A water level recognition method and system

Abstract

The present application belongs to the technical field of water area monitoring, and particularly relates to a water level recognition method and system. The method comprises determining a sampling range according to the form of a target water area; determining a civil camera device in the sampling area and screening to obtain a suitable camera device; collecting and processing water area image data output by the suitable camera device to recognize water level data of the target water area. According to the form of the target water area, the sampling range is determined, targeted sampling can be performed for water areas of different forms, and the accuracy and efficiency of related data sampling are improved. The civil camera device in the sampling area is determined, and a suitable camera device is screened, the existing civil device can be used to reduce hardware cost and increase data collection channels, and the accuracy of subsequent recognition can be improved. The water area image data output by the suitable camera device is collected and processed, and the water level data of the target water area is recognized, and the change of the water level can be accurately recognized.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of water area monitoring, and particularly relates to a water level recognition method and system. BACKGROUND

[0002] Water disaster is one of the natural disasters, which can destroy soil and vegetation, and further affect human activities, so it is necessary to pay attention to weather, rivers and soil and other factors to prevent or reduce the occurrence of water disaster. The most intuitive manifestation of water disaster is the change of water level, and the influence range and potential harm degree of water disaster can be determined by observing the change of water level.

[0003] The water area such as rivers has a wide distribution range, and since the river is formed by the convergence of the upstream water flow, the change of the upstream water level will be fed back to the downstream, and there will be a certain delay. In order to accurately predict the current change of the water level of the river, it is necessary to set up a water level monitoring device to monitor the change of the water level in a wide range. However, this way needs to set up many devices, and the hardware cost and maintenance cost are relatively high, and considering that the change of the water flow in the river is relatively disordered, the device set at a fixed position may not be able to adapt to the change of the water flow all the year round. SUMMARY

[0004] In order to solve or improve the above problems, the present application provides a water level recognition method and system, and the specific technical scheme is as follows:

[0005] The present application provides a water level recognition method, comprising: determining a sampling range according to the form of a target water area; determining a civil camera device in the sampling area and screening to obtain an applicable camera device; collecting and processing water area image data output by the applicable camera device to recognize water level data of the target water area.

[0006] Preferably, the water level recognition method further comprises: determining a water level observation point and a corresponding observation horizon according to the form, setting the sampling range based on the range of the observation horizon; correspondingly, the method further comprises: acquiring a functional parameter of the civil camera device in the sampling area to determine a corresponding functional horizon; if the functional horizon can include the water level observation point and the data amount of the image of the water level observation point is greater than a specified value, marking the civil camera device as the applicable camera device.

[0007] Preferably, the collecting and processing the water area image data output by the applicable camera device comprises: collecting the coordinates of the applicable camera device and matching with the water area reference corresponding to the water level observation point, and selecting a corresponding image processing model to process the water area image data according to the matching relationship and the coordinates.

[0008] Preferably, the water level observation point comprises a water surface and a reference object; correspondingly, the image processing model is used to identify the water level observation point from the water area image data; and the water level data is output according to the pixel change of the water surface and the reference object.

[0009] Preferably, the water level data of the target water area is identified by collecting and processing the water area image data output by the applicable camera device, which comprises: selecting the same water level observation point or different water level observation points in the same region to determine a corresponding set of the applicable camera device; determining a corresponding set of the water level data based on the water area image data output by the set of the applicable camera device; and outputting the final water level data by processing the set of the water level data based on a preset weighting.

[0010] The application provides a water level identification system, which comprises: a first module for determining a sampling range according to the morphology of a target water area; a second module for determining a civil camera device in the sampling area and screening an applicable camera device; and a third module for collecting and processing water area image data output by the applicable camera device to identify water level data of the target water area.

[0011] Preferably, the sampling range is determined according to the morphology of the target water area, which comprises: determining a water level observation point and a corresponding observation view according to the morphology, and setting the sampling range based on the range of the observation view; correspondingly, the civil camera device in the sampling area is determined, and the applicable camera device is screened, which comprises: obtaining the functional parameters of the civil camera device in the sampling area to determine a corresponding functional view; if the functional view can include the water level observation point and the data amount of the image of the water level observation point is greater than a specified value, the civil camera device is marked as the applicable camera device.

[0012] Preferably, the water level data of the target water area is identified by collecting and processing the water area image data output by the applicable camera device, which comprises: collecting the coordinates of the applicable camera device and matching the coordinates with the water area reference object corresponding to the water level observation point, and selecting a corresponding image processing model to process the water area image data according to the matching relationship and the coordinates.

[0013] Preferably, the water level observation point comprises a water surface and a reference object; correspondingly, the image processing model is used to identify the water level observation point from the water area image data; and the water level data is output according to the pixel change of the water surface and the reference object.

[0014] Preferably, the water area image data output by the applicable camera device is collected and processed, and water level data of the target water area is identified, including: selecting the same water level observation point or different water level observation points in the same area to determine a corresponding set of the applicable camera device; determining a corresponding set of the water level data based on the water area image data output by the set of the applicable camera device; and outputting final water level data based on the set of the water level data by preset weighting processing.

[0015] The present application has the advantages that: the sampling range is determined according to the morphology of the target water area, the sampling can be targeted for different morphologies of the water area, the accuracy and efficiency of the relevant data sampling are improved, the civil camera device in the sampling area is determined, and the applicable camera device is screened, the existing civil device can be used to reduce the hardware cost and increase the data collection approach, and the accuracy of subsequent identification can be improved, the water area image data output by the applicable camera device is collected and processed, and the water level data of the target water area is identified, and the change of the water level can be accurately identified. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a schematic diagram of a water level identification method according to the present application;

[0017] Figure 2 is a schematic diagram of a water level identification system according to the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] It should be understood that, as used in the specification and the appended claims, the terms "comprise" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0020] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0021] It should be further understood that the term "and / or" used in the description and claims of the application means one or more of the associated listed items as well as all possible combinations of the items, and includes these combinations.

[0022] To solve or improve the problems raised by the background, the present application provides a water level recognition method as shown in Figure 1 The water level recognition method comprises the following steps: S1, determining a sampling range according to the shape of a target water area; S2, determining civil video shooting devices in the sampling range and screening to obtain applicable video shooting devices; S3, collecting and processing water area image data output by the applicable video shooting devices to recognize water level data of the target water area.

[0023] Water area refers to rivers, lakes, canals, channels, reservoirs, ponds and their management ranges and hydraulic structures. Water area includes naturally formed, artificially constructed or semi-natural and semi-artificial types. Generally speaking, in addition to artificially constructed water areas, their appearance mostly presents a complex shape. At the same time, the equipment for monitoring water level is generally set on the ground or slightly higher buildings or mountains (the image of the ground water area can also be shot from the air, but due to the consistent relationship between the direction of water level rise and the downward direction of the sky, it is not easy to process the specific value of the water level), which causes the monitoring equipment to be unable to properly shoot the image of the water area. In order to better shoot the image of the target water area for subsequent analysis, it is necessary to determine a suitable observation point.

[0024] Specifically, the sampling range is determined according to the shape of the target water area. The principle is that the observation point can observe the water surface of the target water area of a suitable size, can observe suitable reference objects, and can observe specified water level points. The water surface is large enough to facilitate the identification of water-related parts from the target water area image. The number of reference objects and the distinctness of their appearance will affect the accuracy of subsequent comparison between water and reference objects and then obtaining water level data. The reference objects can be rocks, trees, artificial buildings, riverbanks and other objects. Through the comparison between the reference objects and the water-related parts, the water level data can be calculated through a preset formula. Water-related disasters do not occur at all positions in the water area. Generally speaking, only the positions that affect human living environment need to be paid attention to, such as beaches, embankments, cliffs / slopes near residential areas, or places prone to water accumulation and landslides or blockages. The set of observation points corresponding to the specified positions or regions of the target water area can be obtained based on the optical principle, which is the sampling range.

[0025] The civil video equipment includes various fixed cameras or handheld mobile electronic terminals. The fixed cameras are generally monitoring cameras, and the handheld mobile electronic terminals are generally electronic products such as mobile phones. Such civil video equipment is widely used in the current society. Through these devices, a large number of target water area images can be obtained, and the time is unlimited, which is beneficial to alleviate the hardware cost and maintenance cost of the official entity equipment. Of course, not all civil video equipment can be used, which involves the license problem of the holder, and some civil video equipment cannot obtain the image of the target water area, or the pixel of the obtained image is too low to be processed. Therefore, the equipment capable of obtaining the image of the target water area needs to be screened as the applicable video equipment.

[0026] Water will flow in the waterway. Generally, the shape and position of the waterway will not change much, and the environment around the waterway will not change much. Therefore, the waterway can be determined / distinguished through the color, shape and surrounding environment of the water, and then the water level data can be calculated according to the shape of the waterway and the contrast of the reference object, combined with the experience and data of on-site measurement. The principle can include that the waterway and the reference object can be recognized according to the pixel color and position in the image combined with the past data; and the water level data can be calculated according to the change of the pixel distance between the pixels of the waterway and the reference object pixels.

[0027] The method for determining the sampling range according to the shape of the target water area includes: determining a water level observation point and a corresponding observation view range according to the shape, setting the sampling range based on the range of the observation view range; and correspondingly, the method for determining the civil video equipment in the sampling area and screening the applicable video equipment includes: acquiring the function parameters of the civil video equipment in the sampling area to determine the corresponding function view range; if the function view range can include the water level observation point, and the data amount of the image of the water level observation point is greater than a specified value, the civil video equipment is marked as the applicable video equipment.

[0028] The water level observation point is the observed water / reference object. In reality, water generally flows in a channel below the ground. Therefore, due to the obstruction of the ground itself and the objects on the ground, 360° observation cannot be achieved for a specified water level observation point. The set of points that can normally collect the image of the specified water level observation point through optical principles is the observation view range.

[0029] The function parameters of the civil video camera device include the parameters related to the image acquisition capability of the civil video camera device itself (such as the pixel amount, the richness of pixel color, the size of output data amount, etc.), and the current control parameters such as the working time, the shooting angle, etc. The function visual field of the civil video camera device is the range of the shooting image formed at a specified direction and a specified position based on the function parameters. In order to better identify the water and the reference object in the image, the data amount of the image of the water level observation point acquired by the civil video camera device is greater than a specified value, so as to ensure the identification effect.

[0030] The water area image data output by the applicable camera device is collected and processed, including collecting the coordinates of the applicable camera device and matching the water area reference object corresponding to the water level observation point, selecting a corresponding image processing model to process the water area image data according to the matching relationship and the coordinates.

[0031] The water area reference object refers to the object classified as a water area. Because there are many types of water areas, different types of water areas may require different types of image recognition models. In addition, different types of water areas have different appearance characteristics. For example, a river or a sea may have only one bank, a man-made lake may have a man-made guardrail, and a reservoir may have a flood discharge channel and a dam. The existing image recognition model generally needs to be trained to improve the recognition effect. Therefore, there are many image recognition models and recognition principles to choose from. Based on the coordinates of the applicable camera device, the distance between the camera device and the target can be determined. In addition, the type of water area reference object also affects the selection of the image recognition model. The matching relationship includes the number, type, and distribution position relationship of the reference object.

[0032] The water level observation point includes a water surface and a reference object. Correspondingly, the image processing model is used to identify the water level observation point from the water area image data. The water level data is output according to the pixel changes of the water surface and the reference object.

[0033] The water level data of the target water area is identified by collecting and processing the water area image data output by the applicable camera device, including selecting the same water level observation point or different water level observation points in the same area to determine the corresponding set of applicable camera devices. Based on the water area image data output by the set of applicable camera devices, the corresponding set of water level data is determined. The set of water level data is processed based on a preset weighting to output the final water level data.

[0034] The advantage of the scheme is that there are many civil equipment, and because of the large quantity and different shooting positions and shooting qualities, the recognition results are different. In order to improve the accuracy of recognition, the weighted processing can be used, and the principle includes taking the recognition target (that is, the same water level observation point or the same small area in the water area) as the basis, collecting all the applicable camera equipment for recognizing the recognition target, then recognizing the image and obtaining the water level data set generated by the applicable camera equipment, and finally outputting the final water level data based on the preset weighted processing of the water level data set.

[0035] The application provides a water level recognition system as shown in Figure 2 The application provides a water level recognition system as shown in

[0036] The application provides a water level recognition system as shown in

[0037] The application provides a water level recognition system as shown in

[0038] The application provides a water level recognition system as shown in

[0039] The application provides a water level recognition system as shown in

[0040] Those skilled in the art can understand that the units of each example described in combination with the embodiments disclosed in the present embodiment can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, each unit has been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0041] In the embodiments provided in the present application, it should be understood that the division of units is only a logical functional division, and there can be another division manner in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0042] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and the description of the present application.

Claims

1. A water level recognition method characterized by, The method comprises the following steps: determining a sampling range according to the shape of the target water area; determining a civil video camera in the sampling range and screening to obtain an applicable video camera; collecting and processing water area image data output by the applicable video camera to identify water level data of the target water area; determining the sampling range according to the shape of the target water area comprises: determining a water level observation point and a corresponding observation view according to the shape, and setting the sampling range based on the range of the observation view; correspondingly, determining the civil video camera in the sampling range and screening to obtain the applicable video camera comprises: obtaining the functional parameters of the civil video camera in the sampling range to determine the corresponding functional view; if the functional view can include the water level observation point and the data amount of the image obtained by the water level observation point is greater than a specified value, the civil video camera is marked as the applicable video camera; the collecting and processing of the water area image data output by the applicable video camera comprises: collecting the coordinates of the applicable video camera and matching them with the water area reference corresponding to the water level observation point, selecting a corresponding image processing model to process the water area image data according to the matching relationship and the coordinates; the water level observation point comprises a water surface and a reference; correspondingly, the image processing model is used to identify the water level observation point from the water area image data; the water level data is output according to the pixel change of the water surface and the reference; the collecting and processing of the water area image data output by the applicable video camera to identify the water level data of the target water area comprises: selecting the same water level observation point or different water level observation points in the same area to determine a corresponding set of the applicable video cameras; determining a corresponding set of the water level data based on the water area image data output by the set of the applicable video cameras; outputting the final water level data based on the preset weighted processing of the set of the water level data.

2. A water level recognition system, characterized by, The method comprises the following steps: a first module is configured to determine a sampling range according to the shape of a target water area; a second module is configured to determine a civil video camera in the sampling range and screen to obtain an applicable video camera; a third module is configured to collect and process water area image data output by the applicable video camera to identify water level data of the target water area; determining the sampling range according to the shape of the target water area comprises: determining a water level observation point and a corresponding observation view according to the shape, and setting the sampling range based on the range of the observation view; correspondingly, determining the civil video camera in the sampling range and screening to obtain the applicable video camera comprises: obtaining the functional parameters of the civil video camera in the sampling range to determine the corresponding functional view; if the functional view can include the water level observation point and the data amount of the image obtained by the water level observation point is greater than a specified value, the civil video camera is marked as the applicable video camera; the collecting and processing of the water area image data output by the applicable video camera comprises: Collecting coordinates of the applicable camera device and matching with water reference objects corresponding to the water level observation points, selecting corresponding image processing models to process the water image data according to the matching relationship and the coordinates; The water level observation points include a water surface and a reference object; Correspondingly, the image processing model is used to identify the water level observation points from the water image data; According to the pixel changes of the water surface and the reference object, the water level data is outputted; The collection and processing of the water image data outputted by the applicable camera device, the identification of the water level data of the target water area, comprises: Selecting the same water level observation points or different water level observation points in the same area to determine the corresponding set of applicable camera devices; Based on the water image data outputted by the set of applicable camera devices, the set of water level data is determined; Based on the preset weighting, the set of water level data is processed to output the final water level data.

Images