CN115100398A - Meter identification reading method, system, terminal equipment and medium - Google Patents
Meter identification reading method, system, terminal equipment and medium Download PDFInfo
- Publication number
- CN115100398A CN115100398A CN202210833539.XA CN202210833539A CN115100398A CN 115100398 A CN115100398 A CN 115100398A CN 202210833539 A CN202210833539 A CN 202210833539A CN 115100398 A CN115100398 A CN 115100398A
- Authority
- CN
- China
- Prior art keywords
- pointer
- area
- reading
- meter
- target
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention discloses a meter reading identification method, a meter reading identification system, a terminal device and a computer readable storage medium, wherein the method comprises the following steps: reading the position of a pointer in a dial plate area of a pointer instrument, wherein the dial plate area is divided into target areas based on preset color labels; determining whether the location is in the target area to alert when the pointer is in an area other than the target area. The invention can automatically read the position of the pointer in the pointer type instrument so as to give an alarm when the reading of the instrument is abnormal.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a meter identification reading method, a meter identification reading system, terminal equipment and a computer readable storage medium.
Background
Pointer instruments are widely used due to their high reliability and general adaptability to harsh environments. The instrument data monitoring has important significance in the aspects of equipment control, production safety and the like.
Currently, the reading of the numerical value of a pointer instrument generally utilizes a deep learning technology to identify the meter, further divide the meter in the whole picture, then identify and divide the pointer of the divided meter, and finally determine the specific numerical value pointed by the pointer.
However, in the pointer instrument reading mode, the image processing process is complicated, certain requirements are imposed on hardware, and further the instrument reading efficiency is low, the cost is high, and the pointer instrument reading mode cannot be applied to various instrument reading scenes.
Disclosure of Invention
The invention mainly aims to provide a meter reading identification method, a meter reading identification system, terminal equipment and a computer readable storage medium, and aims to automatically read the position of a pointer in a pointer type meter so as to give an alarm when the meter reading is abnormal.
In order to achieve the above object, the present invention provides a meter identification reading method, which comprises the following steps:
reading the position of a pointer in a dial plate area of a pointer instrument, wherein the dial plate area is divided into target areas based on preset color labels;
determining whether the location is in the target area to alert when the pointer is in an area other than the target area.
Optionally, the color label comprises: the first color tag and the second color tag, before the step of reading the position of the pointer in the dial region of the pointer instrument, further include:
and segmenting the dial area by using the first color label and the second color label through a computer vision library OpenCV to obtain a target area.
Optionally, after the step of determining whether the position is in the target area, the method further includes:
if the position is in the target area, ending the reading task of the pointer instrument display number;
and if the position is in other areas outside the target area, triggering an alarm.
Optionally, before the step of reading the position of the pointer in the dial area of the pointer instrument, the method further includes:
and acquiring a target representation picture, and extracting the dial area from the target representation picture.
Optionally, the step of obtaining a target representation picture and extracting the dial area from the target representation picture includes:
acquiring the target table picture at a preset fixed shooting angle through a camera carried by the inspection robot;
and segmenting the target representation picture through a preset detection model to obtain the dial area.
Optionally, before the step of reading the position of the pointer in the dial area of the pointer instrument, the method further includes:
acquiring a to-be-labeled table picture, and labeling the to-be-labeled table picture by using the first color label and the second color label;
and constructing a detection model according to the marked representation picture so as to determine the dial area by using the detection model.
Optionally, the step of constructing the detection model according to the marked representation picture includes:
determining a training set, a verification set and a test set according to the marked representation picture;
training a preset semantic segmentation network based on the training set to obtain a training model;
and verifying the training model based on the verification set, and testing the accuracy of the verified training model according to the test set to obtain the detection model.
In order to achieve the above object, the present invention further provides a meter identification and reading system, including:
the reading module is used for reading the position of a pointer in a dial plate area of the pointer type instrument, and the dial plate area is divided into target areas based on preset color labels;
and the determining module is used for determining whether the position is in the target area or not so as to alarm when the pointer is in other areas except the target area.
In order to achieve the above object, the present invention further provides a terminal device, where the terminal device includes a memory, a processor, and a meter identification reading program stored in the memory and operable on the processor, and when executed by the processor, the meter identification reading program implements the steps of the meter identification reading method as described above.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, having a meter identification reading program stored thereon, where the meter identification reading program, when executed by a processor, implements the steps of the meter identification reading method as described above.
To achieve the above object, the present invention also provides a computer program product comprising a computer program which, when being executed by a processor, implements the steps of the meter identification reading method as described above.
The invention provides a meter reading identification method, a meter reading identification system, a terminal device, a computer readable storage medium and a computer program product, wherein a target area is divided in a dial area of a pointer type meter on the basis of a preset color label by reading the position of a pointer in the dial area; determining whether the location is in the target area to alert when the pointer is in an area other than the target area.
Compared with the mode of reading the indicating number pointed by the pointer in the pointer type instrument in the prior art, the indicating number reading method and the indicating number reading device can divide a target area in the area of the instrument panel according to the color label, further monitor whether the position of the pointer is in the target area, and alarm the abnormal indicating number of the instrument when the position of the pointer is monitored to be in other areas except the target area, so that equipment risk is checked through maintainers. Therefore, the invention simplifies the reading mode of the indicating number of the pointer instrument, improves the automatic reading efficiency of the indicating number of the pointer instrument and saves the hardware cost at the same time. On the basis, when the abnormal indication of the instrument is monitored, the alarm can be given in time, and the safety of the equipment monitored by the pointer instrument is guaranteed.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a first flowchart of a meter reading identification method according to an embodiment of the present invention;
FIG. 3-1 is a first schematic view of a dial area of an embodiment of a meter reading identification method of the present invention;
FIG. 3-2 is a second schematic view of a dial area of an embodiment of the meter reading identification method of the present invention;
FIG. 4 is a second flowchart of an embodiment of a meter reading identification method according to the invention;
FIG. 5-1 is a first schematic view of an inspection robot according to an embodiment of the meter reading identification method of the present invention;
fig. 5-2 is a second schematic diagram of the inspection robot according to the meter reading identification method of the invention;
FIG. 6-1 is a third schematic view of a dial area of an embodiment of the method for reading and identifying a meter according to the invention;
FIG. 6-2 is a fourth schematic view of a dial area according to an embodiment of the reading identification method of the meter;
FIG. 7 is a functional block diagram of a meter identification reading system according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that the terminal device in the embodiment of the present invention may be used to implement automatic reading of the indication number of the pointer instrument.
As shown in fig. 1, the terminal device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory such as a disk memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the device configuration shown in FIG. 1 does not constitute a limitation of meter identification reading devices, and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a kind of computer storage medium, may include therein an operation, a network communication module, a user interface module, and a meter recognition reading program. The operations are programs that manage and control the hardware and software resources of the device, support the running of meter identification reading programs and other software or programs. In the apparatus shown in fig. 1, the user interface 1003 is mainly used for data communication with a client; the network interface 1004 is mainly used for establishing communication connection with a server; and the processor 1001 may be configured to call the meter identification reading program stored in the memory 1005 and perform the following operations:
reading the position of a pointer in a dial plate area of a pointer instrument, wherein the dial plate area is divided into target areas based on preset color labels;
determining whether the location is in the target area to alert when the pointer is in an area other than the target area.
Further, the color label includes: a first color tag and a second color tag, prior to the step of reading the position of the pointer in the dial area of the pointer meter, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005 and perform the following operations:
and segmenting the dial area by using the first color label and the second color label through a computer vision library OpenCV to obtain a target area.
Further, after the step of determining whether the location is in the target area, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005, and perform the following operations:
if the position is in the target area, ending the reading task of the pointer instrument readings;
and if the position is in other areas outside the target area, triggering an alarm.
Further, prior to the step of reading the position of the pointer in the dial region of the pointer meter, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005, and perform the following operations:
and acquiring a target representation picture, and extracting the dial area from the target representation picture.
Further, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005 and perform the following operations:
acquiring the target table picture at a preset fixed shooting angle through a camera carried by the inspection robot;
and segmenting the target representation picture through a preset detection model to obtain the dial area.
Further, prior to the step of reading the position of the pointer in the dial area of the pointer instrument, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005, and perform the following operations:
acquiring a to-be-labeled table picture, and labeling the to-be-labeled table picture by using the first color label and the second color label;
and constructing a detection model according to the marked representation picture so as to determine the dial area by using the detection model.
Further, the processor 1001 may be configured to call a meter identification reading program stored in the memory 1005 and perform the following operations:
determining a training set, a verification set and a test set according to the marked table pictures;
training a preset semantic segmentation network based on the training set to obtain a training model;
and verifying the training model based on the verification set, and testing the accuracy of the verified training model according to the test set to obtain the detection model.
Referring to fig. 2, fig. 2 is a schematic flow chart of a meter reading identification method according to a first embodiment of the present invention.
While a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different than presented herein.
In order to automatically read the reading of a pointer type instrument and timely perform risk investigation when monitoring that the reading of a notation is abnormal, the current method generally relies on a deep learning technology to identify the meter, then divides the meter in the whole picture, and then identifies and divides the pointer in the divided notation picture, and further reads out the specific numerical value pointed by the pointer, which can be summarized as follows: dial area extraction → pointer area extraction → determination of pointer value. However, in the actual meter reading monitoring scene, as long as the pressure value of the pointer type meter, such as a pressure meter, is within a certain range, it can be determined that the device monitored by the meter is currently in a normal working state, and there is no potential accident risk.
Therefore, in this embodiment, the meter is identified by using a deep learning technique, and then the meter is divided in the whole picture, so as to identify the positions of the blue label, the red label and the pointer in the area of the meter panel, and then determine whether the pointer is within the range formed by the blue label and the red label, so as to determine whether the pressure value of the meter is within a reasonable range, which can be summarized as: dial area extraction → hand position acquisition → determination of whether or not the hand is within the preset target area. Therefore, in the embodiment, whether the current reading is abnormal is determined by judging whether the pointer is in the preset area, so that the automatic reading process of the pointer type instrument is simplified, the reading efficiency of the instrument is improved, and an alarm and data feedback are timely carried out when the abnormal reading of the instrument is monitored.
Specifically, the meter reading identification method in this embodiment includes the following steps:
step S10, reading the position of a pointer in a dial area of the pointer instrument, wherein the dial area is divided into target areas based on preset color labels;
it should be noted that, in this embodiment, it is not necessary to accurately identify the pointer reading of the pointer instrument, but only the position of the pointer is identified, and whether the pointer is currently located in the preset area in the dial plate is determined, so that an abnormal alarm can be given in other areas where the pointer is monitored to be located outside the preset area, so as to perform risk troubleshooting by the service staff.
On the basis, after the terminal device obtains the dial plate area of the pointer instrument, the target area can be divided in the dial plate area in advance based on the preset color label, and then whether the position of the pointer instrument is located in the target area formed by dividing the target area based on the color label or not is read. In the embodiment, the inspection robot can be sent to each pointer instrument, and color labels and pointers in the disk area can be automatically identified so as to give an alarm when the reading of the pointer is abnormal.
Step S20, determining whether the position is in the target area, to alarm when the pointer is in other area than the target area.
The terminal device divides the color label in the preset watch panel area to obtain a target area, reads the position of the pointer in the watch panel area, and then further judges whether the current position of the pointer is in the target area, so that abnormal alarm is given when the pointer is in other areas except the target area.
It should be noted that, in this embodiment, for a pointer type instrument, such as a pressure gauge, when a pointer is within a certain range (i.e., a target area), it may be determined that a device monitored by the pressure gauge is currently abnormal and is in a normal operating state, and each pointer type instrument has its corresponding target area, so that a terminal device may dispatch a robot to the pointer type instrument to automatically read the pointer position, and determine the corresponding target area by using a color label according to different instrument types.
In this embodiment, after acquiring the dial area of the pointer instrument, the terminal device divides and extracts a color label pre-labeled in the dial from the dial area, and further reads whether a pointer in the dial area is currently located in a target area, so as to alarm when the pointer is located in another area outside the target area, that is, when the pointer is located in the other area.
Compared with the prior art that the indication number pointed by the pointer in the pointer type instrument is accurately read, in the invention, the target area in the area of the instrument panel is determined according to the color label in advance, and then the indication number abnormity alarm of the instrument is carried out when the monitoring pointer is positioned in other areas except the target area, so that a maintainer is informed to carry out equipment risk investigation. Therefore, the invention simplifies the reading mode of the indicating number of the pointer instrument, improves the automatic reading efficiency of the indicating number of the pointer instrument and saves the hardware cost at the same time. On the basis, when the abnormal indication of the instrument is monitored, the alarm can be given in time, and the safety of equipment monitored by the pointer instrument is guaranteed.
Further, a second embodiment of the meter identification reading of the present invention is presented based on the first embodiment of the meter identification reading of the present invention.
In this embodiment, before the step S10, "before the step of reading the position of the pointer in the dial area of the pointer instrument," the method may further include:
and step S30, segmenting a dial area of the pointer instrument by using the first color label and the second color label through a computer vision library OpenCV to obtain a target area.
It should be noted that, in this embodiment, as shown in fig. 3-1 and fig. 3-2, the color labels used include a first color label (for example, blue) and a second color label (for example, red), where the blue label can represent the minimum value of the number of pointers in the target area, and the red label is the maximum value that can represent the number of pointers in the target area, and it can be determined that the device monitored by the pointer instrument is in a normal operating state as long as it is identified that the meter pointer is in the area formed by the maximum value and the minimum value.
On the basis, after the terminal device obtains the dial area, the first color label, the second color label and the pointer in the dial area are identified. And then, cutting the dial area of the pointer instrument according to the first color label and the second color label by using an industrial personal computer built in the inspection robot through a computer vision library OpenCV to obtain a target area in the dial area, and outputting a dial area image containing the target area, wherein the dial area image is a binary image.
Further, after the step S20, "determining whether the position is in the target area", the method may further include:
step S40, if the position is in the target area, ending the meter identification reading task;
and step S50, if the position is in other areas outside the target area, triggering an alarm.
After identifying the pointer in the dial area, the terminal device further reads whether the pointer is currently in the target area constructed by the first color label and the second color label.
Specifically, for example, as shown in fig. 4, after recognizing the first color tag (blue), the second color tag (red), and the pointer in the meter area, the terminal device will further determine whether the pointer of the meter is currently in the target area constructed by the first color tag and the second color tag. If the pointer is judged to be in the target area currently, the current equipment monitored by the current instrument is considered to be in a normal working state currently, at the moment, the task of reading the instrument display number is finished, and the reading result is returned to the rear-end management platform. If the pointer is judged to be in other areas outside the target area, the equipment monitored by the current instrument is considered to be in an abnormal working state, namely potential accident risk exists, the terminal equipment alarms to remind maintenance personnel to check the equipment risk in time,
further, before "reading the position of the pointer in the dial area of the pointer instrument" in step S10, the method may further include:
step S60, a target representation picture is obtained, and the dial area is extracted from the target representation picture.
Before a dial area of the pointer instrument is divided into target areas based on preset color labels by the terminal equipment, a target representation picture containing the dial area needs to be obtained in advance, and the dial area is extracted from the target representation picture.
Further, the step S60 may include:
step S601, collecting the target table picture at a preset fixed shooting angle through a camera carried by the inspection robot;
step S602, segmenting the target representation picture through a preset detection model to obtain the dial area.
It should be noted that, in this embodiment, the terminal device may dispatch the inspection robot to the pointer instrument, where the inspection robot carries a trained camera as shown in fig. 5-1 and 5-2.
Furthermore, the terminal device can acquire the target representation picture shown in fig. 6-1 and 6-2 at a preset fixed shooting angle through a camera carried by the inspection robot, and further can segment the target representation picture through a target detection algorithm Yolo v5 in the detection model to obtain the dial area shown in fig. 3-1 and 3-2.
Further, before "reading the position of the pointer in the dial area of the pointer instrument" in step S10, the method further includes:
step S70, obtaining a to-be-labeled representation picture, and labeling the to-be-labeled representation picture by using the first color label and the second color label;
and step S80, determining a detection model according to the marked representation picture so as to determine the dial area by using the detection model.
In this embodiment, in order to accurately identify the first color label, the second color label, and the pointer and accurately segment the target region, a detection model capable of accurately identifying the color labels and the pointer needs to be constructed in advance.
Specifically, for example, the method includes the steps of collecting the representation pictures of a plurality of pointer type meters, and labeling each representation picture by using a first color label and a second color label through labelimg software to form a bboxes label file containing a plurality of labeled representation pictures. And then, constructing a detection model according to the marked representation picture so as to identify and divide the color label by using the detection module.
Further, in step S80, the "determining the detection model according to the marked representation picture" may include:
step S801, determining a training set, a verification set and a test set according to the marked table picture;
step S802, training a preset semantic segmentation network based on the training set to obtain a training model;
and S803, verifying the training model based on the verification set, and testing the accuracy of the verified training model according to the test set to obtain the detection model.
After the terminal equipment acquires the marked table pictures of the pointer instrument, classifying the marked table pictures into a test set, a training set and a verification set; inputting the training set into a Yolo v5 semantic segmentation network to obtain a training model; and verifying the accuracy of the training model by using the verification set, testing the accuracy of the verified training model by using the test set, and determining the training model at the moment as a detection model when the accuracy of the training model is higher than a preset accuracy threshold value.
In this embodiment, after acquiring the dial area, the terminal device identifies the first color label, the second color label, and the pointer in the dial area. And then, an industrial personal computer arranged in the inspection robot is used for cutting the dial area of the pointer instrument according to the first color label and the second color label through OpenCV in the detection model to obtain a target area in the dial area. Terminal equipment needs to collect the table picture of a plurality of pointer instruments in advance, and then through labellimg software, each table picture is marked with the first color label and the second color label. And then constructing a detection model according to the marked representation picture. When the terminal device judges that the pointer is currently in the target area, the device monitored by the current instrument can be considered to be currently in a normal working state. If the pointer is judged to be located in other areas except the target area, the equipment monitored by the current instrument can be considered to be in an abnormal working state, namely potential accident risks exist, and at the moment, the terminal equipment gives an alarm.
In the invention, a target area in the meter area is constructed by utilizing the first color label and the second color label, and further, when the monitoring pointer is positioned in other areas except the target area, the alarm of meter indication abnormity is carried out. Therefore, the reading mode of the indicating number of the pointer instrument is simplified without identifying the indicating number of the instrument pointed by the pointer, the automatic reading efficiency of the indicating number of the pointer instrument is improved, and the safety of equipment monitored by the pointer instrument is further guaranteed.
In addition, an embodiment of the present invention further provides a meter identification and reading system, and referring to fig. 7, the meter identification and reading system includes:
the reading module 10 is used for reading the position of a pointer in a dial area of the pointer type instrument, and the dial area is divided into target areas based on preset color labels;
a determining module 20, configured to determine whether the position is in the target area, so as to alarm when the pointer is in another area outside the target area.
Further, the color label includes: a first color label and a second color label, the meter identification reading system, further comprising:
and the segmentation module is used for segmenting the dial area by using the first color label and the second color label through a computer vision library OpenCV to obtain a target area.
Further, the meter identification reading system further comprises:
the ending module is used for ending the reading task of the indicating number of the pointer instrument if the position is in the target area;
and the alarm module is used for triggering an alarm if the position is in other areas except the target area.
Further, the meter identification reading system further comprises:
and the extraction module is used for acquiring a target representation picture and extracting the dial area from the target representation picture.
Further, the extraction module comprises:
the acquisition unit is used for acquiring the target table picture at a preset fixed shooting angle through a camera carried by the inspection robot;
and the second division unit is used for dividing the target representation picture through a preset detection model to obtain the dial area.
Further, the meter identification reading system further comprises:
the marking unit is used for acquiring the to-be-marked representation picture and marking the to-be-marked representation picture by utilizing the first color label and the second color label;
and the construction unit is used for constructing a detection model according to the marked representation picture so as to determine the dial area by using the detection model.
Further, the building unit includes:
the determining subunit is used for determining a training set, a verification set and a test set according to the marked representation pictures;
the training subunit is used for training a preset semantic segmentation network based on the training set to obtain a training model;
and the testing subunit is used for verifying the training model based on the verification set and testing the accuracy of the verified training model according to the testing set to obtain the detection model.
The specific implementation of the meter reading identification system of the present invention has basically the same extension as the embodiments of the meter reading identification method, and is not described herein again.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a meter identification reading program is stored on the storage medium, and when the meter identification reading program is executed by a processor, the steps of the meter identification reading method are implemented as follows.
The embodiments of the meter reading identification device and the computer-readable storage medium of the present invention can refer to the embodiments of the meter reading identification method of the present invention, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A meter identification reading method is characterized by comprising the following steps:
reading the position of a pointer in a dial plate area of a pointer instrument, wherein the dial plate area is divided into target areas based on preset color labels;
determining whether the location is in the target area to alert when the pointer is in an area other than the target area.
2. The meter identification reading method of claim 1, wherein the color label comprises: a first color tag and a second color tag, prior to the step of reading the position of a pointer in a dial region of a pointer instrument, comprising:
and segmenting the dial area by using the first color label and the second color label through a computer vision library OpenCV to obtain a target area.
3. The meter identification reading method of claim 1, after the step of determining whether the location is in the target area, further comprising:
if the position is in the target area, ending the reading task of the pointer instrument display number;
and if the position is in other areas outside the target area, triggering an alarm.
4. The meter identification reading method of claim 1, further comprising, prior to the step of reading the position of the pointer in the meter area of the pointer meter:
and acquiring a target representation picture, and extracting the dial area from the target representation picture.
5. The meter identification reading method of claim 4, wherein the step of obtaining a target representative picture and extracting the dial area from the target representative picture comprises:
acquiring the target table picture at a preset fixed shooting angle through a camera carried by the inspection robot;
and segmenting the target representation picture through a preset detection model to obtain the dial area.
6. The meter identification reading method of claim 2, further comprising, prior to the step of reading the position of the pointer in the meter area of the pointer meter:
acquiring a to-be-labeled table picture, and labeling the to-be-labeled table picture by using the first color label and the second color label;
and constructing a detection model according to the marked representation picture so as to determine the dial area by using the detection model.
7. The meter reading method as set forth in claim 6, wherein the step of constructing a test model from the marked representation picture comprises:
determining a training set, a verification set and a test set according to the marked table pictures;
training a preset semantic segmentation network based on the training set to obtain a training model;
and verifying the training model based on the verification set, and testing the accuracy of the verified training model according to the test set to obtain the detection model.
8. A meter identification reading system, comprising:
the reading module is used for reading the position of a pointer in a dial plate area of the pointer type instrument, and the dial plate area is divided into target areas based on preset color labels;
and the determining module is used for determining whether the position is in the target area or not so as to alarm when the pointer is in other areas except the target area.
9. A terminal device comprising a memory, a processor and a base meter identification reading program stored on the memory and executable on the processor, the meter identification reading program when executed by the processor implementing the steps of the meter identification reading method of any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a meter identification reading program, which when executed by a processor, performs the steps of the meter identification reading method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210833539.XA CN115100398A (en) | 2022-07-15 | 2022-07-15 | Meter identification reading method, system, terminal equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210833539.XA CN115100398A (en) | 2022-07-15 | 2022-07-15 | Meter identification reading method, system, terminal equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115100398A true CN115100398A (en) | 2022-09-23 |
Family
ID=83298795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210833539.XA Pending CN115100398A (en) | 2022-07-15 | 2022-07-15 | Meter identification reading method, system, terminal equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115100398A (en) |
-
2022
- 2022-07-15 CN CN202210833539.XA patent/CN115100398A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6522869B1 (en) | Automatic reading system and reading method of indication value of pointer of analog meter | |
| KR101934571B1 (en) | Analog tester management, and managing method using the same | |
| CN112508109B (en) | Training method and device for image recognition model | |
| US9965841B2 (en) | Monitoring system based on image analysis of photos | |
| CN111724496A (en) | Attendance checking method, attendance checking device and computer readable storage medium | |
| CN115372877B (en) | Lightning arrester leakage ammeter inspection method of transformer substation based on unmanned aerial vehicle | |
| CN110138637B (en) | Test data processing method and device, computer equipment and storage medium | |
| CN111290931B (en) | Method and device for visually displaying buried point data | |
| CN106294161A (en) | The interface function method of testing of a kind of application and device | |
| CN108629310B (en) | Engineering management supervision method and device | |
| KR20170010753A (en) | Method for the optical detection of symbols | |
| CN111310351B (en) | Method and device for monitoring state of workshop equipment, terminal equipment and storage medium | |
| CN115100398A (en) | Meter identification reading method, system, terminal equipment and medium | |
| CN115035481A (en) | Image object distance fusion method, device, equipment and storage medium | |
| CN114896096A (en) | Data center equipment fault prediction system and method based on image recognition algorithm | |
| CN209946948U (en) | Intelligent reinspection equipment of PC component | |
| CN114637721A (en) | Method for configuring and displaying information, computer program product and electronic device thereof | |
| JP6818795B2 (en) | Information processing equipment, information processing methods and computer programs | |
| CN111626369B (en) | Face recognition algorithm effect evaluation method and device, machine readable medium and equipment | |
| CN114827550A (en) | RPA and AI combined monitoring equipment inspection method and device and electronic equipment | |
| JP7500661B2 (en) | COMPUTER DEVICE, CONTROL METHOD, AND COMPUTER PROGRAM | |
| CN116403165B (en) | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium | |
| US20230410516A1 (en) | Information acquisition support apparatus, information acquisition support method, and recording medium storing information acquisition support program | |
| CN115082670A (en) | Instrument data acquisition method, data processing method and equipment | |
| CN113220397B (en) | Dynamic change display system based on AOD information screen display |
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 |