any of the P categories based on any of the three three-dimensional Gabor amplitude features M i using the following formula

The D is a decision matrix of the remote sensing image acquired by the support vector machine, and the n p is the number of non-zero elements of the p-th row in the decision matrix D.
The device according to claim 8, wherein if the similarity measure distance comprises a Hamming distance, the obtaining unit is specifically configured to:

The similarity measure between the hyperspectral remote sensing image t and any training sample s in the training set A is obtained by the following formula:

Where B is the spectral dimension of the original hyperspectral data;

Obtaining a Hamming distance between the hyperspectral remote sensing image t and any of the categories p
for: