CN111259890A - Water level identification method, device and equipment of water level gauge - Google Patents
Water level identification method, device and equipment of water level gauge Download PDFInfo
- Publication number
- CN111259890A CN111259890A CN202010058235.1A CN202010058235A CN111259890A CN 111259890 A CN111259890 A CN 111259890A CN 202010058235 A CN202010058235 A CN 202010058235A CN 111259890 A CN111259890 A CN 111259890A
- Authority
- CN
- China
- Prior art keywords
- water level
- character
- level gauge
- network model
- characters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/04—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by dip members, e.g. dip-sticks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/80—Arrangements for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
A water level identification method of a water level gauge comprises the following steps: acquiring an image to be identified comprising water level gauge information; identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model; identifying the E character in the target frame according to the trained character E detection network model; correcting the recognized E characters according to the intervals among the E characters; and determining a water level value corresponding to the water level line position according to the corrected E character. The detection error caused by shielding can be reduced, and the detection precision of the water level value can be improved.
Description
Technical Field
The application belongs to the field of water level monitoring, and particularly relates to a water level identification method, device and equipment of a water level gauge.
Background
In water conservancy industry uses, often need detect the water level. The current water level detection mode mainly uses a water level meter applied by a float type, a pressure sensing type, an ultrasonic type, a radar, a laser and the like. Due to different structural principles, the limitations and influences of application range, construction cost, construction difficulty and the like need to be considered before practical application of the water level gauges. The video water level meter provides a new water level detection means, which not only can detect the water level, but also can prove the correctness of the detection result of the technology by relying on the network to upload videos/images simultaneously. In addition, the application and maintenance costs of the technical product are also very low. Therefore, the technology has good application prospect and market demand.
When using the video to carry out the water level discernment of water level chi, adopt concentration network technology to carry out the water level discernment of water level chi to the image in the video usually, however, when the scale on the water level chi is sheltered from by the incrustation scale, lead to the edge detection error great, be unfavorable for improving the water level discernment precision of water level chi.
Disclosure of Invention
In view of this, embodiments of the present application provide a method, an apparatus, and a device for identifying a water level of a water level gauge, so as to solve the problem in the prior art that when scales on the water level gauge are covered by scale, an edge detection error is large, which is not beneficial to improving the water level identification precision of the water level gauge.
A first aspect of an embodiment of the present application provides a water level identification method for a water level gauge, where the water level identification method for the water level gauge includes:
acquiring an image to be identified comprising water level gauge information;
identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
identifying the E character in the target frame according to the trained character E detection network model;
correcting the recognized E characters according to the intervals among the E characters;
and determining a water level value corresponding to the water level line position according to the corrected E character.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the water level gauge positioning network model and/or the character E detection network model is an SSD300 target detection network.
With reference to the first aspect, in a second possible implementation manner of the first aspect, before the step of identifying an E character in the target box according to a trained character E detection network model, the method further includes:
cutting the original image according to the identified target frame to obtain a cut image corresponding to the target frame;
and amplifying the cut image to obtain an amplified image in the target frame.
With reference to the first aspect, in a third possible implementation manner of the first aspect, the correcting the recognized E characters according to the intervals between the E characters includes:
comparing a difference value of vertical coordinates between two adjacent E characters in the image with a height value of a single E character;
and determining the number of the E characters inserted between the two E characters according to the ratio of the longitudinal coordinate difference value to the height value of the single E character.
With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the determining, according to the corrected E character, a water level value corresponding to the water level line position includes:
sequencing the corrected E characters;
determining a scale value corresponding to the E character in a fitting mode;
and determining a water level value corresponding to the water level line position according to the determined scale value of the E character.
With reference to the first aspect, in a fifth possible implementation manner of the first aspect, the method further includes:
acquiring first sample data of a water level image of a water level gauge, wherein the first sample data comprises a calibration target frame for calibrating the position of the water level gauge;
inputting the first sample data into a water level gauge positioning network model, and outputting an identification target frame of the first sample data;
and comparing the difference between the calibration target frame and the identification target frame, and adjusting the parameters of the water level gauge positioning network model according to the difference until the difference meets the preset requirement to obtain the trained water level gauge positioning network model.
With reference to the first aspect, in a sixth possible implementation manner of the first aspect, the method further includes:
acquiring second sample data comprising E characters, wherein the second sample data comprises calibration characters with determined positions;
inputting the second sample data into a character E detection network model, and outputting an identification character of the second sample data;
and comparing the difference between the recognition character and the calibration character, and adjusting the parameters of the side dance E detection network model according to the difference until the difference between the recognition character and the calibration character meets the preset requirement to obtain the trained character E detection network model.
A second aspect of the embodiments of the present application provides a water level identification apparatus of a water level gauge, the water level identification apparatus of the water level gauge includes:
the device comprises an image to be identified acquiring unit, a water gauge information acquiring unit and a water gauge information acquiring unit, wherein the image to be identified acquiring unit is used for acquiring an image to be identified comprising water gauge information;
the target frame identification unit is used for identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
the E character recognition unit is used for recognizing the E character in the target frame according to the trained character E detection network model;
the correction unit is used for correcting the recognized E characters according to the intervals among the E characters;
and the water level value determining unit is used for determining the water level value corresponding to the water level line position according to the corrected E character.
A third aspect of the embodiments of the present application provides a water level identification device of a water level gauge, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the water level identification method of the water level gauge according to any one of the first aspect when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for identifying a water level of a water level gauge according to any one of the first aspect
Compared with the prior art, the embodiment of the application has the advantages that: the method comprises the steps of identifying a target frame where a water level scale in an image is located through a trained water level scale positioning network model, detecting E characters in the network model identification target frame according to the trained character E, correcting the E characters according to intervals among the E characters, and determining a water level line position corresponding to a water level value according to the corrected E characters, so that detection errors caused by shielding can be reduced, and the detection precision of the water level value is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation process of a water level identification method of a water level gauge according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating an implementation process of a water level gauge positioning network model training method according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating an implementation of a training method for a character E detection network model according to an embodiment of the present application;
fig. 4 is a schematic flow chart illustrating an implementation of a character correction method according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a blocked water gauge image provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a water gauge image with a partially blocked restoration portion according to an embodiment of the present application;
fig. 7 is a schematic view of a corrected water level gauge image according to an embodiment of the present application;
FIG. 8 is a schematic view of a water level identification device of a water gauge according to an embodiment of the present disclosure;
fig. 9 is a schematic view of a water level identification device of a water level gauge according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
Fig. 1 is a schematic flow chart illustrating an implementation process of a water level identification method of a water level gauge according to an embodiment of the present application, which is detailed as follows:
in step S101, an image to be recognized including water gauge information is acquired;
in the embodiment of the application, the image to be identified can be an image output by video monitoring. The method comprises the steps of continuously acquiring a video comprising a water level gauge through a camera, and extracting the video comprising an image to be identified. The images in the video may be downsampled to obtain a downsampled image of a predetermined resolution. The down-sampled image may have a resolution of 300 x 300, etc.
In step S102, identifying a target frame where a water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
the collected video can be decoded into a single frame RGB format, then the single frame image is downsampled until the resolution is 300 x 300, then the downsampled image data is input into a water level gauge positioning network model, and the position information of the target frame is output.
The water level gauge positioning network model can be an SSD (Single Shot Multbox Detector)300 target detection network, is a target detection algorithm based on a convolutional neural network, and has better speed and higher accuracy than Fast R-CNN. The SSD target detection network combines a YOLO regression idea and an anchor mechanism of Faster R-CNN to achieve coexistence of speed and accuracy. The SSD target detection network uses VGG-16 as a basic network, and adds a new convolutional layer to acquire more feature maps. Because the full convolution structure is used, compared with a full connection layer network structure contained in fast R-CNN, the network computation amount is reduced sharply, and the operation speed is improved. And detecting the target features of all sizes by using a multi-scale feature map mode.
Before identifying the target frame, the method may further include a step of locating a network model for the water level gauge, as shown in fig. 2, including:
in step S201, first sample data of a water level image of a water level gauge is obtained, where the first sample data includes a calibration target frame for calibrating a position of the water level gauge;
before the water level of the water level gauge is identified, a large number of images can be collected through the camera, and the area where the water level gauge is located in the collected images is calibrated, namely the position area of the part of the water level gauge above the water surface is calibrated. When part of the water level gauge is submerged below the water level and an image shot by the camera comprises a blurred and visible underwater part or a reflection image in the water surface, only the part of the water level gauge above the water surface needs to be calibrated, and neither the underwater part nor the reflection needs to be calibrated. By the calibration mode, the trained water level gauge positioning network model can effectively identify the target frame of the water level gauge positioned above the water surface. Namely, the lower frame of the target frame is the position of the horizontal plane.
In step S202, inputting the first sample data into a water level gauge positioning network model, and outputting an identification target frame of the first sample data;
and inputting the image of the calibrated first sample data into the water level gauge positioning network model, and outputting the identification target frame of the position of the water level gauge. And the position of the target frame positions the influence of parameters in the network model according to the water level gauge. The identification target frame identified by the initialized water level gauge positioning network model has a difference with the identification target frame in the first sample data, and the parameters of the water level gauge positioning network model need to be adjusted according to the difference, so that the difference between the two is reduced.
In step S203, the difference between the calibration target frame and the identification target frame is compared, and the parameter of the water level gauge positioning network model is adjusted according to the difference until the difference meets the preset requirement, so as to obtain the trained water level gauge positioning network model.
And in the process of continuously adjusting the parameters of the water level gauge positioning network model, the difference between the obtained identification target frame and the calibration target frame is gradually reduced, and when the difference between the two is smaller than a preset difference value or meets a preset requirement, the training of the water level gauge positioning network model can be stopped to obtain the trained water level gauge positioning network model. And obtaining a target frame corresponding to the water level gauge in the image to be recognized according to the trained water level gauge positioning network model.
In an implementation manner, before recognizing the characters in the target frame, the original image may be cut according to the target frame to obtain a cut image corresponding to the target frame, then the cut image is amplified to obtain an amplified image in the target frame, and then according to step S103, character E detection is performed on the amplified image.
In step S103, identifying an E character in the target frame according to the trained character E detection network model;
after the target frame of the position of the water level gauge in the image to be recognized is obtained, the network model can be further detected according to the trained character E, and the E character included in the target frame can be detected.
The process of obtaining the character E detection network model may be as shown in fig. 3, and includes:
in step S301, second sample data including an E character is acquired, where the second sample data includes a calibration character at a determined position;
specifically, in order to improve the robustness of the character E detection network model, the second sample data may include a plurality of partially occluded characters E. The second sample data may be a target frame marked in the data in the first sample.
In one implementation, the calibration character at the determined position in the second sample data is the character E calibrated in the second sample data. The marked character E may include a position of the marked character E and an image area occupied by the marked character E.
In step S302, inputting the second sample data into the character E detection network model, and outputting an identification character of the second sample data;
the character E detects parameters in the network model and can be initialized to simple values, such as 0 or 1. And inputting the second sample data into the character E detection network model, and outputting the detected character E, namely the recognition character. In general, the initialized character E detects that there is a large difference between the character E output by the network model and the calibration character, including the number, position, etc. of the detected character E.
In step S303, the difference between the recognition character and the calibration character is compared, and the parameters of the side dance E detection network model are adjusted according to the difference until the difference between the recognition character and the calibration character meets the preset requirement, so as to obtain the trained character E detection network model.
And adjusting parameters in the character E detection network model according to the differences between the compared calibration characters and the identification characters, including position differences, quantity differences and the like, so that the differences between the identification characters and the calibration characters obtained through detection are gradually reduced. And when the difference between the detected recognition character and the calibration character meets the preset requirement, obtaining a trained character E detection network model. The characters in the target box in the unknown image can be detected according to the trained character E detection network model.
In step S104, the recognized E characters are corrected according to the interval between E characters;
after detecting the character E in the target frame, there may also be a character E in which the character E in the target frame is blocked, and in order to more accurately determine the scale values corresponding to the positions in the target frame, the recognized character E may be corrected according to the intervals between the characters, which may be specifically shown in fig. 4, including:
in step S401, comparing a difference value of vertical coordinates between two adjacent E characters in the image with a height value of a single E character;
since the size of the captured image is related to the position and angle of the camera, for a fixed position camera, the height value of the single character E corresponding to the fixed position can be calibrated. When the position of the camera is not fixed, or even when the camera position is fixed, the height value of the character E may be determined according to the size of the character E included in the photographed image.
Because the boundary sizes of the characters E in the water level gauge are basically consistent, whether the shielded E characters exist between two adjacent E characters can be determined according to the difference value of the vertical coordinates between the two E characters.
In step S402, the number of E characters inserted between two E characters is determined according to the ratio of the ordinate difference to the height value of a single E character.
If the difference in the vertical coordinate between two adjacent E characters is the height of one character E, one character E is inserted between the two characters E, and likewise, if the difference in the vertical coordinate between two E characters is the height of two characters E, two characters E are inserted between the two characters E. Thereby enabling the occluded character E to be corrected effectively.
In step S105, a water level value corresponding to the water level line position is determined according to the corrected E character.
After the corrected E characters are obtained, the scales corresponding to the E characters can be determined according to the positions of the E characters, and the water level value corresponding to the water level line position can be obtained according to the scales corresponding to the water level line.
For example, in the water level scale image shown in fig. 5, because the water level scale image is blocked, part of the characters E in the water level scale are partially blocked, and also some of the characters E in the water level scale are completely blocked, the characters E can be detected by detecting the network model through the characters E, and the water level scale image shown in fig. 6 is obtained through detection. And then, further correcting the E character to obtain a completely shielded E character, obtaining a water level scale image as shown in fig. 7, sequencing the characters E according to the corrected image, wherein the scale corresponding to the character E with the maximum vertical coordinate is 100cm, the scale corresponds to 90cm and 80cm … … downwards respectively, and fitting the vertical coordinate value and the corresponding scale value curve of the character E in a mode of fitting a quadratic curve. After the scale value corresponding to the character E is determined, the vertical sitting value of the left lower vertex or the right lower vertex of the target frame can be obtained, and the scale value corresponding to the position of the water line can be obtained.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Fig. 8 is a schematic structural diagram of a water level identification device of a water level gauge according to an embodiment of the present application, including:
an image to be identified acquiring unit 801, configured to acquire an image to be identified that includes water gauge information;
a target frame identification unit 802, configured to identify, according to the trained water level gauge positioning network model, a target frame in which the water level gauge in the image to be identified is located;
an E character recognition unit 803, configured to recognize an E character in the target frame according to the trained character E detection network model;
a correction unit 804 for correcting the recognized E characters according to intervals between the E characters;
and a water level value determining unit 805 configured to determine a water level value corresponding to the water level line position according to the corrected E character.
The water level recognition apparatus of the water level line shown in fig. 8 corresponds to the water level recognition method of the water level line shown in fig. 1.
Fig. 9 is a schematic view of a water level identification apparatus of a water gauge according to an embodiment of the present application. As shown in fig. 9, the water level identifying apparatus 9 of the water gauge of this embodiment includes: a processor 90, a memory 91 and a computer program 92, such as a water level identification program for a water gauge, stored in said memory 91 and operable on said processor 90. The processor 90, when executing the computer program 92, implements the steps in the above-described embodiments of the water level identification method for each water level gauge. Alternatively, the processor 90 implements the functions of the modules/units in the above-described device embodiments when executing the computer program 92.
Illustratively, the computer program 92 may be partitioned into one or more modules/units that are stored in the memory 91 and executed by the processor 90 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 92 in the water level identification device 9 of the water gauge. For example, the computer program 92 may be divided into:
the device comprises an image to be identified acquiring unit, a water gauge information acquiring unit and a water gauge information acquiring unit, wherein the image to be identified acquiring unit is used for acquiring an image to be identified comprising water gauge information;
the target frame identification unit is used for identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
the E character recognition unit is used for recognizing the E character in the target frame according to the trained character E detection network model;
the correction unit is used for correcting the recognized E characters according to the intervals among the E characters;
and the water level value determining unit is used for determining the water level value corresponding to the water level line position according to the corrected E character.
The water level identification device 9 of the water level gauge may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The water level identification device of the water gauge may include, but is not limited to, a processor 90 and a memory 91. It will be appreciated by those skilled in the art that fig. 9 is merely an example of the water level identification device 9 of the water level gauge and does not constitute a limitation of the water level identification device 9 of the water level gauge, and that it may comprise more or less components than those shown, or some components may be combined, or different components may be combined, for example, the water level identification device of the water level gauge may further comprise an input output device, a network access device, a bus, etc.
The Processor 90 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 91 may be an internal storage unit of the water level identification device 9 of the water level gauge, such as a hard disk or a memory of the water level identification device 9 of the water level gauge. The memory 91 may also be an external storage device of the water level identification device 9 of the water level gauge, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the water level identification device 9 of the water level gauge. Further, the memory 91 may also include both an internal storage unit and an external storage device of the water level identification device 9 of the water gauge. The memory 91 is used for storing the computer program and other programs and data required for the water level identification device of the water level gauge. The memory 91 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A water level identification method of a water level gauge, the water level identification method of the water level gauge comprising:
acquiring an image to be identified comprising water level gauge information;
identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
identifying the E character in the target frame according to the trained character E detection network model;
correcting the recognized E characters according to the intervals among the E characters;
and determining a water level value corresponding to the water level line position according to the corrected E character.
2. The method for identifying the water level of the water level gauge according to claim 1, wherein the water level gauge positioning network model and/or the character E detection network model is an SSD300 target detection network.
3. The water level identification method of the water level gauge according to claim 1, wherein before the step of identifying the E character in the target frame according to the trained character E detection network model, the method further comprises:
cutting the original image according to the identified target frame to obtain a cut image corresponding to the target frame;
and amplifying the cut image to obtain an amplified image in the target frame.
4. The water level recognition method of the water level gauge according to claim 1, wherein the correcting the recognized E characters according to the intervals between the E characters comprises:
comparing a difference value of vertical coordinates between two adjacent E characters in the image with a height value of a single E character;
and determining the number of the E characters inserted between the two E characters according to the ratio of the longitudinal coordinate difference value to the height value of the single E character.
5. The method for identifying the water level of the water level gauge according to claim 1, wherein the step of determining the water level value corresponding to the water level line position according to the corrected E character comprises:
sequencing the corrected E characters;
determining a scale value corresponding to the E character in a fitting mode;
and determining a water level value corresponding to the water level line position according to the determined scale value of the E character.
6. The water level identification method of a water level gauge according to claim 1, further comprising:
acquiring first sample data of a water level image of a water level gauge, wherein the first sample data comprises a calibration target frame for calibrating the position of the water level gauge;
inputting the first sample data into a water level gauge positioning network model, and outputting an identification target frame of the first sample data;
and comparing the difference between the calibration target frame and the identification target frame, and adjusting the parameters of the water level gauge positioning network model according to the difference until the difference meets the preset requirement to obtain the trained water level gauge positioning network model.
7. The water level identification method of a water level gauge according to claim 1, further comprising:
acquiring second sample data comprising E characters, wherein the second sample data comprises calibration characters with determined positions;
inputting the second sample data into a character E detection network model, and outputting an identification character of the second sample data;
and comparing the difference between the recognition character and the calibration character, and adjusting the parameters of the side dance E detection network model according to the difference until the difference between the recognition character and the calibration character meets the preset requirement to obtain the trained character E detection network model.
8. A water level recognition apparatus of a water level gauge, comprising:
the device comprises an image to be identified acquiring unit, a water gauge information acquiring unit and a water gauge information acquiring unit, wherein the image to be identified acquiring unit is used for acquiring an image to be identified comprising water gauge information;
the target frame identification unit is used for identifying a target frame where the water level gauge in the image to be identified is located according to the trained water level gauge positioning network model;
the E character recognition unit is used for recognizing the E character in the target frame according to the trained character E detection network model;
the correction unit is used for correcting the recognized E characters according to the intervals among the E characters;
and the water level value determining unit is used for determining the water level value corresponding to the water level line position according to the corrected E character.
9. A water level identification device of a water level gauge, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the water level identification method of a water level gauge according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for identifying a water level of a water gauge according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058235.1A CN111259890A (en) | 2020-01-19 | 2020-01-19 | Water level identification method, device and equipment of water level gauge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058235.1A CN111259890A (en) | 2020-01-19 | 2020-01-19 | Water level identification method, device and equipment of water level gauge |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111259890A true CN111259890A (en) | 2020-06-09 |
Family
ID=70947171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010058235.1A Pending CN111259890A (en) | 2020-01-19 | 2020-01-19 | Water level identification method, device and equipment of water level gauge |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259890A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329644A (en) * | 2020-11-06 | 2021-02-05 | 中冶赛迪重庆信息技术有限公司 | Reservoir water level monitoring method and system, medium and electronic terminal |
| CN112926660A (en) * | 2021-02-26 | 2021-06-08 | 武汉大学 | Water level identification system and method with cooperative end edges |
| CN112991342A (en) * | 2021-04-29 | 2021-06-18 | 南京甄视智能科技有限公司 | Water level line detection method, device and system based on water level gauge image |
| CN113221898A (en) * | 2021-04-16 | 2021-08-06 | 北京科技大学 | Automatic water level gauge reading method |
| CN113435442A (en) * | 2021-05-07 | 2021-09-24 | 三峡大学 | Water level measuring method and device, water gauge and electronic equipment |
| CN113537129A (en) * | 2021-07-29 | 2021-10-22 | 河南浩宇空间数据科技有限责任公司 | Water level scale positioning and water level calculating method based on machine vision |
| CN115880683A (en) * | 2023-03-02 | 2023-03-31 | 江西省水利科学院(江西省大坝安全管理中心、江西省水资源管理中心) | Urban waterlogging ponding intelligent water level detection method based on deep learning |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445239A (en) * | 2010-09-29 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Novel water metering method for open channel based on multi-point water level |
| CN103487104A (en) * | 2013-07-03 | 2014-01-01 | 青岛大学 | System and method for collecting and identifying images of capillary pipe liquid level type data |
| US20140267736A1 (en) * | 2013-03-15 | 2014-09-18 | Bruno Delean | Vision based system for detecting a breach of security in a monitored location |
| CN107796488A (en) * | 2017-11-16 | 2018-03-13 | 西安交通大学 | A kind of slosh experimental bench based on motion platform and ultrasonic liquid level sensor |
| CN108549894A (en) * | 2018-04-03 | 2018-09-18 | 哈尔滨哈船智控科技有限责任公司 | A kind of shipping depth gauge image automatic reading method based on deep learning algorithm |
| CN109522889A (en) * | 2018-09-03 | 2019-03-26 | 中国人民解放军国防科技大学 | Hydrological ruler water level identification and estimation method based on image analysis |
| CN109543596A (en) * | 2018-11-20 | 2019-03-29 | 浙江大华技术股份有限公司 | A kind of water level monitoring method, apparatus, electronic equipment and storage medium |
| CN110276285A (en) * | 2019-06-13 | 2019-09-24 | 浙江工业大学 | A kind of shipping depth gauge intelligent identification Method in uncontrolled scene video |
| CN110472636A (en) * | 2019-07-26 | 2019-11-19 | 四创科技有限公司 | Water gauge E font scale recognition methods based on deep learning |
-
2020
- 2020-01-19 CN CN202010058235.1A patent/CN111259890A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102445239A (en) * | 2010-09-29 | 2012-05-09 | 联宇工程技术(武汉)有限公司 | Novel water metering method for open channel based on multi-point water level |
| US20140267736A1 (en) * | 2013-03-15 | 2014-09-18 | Bruno Delean | Vision based system for detecting a breach of security in a monitored location |
| CN103487104A (en) * | 2013-07-03 | 2014-01-01 | 青岛大学 | System and method for collecting and identifying images of capillary pipe liquid level type data |
| CN107796488A (en) * | 2017-11-16 | 2018-03-13 | 西安交通大学 | A kind of slosh experimental bench based on motion platform and ultrasonic liquid level sensor |
| CN108549894A (en) * | 2018-04-03 | 2018-09-18 | 哈尔滨哈船智控科技有限责任公司 | A kind of shipping depth gauge image automatic reading method based on deep learning algorithm |
| CN109522889A (en) * | 2018-09-03 | 2019-03-26 | 中国人民解放军国防科技大学 | Hydrological ruler water level identification and estimation method based on image analysis |
| CN109543596A (en) * | 2018-11-20 | 2019-03-29 | 浙江大华技术股份有限公司 | A kind of water level monitoring method, apparatus, electronic equipment and storage medium |
| CN110276285A (en) * | 2019-06-13 | 2019-09-24 | 浙江工业大学 | A kind of shipping depth gauge intelligent identification Method in uncontrolled scene video |
| CN110472636A (en) * | 2019-07-26 | 2019-11-19 | 四创科技有限公司 | Water gauge E font scale recognition methods based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 王周星: "指针式仪表读数自动识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329644A (en) * | 2020-11-06 | 2021-02-05 | 中冶赛迪重庆信息技术有限公司 | Reservoir water level monitoring method and system, medium and electronic terminal |
| CN112926660A (en) * | 2021-02-26 | 2021-06-08 | 武汉大学 | Water level identification system and method with cooperative end edges |
| CN113221898A (en) * | 2021-04-16 | 2021-08-06 | 北京科技大学 | Automatic water level gauge reading method |
| CN113221898B (en) * | 2021-04-16 | 2022-02-15 | 北京科技大学 | Automatic water level gauge reading method |
| CN112991342A (en) * | 2021-04-29 | 2021-06-18 | 南京甄视智能科技有限公司 | Water level line detection method, device and system based on water level gauge image |
| CN113435442A (en) * | 2021-05-07 | 2021-09-24 | 三峡大学 | Water level measuring method and device, water gauge and electronic equipment |
| CN113537129A (en) * | 2021-07-29 | 2021-10-22 | 河南浩宇空间数据科技有限责任公司 | Water level scale positioning and water level calculating method based on machine vision |
| CN115880683A (en) * | 2023-03-02 | 2023-03-31 | 江西省水利科学院(江西省大坝安全管理中心、江西省水资源管理中心) | Urban waterlogging ponding intelligent water level detection method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259890A (en) | Water level identification method, device and equipment of water level gauge | |
| CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
| CN111047640B (en) | Volumetric flask volume calibration method and device, terminal equipment and storage medium | |
| CN112912932B (en) | Calibration method and device for vehicle-mounted camera and terminal equipment | |
| CN112233076B (en) | Structural vibration displacement measurement method and device based on red round target image processing | |
| CN111325164B (en) | Pointer representation number identification method and device and electronic equipment | |
| CN112254635A (en) | Volume measurement method, device and system | |
| CN110660072B (en) | Method and device for identifying straight line edge, storage medium and electronic equipment | |
| CN111311671B (en) | Workpiece measuring method and device, electronic equipment and storage medium | |
| CN112966711A (en) | Pointer instrument indicating number identification method and system based on convolutional neural network | |
| CN112489140A (en) | Attitude measurement method | |
| CN108235777B (en) | Calibration method and device of ADAS camera, storage medium and terminal equipment | |
| CN110751141A (en) | Meter reading identification method and device, terminal equipment and storage medium | |
| CN111336938A (en) | Robot and object distance detection method and device thereof | |
| CN115546143A (en) | Method and device for positioning center point of wafer, storage medium and electronic equipment | |
| CN114170319A (en) | Method and device for adjusting test target | |
| CN111429399A (en) | Straight line detection method and device | |
| CN112146834A (en) | Method and device for measuring structural vibration displacement | |
| CN113470103A (en) | Method and device for determining camera action distance in vehicle-road cooperation and road side equipment | |
| CN113635299A (en) | Mechanical arm correction method, terminal device and storage medium | |
| CN111652874B (en) | Method, device, terminal and computer readable storage medium for measuring go-no go gauge | |
| CN112686246B (en) | License plate character segmentation method and device, storage medium and terminal equipment | |
| CN111695551B (en) | Method and device for reading dial, computer equipment and readable storage medium | |
| CN117115233B (en) | Dimension measurement method and device based on machine vision and electronic equipment | |
| CN116819561A (en) | Point cloud data matching method, system, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |
|
| RJ01 | Rejection of invention patent application after publication |