Urban ponding monitoring method and device based on fusion of monitoring data and electronic water gauge data

Abstract

The invention provides a monitoring data and electronic water gauge data fused urban ponding monitoring method and device, and the method comprises the following steps: obtaining the current reading of an electronic water gauge, and obtaining a plurality of image sequences comprising continuous to-be-monitored images of an area where the current electronic water gauge is located through a monitoring camera, inputting the image sequence into a pre-trained ponding segmentation model to obtain a ponding area; obtaining a water surface fluctuation factor based on the image sequence, wherein the water surface fluctuation factor represents the water surface fluctuation condition of the ponding area; and correcting the current reading of the electronic water gauge by using the water surface fluctuation factor to obtain the accumulated water depth. According to the scheme, the ponding area is accurately identified through the ponding segmentation model, the water surface fluctuation factor is calculated by combining adjacent image pixel change, the water gauge reading standard deviation and the like to correct the water gauge reading, the monitoring real-time performance and stability are enhanced, the environmental interference and the equipment error influence are reduced, and rapid and accurate urban ponding monitoring is achieved.

Description

Technical Field

[0001] This application relates to the field of waterlogging monitoring, and in particular, to a method and device for urban waterlogging monitoring that integrates monitoring data and electronic water gauge data. Background Art

[0002] With the intensification of global climate change, extreme precipitation events occur frequently, and the problem of urban waterlogging has become increasingly serious, bringing huge challenges to urban transportation, public safety, and infrastructure. Therefore, waterlogging monitoring technology has received extensive attention.

[0003] Among the currently common urban waterlogging monitoring methods, the traditional manual inspection method relies on on-site visual observation and recording of waterlogging by management personnel. Although it is intuitive, it has problems such as poor real-time performance, inability to provide continuous monitoring data, lack of accurate quantification indicators due to subjective judgment, high labor costs, and difficulty in implementation under adverse weather conditions; the electronic water gauge monitoring method is based on a water level sensor installed at waterlogging-prone points to measure the water level in real time to judge the waterlogging situation, but it is easily affected by factors such as sludge deposition, floating object occlusion, and sensor aging, resulting in unstable readings, and the fixed installation position cannot cover the entire waterlogging area and cannot provide spatial distribution information of the waterlogging range; the video monitoring waterlogging identification method installs a video monitoring system at waterlogging-prone points and uses image processing or deep learning algorithms to identify water body areas from the video. However, it can only identify the presence and range of water bodies and cannot directly measure the water depth. The identification accuracy is uncertain due to environmental factors such as light, reflection, and occlusion, and it is difficult to distinguish subtle changes in waterlogging depth only by visual information; the remote sensing and unmanned aerial vehicle monitoring method uses multi-spectral or radar remote sensing technology to detect surface waterlogging conditions, but the time resolution of remote sensing satellites is limited and it is difficult to monitor at high frequencies. Unmanned aerial vehicles are restricted by meteorological conditions, difficult to operate in strong precipitation environments, and have high costs and are difficult to conduct long-term continuous monitoring over a large area.

[0004] In summary, how to quickly and accurately monitor urban waterlogging is an urgent problem to be solved in the prior art. Summary of the Invention

[0005] The embodiments of this application provide a method and device for urban waterlogging monitoring that integrates monitoring data and electronic water gauge data. By accurately identifying the waterlogging area through a waterlogging segmentation model, combining factors such as adjacent image pixel changes and the standard deviation of water gauge readings to calculate the water surface fluctuation factor to correct the water gauge readings, the real-time performance and stability of monitoring are enhanced, the influence of environmental interference and equipment errors is reduced, and rapid and accurate urban waterlogging monitoring is achieved.

[0006] In a first aspect, the embodiments of this application provide a method for urban waterlogging monitoring that integrates monitoring data and electronic water gauge data, and the method includes: Obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence of multiple consecutive images to be monitored including the area where the current electronic water gauge is located, and input the image sequence into a pre-trained water accumulation segmentation model to obtain the water accumulation area; Obtain the pixel gray-scale change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the water surface change parameter, obtain the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, obtain the pixel binary change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the texture change parameter, and perform weighted summation on the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter to obtain the water surface fluctuation factor, where the water surface fluctuation factor represents the water surface fluctuation situation of the water accumulation area; Use the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the water accumulation depth.

[0007] In a second aspect, an embodiment of the present application provides an urban water accumulation monitoring device that fuses monitoring data and electronic water gauge data, including: An acquisition module, configured to obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence of multiple consecutive images to be monitored including the area where the current electronic water gauge is located, and input the image sequence into a pre-trained water accumulation segmentation model to obtain the water accumulation area; A fluctuation calculation module, which obtains the pixel gray-scale change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the water surface change parameter, obtains the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, obtains the pixel binary change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the texture change parameter, and performs weighted summation on the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter to obtain the water surface fluctuation factor, where the water surface fluctuation factor represents the water surface fluctuation situation of the water accumulation area; A correction module, which uses the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the water accumulation depth.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, characterized in that a computer program is stored in the memory, and the processor is configured to run the computer program to execute an urban water accumulation monitoring method that fuses monitoring data and electronic water gauge data.

[0009] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which a computer program is stored, and the computer program includes program codes for controlling a process to execute the process, and when the program codes are executed by a processor, an urban water accumulation monitoring method that fuses monitoring data and electronic water gauge data is implemented.

[0010] The main contributions and innovations of the present invention are as follows: In the embodiments of the present application, by fusing the current readings of the electronic water gauge with the continuous image sequences collected by the monitoring camera, the water accumulation area is accurately identified using the water accumulation segmentation model, and the water surface fluctuation factor is calculated by combining the gray scale and binary changes of adjacent image pixels and the standard deviation of the historical readings of the water gauge to correct the readings of the water gauge. Kalman filtering is used for noise reduction, effectively making up for the deficiencies of a single monitoring method in terms of real-time performance, range coverage, accuracy, and environmental adaptability. It can quickly and accurately identify the urban water accumulation area and measure the depth, enhance the monitoring stability, reduce the influence of environmental interference and equipment errors, and provide reliable data support for urban waterlogging prevention.

[0011] The details of one or more embodiments of the present application are set forth in the following drawings and description, so that the other features, objects, and advantages of the present application become more comprehensible. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings: Figure 1 is a flowchart of a method for monitoring urban water accumulation by fusing monitoring data and electronic water gauge data according to an embodiment of the present application; Figure 2 is an effect diagram of successful pairing of a monitoring camera and an electronic water gauge according to an embodiment of the present application; Figure 3 is a structural diagram of a water accumulation segmentation model according to an embodiment of the present application; Figure 4 is an identification effect diagram of identifying the water accumulation area according to an embodiment of the present application; Figure 5 is a structural block diagram of a device for monitoring urban water accumulation by fusing monitoring data and electronic water gauge data according to an embodiment of the present application; Figure 6 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. On the contrary, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0014] It should be noted that: In other embodiments, the steps of the corresponding method are not necessarily executed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may also be combined into a single step for description in other embodiments.

[0015] Embodiment 1 An urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data is provided in an embodiment of the present application. By using a waterlogging segmentation model to accurately identify waterlogging areas, combining pixel changes in adjacent images, the standard deviation of water gauge readings, etc. to calculate the water surface fluctuation factor to correct the water gauge readings, enhancing the real-time performance and stability of monitoring, reducing the influence of environmental interference and equipment errors, and achieving fast and accurate urban waterlogging monitoring. Specifically, referring to Figure 1 , the method includes: Obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence of multiple consecutive images to be monitored including the area where the current electronic water gauge is located, and input the image sequence into a pre-trained waterlogging segmentation model to obtain the waterlogging area; Obtain the pixel gray-scale change of the same pixel position in the waterlogging area of two adjacent images to be monitored as the water surface change parameter, obtain the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, obtain the pixel binary change of the same pixel position in the waterlogging area of two adjacent images to be monitored as the texture change parameter, and perform weighted summation on the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter to obtain the water surface fluctuation factor, where the water surface fluctuation factor represents the water surface fluctuation situation of the waterlogging area; Use the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the waterlogging depth.

[0016] In some embodiments, in order to ensure that the monitoring camera can clearly capture the electronic water gauge, a monitoring camera needs to be matched with the electronic water gauge first. Specifically, when the horizontal distance between the monitoring camera and the electronic water gauge is less than the distance threshold, and the included angle between the line-of-sight direction vector of the monitoring camera and the direction vector of the electronic water gauge relative to the monitoring camera is less than the angle threshold, use this monitoring camera to obtain multiple consecutive images to be monitored including the area where the current electronic water gauge is located.

[0017] Specifically, the monitoring camera obtains consecutive images to be monitored at the same location and the same shooting angle.

[0018] Specifically, let the installation coordinates of the monitoring camera be , and the installation coordinates of the electronic water gauge be , then the horizontal distance between the monitoring camera and the electronic water gauge is calculated as follows:

[0019] Among them, D is the horizontal distance between the monitoring camera and the electronic water gauge, and the set distance threshold in this solution is , the distance threshold is usually 3 to 10 meters.

[0020] Specifically, the calculation formula for the line-of-sight direction vector of the monitoring camera is as follows:

[0021] Among them, is the line-of-sight direction vector of the monitoring camera, is the horizontal rotation angle of the monitoring camera, is the pitch angle of the camera.

[0022] Specifically, the calculation formula for the direction vector of the electronic water gauge relative to the monitoring camera is as follows:

[0023] Among them, is the direction vector of the electronic water gauge relative to the monitoring camera, is the installation coordinate of the monitoring camera, is the installation coordinate of the electronic water gauge.

[0024] Specifically, the calculation formula for the included angle between the line-of-sight direction vector of the monitoring camera and the direction vector of the electronic water gauge relative to the monitoring camera is as follows:

[0025] Among them, is the included angle between the line-of-sight direction vector of the monitoring camera and the direction vector of the electronic water gauge relative to the monitoring camera, is the direction vector of the electronic water gauge relative to the monitoring camera, is the line-of-sight direction vector of the monitoring camera, and the set angle threshold in this solution is , the angle threshold is usually 10° to 15°.

[0026] That is to say, in this solution, when and , it means that the monitoring camera may clearly capture the electronic water gauge, and the corresponding monitoring camera and electronic water gauge are paired. The effect diagram of the successful pairing of the monitoring camera and the electronic water gauge is as Figure 2 shown.

[0027] In some embodiments, the structure of the water accumulation segmentation model is as Figure 3As shown, the water accumulation segmentation model includes an encoding module, a decoding module, a timing analysis module, and an output module. The encoding module is used to extract the color feature map, the water accumulation surface fluctuation feature map, and the water accumulation edge feature map of each image to be monitored, and superimpose the color feature map, the water accumulation edge feature map, and the water accumulation texture feature map of each image to be monitored to obtain a comprehensive feature map. The decoding module decodes the comprehensive feature map of each image to be monitored and inputs it into the timing analysis module. The timing analysis module performs fusion analysis on the timing information of each comprehensive feature map to obtain the water accumulation area and outputs it through the output module.

[0028] Exemplarily, by inputting the image sequence diagram , , into the water accumulation segmentation model, the encoding module outputs the color feature map , the water accumulation surface fluctuation feature map , and the water accumulation edge feature map , and then superimpose the color feature map, the water accumulation surface fluctuation feature map, and the water accumulation edge feature map to obtain the comprehensive feature map .

[0029] Furthermore, the encoding module is composed of multiple encoding units connected in series, and each encoding unit includes an encoder, a channel attention mechanism, and a dilated convolutional layer.

[0030] Specifically, the encoder is used to extract the feature representation of the image to be monitored; the channel attention mechanism dynamically adjusts each channel, so that the model pays more attention to those water accumulation areas with low saturation and low contrast. The channel attention mechanism improves the recognition accuracy of water accumulation areas in complex urban environments by enhancing the expression ability of these water body features; the dilated convolutional layer captures water body features of different scales by expanding the receptive field. Since there are usually various water body areas of different scales in urban areas, such as street water accumulation and water accumulation around sewers, dilated convolution can help the model extract the features of these areas while maintaining the resolution, thereby improving the accurate recognition of water accumulation areas, especially in the face of dense cities and complex ground reflections.

[0031] In some specific embodiments, the principle of the encoding module for extracting the color feature map, the water accumulation surface fluctuation feature map, and the water accumulation edge feature map is described here. Before the encoding module performs feature extraction, considering that urban water accumulation usually has a specific color distribution, such as low gray level and strong blue channel, so before inputting the image to be monitored into the encoding module, the image to be monitored is converted into the HSV color space. Then, the feature extraction formula of the color feature map is expressed as:

[0032] Among them, x and y represent the pixel coordinates on the image to be monitored. is a preset color threshold. is the channel pixel value of the blue channel. is the channel pixel value of the red channel. is the feature extraction result of the (x, y) coordinates on the color feature map. That is to say, when extracting features from the color feature map, when the value of the (x, y) coordinates is assigned 1, the pixel value of the coordinate point (x, y) is retained, and when the value of the (x, y) coordinates is assigned 0, the pixel value of the coordinate point (x, y) is not retained. This solution highlights the water accumulation area in the image to be monitored by setting the threshold of each channel in the HSV color space, providing favorable information for subsequent water accumulation recognition.

[0033] Specifically, the Laplacian variance is used to calculate the influence on each pixel point on the water surface of the image to be monitored, so as to extract the fluctuation feature map of the water surface. The formula is expressed as:

[0034] Among them, is the feature extraction result of the (x, y) coordinates on the water surface fluctuation feature map. is a preset fuzzy threshold. is the variance of the pixels after the Laplacian transform of the (x, y) of the image to be monitored. That is to say, when extracting the water surface fluctuation feature map, when the value of the (x, y) coordinates is assigned 1, the pixel value of the coordinate point (x, y) is retained, and when the value of the (x, y) coordinates is assigned 0, the pixel value of the coordinate point (x, y) is not retained.

[0035] Specifically, the Canny edge detection algorithm is used to extract the edge features of the image to be monitored to obtain the water accumulation edge feature map. The Canny edge detection algorithm is a commonly used edge feature extraction method and will not be elaborated here.

[0036] In some specific embodiments, the encoding units in the encoding module gradually increase from 128 channels to 1024 channels to extract the abstract features of the water body layer by layer, while retaining the low-level spatial information to adapt to the complex water accumulation scenarios in the city. The decoding module consists of multiple decoding units. The number of decoding units is the same as the number of encoding units, and each layer of decoding units is directly connected to the corresponding encoding unit. The decoding units gradually restore the information of the water accumulation area in the urban environment through the process of restoring the resolution, and at the same time fuse with the low-level features extracted by the corresponding encoding units to improve the accuracy of water body segmentation. Especially in the city, the decoding units can effectively distinguish the boundary between the water accumulation and the surrounding complex environment, improving the recognition accuracy of the urban water accumulation area. The recognition effect diagram of the water accumulation area identified by this solution is asFigure 4 as shown

[0037] In some embodiments, the timing analysis module is an LSTM structure. By fusing the timing information of adjacent front and back frames of the to-be-monitored images, the model can span temporal continuity to reduce the influence of illumination changes, moving objects, or reflected light within a short period of time, so as to more stably identify the water accumulation area, especially in an urban environment with strong light changes or dynamic object interference.

[0038] In some embodiments, the output module outputs the result of the timing analysis module to obtain the water accumulation area. The output module is a decoding unit. By decoding, the edge of the water accumulation area is obtained, and then the water accumulation area is acquired according to the edge of the water accumulation area. The calculation of the edge of the water accumulation area is represented by the following formula:

[0039] where is the edge of the water accumulation area, is the color feature map, is the water surface fluctuation feature map, is the water accumulation edge feature map, is the corresponding to-be-monitored image.

[0040] In some embodiments, the ratio of the number of pixel points in the water accumulation area to the total number of pixel points in the to-be-monitored image is judged. If the ratio is greater than the water accumulation threshold, it is judged that there is water accumulation in this area; if the ratio is not greater than the water accumulation threshold, it is judged that there is no water accumulation in this area. That is to say, in this solution, only when it is judged that there is water accumulation in this area will the subsequent calculation of the water accumulation depth be carried out. If there is no water accumulation, there is no need to calculate the water accumulation depth.

[0041] Specifically, the formula for judging whether there is water accumulation is expressed as follows:

[0042] where is the ratio of the number of pixel points in the water accumulation area to the total number of pixel points in the to-be-monitored image, is the number of pixel points in the water accumulation area.

[0043] In some specific embodiments, the calculation method of the water surface change parameter is as follows:

[0044] where is the water surface change parameter, W is the water accumulation area, x and y are the pixel coordinates within the water accumulation area, is the gray value of the to-be-monitored image at the t-th frame at the pixel coordinates (x, y), is the gray value of the image to be monitored at the t-1th frame at the pixel coordinates (x, y).

[0045] That is to say, the number of pixel points and the pixel point positions occupied by the water accumulation area in the same group of image sequences in this solution are the same. Therefore, the change of the water surface can be represented by the gray values of the corresponding pixel points in two adjacent frames.

[0046] In some specific embodiments, the calculation method of the water gauge reading fluctuation intensity parameter is as follows:

[0047] Among them, is the water gauge reading fluctuation intensity parameter, N is the time window size, is the average reading within the time window size, is the historical reading of the electronic water gauge.

[0048] In some specific embodiments, the calculation method of the texture change parameter is as follows:

[0049] Among them, is the texture change parameter, W is the water accumulation area, x, y are the pixel coordinates within the water accumulation area, is the binary mode of the image to be monitored at the tth frame at the pixel coordinates (x, y), is the binary mode of the image to be monitored at the t-1th frame at the pixel coordinates (x, y).

[0050] In some specific embodiments, the calculation formula of the water surface fluctuation factor is expressed as:

[0051] Among them, is the water surface fluctuation factor, is the water surface change parameter, is the water gauge reading fluctuation intensity parameter, is the texture change parameter, is the weight parameter, Adjusted according to experimental data.

[0052] Specifically, in this solution, when is relatively large, it indicates that the water surface is in a state of violent fluctuation, and at this time, the credibility of the reading of the electronic water gauge decreases.

[0053] In some specific embodiments, the formula for correcting the current reading of the electronic water gauge using the water surface fluctuation factor is expressed as:

[0054] Among them, is the water accumulation depth, is the current reading of the electronic water gauge, is the water surface fluctuation factor, is the dynamic adjustment coefficient.

[0055] That is to say, in this solution, a fluctuation threshold is set. When , it indicates that the water surface fluctuates greatly. At this time, the dynamic adjustment coefficient takes a larger value to reduce the error, and vice versa.

[0056] In some specific embodiments, Kalman filtering is used to denoise the water accumulation depth. Specifically, first calculate the state equation of Kalman filtering:

[0057] where, is the water level change rate, and the water level change rate is estimated from the historical water accumulation depth.

[0058] Calculate the observation equation of Kalman filtering:

[0059] where, is the corrected water gauge measurement value, is the observation noise.

[0060] Calculate the Kalman gain and denoise the water accumulation depth based on the Kalman gain:

[0061]

[0062] where, is the prediction error covariance, is the measurement noise variance, is the Kalman gain, which is used to determine the weight during fusion, is the corrected water gauge measurement value, is the water accumulation depth.

[0063] Embodiment 2 Based on the same concept, referring to Figure 5 , this application also proposes an urban water accumulation monitoring device for fusing monitoring data and electronic water gauge data, including: An acquisition module, configured to acquire the current reading of the electronic water gauge, and use a monitoring camera to acquire an image sequence of multiple consecutive to-be-monitored images including the area where the current electronic water gauge is located, and input the image sequence into a pre-trained water accumulation segmentation model to obtain a water accumulation area; A fluctuation calculation module obtains the pixel gray-scale change situation of the same pixel positions in the water accumulation area of two adjacent images to be monitored as the water surface change parameter, obtains the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, obtains the pixel binary change situation of the same pixel positions in the water accumulation area of two adjacent images to be monitored as the texture change parameter, and sums up the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter after weighting to obtain a water surface fluctuation factor, where the water surface fluctuation factor represents the water surface fluctuation situation of the water accumulation area; A correction module corrects the current reading of the electronic water gauge using the water surface fluctuation factor to obtain the water accumulation depth.

[0064] Embodiment III This embodiment also provides an electronic device. Refer to Figure 6 , which includes a memory 404 and a processor 402. A computer program is stored in the memory 404, and the processor 402 is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0065] Specifically, the above-mentioned processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC for short), or may be configured as one or more integrated circuits for implementing the embodiments of the present application.

[0066] Among them, the memory 404 may include a mass memory 404 for data or instructions. By way of example and not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 404 may include removable or non-removable (or fixed) media. Where appropriate, the memory 404 may be internal or external to the data processing device. In a particular embodiment, the memory 404 is non-volatile memory. In a particular embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. Where appropriate, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0067] The memory 404 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402.

[0068] By reading and executing the computer program instructions stored in the memory 404, the processor 402 implements any one of the urban waterlogging monitoring methods for fusing monitoring data and electronic water gauge data in the above embodiments.

[0069] Optionally, the above electronic device may further include a transmission device 406 and an input / output device 408. Among them, the transmission device 406 is connected to the above processor 402, and the input / output device 408 is connected to the above processor 402.

[0070] The transmission device 406 can be used to receive or send data via a network. Specific examples of the above network may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0071] The input / output device 408 is used to input or output information. In this embodiment, the input information can be the readings of the electronic water gauge, image sequences, etc., and the output information can be the water surface fluctuation situation, waterlogging depth, etc.

[0072] Optionally, in this embodiment, the above processor 402 can be set to execute the following steps through a computer program: Obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence of multiple consecutive images to be monitored including the area where the current electronic water gauge is located, and input the image sequence into a pre-trained waterlogging segmentation model to obtain a waterlogging area; Obtain the pixel gray change situation of the same pixel position in the waterlogging area of two adjacent images to be monitored as the water surface change parameter, obtain the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, obtain the pixel binary change situation of the same pixel position in the waterlogging area of two adjacent images to be monitored as the texture change parameter, and perform weighted summation on the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter to obtain a water surface fluctuation factor, and the water surface fluctuation factor represents the water surface fluctuation situation of the waterlogging area; Use the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the waterlogging depth.

[0073] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0074] Generally, various embodiments can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the present invention can be implemented in hardware, while other aspects can be implemented by firmware or software executed by a controller, microprocessor, or other computing device. However, the present invention is not limited thereto. Although various aspects of the present invention can be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, the blocks, devices, systems, technologies, or methods described herein can be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or a controller or other computing device, or some combination thereof.

[0075] Embodiments of the present invention can be implemented by computer software, which can be executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. A computer software or program (also referred to as a program product), including software routines, applets, and / or macros, can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. The computer program product can include one or more computer-executable components configured to perform the embodiments when the program runs. The one or more computer-executable components can be at least one software code or a part thereof. Additionally, in this regard, it should be noted that any box in the logical flow, as Figure 6 described herein, can represent a program step, or an interconnected logical circuit, box, and function, or a combination of a program step and a logical circuit, box, and function. The software can be stored on physical media such as memory chips or storage blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs. The physical media are non-transitory media.

[0076] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0077] The above embodiments only represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data, characterized in that, It includes the following steps: Obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence of multiple consecutive images to be monitored including the area where the current electronic water gauge is located. Input the image sequence into a pre-trained water accumulation segmentation model to obtain the water accumulation area; Obtain the pixel gray-scale change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the water surface change parameter, obtain the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, and obtain the pixel binary change of the same pixel position in the water accumulation area of two adjacent images to be monitored as the texture change parameter. Weightedly sum the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter to obtain the water surface fluctuation factor, and the water surface fluctuation factor represents the water surface fluctuation of the water accumulation area; Use the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the water accumulation depth.

2. The urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data according to claim 1, wherein When the horizontal distance between the monitoring camera and the electronic water gauge is less than the distance threshold, and the included angle between the line-of-sight direction vector of the monitoring camera and the direction vector of the electronic water gauge relative to the monitoring camera is less than the angle threshold, use this monitoring camera to obtain multiple consecutive images to be monitored including the area where the current electronic water gauge is located.

3. The urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data according to claim 1, wherein The water accumulation segmentation model includes an encoding module, a decoding module, and a temporal analysis module. The encoding module is used to extract the color feature map, the water accumulation surface fluctuation feature map, and the water accumulation edge feature map of each image to be monitored, and superimpose the color feature map, the water accumulation edge feature map, and the water accumulation texture feature map of each image to be monitored to obtain a comprehensive feature map. The decoding module decodes the comprehensive feature map of each image to be monitored and then inputs all the decoded comprehensive feature maps into the temporal analysis module. The temporal analysis module performs fusion analysis on the temporal information of each comprehensive feature map to obtain the water accumulation area.

4. The urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data according to claim 3, wherein The encoding module is composed of multiple encoding units connected in series, and each encoding unit includes an encoder, a channel attention mechanism, and a dilated convolutional layer.

5. A method for monitoring urban waterlogging by fusing monitoring data and electronic water gauge data according to claim 1, characterized in that The calculation method of the water surface change parameter is as follows: ； Among them, is the water surface change parameter, W is the water accumulation area, and x, y are the pixel coordinates within the water accumulation area. is the gray value of the image to be monitored at the t-th frame at the pixel coordinates (x, y). is the gray value of the image to be monitored at the (t - 1)-th frame at the pixel coordinates (x, y). The calculation method of the water gauge reading fluctuation intensity parameter is as follows: ； Among them, is the wave intensity parameter of the water gauge reading, N is the size of the time window, is the average reading within the time window size, is the historical reading of the electronic water gauge; The calculation method of the texture change parameter is as follows: ； Among them, is the texture change parameter, W is the water accumulation area, and x, y are the pixel coordinates within the water accumulation area. is the binary pattern at the pixel coordinates (x, y) of the image to be monitored in the t-th frame. is the binary pattern at the pixel coordinates (x, y) of the image to be monitored in the (t - 1)-th frame.

6. The urban waterlogging monitoring method for fusing monitoring data and electronic water gauge data according to claim 1, characterized in that, The formula for correcting the current reading of the electronic water gauge using the water surface fluctuation factor is expressed as: ； Among them, is the water accumulation depth, is the current reading of the electronic water gauge, is the water surface fluctuation factor, is the dynamic adjustment coefficient.

7. An urban waterlogging monitoring device that fuses monitoring data and electronic water gauge data, characterized in that, It includes: An acquisition module, which is used to obtain the current reading of the electronic water gauge, and use a monitoring camera to obtain an image sequence composed of multiple consecutive images to be monitored including the electronic water gauge, and input the image sequence into a pre-trained water accumulation segmentation model to obtain the water accumulation area; A fluctuation calculation module, which calculates the pixel gray-scale change of the relative position in the water accumulation area of two adjacent images to be monitored as the water surface change parameter, calculates the standard deviation of the historical readings of the electronic water gauge as the water gauge reading fluctuation intensity parameter, calculates the pixel binary change of the relative position in the water accumulation area of two adjacent images to be monitored as the texture change parameter, and weightedly sums the water surface change parameter, the water gauge reading fluctuation intensity parameter, and the texture change parameter as the water surface fluctuation factor. The water surface fluctuation factor represents the water surface fluctuation of the water accumulation area; A correction module, which uses the water surface fluctuation factor to correct the current reading of the electronic water gauge to obtain the water accumulation depth.

8. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to run the computer program to execute a method for monitoring urban waterlogging by fusing monitoring data and electronic water gauge data according to any one of claims 1-6.

9. A readable storage medium, characterized in that, A computer program is stored in the readable storage medium, and the computer program includes program codes for controlling a process to execute the process. When the program codes are executed by a processor, a method for monitoring urban waterlogging by fusing monitoring data and electronic water gauge data according to any one of claims 1-6 is implemented.

Images