Dross area calculation method, device and equipment, and storage medium

Abstract

The application discloses a scum area calculation method, device and equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring panoramic image data of a reservoir area of a hydropower station; determining a scum area of the reservoir area of the hydropower station according to the panoramic image data; and determining the area of the scum area. Through the above method, the automatic calculation method for the scum area of the reservoir area of the hydropower station based on images realizes the area calculation problem of a large-scale object at a long distance, reduces the labor cost, and improves the work efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a floating sludge area calculation method, device, equipment and storage medium. BACKGROUND

[0002] At present, due to the slow flow speed of the downstream of the river channel, the water power station reservoir area is beneficial to the growth of a large number of aquatic plants, and the plants are connected with each other on the surface of the reservoir area to form a floating sludge area with a large area and an irregular shape. The reservoir area receives water flow from the upstream tributary river channel, and various floating objects and garbage carried in the river channel are blocked by the dam and gathered together to form a floating sludge gathering area in the reservoir area. Aquatic plants and floating objects are often the main components of the floating sludge in the reservoir area. The size of the floating sludge area in the reservoir area directly reflects the degree of aggregation of the floating sludge. If the floating sludge aggregates to a certain degree, it will enter the water turbine part of the generator through the water inlet pipe of the generator, causing damage to the power generation equipment. The accumulation of floating sludge will affect the water inflow of the generator, causing the power generation of the generator set to be unstable, and reducing the power generation quality of the power station. The floating sludge in the reservoir area is large in area and irregular in shape, and the measurement of the area is very difficult. Only the experience of the staff can be used for estimation, resulting in that the production scheduling of the hydropower station cannot accurately formulate the floating sludge cleaning plan. In summary, the floating sludge area in the hydropower station reservoir area is currently roughly estimated by manual experience in the cleaning process of the floating sludge, and the automatic and accurate measurement of the floating sludge area in the reservoir area has not been realized.

[0003] At present, the demand for electric power resources in social production and life puts forward higher requirements. While increasing the amount of power generation, it is necessary to ensure the stability of power supply quality. The accumulation of floating sludge in the reservoir area of the hydropower station will affect the stability of the power generation quality of the hydropower station, and is also a potential threat to the generator accident of the hydropower station. In the daily maintenance of the reservoir area, the area of the floating sludge in the reservoir area is mainly estimated by the experience of the staff. This method is greatly affected by human subjective factors, and the error of the estimated area is large, which is not conducive to guiding the on-site maintenance and cleaning of the floating sludge.

[0004] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a floating sludge area calculation method, device, equipment and storage medium, which aims to solve the technical problem of inaccurate manual estimation of the floating sludge area in the prior art.

[0006] In order to achieve the above-mentioned purpose, the present application provides a floating sludge area calculation method, which comprises the following steps:

[0007] Obtain panoramic image data of the reservoir area of the hydropower station;

[0008] determine a scum area of the reservoir area of the hydropower station according to the panoramic image data;

[0009] determine an area of the scum area.

[0010] Optionally, the acquiring panoramic image data of the reservoir area of the hydropower station comprises:

[0011] acquiring a plurality of image data of the reservoir area of the hydropower station;

[0012] acquiring longitude and latitude information of the plurality of image data;

[0013] generating panoramic image data according to the plurality of image data and the longitude and latitude information.

[0014] Optionally, the determining the scum area of the reservoir area of the hydropower station according to the panoramic image data comprises:

[0015] performing down-sampling processing on the panoramic image data to obtain down-sampled image data;

[0016] performing gradient calculation on the down-sampled image data to obtain gradient image data;

[0017] determining the scum area of the reservoir area of the hydropower station according to the gradient image data.

[0018] Optionally, the determining the scum area of the reservoir area of the hydropower station according to the gradient image data comprises:

[0019] determining a suspected scum area of the reservoir area of the hydropower station according to the gradient image data;

[0020] determining a gray level histogram of the suspected scum area;

[0021] determining a color feature vector of the suspected scum area according to the gray level histogram;

[0022] determining the scum area of the reservoir area of the hydropower station according to the color feature vector.

[0023] Optionally, the determining the scum area of the reservoir area of the hydropower station according to the color feature vector comprises:

[0024] inputting the color feature vector into a preset algorithm model;

[0025] determining a scum area in the suspected scum area based on the color feature vector according to the preset algorithm model and a corresponding algorithm sample library.

[0026] Optionally, the determining the area of the scum area comprises:

[0027] determining pixel point coordinates of the scum area in the panoramic image data.

[0028] determine the circumscribed rectangle image coordinates of the scum region according to the pixel point coordinates;

[0029] determine the area of the scum region according to the circumscribed rectangle image coordinates.

[0030] Optionally, the method further comprises: converting the circumscribed rectangle image coordinates into first preset coordinates;

[0031] converting the first preset coordinates into second preset coordinates;

[0032] determining the area of the scum region according to the second preset coordinates.

[0033] In addition, to achieve the above object, the present application further provides a scum region area calculation device, which comprises:

[0034] an acquisition module configured to acquire panoramic image data of a reservoir area of a hydropower station;

[0035] a determination module configured to determine a scum region of the reservoir area of the hydropower station according to the panoramic image data; and a calculation module configured to determine an area of the scum region.

[0036] In addition, to achieve the above object, the present application further provides a scum region area calculation device, which comprises: a memory, a processor, and a scum region area calculation program stored in the memory and executable on the processor, wherein the scum region area calculation program is configured to implement the steps of the scum region area calculation method as described above.

[0037] In addition, to achieve the above object, the present application further provides a storage medium, wherein the storage medium stores a scum region area calculation program, and the scum region area calculation program, when executed by a processor, implements the steps of the scum region area calculation method as described above.

[0038] The present application acquires panoramic image data of a reservoir area of a hydropower station, determines a scum region of the reservoir area of the hydropower station according to the panoramic image data, and determines an area of the scum region. In this way, the image-based automatic calculation method for the scum area of the reservoir area of the hydropower station solves the problem of calculating the area of a large-scale object at a long distance, reduces the labor cost, and improves the work efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a structural schematic diagram of a scum region area calculation device of a hardware running environment related to the embodiment scheme of the present application;

[0040] Figure 2 Flowchart of the first embodiment of the dross area calculation method of the present application;

[0041] Figure 3 Panoramic gradient map of the library area of the first embodiment of the dross area calculation method of the present application;

[0042] Figure 4 Flowchart of the second embodiment of the dross area calculation method of the present application at step S23;

[0043] Figure 5 Principle diagram of the composition of the dross area histogram feature group of the first embodiment of the dross area calculation method of the present application;

[0044] Figure 6 Flowchart of the third embodiment of the dross area calculation method of the present application at step S30;

[0045] Figure 7 Dross area map of the first embodiment of the dross area calculation method of the present application;

[0046] Figure 8 Overall flowchart of the first embodiment of the dross area calculation method of the present application;

[0047] Figure 9 Structure block diagram of the first embodiment of the dross area calculation device of the present application.

[0048] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0050] Reference Figure 1 , Figure 1 Structure diagram of the dross area calculation device of the hardware running environment involved in the embodiment scheme of the present application.

[0051] As Figure 1As shown in the figure, the scum area calculation device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM) such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0052] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the scum area calculation device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0053] As Figure 1 As shown in the figure, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a scum area calculation program.

[0054] In Figure 1 In the scum area calculation device shown in the figure, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the scum area calculation device can be arranged in the scum area calculation device, and the scum area calculation device calls the scum area calculation program stored in the memory 1005 through the processor 1001, and executes the scum area calculation method provided by the embodiment of the present application.

[0055] The embodiment of the present application provides a scum area calculation method, which refers to Figure 2 , Figure 2 is a flowchart of a first embodiment of a scum area calculation method of the present application.

[0056] In this embodiment, the scum area calculation method includes the following steps:

[0057] Step S10: Obtain panoramic image data of the reservoir area of the hydropower station.

[0058] It should be noted that the execution subject of the embodiment is a scum area calculation device, which can be a smart phone, a tablet computer, a notebook computer, a server, an embedded device, or other devices with computing functions.

[0059] It should be understood that image data is widely used in various industries due to its non-contact, long-distance, rich information, and low hardware cost. In this embodiment, the visible light imaging device carried by the inspection unmanned aerial vehicle of the reservoir area of the hydropower station is used to obtain image data in real time on the flight route. The camera shooting angle and shooting speed can be controlled by a gimbal, and the panoramic image data can be transmitted back to the base station for analysis using the image transmission device carried by the unmanned aerial vehicle, or the panoramic image data can be analyzed in real time by the embedded device on the unmanned aerial vehicle.

[0060] Further, the obtaining of the panoramic image data of the reservoir area of the hydropower station comprises: obtaining a plurality of image data of the reservoir area of the hydropower station; obtaining the latitude and longitude information of the plurality of image data; and generating panoramic image data according to the plurality of image data and the latitude and longitude information.

[0061] It can be understood that due to the limited resolution of the imaging device carried by the inspection unmanned aerial vehicle of the hydropower station, the entire panoramic image of the reservoir area of the hydropower station cannot be obtained on one image, and the calculation of the scum area of the reservoir area is a global scale analysis concept, so the image stitching technology is needed to obtain the panoramic image data of the reservoir area of the hydropower station.

[0062] It can be understood that the unmanned aerial vehicle is also equipped with a positioning device, so that the latitude and longitude information of the image is recorded when the image is taken. Therefore, when the plurality of image data is spliced into one panoramic image data, the latitude and longitude information of all the image data needs to be summarized to obtain one panoramic image data with complete latitude and longitude information.

[0063] Step S20: Determine the scum area of the reservoir area of the hydropower station according to the panoramic image data.

[0064] In a specific implementation, since the panoramic image of the reservoir area of the hydropower station has been taken, the non-water area in the water area can be directly identified and recognized as the scum area, but this method has low accuracy. Therefore, the determination of the scum area of the reservoir area of the hydropower station according to the panoramic image data comprises:

[0065] Step S21: Perform down-sampling processing on the panoramic image data to obtain down-sampled image data;

[0066] Understandably, based on the observation and analysis of multiple panoramic images of the hydropower station area, the following characteristics were found in the scum area of ​​the hydropower station reservoir: 1. The color distribution within the scum area is consistent, and the grayscale value of the pixels within the area varies little; 2. The color characteristics of the scum area are biased towards green, and the grayscale value of the pixels within the area shows that the G channel value is greater than the R(B) channel value; 3. The outline of the scum area is irregular and its position is relatively random and not fixed.

[0067] In practical implementation, since panoramic images typically have resolutions exceeding 100 million pixels, processing such image data requires high-performance equipment and does not meet real-time processing requirements. To overcome the contradiction between hardware computing performance and algorithm complexity, downsampling processing is necessary for high-resolution panoramic images. During image downsampling, a mean template is used to perform a convolution operation on the original image (i.e., the panoramic image data) to obtain downsampled image data. This approach achieves both image downsampling and image smoothing. The calculation formula is shown below, where S represents the input original image, I represents the output result of the convolution operation, T represents the convolution template, and x and y represent the horizontal and vertical coordinates of the pixel, respectively.

[0068] I(x,y)=S(x,y)*T(x,y) Formula 1;

[0069]

[0070] Step S22: Perform gradient calculation on the downsampled image data to obtain gradient image data;

[0071] Step S23: Determine the scum area of ​​the hydropower station reservoir based on the gradient image data.

[0072] It should be noted that, after analyzing the characteristics of the image sample data of the scum area, it was found that the scum area in the image exhibits a consistent pixel value distribution, meaning that the image gradient value response within this area is relatively small. In this embodiment, the Sobel operator is used to calculate the gradient of the downsampled image data, thereby obtaining gradient image data. Thresholding is used to extract points with small gradient changes in the downsampled image data; these points are distributed within the scum-like areas of the downsampled image data. The gradient calculation formula is as follows: where g(x) is the gradient in the x-direction, g(y) is the gradient in the y-direction, and G is the gradient of the image at point (x,y). After downsampling the panoramic image of the reservoir area, the extracted gradient image is as follows: Figure 3 As shown, the white area represents a uniform grayscale scum region with a small gradient.

[0073]

[0074]

[0075] Step S30: determining the area of the scum region.

[0076] It can be understood that, since the panoramic image data contains longitude and latitude information, each pixel point in the panoramic image data corresponds to a fixed area, and the area of the scum region can be calculated by determining the number of pixel points occupied by the scum region in the panoramic image data.

[0077] The embodiment obtains panoramic image data of a reservoir area of a hydropower station, determines a scum region of the reservoir area of the hydropower station according to the panoramic image data, and determines the area of the scum region. Through the above manner, the image-based automatic calculation method for the scum area of the reservoir area of the hydropower station realizes the calculation of the area of a large-scale object at a long distance, reduces the labor cost, and improves the work efficiency.

[0078] Reference Figure 4 , Figure 4 FIG. 2 is a flowchart of a second embodiment of a scum region area calculation method according to the present application. Based on the first embodiment, the scum region area calculation method of the present embodiment further includes the following steps in step S23.

[0079] Step S231: determining a suspected scum region of the reservoir area of the hydropower station according to the gradient image data. It should be noted that, since the gradient image data cannot accurately determine the scum region, the white region in the gradient image is determined as the suspected scum region, and the suspected scum region needs to be further analyzed. Step S232: determining a gray level histogram of the suspected scum region.

[0080] In a specific implementation, the color feature of the scum region is biased towards green, and the gray value of the pixel point in the region is represented as G channel value greater than R(B) channel value. In the present embodiment, the gray level histogram of the image is used to describe the color feature of the scum region.

[0081] Step S233: determining a color feature vector of the suspected scum region according to the gray level histogram. It can be understood that, the R, G, and B three gray level histograms of the suspected scum region (the gray level histogram of each channel is 256 dimensions) are concatenated together to form a 786-dimensional feature vector, as shown in FIG. 3. Figure 5

[0082] Step S234: determining the scum region of the reservoir area of the hydropower station according to the color feature vector.

[0083] Further, the determination of the scum region of the reservoir area of the hydropower station according to the color feature vector includes: inputting the color feature vector into a preset algorithm model; and determining the scum region in the suspected scum region based on the color feature vector according to the preset algorithm model and a corresponding algorithm sample library. ​

[0084] It should be noted that the suspected scum area extracted in the gray scale histogram is divided into two categories: scum area and non-scum area, and the scum recognition problem is attributed to a binary classification problem. The time complexity and space complexity of the scum area recognition algorithm are balanced; in addition, the scum recognition scene of the hydropower station is relatively fixed, and the fluctuation range of the reservoir area feature is small. The preset algorithm model in the embodiment is a K-nearest neighbor algorithm, the color feature vector to be classified is input into the preset algorithm model, and each feature in the color feature vector is calculated and compared with the corresponding feature of the data in the algorithm sample library. The classification label of the most similar data (nearest neighbor) in the sample set is extracted, so as to distinguish the scum area in the suspected scum area.

[0085] The embodiment determines the suspected scum area of the reservoir area of the hydropower station according to the gradient image data; determines the gray scale histogram of the suspected scum area; determines the color feature vector of the suspected scum area according to the gray scale histogram; and determines the scum area of the reservoir area of the hydropower station according to the color feature vector. The scum area and the non-scum area can be more accurately distinguished, so as to further improve the calculation accuracy of the scum area.

[0086] Reference Figure 6 , Figure 6 The flowchart of the third embodiment of the scum area calculation method of the application is shown. Based on the first embodiment, the scum area calculation method of the embodiment further includes the following steps in the step S30.

[0087] Step S31: determining the pixel point coordinates of the scum area in the panoramic image data.

[0088] In a specific implementation, since the reservoir image obtained by the unmanned aerial vehicle imaging device used in the embodiment has latitude and longitude information, the panoramic image data with geographical coordinates can be obtained by combining the puzzle algorithm. After the irregular scum area of the reservoir shape is recognized by the image processing technology (for example, the white area in the rectangular frame shown in the figure), the area of the scum area is described by the pixel points in the image, so that the pixel point coordinates of the scum area in the panoramic image data can be determined. Figure 7

[0089] Step S32: determining the circumscribed rectangular image coordinates of the scum area according to the pixel point coordinates.

[0090] It can be understood that the circumscribed rectangle is made for the scum area, and the coordinates of the circumscribed rectangle in the image, that is, the circumscribed rectangular image coordinates, are determined.

[0091] Step S33: determining the area of the scum area according to the circumscribed rectangular image coordinates.

[0092] ​It should be noted that the area of the circumscribed rectangle in the image is denoted as A, and the unit is pixel number, and the calculation method is as follows: wherein x1, y1 are the upper left point coordinates of the circumscribed rectangle of the scum region in the image, and x2, y2 are the lower right point coordinates of the circumscribed rectangle of the scum region in the image.

[0093] A = (y2-y1)*(x2-x1) Formula five;

[0094] Further, the area of the scum region is determined according to the circumscribed rectangular image coordinates, comprising: converting the circumscribed rectangular image coordinates into first preset coordinates; converting the first preset coordinates into second preset coordinates; determining the area of the scum region according to the second preset coordinates.

[0095] It should be understood that the upper left point and the lower right point of the circumscribed rectangle of the scum region rectangular frame are converted into wgs84 coordinates (i.e. first preset coordinates), and the wgs84 coordinates are converted into web Mercator coordinates (i.e. second preset coordinates, coordinate system in meters), and the conversion code is as follows:

[0096] Image coordinates to wgs84 coordinates code:

[0097]

[0098]

[0099]

[0100] The conversion relationship of image coordinates to web Mercator coordinates is represented by f, and the conversion mode is given by the above code, as shown in formula 6, wherein x, y are image coordinates, wx, wy are web Mercator coordinates, and the unit is meter. Wherein wA is the area of the circumscribed rectangle of the scum region in the web Mercator coordinate system, and the unit is square meter, and the calculation formula is as shown in formula 7. The area of the scum region in the web Mercator coordinate system is represented as wA0, and the calculation formula is as shown in formula 8.

[0101] (wx,wy)=f(x,y) Formula 6;

[0102] wA=(wy2-wy1)*(wx2-wx1) Formula 7;

[0103] wA0=A0 / A*wA Formula 8;

[0104] The overall flowchart of the embodiment is shown in Figure 8 .

[0105] The embodiment determines pixel point coordinates of the scum region in the panoramic image data, determines circumscribed rectangular image coordinates of the scum region according to the pixel point coordinates, and determines the area of the scum region according to the circumscribed rectangular image coordinates. In this way, the area of an irregular scum region can be accurately calculated.

[0106] In addition, the embodiment of the present application further provides a storage medium, wherein the storage medium stores a scum region area calculation program, and the scum region area calculation program is executed by a processor to implement the steps of the scum region area calculation method.

[0107] Since the storage medium adopts all the technical solutions of the above embodiments, it at least has all the beneficial effects brought by the technical solutions of the above embodiments, which will not be repeated here.

[0108] Reference Figure 9 , Figure 9 is a structural block diagram of a first embodiment of the scum region area calculation device of the present application. As shown in Figure 9 , the scum region area calculation device provided by the embodiment of the present application comprises:

[0109] The acquisition module 10 is configured to acquire panoramic image data of a reservoir area of a hydropower station.

[0110] The determination module 20 is configured to determine a scum region of the reservoir area of the hydropower station according to the panoramic image data.

[0111] In an embodiment, the acquisition module 10 is further configured to acquire a plurality of image data of the reservoir area of the hydropower station.

[0112] The latitude and longitude information of the plurality of image data is acquired.

[0113] The panoramic image data is generated according to the plurality of image data and the latitude and longitude information.

[0114] In an embodiment, the determination module 20 is further configured to perform down-sampling processing on the panoramic image data to obtain down-sampled image data.

[0115] Gradient calculation is performed on the down-sampled image data to obtain gradient image data.

[0116] The scum region of the reservoir area of the hydropower station is determined according to the gradient image data.

[0117] In an embodiment, the determination module 20 is further configured to determine a suspected scum region of the reservoir area of the hydropower station according to the gradient image data.

[0118] The gray level histogram of the suspected scum region is determined.

[0119] determine a color feature vector of the suspected scum region according to the gray histogram;

[0120] determine a scum region of the reservoir area of the hydropower station according to the color feature vector.

[0121] In an embodiment, the determining module 20 is further configured to input the color feature vector into a preset algorithm model;

[0122] determine the scum region in the suspected scum region based on the color feature vector according to the preset algorithm model and a corresponding algorithm sample library.

[0123] In an embodiment, the calculating module 30 is further configured to determine a pixel point coordinate of the scum region in the panoramic image data;

[0124] determine a circumscribed rectangle image coordinate of the scum region according to the pixel point coordinate;

[0125] determine an area of the scum region according to the circumscribed rectangle image coordinate.

[0126] In an embodiment, the calculating module 30 is further configured to convert the circumscribed rectangle image coordinate into a first preset coordinate;

[0127] convert the first preset coordinate into a second preset coordinate;

[0128] determine the area of the scum region according to the second preset coordinate.

[0129] It should be understood that the above is only for illustration, and does not constitute any limitation on the technical solutions of the present application. In specific applications, those skilled in the art can set up as needed, and the present application does not limit this.

[0130] The embodiment obtains panoramic image data of a reservoir area of a hydropower station; determines a scum region of the reservoir area of the hydropower station according to the panoramic image data; and determines an area of the scum region. In this way, the image-based automatic calculation method for the scum area of the reservoir area of the hydropower station realizes the calculation of the area of a large-scale object at a long distance, reduces the labor cost, and improves the work efficiency.

[0131] Specifically, the embodiment of the present application realizes the automatic and accurate measurement of long-distance large-scale objects by using visible light image data based on unmanned aerial vehicle aerial photography. The method proposed in the present application uses a visible light band imaging device to obtain image data to automatically calculate the floating sludge area of the reservoir area of a hydropower station, avoiding the use of a manual measurement method which is expensive, inefficient and has large errors. The present application uses an image-based automatic calculation method for the floating sludge area of the reservoir area of a hydropower station to realize the area calculation problem of long-distance large-scale objects, which reduces the labor cost and improves the work efficiency.

[0132] It should be noted that the above-described workflow is only illustrative and does not limit the scope of protection of the present application. In actual application, a person skilled in the art can select part or all of them according to actual needs to achieve the purpose of the embodiment scheme, which is not limited here.

[0133] In addition, technical details not described in detail in the present embodiment can be referred to the floating sludge area calculation method provided by any embodiment of the present application, which will not be described here.

[0134] In addition, it should be noted that in this paper, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system 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 system. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or system including the element.

[0135] The above-mentioned embodiment number of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0136] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a read only memory (Read Only Memory, ROM) / RAM, a magnetic disk, an optical disk), and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

[0137] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application, and any equivalent structure or equivalent process conversion, or direct or indirect application in other related technical fields, which are made by using the content of the present application specification and drawings, are also included in the patent protection scope of the present application.

Claims

1. A dross area calculation method characterized by comprising: The scum area calculation method comprises: Obtaining panoramic image data of a reservoir area of a hydropower station; Determining a scum area of the reservoir area of the hydropower station according to the panoramic image data; Determining an area of the scum area; The method comprises: Down-sampling the panoramic image data to obtain down-sampled image data; Calculating gradients of the down-sampled image data to obtain gradient image data; Determining the scum area of the reservoir area of the hydropower station according to the gradient image data; The method comprises: Determining a suspected scum area of the reservoir area of the hydropower station according to the gradient image data; Determining a grayscale histogram of the suspected scum area; Determining a color feature vector of the suspected scum area according to the grayscale histogram; Determining the scum area of the reservoir area of the hydropower station according to the color feature vector; The method comprises: Inputting the color feature vector into a preset algorithm model; Determining the scum area in the suspected scum area according to the color feature vector based on the preset algorithm model and a corresponding algorithm sample library.

2. The method of claim 1, wherein, The method comprises: Obtaining multiple image data of the reservoir area of the hydropower station; Obtaining latitude and longitude information of the multiple image data; Generating panoramic image data according to the multiple image data and the latitude and longitude information.

3. The method of claim 1, wherein, The method comprises: Determining pixel point coordinates of the scum area in the panoramic image data; Determining circumscribed rectangular image coordinates of the scum area according to the pixel point coordinates; Determining the area of the scum area according to the circumscribed rectangular image coordinates.

4. The method of claim 3, wherein, The method comprises: Converting the circumscribed rectangular image coordinates into first preset coordinates; Converting the first preset coordinates into second preset coordinates; Determining the area of the scum area according to the second preset coordinates.

5. A scum area area calculation device characterized by comprising: The scum area calculation device comprises: An obtaining module, configured to obtain panoramic image data of a reservoir area of a hydropower station; A determining module, configured to determine a scum area of the reservoir area of the hydropower station according to the panoramic image data; A calculating module, configured to determine an area of the scum area; The method comprises: Down-sampling the panoramic image data to obtain down-sampled image data; Calculating gradients of the down-sampled image data to obtain gradient image data; Determining the scum area of the reservoir area of the hydropower station according to the gradient image data; The method comprises: Determining a suspected scum area of the reservoir area of the hydropower station according to the gradient image data; Determining a grayscale histogram of the suspected scum area; Determining a color feature vector of the suspected scum area according to the grayscale histogram; Determining the scum area of the reservoir area of the hydropower station according to the color feature vector; The determining the scum area of the hydropower station reservoir according to the color feature vector comprises: inputting the color feature vector into a preset algorithm model; determining the scum area in the suspected scum area based on the color feature vector according to the preset algorithm model and a corresponding algorithm sample library.

6. A scum area area calculation device characterized by comprising: The device comprises a memory, a processor, and a scum area area calculation program stored on the memory and executable on the processor, and the scum area area calculation program is configured to implement the scum area area calculation method according to any one of claims 1 to 4.

7. A storage medium, characterized by The storage medium stores a scum area area calculation program, and the scum area area calculation program is executed by the processor to implement the scum area area calculation method according to any one of claims 1 to 4.

Images