Urban river network water system polluted water body identification method and device, storage medium and equipment

Abstract

The invention provides an urban river network water system polluted water body identification method and device, a storage medium and equipment, and the method comprises the steps: obtaining a water system remote sensing image of a target urban river network water system; the water system remote sensing image comprises reflectivity data of a plurality of water body pixels; the reflectivity data comprises reflectivity of water body pixels corresponding to a plurality of wavebands; obtaining reflectivity mean value data of the water system remote sensing image according to the reflectivity data of the plurality of water body pixels; the reflectivity mean value data comprises reflectivity mean values of a plurality of wave bands; and according to the reflectivity data of the plurality of water body pixels and the reflectivity mean value data, obtaining polluted water body identification results of the plurality of water body pixels. The process of obtaining the polluted water body recognition result is simplified, and the efficiency of recognizing the sewage water body can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of polluted water body identification, and specifically to a method, device, storage medium and equipment for identifying polluted water bodies in urban river networks. Background Art

[0002] Identifying urban water pollution is of great significance to urban ecological development. Efficiently and accurately identifying urban water pollution information allows for timely pollution control. In existing technologies, water pollution identification requires inverting and calculating multiple water quality parameters based on remote sensing images of the water system. These parameters are then compared against water environment quality standards to determine whether the water is polluted. However, the process of using water quality parameter inversion models to assist in identifying urban water pollution is complex and time-consuming, and the accuracy of existing water quality parameter inversion models is only around 80%. Consequently, existing technologies, despite this complex and time-consuming process, can only achieve water pollution identification results with an accuracy of around 80%, resulting in low efficiency in identifying urban water pollution. Summary of the Invention

[0003] The purpose of this application is to overcome the shortcomings and deficiencies in the existing technology and to provide a method, device, storage medium and equipment for identifying polluted water bodies in urban river networks, which simplifies the process of obtaining polluted water body identification results and can improve the efficiency of identifying sewage water bodies.

[0004] The first embodiment of the present application discloses a method for identifying polluted water bodies in an urban river network, comprising:

[0005] Acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectance data of a plurality of water body pixels; the reflectance data includes reflectances of a plurality of bands corresponding to the water body pixels;

[0006] Obtaining reflectivity mean data of the water system remote sensing image based on the reflectivity data of the plurality of water body pixels; the reflectivity mean data includes reflectivity mean values ​​of a plurality of bands;

[0007] According to the reflectivity data of the plurality of water body pixels and the reflectivity mean data, a polluted water body identification result of the plurality of water body pixels is obtained.

[0008] The second embodiment of the present application discloses a device for identifying polluted water bodies in an urban river network, comprising:

[0009] A remote sensing image acquisition module is used to acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectivity data of a plurality of water body pixels; the reflectivity data includes reflectivity of a plurality of bands corresponding to the water body pixels;

[0010] A reflectivity mean data acquisition module is used to obtain reflectivity mean data of the water system remote sensing image based on the reflectivity data of the multiple water body pixels; the reflectivity mean data includes reflectivity mean values ​​of multiple bands;

[0011] The polluted water body identification result acquisition module is used to obtain the polluted water body identification results of the multiple water body pixels according to the reflectivity data of the multiple water body pixels and the reflectivity mean data.

[0012] Compared with the related art, the present application first obtains the water system remote sensing image of the target city's river network, and then obtains the reflectivity mean data based on the reflectivity data of multiple water body pixels in the water system remote sensing image, and then obtains the polluted water body identification results of multiple water body pixels based on the reflectivity data of each of the water body pixels and the reflectivity mean data, which simplifies the process of obtaining the polluted water body identification results and can improve the efficiency of identifying urban sewage water bodies.

[0013] In order to more clearly understand the present application, the specific implementation methods of the present application will be described below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of a method for identifying polluted water bodies in an urban river network according to one embodiment of the present application.

[0015] Figure 2 This is a schematic diagram of remote sensing reflections of 46 water body pixels in a method for identifying polluted water bodies in an urban river network according to an embodiment of the present application.

[0016] Figure 3 This is a schematic diagram of the polluted water body identification results of 46 water body pixels of the urban river network polluted water body identification method according to an embodiment of the present application.

[0017] Figure 4 This is an enlarged remote sensing image of a first area of ​​a target city in a method for identifying polluted water bodies in an urban river network according to an embodiment of the present application.

[0018] Figure 5 This is an enlarged view of a remote sensing image of a second area of ​​a target city in a method for identifying polluted water bodies in an urban river network according to an embodiment of the present application.

[0019] Figure 6 This is a schematic diagram of the polluted water body identification results in the first area of ​​a target city of a method for identifying polluted water bodies in an urban river network system according to an embodiment of the present application.

[0020] Figure 7 This is a schematic diagram of the polluted water body identification results in the second area of ​​a target city of a method for identifying polluted water bodies in an urban river network system according to an embodiment of the present application.

[0021] Figure 8 This is a schematic diagram of randomly selected water body pixels in the first area of ​​a target city in a method for identifying polluted water bodies in an urban river network according to an embodiment of the present application.

[0022] Figure 9 This is a schematic diagram of randomly selected water body pixels in the second area of ​​a target city in a method for identifying polluted water bodies in an urban river network according to an embodiment of the present application.

[0023] Figure 10 This is a module connection diagram of a device for identifying polluted water bodies in an urban river network according to one embodiment of the present application.

[0024] 200. Urban river network polluted water body identification device; 201. Remote sensing image acquisition module; 202. Reflectance mean value data acquisition module; 203. Polluted water body identification result acquisition module. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0026] It should be clear that the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the embodiments of the present application.

[0027] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of this application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates other meanings. The words "if" / "if" used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0028] In addition, in this application, unless otherwise specified, "plurality" refers to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0029] See also Figure 1 , which is a flow chart of the method for identifying polluted water bodies in urban river networks according to the first embodiment of the present application. The method for identifying polluted water bodies in urban river networks according to the first embodiment of the present application comprises the following steps:

[0030] S1: Acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectance data of a plurality of water body pixels; the reflectance data includes reflectance of the water body pixels corresponding to a plurality of bands.

[0031] The target city is a densely populated area with administrative boundaries, and the river network is an important part of the urban ecosystem and infrastructure, with multiple functions in flood control and drainage, ecological regulation, and water resources management.

[0032] Water system remote sensing images can be obtained by locating and screening urban remote sensing images of a target city based on its river network distribution. Urban remote sensing images are collected by sensors aboard aircraft or satellite platforms, recording electromagnetic wave information reflected or radiated by ground objects in the target city. Sensor types include visible light sensors and infrared sensors. After obtaining urban remote sensing images, geometric and radiometric corrections are performed to improve the accuracy of the urban remote sensing images, thereby improving the accuracy of the resulting water system remote sensing images.

[0033] S2: Obtaining mean reflectivity data of the water system remote sensing image based on the reflectivity data of the multiple water body pixels; the mean reflectivity data includes mean reflectivity values ​​of multiple bands.

[0034] Among them, the sum of the reflectances of multiple water body pixels corresponding to each band is divided by the number of pixels of the multiple water body pixels to obtain the mean reflectance of each band of the water system remote sensing image.

[0035] S3: Obtaining polluted water body identification results of the multiple water body pixels according to the reflectivity data of the multiple water body pixels and the reflectivity mean data.

[0036] Among them, since the remote sensing reflectivity of polluted water bodies and unpolluted general water bodies is different, specifically, the reflectivity of polluted water bodies in multiple bands is higher than that of general water bodies. Since the target city river network water system includes both polluted water bodies and general water bodies, and the reflectivity mean is obtained based on all water body pixels of the water system remote sensing image of the target city river network water system, that is, the reflectivity mean is obtained based on the reflectivity of polluted water bodies and general water bodies in the target city river network water system. Therefore, according to the reflectivity data of each of the water body pixels and the reflectivity mean data, the water body pixels can be directly and efficiently identified for pollution, thereby obtaining the polluted water body identification results of multiple water body pixels.

[0037] Compared with the related art, the present application first obtains the water system remote sensing image of the target city's river network, and then obtains the reflectivity mean data based on the reflectivity data of multiple water body pixels in the water system remote sensing image, and then obtains the polluted water body identification results of multiple water body pixels based on the reflectivity data of each of the water body pixels and the reflectivity mean data, which simplifies the process of obtaining the polluted water body identification results and can improve the efficiency of identifying urban sewage water bodies.

[0038] In a feasible embodiment, the step S3: obtaining the polluted water body identification results of the plurality of water body pixels based on the reflectivity data of the plurality of water body pixels and the reflectivity mean data, includes:

[0039] S31: Obtaining pixel reflection parameters of each of the water body pixels according to the reflectivity data and the reflectivity mean data.

[0040] The pixel reflection parameter is the ratio of the reflectivity data to the reflectivity mean data, specifically, the ratio of the reflectivity of each band to the reflectivity mean.

[0041] S32: Obtaining a polluted water body identification result for each of the water body pixels according to the reflection parameter of each of the pixel pixels and a preset parameter threshold.

[0042] The parameter threshold is a threshold parameter set by the user, for example, the parameter threshold can be set to 1. By comparing the pixel reflection parameter with the parameter threshold, the polluted water body identification result of the corresponding water pixel can be obtained according to the comparison result.

[0043] In this embodiment, based on the pixel reflection parameter and the parameter threshold, the polluted water body identification result of the corresponding water body pixel can be accurately obtained.

[0044] In a feasible embodiment, the step S31: obtaining the pixel reflection parameter of each of the water body pixels according to the reflectivity data and the reflectivity mean data, includes:

[0045] S311: Obtaining band reflection parameters of the multiple bands of the water body pixel according to the ratio of the reflectivity of the multiple bands of the water body pixel to the mean reflectivity of the corresponding bands.

[0046] The band reflection parameter of band N can be obtained by the following formula:

[0047]

[0048] Among them, P N is the band reflection parameter of band N of water pixel, R N is the band reflectance of band N of water pixel, R' N is the mean reflectivity of band N.

[0049] S312: Obtain pixel reflection parameters of the water body pixel according to the product of the band reflection parameters of multiple bands.

[0050] In this embodiment, the pixel reflection parameters of the water body pixels can be accurately obtained based on the respectively calculated reflection parameters of the multiple bands.

[0051] In a feasible embodiment, the reflectances of the multiple bands include a blue band reflectance, a green band reflectance, a red band reflectance, and a near-infrared band reflectance; the average reflectances of the multiple bands include an average reflectance of the blue band, an average reflectance of the green band, an average reflectance of the red band, and an average reflectance of the near-infrared band. Therefore, step S311 includes the following steps:

[0052] S3111: Obtain a blue band reflection parameter of the water body pixel according to the blue band reflectivity and the average of the blue band reflectivity.

[0053] The blue band reflection parameter of water pixels can be obtained by the following formula:

[0054]

[0055] Among them, P 蓝 is the blue band reflection parameter of water pixel, R 蓝 is the blue band reflectance of water pixels, R' 蓝 is the mean reflectivity of the blue band.

[0056] S3112: Obtain a green band reflection parameter of the water body pixel according to the green band reflectivity and the average of the green band reflectivity.

[0057] The green band reflection parameter of water pixels can be obtained by the following formula:

[0058]

[0059] Among them, P 绿 is the green band reflection parameter of water pixel, R 绿 is the green band reflectance of water pixels, R' 绿 is the mean reflectance of the green band.

[0060] S3113: Obtain a red band reflection parameter of the water body pixel according to the red band reflectivity and the average of the red band reflectivity.

[0061] The red band reflection parameter of water pixels can be obtained by the following formula:

[0062]

[0063] Among them, P 红 is the red band reflection parameter of water pixel, R 红 is the red band reflectance of water pixels, R' 红 is the mean reflectivity of the red band.

[0064] S3114: Obtaining a near-infrared band reflectance parameter of the water body pixel according to the near-infrared band reflectance and the mean of the near-infrared band reflectance.

[0065] The near-infrared band reflectance parameters of water pixels can be obtained by the following formula:

[0066]

[0067] Among them, P 近红 is the near-infrared band reflectance parameter of water pixels, R 近红 is the near-infrared band reflectance of water pixels, R' 近红 is the mean reflectivity in the near-infrared band.

[0068] Step S32 includes: obtaining the pixel reflection parameter according to the blue band reflection parameter, the green band reflection parameter, the red band reflection parameter and the near-infrared band reflection parameter.

[0069] The pixel reflection parameter of the water pixel can be obtained by the following formula:

[0070]

[0071] Among them, P is the pixel reflection parameter of the water pixel.

[0072] In this embodiment, the pixel reflection parameters of the water body pixels can be accurately obtained according to the reflection parameters of the water body pixels corresponding to the blue band, the green band, the red band, and the near-infrared band.

[0073] In a feasible embodiment, the step S32: obtaining the polluted water body identification result of each of the water body pixels according to the reflection parameters of each of the pixel pixels and a preset parameter threshold, includes:

[0074] If the pixel reflection parameter is less than the parameter threshold, the polluted water body identification result of the corresponding water body pixel is a general water body; if the pixel reflection parameter is greater than or equal to the parameter threshold, the polluted water body identification result of the corresponding water body pixel is a polluted water body.

[0075] In this embodiment, the polluted water body identification result can be obtained quickly and accurately according to the pixel reflection parameter and the parameter threshold.

[0076] In a feasible embodiment, the step of S1: obtaining a remote sensing image of a river network of a target city includes:

[0077] S11: Obtain urban remote sensing images and river network distribution maps of the target city.

[0078] River network maps are used to display the types, directions, density, and interconnectedness of rivers, lakes, and canals within the target city area. These maps can be obtained from domestic and international hydrological databases or websites, such as HydroSHEDS (a high-resolution global hydrological dataset), the National Hydrological Database, the Ministry of Water Resources' official website, or the Ministry of Natural Resources' "Tiantutu" platform.

[0079] S12: Obtain the water system remote sensing image according to the urban remote sensing image and the river network distribution map.

[0080] Among them, based on the geographic coordinates and according to the river network area marked in the river network distribution map, the remote sensing image of the river network area can be extracted from the urban remote sensing image to obtain the water system remote sensing image.

[0081] In this embodiment, by combining the urban remote sensing image and the river network distribution map, the water system remote sensing image of the target city can be accurately obtained.

[0082] In a feasible embodiment, the step of S12: obtaining the water system remote sensing image according to the urban remote sensing image and the river network distribution map, includes:

[0083] S121: Obtaining the imaging time of the urban remote sensing image, the meteorological data corresponding to the imaging time, and the generation time of the river network distribution map.

[0084] The imaging time and the image generation time are accurate to a specific date, for example, the image generation time is March 1, 2025, and the imaging time is April 22, 2025. The meteorological data is the meteorological data of the target city, including atmospheric composition data (such as water vapor content, aerosol concentration, and gas distribution such as ozone and carbon dioxide), cloud and fog data (such as cloud amount, cloud type, fog distribution and thickness, etc.), precipitation data, temperature data, humidity data, radiation data, etc.

[0085] S122: Input the urban remote sensing image, the imaging time, the meteorological data, the river network distribution map and the map generation time into the trained water system remote sensing image prediction model to obtain the water system remote sensing image output by the water system remote sensing image prediction model in combination with the time dimension, space dimension and meteorological variables.

[0086] For example, in one embodiment, the water system remote sensing image prediction model includes a variational mode decomposition layer (VMD), a feature vector extraction layer (CNN), a temporal feature extraction layer (LSTM), a feature fusion layer and a SOFTMAX layer; in other embodiments, the water system remote sensing image prediction model can also adopt a deep learning network model with other structures.

[0087] The variational mode decomposition layer is used to perform mode decomposition on the training samples to obtain multiple intrinsic mode functions (IMFs), where each IMF represents a different frequency component of the image; the feature vector layer is used to extract features from the IMF to obtain a one-dimensional feature vector; the time series feature extraction layer is used to extract features of time series correlation from the one-dimensional feature vector to obtain a time series feature vector; the feature fusion layer is used to fuse the time series feature vectors of the same group of training samples to obtain a fused feature vector; the SOFTMAX layer is used to perform dimensionality reduction classification on the fused feature vector.

[0088] The water system remote sensing image prediction model is obtained through the following training:

[0089] Acquire multiple sets of training samples for the target city; each set of training samples includes historical city remote sensing image samples, historical imaging time, corresponding historical meteorological data samples, historical river network distribution map samples, and historical map generation time; wherein the historical city remote sensing image samples are annotated with water system remote sensing images;

[0090] An initial network model is trained based on the multiple training samples to obtain the water system remote sensing image prediction model.

[0091] During the training process, a loss function is constructed based on the dimensionality reduction classification output by the SOFTMAX layer and the water system remote sensing images annotated with historical urban remote sensing image samples, and the model parameters of the water system remote sensing image prediction model are updated in combination with the gradient descent method.

[0092] Since the river network distribution map is image data that is generally updated after a long period of time, there may be a time difference between the imaging time of the urban remote sensing image and the generation time of the river network distribution map. The time difference may be as long as several months or even a year. Under this time difference, the actual river network distribution may change. Moreover, since the urban remote sensing image is also affected by meteorological data, the accuracy of the obtained water system remote sensing image will be reduced due to the influence of multiple temperature factors such as time dimension, spatial dimension and meteorological variables when the water system remote sensing image is directly obtained through geolocation based on the urban remote sensing image and the river network distribution map with this time difference. The water system remote sensing image prediction model obtained by training based on multiple training samples including historical urban remote sensing image samples, historical imaging time samples and historical meteorological data samples corresponding to the historical urban remote sensing image samples, historical river network distribution map samples, and historical map generation time samples corresponding to the historical river network distribution map samples combines the time dimension, spatial dimension and meteorological variables to predict the water system remote sensing image, which can improve the accuracy of the obtained water system remote sensing image.

[0093] In this embodiment, the water system remote sensing image of the target city can be accurately obtained through the trained water system remote sensing image prediction model.

[0094] In order to further illustrate the technical solution of this application, this application also provides the following detection test examples:

[0095] This application obtains polluted water body identification results of multiple water body pixels of the target city river network water system through the above-mentioned urban river network water system polluted water body identification method.

[0096] See also Figure 2-3 According to the results of polluted water body identification, 46 water body pixels (including 23 polluted water body pixels and 23 normal water body pixels) were randomly selected for sampling verification. The reflectance of the selected 46 water body pixels in multiple bands and the reflectance average of the water system remote sensing image of the target city are as follows: Figure 2 As shown in the figure, the pixel reflection parameters of the selected 46 water pixels are as follows Figure 3 shown.

[0097] After water quality sampling and testing at the locations corresponding to the 46 water pixels, the sampling and testing results were consistent with the polluted water identification results for the 46 water pixels. That is, the 23 normal water pixels selected based on the polluted water identification results were actually sampled and tested as unpolluted, while the 23 polluted water pixels selected based on the polluted water identification results were actually sampled and tested as polluted. Therefore, the identification and sampling results for the 46 water pixels are shown in Table 1:

[0098]

[0099] Table 1

[0100] According to the above detection test, the polluted water body identification results obtained by this application through the above urban river network water system polluted water body identification method are that the results of 46 randomly selected water body pixels are completely correct, and the identification accuracy can reach up to 100%.

[0101] In order to prevent the influence of survivor bias, this application also randomly selected different numbers of water body pixels for detection based on multiple polluted water body identification results.

[0102] See also Figure 4-7 In another test, the water system remote sensing image obtained by this application is as follows Figure 4 and Figure 5 As shown (wherein, since the target city is too large, in order to improve the clarity of the water system remote sensing image of the target city, the target city is divided into a first area and a second area, and the water system remote sensing images of the first area and the second area are displayed respectively), the polluted water body identification results of the plurality of water body pixels obtained by the urban river network water system polluted water body identification method of the present application are as follows Figure 6 and Figure 7 As shown, Figure 6 The water body pixels whose polluted water body identification results are polluted water bodies are marked in red, and the water body pixels whose polluted water body identification results are general water bodies are marked in blue.

[0103] See also Figure 8 and 9 ,According to the results of polluted water body identification, 94 water body pixels (including 45 polluted water body pixels and 49 general water body pixels) were randomly selected. Figure 8 and Figure 9 As shown in the figure, 45 polluted water pixels are marked with red crosses and red Xs, and 49 normal water pixels are marked with regular triangles and inverted triangles. Water quality sampling and testing were performed based on the corresponding positions of the 94 water pixels. The results showed that the identification of 44 polluted water pixels was consistent with the sampling and testing results, and the identification of 47 normal water pixels was consistent with the sampling and testing results. The data results are shown in Table 2:

[0104]

[0105]

[0106] Table 2

[0107] According to the above test, the accuracy of the polluted water body identification result obtained by the present application through the above urban river network water system polluted water body identification method in another test reached (44+47) / 94=96.8%.

[0108] To sum up, this application does not require the known (extraction, cognition, understanding) reflectivity characteristics of polluted water pixels or general water pixels, simplifies the polluted water identification process, does not require the water quality parameter remote sensing inversion calculation steps, eliminates the interference of error propagation in the water quality parameter remote sensing inversion process, and can efficiently and accurately identify polluted water bodies.

[0109] See also Figure 10 The second embodiment of the present application provides a device for identifying polluted water bodies in an urban river network, comprising:

[0110] A remote sensing image acquisition module is used to acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectivity data of a plurality of water body pixels; the reflectivity data includes reflectivity of a plurality of bands corresponding to the water body pixels;

[0111] A reflectivity mean data acquisition module is used to obtain reflectivity mean data of the water system remote sensing image based on the reflectivity data of the multiple water body pixels; the reflectivity mean data includes reflectivity mean values ​​of multiple bands;

[0112] The polluted water body identification result acquisition module is used to obtain the polluted water body identification results of the multiple water body pixels according to the reflectivity data of the multiple water body pixels and the reflectivity mean data.

[0113] It should be noted that the urban river network water system polluted water body identification device provided in the second embodiment of this application only uses the division of the above-mentioned functional modules as an example when executing the urban river network water system polluted water body identification method. In actual application, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the urban river network water system polluted water body identification device provided in the second embodiment of this application and the urban river network water system polluted water body identification method of the first embodiment of this application are based on the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0114] A third embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for identifying polluted water bodies in urban river networks as described above.

[0115] The fourth embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable by the processor. When the processor executes the computer program, the steps of the method for identifying polluted water bodies in urban river networks are implemented as described above.

[0116] The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. Those of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0117] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0118] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the function selected in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 function selected in a box or multiple boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 steps for the function selected in a box or multiple boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0124] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for identifying polluted water bodies in urban river networks, characterized in that: include: Acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectance data of a plurality of water body pixels; the reflectance data includes reflectances of a plurality of bands corresponding to the water body pixels; Obtaining reflectivity mean data of the water system remote sensing image based on the reflectivity data of the plurality of water body pixels; the reflectivity mean data includes reflectivity mean values ​​of a plurality of bands; According to the reflectivity data of the plurality of water body pixels and the reflectivity mean data, a polluted water body identification result of the plurality of water body pixels is obtained.

2. The method for identifying polluted water bodies in urban river networks according to claim 1, characterized in that: The step of obtaining the polluted water body identification results of the plurality of water body pixels based on the reflectivity data of the plurality of water body pixels and the reflectivity mean data comprises: Obtaining pixel reflection parameters of each water body pixel according to the reflectivity data and the reflectivity mean data; According to the reflection parameters of each pixel and the preset parameter threshold, the polluted water body identification result of each water body pixel is obtained.

3. The method for identifying polluted water bodies in urban river networks according to claim 2, characterized in that: The step of obtaining the polluted water body identification result of each water body pixel according to the reflection parameter of each pixel and the preset parameter threshold comprises: If the pixel reflection parameter is less than the parameter threshold, the polluted water body identification result of the corresponding water body pixel is a general water body; if the pixel reflection parameter is greater than or equal to the parameter threshold, the polluted water body identification result of the corresponding water body pixel is a polluted water body.

4. The method for identifying polluted water bodies in urban river networks according to claim 2, characterized in that: The step of obtaining the pixel reflection parameter of each of the water body pixels according to the reflectivity data and the reflectivity mean data comprises: Obtaining band reflection parameters of the multiple bands of the water body pixel according to the ratio of the reflectivity of the multiple bands of the water body pixel to the mean value of the reflectivity of the corresponding bands; The pixel reflection parameter of the water body pixel is obtained according to the product of the band reflection parameters of multiple bands.

5. The method for identifying polluted water bodies in urban river networks according to any one of claims 1 to 4, characterized in that: The reflectivities of multiple bands include the reflectivity of the blue band, the reflectivity of the green band, the reflectivity of the red band, and the reflectivity of the near-infrared band; the average reflectivities of multiple bands include the average reflectivity of the blue band, the average reflectivity of the green band, the average reflectivity of the red band, and the average reflectivity of the near-infrared band.

6. The method for identifying polluted water bodies in urban river networks according to claim 1, characterized in that: The step of obtaining a remote sensing image of a river network in a target city includes: Obtain urban remote sensing images and river network distribution maps of the target city; The water system remote sensing image is obtained based on the urban remote sensing image and the river network distribution map.

7. The method for identifying polluted water bodies in urban river networks according to claim 6, characterized in that: The step of obtaining the water system remote sensing image based on the urban remote sensing image and the river network distribution map includes: Obtaining the imaging time of the urban remote sensing image, the meteorological data corresponding to the imaging time, and the generation time of the river network distribution map; The urban remote sensing image, the imaging time, the meteorological data, the river network distribution map and the map generation time are input into the trained water system remote sensing image detection model to obtain the water system remote sensing image output by the water system remote sensing image detection model in combination with the time dimension, spatial dimension and meteorological variables.

8. A device for identifying polluted water bodies in urban river networks, characterized in that: include: A remote sensing image acquisition module is used to acquire a water system remote sensing image of a river network in a target city; the water system remote sensing image includes reflectivity data of a plurality of water body pixels; the reflectivity data includes reflectivity of a plurality of bands corresponding to the water body pixels; A reflectivity mean data acquisition module is used to obtain reflectivity mean data of the water system remote sensing image based on the reflectivity data of the multiple water body pixels; the reflectivity mean data includes reflectivity mean values ​​of multiple bands; The polluted water body identification result acquisition module is used to obtain the polluted water body identification results of the multiple water body pixels according to the reflectivity data of the multiple water body pixels and the reflectivity mean data.

9. A computer storage medium, wherein the computer-readable storage medium stores a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying polluted water bodies in urban river networks as described in any one of claims 1 to 6 are implemented.

10. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable by the processor, wherein when the processor executes the computer program, the steps of the method for identifying polluted water bodies in urban river networks as described in any one of claims 1 to 6 are implemented.

Images