Hyperspectral band selection method based on target background difference maximization

Abstract

The embodiment of the invention relates to the technical field of remote sensing, in particular to a hyperspectral band selection method based on target background difference maximization. The invention provides a hyperspectral band selection method based on target background difference maximization, and the method comprises the steps: obtaining the target background contrast of each band and local background data corresponding to each band according to hyperspectral image data; selecting a preset number of wavebands from all the wavebands, and traversing all the wavebands to form a plurality of different waveband combinations; extracting the target background contrast and the local background data of each wave band in all wave band combinations to form a contrast vector and a covariance matrix of a local background; and determining the signal-to-clutter ratio of the corresponding wave band combination through the contrast vector and the covariance matrix of the local background, and outputting the wave band combination with the maximum signal-to-clutter ratio. The invention provides a hyperspectral wave band selection method based on target background difference maximization, which can efficiently and accurately select a required wave band.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of remote sensing technology, and in particular to a hyperspectral band selection method based on maximizing target-background difference. Background Art

[0002] Hyperspectral remote sensing technology plays an important role in the field of earth observation and is widely used in agriculture, environmental monitoring, resource exploration and other fields. Band selection, as one of the key technologies of hyperspectral remote sensing detection, aims to optimize sensor design, improve data collection efficiency, and better meet user needs. The principles and motivations behind it are designed to involve multiple factors, including band correlation, spectral characteristics, data processing complexity, and sensor performance. Hyperspectral remote sensing sensors can usually capture spectral information in hundreds or even thousands of narrow bands. This high-dimensional data set contains a lot of redundant information, and in some cases some bands are not sensitive to specific applications.

[0003] Current band selection usually relies on manual experience and expertise, and lacks efficient and automated methods to improve the level of intelligence, which limits the application of band selection in large-scale hyperspectral remote sensing data. The universality and stability of band selection algorithms need to be improved. Due to the complexity and diversity of hyperspectral remote sensing data, some band selection algorithms may perform well on some data sets, but may fail on other data sets. Some band selection methods focus too much on improving data acquisition efficiency and reducing data processing complexity, but ignore data quality and accuracy to a certain extent, which may result in the selected bands being unable to fully meet the needs of specific applications, thereby affecting the effect of hyperspectral remote sensing image data in actual applications. Summary of the invention

[0004] The embodiment of the present invention provides a hyperspectral band selection method based on maximizing the target-background difference, which can select the required bands efficiently and accurately.

[0005] In a first aspect, an embodiment of the present invention provides a hyperspectral band selection method based on maximizing target-background difference, comprising: According to the hyperspectral image data, the target background contrast of each band and the local background data corresponding to each band are obtained; Selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; Extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The signal-to-noise ratio of the corresponding band combination is determined by the contrast vector and the covariance matrix of the local background, and the band combination with the largest signal-to-noise ratio is output.

[0006] In a second aspect, an embodiment of the present invention further provides a hyperspectral band selection device based on maximizing target-background difference, used to implement any of the above methods, the device comprising: A calculation unit, used for obtaining the target background contrast of each band and the local background data corresponding to each band according to the hyperspectral image data; A combination unit, used for selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; An extraction unit, used for extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The output unit is used to determine the signal-to-noise ratio of the corresponding band combination through the contrast vector and the covariance matrix of the local background, and output the band combination with the maximum signal-to-noise ratio.

[0007] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0008] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method described in any embodiment of this specification.

[0009] The embodiment of the present invention provides a hyperspectral band selection method, device, electronic device and storage medium based on maximizing the difference between target and background. Starting from maximizing the difference between target and background, the present invention proposes restrictions on the selection of band combinations, and obtains the signal-to-noise ratio under different band combinations by calculating the contrast of each band image and the background correlation matrix between bands, and finally selects the band combination with the maximum difference. The method has the advantages of optimizing the design of remote sensing imaging sensors, improving data acquisition efficiency and better meeting user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 is a flow chart of a hyperspectral band selection method based on maximizing target-background difference provided by one embodiment of the present invention; Figure 2 is an example diagram of a background correlation coefficient matrix provided by an embodiment of the present invention; Figure 3 This is an example diagram of a dual-band joint signal-to-noise ratio matrix provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0013] The specific implementation of the above concept is described below.

[0014] Please refer to Figure 1 , an embodiment of the present invention provides a hyperspectral band selection method based on maximizing target-background difference, the method comprising: According to the hyperspectral image data, the target background contrast of each band and the local background data corresponding to each band are obtained; Selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; Extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The signal-to-noise ratio of the corresponding band combination is determined by the contrast vector and the covariance matrix of the local background, and the band combination with the largest signal-to-noise ratio is output.

[0015] The present invention starts from maximizing the difference between the target and the background, proposes restrictions on the selection of band combinations, calculates the contrast of each band image and the background correlation matrix between the bands, obtains the signal-to-noise ratio under different band combinations, and finally selects the band combination with the maximum difference. This method has the advantages of optimizing the design of remote sensing imaging sensors, improving data acquisition efficiency, and better meeting user needs.

[0016] In some embodiments of the present invention, the target background contrast is calculated by the following formula: in represents the target-background contrast of the image in the tth band, represents the gray value of the i-th pixel belonging to the target area, represents the gray value of the jth pixel belonging to the background area, N represents the number of pixels in the target area, and M represents the number of pixels in the background area.

[0017] The mean square error, as an indicator that can represent the image contrast, can characterize the difference between the target and the background in the image.

[0018] In some embodiments of the present invention, the number of the band combinations is Wherein, C is a combination formula, K is the number of bands, and n is the preset number.

[0019] In some embodiments of the present invention, the contrast vector is as follows: Among them, C i represents the actual target-background contrast of a band, and n is the preset number.

[0020] In some embodiments of the present invention, the covariance matrix of the local background is obtained by the following formula: Among them, M is the covariance matrix of the local background, B is the matrix composed of the local background data of the corresponding band, and E(B) is the average value of B.

[0021] By selecting background pixels of a certain length in each band to form a vector, the pure background of the image can be approximately represented. By calculating the covariance matrix of the background vector in the band combination, the correlation of the background between bands can be calculated.

[0022] In some embodiments of the present invention, the signal-to-noise ratio is calculated by the following formula: Wherein, SCR is the signal-to-clutter ratio, b is the contrast vector, and M is the covariance matrix of the local background.

[0023] The difference between the target and the background can be expressed by the signal-to-clutter ratio. We can calculate the signal-to-clutter ratio based on the global contrast of the image itself and the similarity of the local background between the bands. The larger the signal-to-clutter ratio value, the more the selected band combination can reflect the difference between the target and the background, and the more it can reflect the characteristics of the target.

[0024] In a specific embodiment of the present invention, a hyperspectral remote sensing data with 25 channels can be selected for analysis, the upper limit of the band combination is set to 10, the contrast of each channel image is calculated, the correlation matrix of the local background is calculated, and the signal-to-noise ratio between the band combinations is calculated.

[0025] Taking dual-band selection as an example, Figure 2Shows the correlation between the local background of the two bands, Figure 3 The joint signal-to-noise ratio matrix of the dual bands is displayed, and the joint band corresponding to the maximum value in the matrix is ​​the optimal dual-band channel selection result.

[0026] In summary, the present invention utilizes the difference between the target and the background of hyperspectral remote sensing data, and selects the optimal band combination by calculating the signal-to-noise ratio of different band combinations. This is of great significance for optimizing sensor band design, improving data acquisition efficiency, reducing data processing complexity, and improving data quality and accuracy.

[0027] An embodiment of the present invention provides a hyperspectral band selection device based on maximizing the target-background difference. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. From a hardware perspective, a hardware architecture diagram of an electronic device in which a hyperspectral band selection device based on maximizing the target-background difference provided in an embodiment of the present invention is located, in addition to a processor, memory, network interface, and non-volatile memory, the electronic device in the embodiment where the device is located can generally include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, as a device in a logical sense, it is formed by the CPU of the electronic device in which it is located reading the corresponding computer program in the non-volatile memory into the memory and running it. A hyperspectral band selection device based on maximizing the target-background difference provided in this embodiment includes: A calculation unit, used for obtaining the target background contrast of each band and the local background data corresponding to each band according to the hyperspectral image data; A combination unit, used for selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; An extraction unit, used for extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The output unit is used to determine the signal-to-noise ratio of the corresponding band combination through the contrast vector and the covariance matrix of the local background, and output the band combination with the maximum signal-to-noise ratio.

[0028] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on a hyperspectral band selection device based on maximizing the target-background difference. In other embodiments of the present invention, a hyperspectral band selection device based on maximizing the target-background difference may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0029] The information interaction, execution process and other contents between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention. For the specific contents, please refer to the description in the embodiment of the method of the present invention, and no further description is given here.

[0030] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a hyperspectral band selection method based on maximizing the target-background difference in any embodiment of the present invention is implemented.

[0031] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes a hyperspectral band selection method based on maximizing the target-background difference in any embodiment of the present invention.

[0032] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program code stored in the storage medium.

[0033] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0034] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0035] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0036] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0037] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical factors in the process, method, article or device including the elements.

[0038] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A hyperspectral band selection method based on maximizing target-background difference, characterized in that: include: According to the hyperspectral image data, the target background contrast of each band and the local background data corresponding to each band are obtained; Selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; Extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The signal-to-noise ratio of the corresponding band combination is determined by the contrast vector and the covariance matrix of the local background, and the band combination with the largest signal-to-noise ratio is output.

2. The method according to claim 1, characterized in that The target background contrast is calculated by the following formula: in represents the target-background contrast of the image in the tth band, represents the gray value of the i-th pixel belonging to the target area, represents the gray value of the jth pixel belonging to the background area, N represents the number of pixels in the target area, and M represents the number of pixels in the background area.

3. The method according to claim 1, characterized in that The number of the band combinations is Wherein, C is a combination formula, K is the number of bands, and n is the preset number.

4. The method according to claim 1, characterized in that: The contrast vector is as follows: Among them, C i represents the actual target-background contrast of a band, and n is the preset number.

5. The method according to claim 1, characterized in that: The covariance matrix of the local background is obtained by the following formula: Among them, M is the covariance matrix of the local background, B is the matrix composed of the local background data of the corresponding band, and E(B) is the average value of B.

6. The method according to claim 1, characterized in that The signal-to-noise ratio is calculated by the following formula: Wherein, SCR is the signal-to-clutter ratio, b is the contrast vector, and M is the covariance matrix of the local background.

7. A hyperspectral band selection device based on maximizing target-background difference, characterized in that: For implementing the method described in any one of claims 1 to 6, the device comprises: A calculation unit, used for obtaining the target background contrast of each band and the local background data corresponding to each band according to the hyperspectral image data; A combination unit, used for selecting a preset number of bands from all bands, traversing all bands, and forming a plurality of different band combinations; An extraction unit, used for extracting the target background contrast and the local background data of each band in all band combinations to form a contrast vector and a covariance matrix of the local background; The output unit is used to determine the signal-to-noise ratio of the corresponding band combination through the contrast vector and the covariance matrix of the local background, and output the band combination with the maximum signal-to-noise ratio.

8. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 6.

Images