Hyperspectral water depth inversion method, device, equipment, storage medium and program product

Abstract

The application provides a hyperspectral water depth inversion method, device, equipment, storage medium and program product, and is applied to the technical field of water depth inversion. The method comprises the following steps: acquiring hyperspectral data; converting reflectivity spectrum data of the hyperspectral data into absorbance spectrum data based on the Beer-Lambert law, and performing radiation transfer model conversion of the absorbance, the sensitive degree of the absorbance spectrum data to water depth is greater than the sensitive degree of the reflectivity spectrum data to water depth; establishing a nonlinear equation group of spectral data and water depth parameters according to the radiation transfer model and the absorbance spectrum data; and solving the nonlinear equation group to obtain a water depth inversion result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water depth inversion, and particularly relates to a hyperspectral water depth inversion method, device, equipment, storage medium and program product. BACKGROUND

[0002] Coastal zones, islands and coral reefs and other shallow water areas provide key environmental elements for the biodiversity and sustainable development of marine ecosystems, and the water depth data obtained by water depth inversion in the shallow water area can be applied to the fields of navigation safety, port planning, marine engineering design, marine scientific research and marine resource development, so it is crucial to perform water depth inversion in the near-shore shallow sea area.

[0003] In the prior art, with the successful launch of numerous remote sensing satellites, the research on water depth inversion of the coastal zone and the surrounding area of the island reef by using remote sensing technology has also developed rapidly, forming water depth inversion methods based on multi-spectral, synthetic aperture radar and hyperspectral data. Among them, the single-band and band ratio empirical regression model is used to invert the near-shore shallow sea water depth by using clear-sky multi-spectral data and all-weather image, the mapping relationship between water depth and remote sensing data is established by calibrating the field measured water depth data, and the water depth inversion in the shallow sea area is realized. The clear-sky hyperspectral data can provide rich spectral information in the shallow sea area, and the shallow sea water depth physical quantity is contained in the parameter of the water body radiation transfer model, so that the parameter in the water body radiation transfer model can be inverted by using the hyperspectral data, and the water depth inversion can be realized without calibrating the field measured water depth data.

[0004] However, due to the high absorption coefficient and low reflectivity value of the water body, the response value of the water body pixel in the hyperspectral image is low and the range is small, so the weak water body radiation signal is easily submerged in the background noise, which is not conducive to the water depth inversion of different water body pixels. SUMMARY

[0005] The present application provides a hyperspectral water depth inversion method, device, equipment, storage medium and program product to solve the problem of low water depth inversion accuracy caused by weak water body radiation signal.

[0006] The present application provides a hyperspectral water depth inversion method, comprising: acquiring hyperspectral data; converting reflectivity spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing radiation transfer model conversion of the absorbance, the sensitivity of the absorbance spectral data to water depth is less than the sensitivity of the reflectivity spectral data to water depth; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiation transfer model and the absorbance spectral data; and solving the nonlinear equation set to obtain a water depth inversion result.

[0007] The application provides a hyperspectral water depth inversion method, and the reflectivity spectrum data of the hyperspectral data is converted into absorbance spectrum data based on the Beer-Lambert law, and the method comprises the following steps:

[0008] According to the formula The reflectivity spectrum data of the hyperspectral data is converted into absorbance spectrum data, wherein A represents absorbance, I represents reflected radiation intensity, I represents incident radiation intensity, and R represents reflectivity.

[0009] The application provides a hyperspectral water depth inversion method, and the hyperspectral data is obtained, comprising the following steps: collecting original hyperspectral data by a hyperspectral detector; performing a pretreatment operation on the original hyperspectral data to obtain surface reflectivity data, wherein the pretreatment operation comprises, in sequence, radiation correction, geometric correction and atmospheric correction; screening water body pixels for water depth inversion from the surface reflectivity data, and correcting abnormal water body pixels caused by solar glint due to water surface fluctuation to obtain the hyperspectral data.

[0010] The application provides a hyperspectral water depth inversion method, and the reflectivity spectrum data of the hyperspectral data is converted into absorbance spectrum data based on the Beer-Lambert law, and after the radiation transmission model conversion of the absorbance, the method further comprises the following steps: performing filter processing on the absorbance spectrum data based on filter coefficients of a given window size and order.

[0011] The application provides a hyperspectral water depth inversion method, and the reflectivity spectrum data of the hyperspectral data is converted into absorbance spectrum data based on the Beer-Lambert law, and after the radiation transmission model conversion of the absorbance, the method further comprises the following steps: performing parameterization processing on unknown vector parameters in a radiation transmission model equation.

[0012] The application provides a hyperspectral water depth inversion method, and the reflectivity spectrum data of the hyperspectral data is converted into absorbance spectrum data based on the Beer-Lambert law, and after the radiation transmission model conversion of the absorbance, the method further comprises the following steps: performing parameterization processing on unknown vector parameters in a radiation transmission model equation.

[0013] The application further provides a hyperspectral water depth inversion device, comprising the following modules: an acquisition module and a processing module; the acquisition module is used for acquiring hyperspectral data; the processing module is used for converting reflectivity spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing radiation transfer model conversion of the absorbance; the sensitivity of the absorbance spectral data to water depth is greater than the sensitivity of the reflectivity spectral data to water depth; a nonlinear equation set of spectral data and water depth parameters is established according to the radiation transfer model and the absorbance spectral data; and a water depth inversion result is obtained by solving the nonlinear equation set.

[0014] According to the hyperspectral water depth inversion device provided by the application, the processing module is used for:

[0015] According to the formula The reflectivity spectral data of the hyperspectral data is converted into absorbance spectral data; wherein A represents absorbance, I represents reflected radiation intensity, represents incident radiation intensity, and R represents reflectivity.

[0016] According to the hyperspectral water depth inversion device provided by the application, the acquisition module is used for collecting original hyperspectral data by a hyperspectral detector; a preprocessing operation is performed on the original hyperspectral data to obtain surface reflectivity data, the preprocessing operation comprises, in sequence, radiation correction, geometric correction and atmospheric correction; water body pixels for water depth inversion are screened from the surface reflectivity data, and abnormal water body pixels caused by solar glint due to water surface fluctuation are corrected to obtain the hyperspectral data.

[0017] According to the hyperspectral water depth inversion device provided by the application, after the reflectivity spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and radiation transfer model conversion of the absorbance is performed, the processing module is used for performing filtering processing on the absorbance spectral data based on a filter coefficient of a given window size and order.

[0018] According to the hyperspectral water depth inversion device provided by the application, after the reflectivity spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and radiation transfer model conversion of the absorbance is performed, the processing module is used for performing parameterization processing on unknown vector parameters in a radiation transfer model equation.

[0019] According to the hyperspectral water depth inversion device provided by the application, the processing module is used for obtaining a water depth inversion result by solving the nonlinear equation set through a hybrid optimization algorithm; wherein the hybrid optimization algorithm is generated based on a particle swarm optimization algorithm and a trust region strategy optimization algorithm.

[0020] The application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the hyperspectral water depth inversion method according to any one of the above when executing the program.

[0021] The application further provides a non-transitory computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the hyperspectral water depth inversion method according to any one of the above.

[0022] The application further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the hyperspectral water depth inversion method according to any one of the above.

[0023] The hyperspectral water depth inversion method, device, equipment, storage medium and program product provided by the application can convert the reflectance spectrum data of the hyperspectral data into the absorbance spectrum data based on the Beer-Lambert law and perform the radiation transfer model conversion of the absorbance, because the sensitivity of the absorbance spectrum data to water depth is greater than that of the reflectance spectrum data to water depth, the weak information of the water body radiation signal can be enhanced, the water body pixel spectrum of different water depths has stronger distinguishability, and thus the accuracy of the hyperspectral data water depth inversion is improved. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0025] Figure 1 is a flowchart of the hyperspectral water depth inversion method provided by the application;

[0026] Figure 2 is a flowchart of the hybrid optimization algorithm provided by the application;

[0027] Figure 3 is a structural schematic diagram of the hyperspectral water depth inversion device provided by the application;

[0028] Figure 4 is a structural schematic diagram of the electronic device provided by the application. DETAILED DESCRIPTION

[0029] In the description of the application, the technical solutions and advantages of the present application will be clearer, the technical solutions of the present application will be described clearly and completely below in combination with the drawings in the application. Obviously, the described embodiments are some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0030] It should be noted that in the embodiments of the present application, the words such as "exemplary" or "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "exemplary" or "for example" are intended to present the relevant concept in a specific manner.

[0031] It should be noted that in this paper, the term "include", "contain" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitation, the element defined by the sentence "including a…" does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but can also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method can be performed in an order different from the described order, and various steps can also be added, omitted or combined. In addition, the features described with reference to some examples can be combined in other examples.

[0032] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second" and the like are used to distinguish the same or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second" and the like are not limited in number and execution order.

[0033] The embodiments of the present application describe some exemplary embodiments for the purpose of illustration. It should be understood that the present application can be implemented in other ways not specifically shown in the drawings.

[0034] As shown in Figure 1 The present application provides a hyperspectral water depth inversion method, which can be applied to a hyperspectral water depth inversion device. The hyperspectral water depth inversion method can include S101-S104:

[0035] S101, the hyperspectral water depth inversion device acquires hyperspectral data.

[0036] Optionally, the acquiring of the hyperspectral data comprises: collecting original hyperspectral data by a hyperspectral detector; performing a preprocessing operation on the original hyperspectral data to obtain surface reflectivity data, the preprocessing operation comprising, in sequence, radiation correction, geometric correction, and atmospheric correction; screening water body pixels for water depth inversion from the surface reflectivity data, and correcting abnormal water body pixels caused by water surface fluctuation to cause solar glint, to obtain the hyperspectral data.

[0037] Specifically, the hyperspectral water depth inversion device can first collect original hyperspectral data by a hyperspectral detector, the original hyperspectral data being a response value after photoelectric conversion of the hyperspectral detector, usually referred to as a DN (Digital Number) value, which does not have physical meaning and needs to be converted into a corresponding radiance value through relative and absolute radiation correction processing, the conversion formula being shown in the following formula (1):

[0038] ; (1)

[0039] Wherein, L represents the radiance value, subscript i represents the waveband index, and k and b represent the correction gain and bias of the hyperspectral detector after radiation calibration, respectively.

[0040] Then, the hyperspectral water depth inversion device can select matching homonymic points of the image to be processed and reference data based on reference image data; then, according to the selected matching homonymic points, a rational polynomial of a hyperspectral image transformation model is established; then, using the control point image coordinates and geographic coordinates, the least squares estimation method is used to solve the rational polynomial coefficients; finally, the geographic coordinates of the image pixels are solved one by one according to the obtained transformation parameters, and the original image is resampled and output to obtain a geometrically corrected hyperspectral image with geographic coordinates containing shallow water areas.

[0041] Then, the hyperspectral water depth inversion device can use an atmospheric radiation transfer model to perform atmospheric correction on the hyperspectral image data, the atmospheric radiation transfer model describing the radiance value entering the entrance pupil of the sensor as the sum of direct radiation, indirect radiation, and path radiation, as shown in the following formula (2):

[0042] ; (2)

[0043] Wherein, is the surface reflectivity corresponding to the pixel, is the average surface reflectivity of the surrounding area of the pixel, is the spherical albedo of the atmosphere, The radiance, A, B of the atmospheric backscattering depend on coefficients of the atmosphere and geometric conditions.

[0044] By establishing a water vapor content and model parameter lookup table, the input hyperspectral radiance data can be converted into surface reflectance data above the water surface.

[0045] After the preprocessing operation is completed, the hyperspectral water depth inversion device can screen water body pixels for water depth inversion from the surface reflectance data, and establish a water body spectral index (WSI), as shown in the following formula (3):

[0046] ; (3)

[0047] Wherein, R is reflectance, subscript g is green light band, and subscript r is near-infrared band.

[0048] The hyperspectral water depth inversion device can judge each pixel in the hyperspectral image one by one, and when the WSI value is greater than 0, the pixel is a water body pixel and a corresponding image mask is generated.

[0049] Finally, since the water area in the shallow sea area is close to the shore and usually has large wave fluctuations, the water body pixel reflection radiation in the hyperspectral image may be affected by the sun glint caused by the wave fluctuations, resulting in abnormal water body remote sensing reflectance in the image, which is no longer suitable for water depth inversion. The hyperspectral water depth inversion device can use a water body reflectance index model correction method, which can describe the water body reflection radiation as two parts, one part is the reflection radiation of the water body itself, and the other part is the specular reflection of the water surface (i.e. sun glint), as shown in the following formula (4):

[0050] ; (4)

[0051] Wherein, is the total reflection radiation of the water body, is the reflection radiation of the water body itself, is the sun glint reflectance, is the sun glint radiation.

[0052] The hyperspectral water depth inversion device can use a multi-band brightness threshold method to calculate to remove the sun glint reflectance in the reflectance, and obtain the hyperspectral data.

[0053] S102, the hyperspectral water depth inversion device converts the reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performs radiation transfer model conversion of absorbance.

[0054] The sensitivity of the absorbance spectral data to water depth is greater than the sensitivity of the reflectance spectral data to water depth.

[0055] Optionally, the hyperspectral water depth inversion device converts the reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and the method comprises the following steps of:

[0056] According to the formula The reflectance spectral data of the hyperspectral data is converted into absorbance spectral data; wherein A represents absorbance, I represents reflected radiation intensity, represents incident radiation intensity, and R represents reflectance.

[0057] Specifically, the radiation energy of the solar radiation reflected into the hyperspectral detector through the water body is low, and generally, the reflectance of a typical water body pixel in the visible light band in the hyperspectral image is less than 0.2, and the reflectance value in the infrared band is close to 0. In the current hyperspectral remote sensing water depth inversion method, the water body surface reflectance is used to invert the water body bottom depth, but the reflectance signal is weak and the change range is small, which is not conducive to the accurate inversion of the water depth.

[0058] In the Beer-Lambert law used to describe the absorption characteristics of light propagation in a solution, a new physical quantity-absorbance is proposed. The physical quantity is used to represent the absorption capacity of the solution to light, and the absorbance is proportional to the absorption coefficient of the solution and the path length of the light. Therefore, for the near-shore shallow sea area, the absorbance is a more suitable physical quantity for water depth inversion than the reflectance. The present application proposes a method of spectral transformation to transform the reflectance spectral data into absorbance spectral data, so as to enhance the weak spectral information of the water body. The specific spectral transformation formula is shown in the following formula (5):

[0059] ; (5)

[0060] Wherein A represents absorbance, I represents reflected radiation intensity, represents incident radiation intensity, and R represents reflectance.

[0061] According to the above formula (5), the reflectance data is first taken as the reciprocal and then taken as the logarithm, and the absorbance data can be obtained. After spectral transformation, the numerical value of the spectral data is increased, and the range is raised to [0, 3].

[0062] It should be noted that due to the strong absorbance of the water body, the water body absorbance signal is significantly improved compared with the water body reflectance signal, so that the water body pixel spectra of different water depths have stronger distinguishability, and the accuracy of the hyperspectral data water depth inversion is improved.

[0063] Optionally, after converting the reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, the hyperspectral water depth inversion device can filter the absorbance spectral data based on filter coefficients of a given window size and order.

[0064] Specifically, the hyperspectral detector acquires spectral data with high spectral resolution by designing more imaging band numbers or narrower imaging band widths, but the problem that follows is that the radiant energy entering a single imaging band is greatly reduced, and due to the inaccuracy of the radiation calibration coefficient and the unevenness of the atmospheric correction, unnatural peaks and pseudo-absorption are generated in some bands of the hyperspectral data, which are called spectral "artifacts". The present application can use an S-G filter to remove spectral "artifacts". That is, the hyperspectral water depth inversion device can first calculate filter coefficients of a given window size and order; then slide the S-G filter to the last band in the spectral dimension of the absorbance hyperspectral data, to obtain spectral data after "artifact" removal. In this way, unnatural peaks and pseudo-absorption on the spectrum can be eliminated, background noise can be reduced, and the accuracy of hyperspectral data water depth inversion can be improved.

[0065] Optionally, the hyperspectral water depth inversion device can perform a radiation transfer model conversion of absorbance based on the Beer-Lambert law.

[0066] Specifically, the radiation transfer model can be a Hydrolight model, which converts the remote sensing reflectance above the water surface defined as the ratio of the water-leaving radiance to the downward irradiance above the water surface. Based on the divergence and reflection factors of the water-air interface, the remote sensing reflectance above the water surface is converted into the remote sensing reflectance below the water surface using the following formula (6) :

[0067] ; (6)

[0068] wherein, represents the water-air divergence factor, represents the internal reflection factor of the water-air interface, represents the remote sensing reflectance below the water surface.

[0069] Based on the Beer-Lambert law, i.e., the absorption of light is exponentially related to the path length of light passing through, a physical model of the scattering coefficient, the absorption coefficient, the bottom albedo, and the bottom depth of the water body components can be established, as shown in the following formula (7):

[0070] ; (7)

[0071] wherein, is the optical deep-water remote sensing reflectance, represents the optical path correction factor, represents the zenith angle of the propagation path of light in water and the vertical direction, is the optical path lengthening coefficient of water body scattering, is the optical path lengthening coefficient of bottom scattering, is the seawater attenuation coefficient, represents the water depth, i.e. the vertical distance of light propagation from the water surface to the bottom, is the seawater bottom reflectivity, is the seawater inherent optical property coefficient, and the above coefficients can be calculated by using the water body component scattering and absorption coefficients.

[0072] S103, the hyperspectral water depth inversion device establishes a nonlinear equation set of spectral data and water depth parameters according to the radiation transfer model and the absorbance spectral data.

[0073] By transforming the reflectance spectral data into absorbance spectral data and performing radiation transfer model transformation of absorbance, the above formula (6) can be transformed into the following formula (8), and thus the nonlinear equation set can be established by using the absorbance data and formula (8).

[0074] ; (8)

[0075] wherein, represents the remote sensing absorbance.

[0076] Optionally, the hyperspectral water depth inversion device can perform parameterization processing on the unknown vector parameters in the radiation transfer model equation.

[0077] Specifically, in the nonlinear equation set established above, since the scattering and absorption coefficients of the water body components vary with the wavelength, only n nonlinear equations can be established for n independent wave bands, and the number of unknowns is 4n+1. At this time, the equation set is an "underdetermined" equation set, and other constraint conditions need to be introduced. The present application uses the HOPE parameterization process to parameterize the absorption and scattering coefficients of the water body components with wavelength into a function of a certain special wave band. The specific process is as follows:

[0078] (a) phytoplankton pigment absorption coefficient is fitted using the absorption coefficient at 440 nm, as shown in formula (9). Wherein, is the absorption coefficient of phytoplankton at 440 nm, and two empirical coefficients , use Lee's fitting results.

[0079] ; (9)

[0080] (b) Absorption coefficient of colored soluble organic matter and debris Its parameterization formula is shown in the following formula (10), where, , It is the spectral slope. It is the sum of the absorption spectra of organic matter and debris at 440 nm, and the average of the spectral slopes is taken. =0.015nm-1.

[0081] ; (10)

[0082] (c) Backscattering coefficient of suspended particles , is defined as formula (11). Y is the backscattering coefficient of a 400nm suspended particle, and Y is an empirical value.

[0083] ; (11)

[0084] (d) Bottom albedo The parameterization formula is shown in formula (12) below, where, The albedo of the water sediment at 550 nm. It is a substrate reflectance spectrum normalized using 550nm substrate albedo. Common substrate types include sand, aquatic plants, and seaweed.

[0085] ;(12)

[0086] This completes the parameterization of the Hydrolight model, and the wavelength-dependent nonlinear equations are now complete. , , , The unknown coefficients are transformed into first-order functions of coefficients at a specific wavelength. At this point, the unknowns in the system of equations are respectively... .

[0087] S104. The hyperspectral water depth inversion device solves the nonlinear equations to obtain the water depth inversion results.

[0088] Specifically, the preceding steps established the relationship between absorbance (A) spectral data and the scattering and absorption coefficients of water components. ), bottom albedo ( ) and bottom depth ( The nonlinear equation set between the two is shown in the following formula (13). When the number of bands participating in the water depth inversion n>5, an "overdetermined" equation set can be obtained (the pure water absorption coefficient and backscattering coefficient are measured by laboratory). The "overdetermined" equation set has a least squares solution.

[0089] ; (13)

[0090] Optionally, the hyperspectral water depth inversion device can obtain the water depth inversion result by solving the nonlinear equation set through a hybrid optimization algorithm; wherein the hybrid optimization algorithm is generated based on a particle swarm optimization algorithm (PSO) and a trust region policy optimization algorithm (TRPO).

[0091] Specifically, the hyperspectral water depth inversion device can obtain the least square solution (i.e., the optimal estimate of the model parameters) of the nonlinear equation set through a hybrid optimization algorithm. This solving problem has the characteristics of complex equation structure, high dimension of solution space (5 dimensions), and large search range. PSO has low dependence on the initial value of unknown parameters and good global search ability, but the local optimization ability of PSO is weak, the convergence speed is slow, and the optimization result is unstable. TRPO has efficient local optimization ability and can quickly converge to a local optimal solution, but it has strong dependence on the initial point. When the initial point is far from the optimal solution, the optimization accuracy is low, the convergence speed is slow, and it is easy to fall into a local optimal solution. The hybrid optimization algorithm can combine the two, first use PSO to randomly generate multiple initial solutions, and perform global search by sharing search information between the particle swarm; then use the optimization results obtained by the particle swarm search as the initial solution of TRPO; finally, use TRPO for fine local optimization to find the global optimal solution faster and more accurately. The robustness of PSO is used in the whole optimization process to a great extent to compensate for the dependence of the TRPO algorithm on the initial solution, and TRPO can further improve the accuracy and stability of the optimization result of PSO. The hybrid optimization algorithm combines the advantages of the particle swarm optimization algorithm and the trust region policy optimization algorithm, has low sensitivity to the initial value of unknown parameters, good global search ability, fast convergence speed in the optimization process, and stable optimization results.

[0092] As shown in FIG. 1, a flowchart of the hybrid optimization algorithm is shown, and the fitness function used in the optimization process is the residual sum of squares of the model simulated spectrum and the measured spectrum. The whole optimization process is divided into two stages: Figure 2 The first stage is the PSO algorithm optimization stage. First, the PSO initialization is performed to obtain the inertia factor, learning factor, particle swarm position, particle swarm speed, fitness function, and particle swarm fitness value. The PSO initial parameter settings are shown in Table 1:

[0093] Table 1

[0094]

[0095] ​​​

[0096] Then, the particle individual, the group history best position are found by minimizing the fitness function, if the iteration stop criterion is not met, each particle shares its search information to obtain a new search speed The calculation formula is shown in formula (14):

[0097] ; (14)

[0098] wherein, is an inertia factor, is a self-learning factor, is a group learning factor, represents a random number generation function, k is the iteration number, is the current position of the particle, is the historical best position of the particle, is the group historical best position, and the particle position is updated continuously; the particle swarm historical best position is output when the iteration is stopped, and the PSO optimization result is obtained.

[0099] The second stage is the TRPO algorithm optimization stage. First, initialize TRPO, and use the solution close to the global optimum obtained by the PSO algorithm as the initial value of the unknown parameter; then start iteration optimization, calculate the fitness value and Jacobian matrix, solve the trust region subproblem, as shown in formula (15):

[0100] ; (15)

[0101] wherein, is a fitness function, is a Jacobian matrix, is a trust region size.

[0102] If the iteration stop criterion is not met, update the trust region size, and calculate the new parameter value from the new trust region step; finally, when the stop criterion is met, output the parameter optimization result, and obtain the least square solution of the nonlinear equation set. The step is solved for each pixel of the hyperspectral data, and the water depth (z) value is extracted from it, so that the water depth inversion map corresponding to the hyperspectral image can be obtained.

[0103] The above hybrid optimization algorithm combines the advantages of the particle swarm optimization algorithm and the trust region strategy optimization algorithm, and is used to obtain the least square solution of the equation set established between the water body hyperspectral data and the radiation transfer model. In a larger solution space range, global fast search and local fine optimization can be performed, and the dependence on the initial value of the unknown parameter is greatly reduced.

[0104] ​In the embodiments of the present application, the reflectance spectrum data of the hyperspectral data can be converted into the absorbance spectrum data based on the Beer-Lambert law, and the radiation transfer model of the absorbance is converted. Since the sensitivity of the absorbance spectrum data to water depth is greater than the sensitivity of the reflectance spectrum data to water depth, the weak information of the water body radiation signal can be enhanced, so that the water body pixel spectrum of different water depths has stronger distinguishability, thereby improving the accuracy of the hyperspectral data water depth inversion.

[0105] The above mainly introduces the scheme provided by the embodiments of the present application from the perspective of the method. In order to realize the above functions, it contains the hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed in the present application, the embodiments of the present application can be realized in the form of hardware or the combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0106] The execution subject of the hyperspectral water depth inversion method provided by the embodiments of the present application can be a hyperspectral water depth inversion device, or a control module for hyperspectral water depth inversion in the hyperspectral water depth inversion device. In the embodiments of the present application, the hyperspectral water depth inversion device executes the hyperspectral water depth inversion method as an example to illustrate the hyperspectral water depth inversion device provided by the embodiments of the present application.

[0107] It should be noted that the embodiments of the present application can divide the functional modules of the hyperspectral water depth inversion device according to the above method examples, for example, each functional module can be divided according to each function, or two or more functions can be integrated in one processing module. The above integrated module can be realized in the form of hardware or software functional module. Optionally, the division of the module in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division manner.

[0108] As Figure 3As shown, the embodiment of the present application provides a hyperspectral water depth inversion device 300. The hyperspectral water depth inversion device 300 comprises an acquisition module 301 and a processing module 302; the acquisition module 301 is configured to acquire hyperspectral data; the processing module 302 is configured to convert reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and perform radiative transfer model conversion of the absorbance, the sensitivity of the absorbance spectral data to water depth being greater than the sensitivity of the reflectance spectral data to water depth; establish a nonlinear equation set of spectral data and water depth parameters according to the radiative transfer model and the absorbance spectral data; and solve the nonlinear equation set to obtain a water depth inversion result.

[0109] Optionally, the processing module 302 is configured to:

[0110] According to the formula convert the reflectance spectral data of the hyperspectral data into absorbance spectral data; wherein A represents absorbance, I represents reflected radiation intensity, represents incident radiation intensity, and R represents reflectance.

[0111] Optionally, the acquisition module 301 is configured to: collect original hyperspectral data by a hyperspectral detector; perform a preprocessing operation on the original hyperspectral data to obtain ground surface reflectance data, the preprocessing operation comprising, in sequence, radiation correction, geometric correction, and atmospheric correction; select water body pixels for water depth inversion from the ground surface reflectance data, and correct abnormal water body pixels caused by solar glint due to water surface undulation to obtain the hyperspectral data.

[0112] Optionally, after the reflectance spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and the radiative transfer model conversion of the absorbance is performed, the processing module 302 is configured to perform filtering processing on the absorbance spectral data based on a filter coefficient of a given window size and order.

[0113] Optionally, after the reflectance spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and the radiative transfer model conversion of the absorbance is performed, the processing module 302 is configured to perform parameterization processing on unknown vector parameters in a radiative transfer model equation.

[0114] Optionally, the processing module 302 is configured to solve the nonlinear equation set by a hybrid optimization algorithm to obtain a water depth inversion result; wherein the hybrid optimization algorithm is generated based on a particle swarm optimization algorithm and a trust region strategy optimization algorithm.

[0115] In the embodiments of the present application, the reflectance spectrum data of the hyperspectral data can be converted into the absorbance spectrum data based on the Beer-Lambert law, and the radiation transfer model of the absorbance is transformed. Since the sensitivity of the absorbance spectrum data to water depth is greater than that of the reflectance spectrum data to water depth, the weak information of the water body radiation signal can be enhanced, so that the water body pixel spectrum of different water depths has stronger distinguishability, thereby improving the accuracy of the hyperspectral data water depth inversion.

[0116] Figure 4 An example of a schematic diagram of a physical structure of an electronic device is shown in Figure 4 As shown, the electronic device can include a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 can communicate with each other through the communications bus 440. The processor 410 can invoke the logical instructions in the memory 430 to execute the hyperspectral water depth inversion method, which includes: obtaining hyperspectral data; converting the reflectance spectrum data of the hyperspectral data into the absorbance spectrum data based on the Beer-Lambert law, and performing the radiation transfer model transformation of the absorbance, wherein the sensitivity of the absorbance spectrum data to water depth is greater than that of the reflectance spectrum data to water depth; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiation transfer model and the absorbance spectrum data; and solving the nonlinear equation set to obtain a water depth inversion result.

[0117] In addition, the logical instructions in the memory 430 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium, includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0118] In another aspect, the present application also provides a computer program product comprising a computer program, the computer program being stored in a non-transitory computer-readable storage medium, and the computer program being executable by a processor to enable a computer to perform the hyperspectral water depth inversion method provided by the above-mentioned methods, the method comprising: obtaining hyperspectral data; converting reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing a radiative transfer model transformation of the absorbance, the absorbance spectral data being more sensitive to water depth than the reflectance spectral data; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiative transfer model and the absorbance spectral data; and solving the nonlinear equation set to obtain a water depth inversion result.

[0119] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the hyperspectral water depth inversion method provided by the above-mentioned methods, the method comprising: obtaining hyperspectral data; converting reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing a radiative transfer model transformation of the absorbance, the absorbance spectral data being more sensitive to water depth than the reflectance spectral data; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiative transfer model and the absorbance spectral data; and solving the nonlinear equation set to obtain a water depth inversion result.

[0120] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0121] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments.

[0122] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for hyperspectral water depth inversion, characterized in that, The method comprises the following steps: obtaining hyperspectral data; converting reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing radiative transfer model conversion of the absorbance, the absorbance spectral data being more sensitive to water depth than the reflectance spectral data; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiative transfer model and the absorbance spectral data; solving the nonlinear equation set to obtain water depth inversion results; the obtaining hyperspectral data comprises: collecting original hyperspectral data by a hyperspectral detector; performing preprocessing operations on the original hyperspectral data to obtain ground surface reflectance data, the preprocessing operations comprising, in sequence, radiation correction, geometric correction, and atmospheric correction; selecting water body pixels for water depth inversion from the ground surface reflectance data, and correcting abnormal water body pixels caused by solar glint due to water surface undulation to obtain the hyperspectral data; after the reflectance spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and the radiative transfer model conversion of the absorbance is performed, the method further comprises: filtering the absorbance spectral data based on filter coefficients of a given window size and order.

2. The hyperspectral water depth inversion method according to claim 1, characterized in that, the converting reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law comprises: According to the formula converting the reflectance spectral data of the hyperspectral data to absorbance spectral data; where A represents the absorbance, I represents the reflected radiation intensity, where I represents the incident radiation intensity, R represents the reflectance.

3. The hyperspectral water depth inversion method according to claim 1, characterized in that, after the reflectance spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and the radiative transfer model conversion of the absorbance is performed, the method further comprises: performing parameterization processing on unknown vector parameters in the radiative transfer model equation.

4. The hyperspectral water depth inversion method according to any one of claims 1-3, characterized in that, the solving the nonlinear equation set to obtain water depth inversion results comprises: solving the nonlinear equation set by a hybrid optimization algorithm to obtain water depth inversion results; wherein the hybrid optimization algorithm is generated based on a particle swarm optimization algorithm and a trust region strategy optimization algorithm.

5. A hyperspectral water depth inversion device, characterized in that, The method comprises the following steps: obtaining hyperspectral data; converting reflectance spectral data of the hyperspectral data into absorbance spectral data based on the Beer-Lambert law, and performing radiative transfer model conversion of the absorbance, the absorbance spectral data being more sensitive to water depth than the reflectance spectral data; establishing a nonlinear equation set of spectral data and water depth parameters according to the radiative transfer model and the absorbance spectral data; solving the nonlinear equation set to obtain water depth inversion results; the obtaining hyperspectral data comprises: collecting original hyperspectral data by a hyperspectral detector; performing preprocessing operations on the original hyperspectral data to obtain ground surface reflectance data, the preprocessing operations comprising, in sequence, radiation correction, geometric correction, and atmospheric correction; selecting water body pixels for water depth inversion from the ground surface reflectance data, and correcting abnormal water body pixels caused by solar glint due to water surface undulation to obtain the hyperspectral data; after the reflectance spectral data of the hyperspectral data is converted into absorbance spectral data based on the Beer-Lambert law and the radiative transfer model conversion of the absorbance is performed, the method further comprises: filtering the absorbance spectral data based on filter coefficients of a given window size and order. Filter the absorbance spectral data based on the filter coefficients of the given window size and order.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the hyperspectral water depth inversion method according to any one of claims 1-4 when executing the computer program.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the hyperspectral water depth inversion method according to any one of claims 1-4.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the hyperspectral water depth inversion method according to any one of claims 1-4. The computer program is executed by the processor to implement the hyperspectral water depth inversion method according to any one of claims 1-4.

Images