A real-time cross-sectional water quality detection method and device based on imaging hyperspectral

Abstract

The disclosed embodiments provide a real-time cross-sectional water quality detection method and device based on imaging hyperspectral. It includes: determining the response position of the optical fiber bundle of the hyperspectral imager, and adjusting the target exposure time of the spectral imager; acquiring the collected data of the water surface to be tested based on the response position and the target exposure time under no light conditions, and processing the collected data to generate processed data; performing calculations in the spectral dimension according to the processed data to generate reflectivity data, and inverting water quality parameters according to the reflectivity data; and generating water quality detection results in real time according to the water quality parameters. Cross-sectional water quality monitoring can be performed, with a wider coverage range and an adjustable monitoring range. The inversion results are effectively improved by fusing multi-dimensional data sources, thereby improving accuracy. Through the online calibration function, the instrument can obtain more accurate data for a long time. Compared with traditional instruments, there is no need to place reference targets, and it is easier to deploy and implement in special geographical environments.

Description

Technical Field

[0001] The present invention relates to the field of spectral imaging, and in particular to a real-time cross-section water quality detection method and device based on imaging hyperspectral. Background Art

[0002] The spectrometer can not only obtain the spatial distribution information of ground objects, but also simultaneously obtain their spectral information for analyzing material composition. It plays an important role in agricultural pest and disease detection, forestry tree species identification, water environment testing and other fields.

[0003] In water quality testing, spectral imaging technology is mainly used to detect pollutants such as organic matter, inorganic matter, and microorganisms in water. By analyzing spectral data, it is possible to determine whether these pollutants exist in the water, and to determine their concentration and distribution.

[0004] Current hyperspectral imagers generally have difficulty in real-time calculation of reflectivity and are easily affected by changes in ambient light. Traditional processing methods usually require the placement of reflectivity plate targets, ambient light collectors and other auxiliary equipment during the data collection process. In particular, water surface monitoring is more difficult to implement and it is relatively difficult to collect ideal data. In addition, the data processing process requires comprehensive processing of data generated by multiple instruments, which often leads to a loss of precision, thus affecting the accuracy of the data results. Summary of the invention

[0005] The purpose of the present invention is to overcome the problems of difficult reflectance calculation, few monitoring points, large system errors, unclear monitoring points and easy missed detection in the hyperspectral water quality monitoring system of the prior art solutions, and provide a real-time cross-sectional water quality detection method and device based on imaging hyperspectral, which can solve the spectral wavelength drift caused by environmental changes or other factors, and determine the water quality detection results by obtaining real-time reflectance data and inputting it into the algorithm model.

[0006] In a first aspect, the present disclosure provides a real-time cross-sectional water quality detection method based on imaging hyperspectral, the method comprising:

[0007] Determine the fiber bundle response position of the hyperspectral imager and adjust the target exposure time of the hyperspectral imager;

[0008] acquiring collected data of the water surface to be measured based on the response position and the target exposure time under no-light conditions, and processing the collected data to generate processed data;

[0009] Performing calculations in the spectral dimension according to the processed data to generate reflectance data, and inverting water quality parameters according to the reflectance data;

[0010] Generate water quality test results in real time based on water quality parameters.

[0011] Optionally, the method also includes: collecting spectral data through a hyperspectral imager in a specified calibration environment, and determining standard data corresponding to the specified calibration environment; determining a wavelength drift value between the spectral data and the standard data based on a preset algorithm, and calibrating the hyperspectral imager according to the wavelength drift value.

[0012] Optionally, determining the response position of the fiber optic bundle of the hyperspectral imager includes: placing the fiber optic bundle at a specified position, and sequentially using the fiber optic bundle as a target fiber optic bundle, wherein the number of the fiber optic bundles is at least one; determining a light spot position corresponding to the target fiber optic bundle in the hyperspectral imager in a specified test environment; and using the light spot position as the response position.

[0013] Optionally, determining the target exposure time of the hyperspectral imager includes: obtaining the target spectral radiance corresponding to a specified channel of the hyperspectral imager; obtaining a preset exposure time list, wherein the exposure time list includes exposure times corresponding to each spectral radiance; matching the target spectral radiance through the exposure time list to obtain a target exposure time that matches the target spectral radiance.

[0014] Optionally, the collected data is processed to generate processed data, including: determining the actual number of optical fiber bundles, and determining the target column data in the collected data based on the actual number; calculating the data mean corresponding to each other column data in the collected data except the target column data; replacing the target column data in the collected data by the data mean to generate processed data.

[0015] Optionally, operations are performed in the spectral dimension based on the processed data to generate reflectance data, and water quality parameters are inverted based on the reflectance data, including: substituting the processed data into a specified algorithm to perform operations in the spectral dimension to generate reflectance data; and inputting the reflectance data and target column data into a preset algorithm model to obtain the water quality parameters output by the model.

[0016] Optionally, water quality test results are generated in real time based on water quality parameters, including: when the water quality parameters exceed the corresponding water quality parameter threshold interval, determining the water quality parameters to be abnormal water quality parameters; when the water quality parameters meet the corresponding water quality parameter threshold interval, determining the water quality parameters to be normal water quality parameters; and using the normal water quality parameters and the abnormal water quality parameters as water quality test results.

[0017] In a second aspect, the present disclosure also provides a real-time cross-sectional water quality detection device based on imaging hyperspectral, the device comprising:

[0018] A response position and exposure time determination module, used to determine the response position of the optical fiber bundle of the hyperspectral imager and determine the exposure time of the hyperspectral imager;

[0019] A data collection processing module is used to obtain the collected data of the water surface to be measured based on the response position and exposure time under no light conditions, and process the collected data to generate processed data;

[0020] A reflectivity and water quality parameter determination module, used to generate reflectivity data by performing calculations in the spectral dimension according to the processed data, and invert water quality parameters according to the reflectivity data;

[0021] The water quality test result determination module is used to generate water quality test results in real time according to water quality parameters.

[0022] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0023] at least one processor; and

[0024] a memory communicatively connected to at least one processor; wherein,

[0025] When the memory stores a computer program that can be executed by at least one processor, the computer program is executed by at least one processor so that the at least one processor can execute a real-time cross-sectional water quality detection method based on imaging hyperspectral as in any embodiment of the present disclosure.

[0026] In a fourth aspect, an embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, a real-time cross-sectional water quality detection method based on imaging hyperspectral as in any embodiment of the present disclosure is implemented.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description.

[0028] Therefore, the present invention has the following beneficial effects:

[0029] 1. It can carry out cross-section monitoring, with a wider coverage and adjustable monitoring range.

[0030] 2. It has the function of automatic online calibration, so that the instrument can obtain more accurate data for a long time.

[0031] 3. With automatic exposure function, the instrument can work in various lighting environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a flow chart of a real-time cross-section water quality detection method based on imaging hyperspectral according to Embodiment 1 of the present invention;

[0034] Figure 2 is a structural schematic diagram of a data acquisition device based on imaging hyperspectral according to Embodiment 1 of the present invention;

[0035] Figure 3 This is a schematic structural diagram of a real-time cross-sectional water quality detection device based on imaging hyperspectral according to Embodiment 2 of the present invention;

[0036] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Embodiment 1

[0040] Figure 1A flowchart of a real-time cross-sectional water quality detection method based on imaging hyperspectral is provided for the first embodiment of the present invention. This embodiment can be applied to the case of detecting water quality. The method can be executed by a water quality detection device based on imaging hyperspectral provided by the embodiment of the present disclosure. The device can be implemented in software and / or hardware and can generally be integrated in a computer device. The method of the embodiment of the present disclosure specifically includes:

[0041] S110: Determine the optical fiber bundle response position of the hyperspectral imager, and adjust the target exposure time of the hyperspectral imager.

[0042] Among them, a hyperspectral imager is an instrument that can simultaneously obtain the spectral information and spatial information of an object. It can measure the reflectivity or transmittance of an object by dividing light into different wavelengths. A hyperspectral imager usually includes components such as a light source, a spectrometer, a detector, and an optical system, where the optical system is responsible for guiding the light emitted by the light source to the detector.

[0043] Optionally, determining the response position of the fiber optic bundle of the hyperspectral imager includes: placing the fiber optic bundle at a specified position, and sequentially using the fiber optic bundle as a target fiber optic bundle, wherein the number of the fiber optic bundles is at least one; determining a light spot position corresponding to the target fiber optic bundle in the hyperspectral imager in a specified test environment; and using the light spot position as the response position.

[0044] The light spot refers to the bright spot formed by the target fiber bundle on the detector, and its position can reflect the position of the target fiber bundle in the hyperspectral imager. When determining the response position of the fiber bundle of the hyperspectral imager, it is necessary to ensure the stability and consistency of the test environment to avoid the influence of external factors on the test results. In addition, the test results need to be repeated and verified many times to ensure the accuracy and reliability of the test results.

[0045] Figure 2 A structural schematic diagram of a data acquisition device based on imaging hyperspectral is provided for the first embodiment of the present invention. Figure 2 There are 4 optical fiber bundles in the figure, among which 1 is a scanning galvanometer, 2 is a mercury lamp, 3 is a lens, 4 is a shutter, 5 is an FC interface female socket, 6 is an FC interface female socket, 7 is an FC interface female socket, 8 is an FC interface female socket, 9 is a hyperspectral camera, 10 is 45 degree downward observation, 11 is 45 degree upward observation, 12 is vertical upward observation, 13 is a cosine corrector, 14 is used to measure reflectivity, and 15 is a reflectivity plate.

[0046] Exemplarily, in this embodiment, the number of optical fiber bundles is 4 for illustration. The technical solution of the embodiment of the present invention is improved for the imaging hyperspectral imager. One end of the four optical fiber bundles is installed at the end of the slit of the hyperspectral imager and arranged in sequence. The core diameters of the two optical fibers are required to match the slit width, and the center positions of the optical fiber core diameters and the slit centers are aligned. The other end of the optical fiber is connected to the FC interface female socket of the device housing; the first optical fiber root is connected to the collimator to observe the water surface at 45 degrees downward, the second optical fiber is connected to the collimator to observe the environment at 45 degrees upward, the third optical fiber is connected to the collimator and the cosine corrector to observe the ambient light vertically upward, and the fourth optical fiber is connected to the collimator to observe the reflectivity plate for measuring the reflectivity spectrum. The optical fiber can be quickly connected through the FC interface, and the hyperspectral imager can realize different cross-section monitoring and spectral wavelength online calibration functions by adjusting the pointing angle of the scanning galvanometer, and the dark background subtraction function can be realized by controlling the shutter.

[0047] Specifically, when calibrating the response position, optical fibers one, two, three, and four can be connected to chanel1, chanel2, chanel3, and chanel4, and the hyperspectral imager can be connected to dedicated data acquisition and analysis software. First, the fiber bundle of chanel1 is used as the target fiber bundle and aligned with the halogen lamp. Chanel2, chanel3, and chanel4 are kept in a dark environment. The position of the light spot in the software is observed and the position (x1, y1) is recorded. By analogy, the response positions corresponding to chanel2, chanel3, and chanel4 can be calibrated in turn.

[0048] Optionally, the method also includes: collecting spectral data through a hyperspectral imager in a specified calibration environment, and determining standard data corresponding to the specified calibration environment; determining a wavelength drift value between the spectral data and the standard data based on a preset algorithm, and calibrating the hyperspectral imager according to the wavelength drift value.

[0049] Specifically, it can be achieved by placing the hyperspectral imager in a specific environment and recording its measurement results. Exemplarily, the specified calibration environment can be that the scanning galvanometer is rotated to a direction with an angle of 45 degrees with the Y-axis, and the mercury lamp is turned on by software control. And it can be achieved by using standard substances or reference spectra. Standard substances are substances whose chemical composition and spectral characteristics are known, which can be used to verify whether the measurement results of the hyperspectral imager are accurate. The reference spectrum is a spectrum whose spectral characteristics are known, which can be used to compare with the measurement results of the hyperspectral imager. This is achieved by using spectral analysis software. The spectral analysis software can compare the measurement results of the hyperspectral imager with the standard data and calculate the difference between them, that is, the wavelength drift value.

[0050] Furthermore, the hyperspectral imager can be calibrated according to the wavelength drift value by adjusting the parameters of the hyperspectral imager. For example, the light source intensity, detector sensitivity and other parameters of the hyperspectral imager can be adjusted to make its measurement results more accurate. Through the above steps, the hyperspectral imager can be calibrated to ensure the accuracy of its measurement results. It should be noted that when calibrating, appropriate standard substances and reference spectra should be selected, and the correct preset algorithm and spectral analysis software should be used.

[0051] Optionally, determining the target exposure time of the hyperspectral imager includes: obtaining the target spectral radiance corresponding to a specified channel of the hyperspectral imager; obtaining a preset exposure time list, wherein the exposure time list includes exposure times corresponding to each spectral radiance; matching the target spectral radiance through the exposure time list to obtain a target exposure time that matches the target spectral radiance.

[0052] The exposure time list refers to the exposure time settings of the hyperspectral imager at different spectral radiances. These exposure times are determined based on the performance of the hyperspectral imager and the characteristics of the water body to be measured. Exemplarily, when the number of fiber bundles is 4, the designated fiber bundle may be the channel corresponding to the 4th fiber bundle.

[0053] Specifically, the target spectral radiance is compared with the spectral radiance in the exposure time list. If the target spectral radiance has a corresponding exposure time in the exposure time list, the exposure time can be used as the target exposure time. If the target spectral radiance is not in the exposure time list, the exposure time closest to the target spectral radiance can be selected as the target exposure time.

[0054] It should be noted that when determining the target exposure time of the hyperspectral imager, it is necessary to consider the characteristics of the water body to be tested and the performance of the hyperspectral imager. Different water bodies to be tested may have different spectral characteristics, so different exposure times need to be selected. In addition, the performance of the hyperspectral imager will also affect the selection of exposure time, such as the sensitivity of the detector, the intensity of the light source, etc. Therefore, when determining the target exposure time of the hyperspectral imager, it is necessary to comprehensively consider the characteristics of the water body to be tested and the performance of the hyperspectral imager to select a suitable exposure time.

[0055] S120: Acquire collected data of the water surface to be measured based on the response position and the target exposure time under a no-light condition, and process the collected data to generate processed data.

[0056] Optionally, the collected data is processed to generate processed data, including: determining the actual number of optical fiber bundles, and determining the target column data in the collected data based on the actual number; calculating the data mean corresponding to each other column data in the collected data except the target column data; replacing the target column data in the collected data by the data mean to generate processed data.

[0057] The no-light condition refers to collecting data by pushing the shutter under the condition of blocking the slit, and the collected data can be recorded as dark_data.

[0058] Specifically, after determining the actual number of optical fiber bundles, it is necessary to determine the target column data in the collected data according to the actual number. The target column data refers to the spectral data corresponding to the optical fiber bundle in contact with the water body to be tested. And after determining the target column data, it is necessary to calculate the data mean corresponding to each other column data in the collected data except the target column data. These data means can reflect the overall spectral characteristics of the water body to be tested.

[0059] Furthermore, after calculating the data mean corresponding to each other column data, the target column data in the collected data needs to be replaced by the data mean to generate the processed data. That is, the data in the x1, x2, x3, x4 columns in dark_data is replaced by the mean of the x1, x2, x3, x4 columns divided by dark_data.

[0060] S130: Performing calculations in the spectral dimension according to the processed data to generate reflectance data, and inverting water quality parameters according to the reflectance data.

[0061] Specifically, it can be achieved by using various water quality parameter calculation formulas, such as chlorophyll concentration formula, turbidity formula, etc. Water quality parameters can be used for further analysis and processing.

[0062] Optionally, operations are performed in the spectral dimension based on the processed data to generate reflectance data, and water quality parameters are inverted based on the reflectance data, including: substituting the processed data into a specified algorithm to perform operations in the spectral dimension to generate reflectance data; and inputting the reflectance data and target column data into a preset algorithm model to obtain the water quality parameters output by the model.

[0063] Exemplarily, reflectivity data R = (cub_data-dark_data / chanel4_data-dark_data)*reflectivity_data, after calculating the data in the spectral dimension according to the above formula, the reflectivity data can be obtained. Among them, cub_data is the data collected by the hyperspectral imager, reflectivity_data is the calibration file of the reflectivity board, dark_data is the data under no light conditions, and chanel4_data is the spectral data of the chanel4 channel.

[0064] Furthermore, the reflectance data and target column data are input into a preset algorithm model to obtain the water quality parameters output by the model. The algorithm model can be an algorithm based on machine learning, such as support vector machine (SVM), random forest (RF), etc., or an algorithm based on a physical model, such as spectral absorption coefficient method, spectral reflectance coefficient method, etc.

[0065] S140: Generate water quality test results in real time according to water quality parameters.

[0066] Specifically, it can be achieved by using various data visualization tools, such as line graphs, bar graphs, etc. Water quality test results can be used to monitor and evaluate water quality conditions, and take corresponding measures to improve water quality. Water quality parameters include but are not limited to chemical oxygen demand COD, dissolved oxygen DO, total nitrogen TN, total phosphorus TP, ammonia nitrogen NH3N, chlorophyll aCHLA and total suspended particulate matter concentration SS.

[0067] Optionally, water quality test results are generated in real time based on water quality parameters, including: when the water quality parameters exceed the corresponding water quality parameter threshold interval, determining the water quality parameters to be abnormal water quality parameters; when the water quality parameters meet the corresponding water quality parameter threshold interval, determining the water quality parameters to be normal water quality parameters; and using the normal water quality parameters and the abnormal water quality parameters as water quality test results.

[0068] Specifically, the threshold interval of water quality parameters can be determined according to national or local water quality standards. The threshold interval of water quality parameters can be adjusted according to different water quality parameters. For example, the threshold interval of chemical oxygen demand can be 5-8 mg / L. By comparing the acquired water quality parameters with the threshold interval, it can be determined whether the water quality parameters exceed the threshold interval. If the water quality parameters exceed the threshold interval, the water quality parameters are determined to be abnormal water quality parameters; if the water quality parameters meet the threshold interval, the water quality parameters are determined to be normal water quality parameters. Finally, the normal water quality parameters and abnormal water quality parameters are displayed to the user as water quality test results. The water quality test results can be presented in the form of text, tables or charts so that users can better understand the water quality conditions.

[0069] The technical solution of the embodiment of the present invention determines the response position of the optical fiber bundle of the hyperspectral imager and adjusts the target exposure time of the hyperspectral imager; obtains the collected data of the water surface to be tested based on the response position and the target exposure time under no light conditions, and processes the collected data to generate processed data; performs calculations in the spectral dimension according to the processed data to generate reflectance data, and inverts water quality parameters according to the reflectance data; generates water quality detection results in real time according to the water quality parameters, and can perform cross-sectional water quality monitoring, with a wider coverage range and an adjustable monitoring range. The inversion results are effectively improved by fusing multi-dimensional data sources, and the accuracy is improved. Through the online calibration function, the instrument can obtain more accurate data for a long time. Compared with traditional instruments, there is no need to place reference targets, and it is easier to deploy and implement in special geographical environments.

[0070] Embodiment 2

[0071] Figure 3 The following is a schematic diagram of the structure of a real-time cross-sectional water quality detection device based on imaging hyperspectral provided in the second embodiment of the present invention. The device can be implemented in software and / or hardware, and can generally be integrated into an electronic device that executes the method. Figure 3 As shown, the device includes: a response position and exposure time determination module 210, which is used to determine the response position of the optical fiber bundle of the hyperspectral imager and determine the exposure time of the hyperspectral imager;

[0072] The collected data processing module 220 is used to obtain the collected data of the water surface to be measured based on the response position and exposure time under the condition of no illumination, and process the collected data to generate processed data;

[0073] A reflectivity and water quality parameter determination module 230, for performing calculations in the spectral dimension according to the processed data to generate reflectivity data, and inverting water quality parameters according to the reflectivity data;

[0074] The water quality detection result determination module 240 is used to generate water quality detection results in real time according to water quality parameters.

[0075] Optionally, the device also includes: a wavelength calibration module, which is used to: collect spectral data through a hyperspectral imager in a specified calibration environment, and determine standard data corresponding to the specified calibration environment; determine the wavelength drift value between the spectral data and the standard data based on a preset algorithm, and calibrate the hyperspectral imager according to the wavelength drift value.

[0076] Optionally, the response position and exposure time determination module 210 specifically includes: a response position determination unit, used to: place the optical fiber bundle at a specified position, and take the optical fiber bundle as a target optical fiber bundle in turn, wherein the number of optical fiber bundles is at least one; determine the light spot position corresponding to the target optical fiber bundle in the hyperspectral imager in a specified test environment; and take the light spot position as the response position.

[0077] Optionally, the response position and exposure time determination module 210 specifically includes: an exposure time determination unit, used to: obtain the target spectral radiance corresponding to a specified channel of the hyperspectral imager; obtain a preset exposure time list, wherein the exposure time list includes the exposure time corresponding to each spectral radiance; match the target spectral radiance through the exposure time list to obtain a target exposure time that matches the target spectral radiance.

[0078] Optionally, the acquisition data processing module 220 is specifically used to: determine the actual number of optical fiber bundles, and determine the target column data in the acquisition data based on the actual number; calculate the data mean corresponding to each other column data in the acquisition data except the target column data; replace the target column data in the acquisition data with the data mean to generate processed data.

[0079] Optionally, the reflectivity and water quality parameter determination module 230 is specifically used to: substitute the processed data into a specified algorithm to perform spectral dimension operations to generate reflectivity data; input the reflectivity data and target column data into a preset algorithm model to obtain the water quality parameters output by the model.

[0080] Optionally, the water quality test result determination module 240 is specifically used to: when the water quality parameter exceeds the corresponding water quality parameter threshold interval, determine the water quality parameter as an abnormal water quality parameter; when the water quality parameter satisfies the corresponding water quality parameter threshold interval, determine the water quality parameter as a normal water quality parameter; and use the normal water quality parameters and the abnormal water quality parameters as the water quality test results.

[0081] The technical solution of the embodiment of the present invention determines the response position of the optical fiber bundle of the hyperspectral imager and adjusts the target exposure time of the hyperspectral imager; obtains the collected data of the water surface to be tested based on the response position and the target exposure time under no light conditions, and processes the collected data to generate processed data; performs calculations in the spectral dimension according to the processed data to generate reflectance data, and inverts water quality parameters according to the reflectance data; generates water quality detection results in real time according to the water quality parameters, and can perform cross-sectional water quality monitoring, with a wider coverage range and an adjustable monitoring range. The inversion results are effectively improved by fusing multi-dimensional data sources, and the accuracy is improved. Through the online calibration function, the instrument can obtain more accurate data for a long time. Compared with traditional instruments, there is no need to place reference targets, and it is easier to deploy and implement in special geographical environments.

[0082] A real-time cross-sectional water quality detection device based on imaging hyperspectrum provided in an embodiment of the present invention can execute a real-time cross-sectional water quality detection method based on imaging hyperspectrum provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0083] Embodiment 3

[0084] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0085] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0086] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0087] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a real-time cross-sectional water quality detection method based on imaging hyperspectral. That is: determine the response position of the optical fiber bundle of the hyperspectral imager, and adjust the target exposure time of the hyperspectral imager; obtain the collected data of the water surface to be tested based on the response position and the target exposure time under no light conditions, and process the collected data to generate processed data; perform operations in the spectral dimension according to the processed data to generate reflectance data, and invert water quality parameters according to the reflectance data;

[0088] Generate water quality test results in real time based on water quality parameters.

[0089] In some embodiments, a real-time cross-sectional water quality detection method based on imaging hyperspectral may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the real-time cross-sectional water quality detection method based on imaging hyperspectral described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute a real-time cross-sectional water quality detection method based on imaging hyperspectral in any other appropriate manner (e.g., by means of firmware).

[0090] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0092] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0093] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0094] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0095] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0096] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time cross-section water quality detection method based on imaging hyperspectral, characterized in that: include: Determining a fiber bundle response position of a hyperspectral imager and adjusting a target exposure time of the hyperspectral imager; Acquire collected data of the water surface to be measured based on the response position and the target exposure time under no-light conditions, and process the collected data to generate processed data; Performing calculations in a spectral dimension according to the processed data to generate reflectance data, and inverting water quality parameters according to the reflectance data; Generating water quality test results in real time according to the water quality parameters; Wherein, determining the optical fiber bundle response position of the hyperspectral imager comprises: Placing an optical fiber bundle at a designated position, and sequentially using the optical fiber bundle as a target optical fiber bundle, wherein the number of the optical fiber bundle is at least one; Determine the spot position corresponding to the target optical fiber bundle in the hyperspectral imager in a specified test environment; Using the light spot position as the response position; Wherein, adjusting the target exposure time of the hyperspectral imager includes: Obtaining the target spectral radiance corresponding to a specified channel of the hyperspectral imager; Obtaining a preset exposure time list, wherein the exposure time list includes exposure times corresponding to respective spectral radiances; Matching the target spectral radiance through the exposure time list to obtain a target exposure time that matches the target spectral radiance; Wherein, the processing of the collected data to generate processed data includes: Determine the actual number of the optical fiber bundles, and determine the target column data in the collected data according to the actual number; Calculate the data mean corresponding to each other column data in the collected data except the target column data; The target column data in the collected data is replaced by the data mean value to generate the processed data.

2. A real-time cross-sectional water quality detection method based on imaging hyperspectral according to claim 1, characterized in that: The method further comprises: Collecting spectral data by the hyperspectral imager in a specified calibration environment, and determining standard data corresponding to the specified calibration environment; The wavelength drift value between the spectral data and the standard data is determined based on a preset algorithm, and the hyperspectral imager is calibrated according to the wavelength drift value.

3. The real-time cross-sectional water quality detection method based on imaging hyperspectral according to claim 1 is characterized in that: The step of performing calculations in a spectral dimension according to the processed data to generate reflectance data, and inverting water quality parameters according to the reflectance data comprises: Substituting the processed data into a specified algorithm to perform spectral dimension operations to generate the reflectance data; The reflectivity data and the target column data are input into a preset algorithm model to obtain water quality parameters output by the model.

4. The real-time cross-sectional water quality detection method based on imaging hyperspectral according to claim 1 is characterized in that: Generating water quality detection results in real time according to the water quality parameters includes: When a water quality parameter exceeds a corresponding water quality parameter threshold interval, determining that the water quality parameter is an abnormal water quality parameter; When the water quality parameter meets the corresponding water quality parameter threshold interval, determining that the water quality parameter is a normal water quality parameter; The normal water quality parameters and the abnormal water quality parameters are used as the water quality detection results.

5. A real-time cross-sectional water quality detection device based on imaging hyperspectral, characterized in that: include: A response position and exposure time determination module, used to determine the response position of the optical fiber bundle of the hyperspectral imager and determine the exposure time of the hyperspectral imager; A data collection processing module, used for acquiring the collected data of the water surface to be measured based on the response position and the exposure time under no light conditions, and processing the collected data to generate processed data; A reflectivity and water quality parameter determination module, used to perform calculations in the spectral dimension according to the processed data to generate reflectivity data, and invert water quality parameters according to the reflectivity data; A water quality test result determination module, used to generate a water quality test result in real time according to the water quality parameters; The response position and exposure time determination module specifically includes: a response position determination unit, which is used to: place the optical fiber bundle at a specified position, and sequentially use the optical fiber bundle as a target optical fiber bundle, wherein the number of the optical fiber bundle is at least one; determine the light spot position corresponding to the target optical fiber bundle in the hyperspectral imager in a specified test environment; and use the light spot position as the response position; Among them, the response position and exposure time determination module specifically includes: an exposure time determination unit, which is used to: obtain the target spectral radiance corresponding to the specified channel of the hyperspectral imager; obtain a preset exposure time list, wherein the exposure time list includes the exposure time corresponding to each spectral radiance; match the target spectral radiance through the exposure time list to obtain a target exposure time that matches the target spectral radiance; Among them, the acquisition data processing module is specifically used to: determine the actual number of the optical fiber bundles, and determine the target column data in the acquisition data according to the actual number; calculate the data mean corresponding to each other column data in the acquisition data except the target column data; replace the target column data in the acquisition data with the data mean to generate the processed data.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method according to any one of claims 1 to 4 when executed.

Images