CN109977725B - Water meter reading method and system - Google Patents
Water meter reading method and system Download PDFInfo
- Publication number
- CN109977725B CN109977725B CN201711443684.2A CN201711443684A CN109977725B CN 109977725 B CN109977725 B CN 109977725B CN 201711443684 A CN201711443684 A CN 201711443684A CN 109977725 B CN109977725 B CN 109977725B
- Authority
- CN
- China
- Prior art keywords
- water meter
- meter image
- image
- dial
- pointer
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 530
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 65
- 238000012806 monitoring device Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 9
- 238000013499 data model Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a water meter reading method and a system, wherein the method comprises the following steps: the water meter monitoring equipment uploads the 1 st water meter image to a server; the server obtains pointer position information in the 1 st water meter image and the rotation angle of the 1 st water meter image; the pointer position information of the 1 st water meter image is sent to water meter monitoring equipment; the water meter monitoring equipment performs image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; obtaining pointer position change information of an ith water meter image relative to the 1 st water meter image; transmitting pointer position change information to the server; the server obtains the corresponding reading of each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information; therefore, the combined identification of the water meter monitoring equipment and the server on the water meter dial can reduce the image uploading power consumption and the image identification processing calculated amount of the water meter monitoring equipment.
Description
Technical Field
The invention relates to the field of water meter data acquisition, in particular to a water meter reading method and system, which can be applied to remote meter reading of an intelligent water meter.
Background
Along with the development of the internet of things, the remote meter reading service for the water meter becomes an emerging service field of the internet of things; the current remote meter reading service of the Internet of things can be divided into meter reading service aiming at an intelligent water meter and meter reading service aiming at a traditional non-intelligent water meter; when the meter reading business aiming at the intelligent water meter is realized, the intelligent water meter can directly report own data remotely to realize meter reading; when the traditional meter reading business of the non-intelligent water meter is realized, after the non-intelligent water meter is hung with monitoring equipment, the monitoring equipment is used for collecting and reporting the data of the non-intelligent water meter; for example, currently, when a meter is read for a non-intelligent water meter, the common methods are: and reading dial information of the non-intelligent water meter by using an external camera of the non-intelligent water meter.
In the field of non-intelligent water meter reading, the current meter reading based on camera image acquisition mainly comprises the following two meter reading schemes:
meter reading scheme 1): the shot pictures are directly uploaded by using the monitoring equipment, and then the water meter reading in the pictures is identified by the remote server.
Meter reading scheme 2): the monitoring equipment identifies the locally shot water meter picture, and then uploads the identification result.
For meter reading scheme 1), the local monitoring equipment does not need to carry out processing such as picture identification, and the requirement on the local computing capacity of the monitoring equipment is low, but more communication resources (more flow) are consumed due to the fact that pictures are required to be sent to a remote server, and the power consumption of the monitoring equipment in the uploading process is also larger, so that the service life of the monitoring equipment is influenced;
for meter reading scheme 2), although the communication resources consumed by uploading the identification result (usually the reading of the water meter) are less, the local image identification calculation amount of the monitoring equipment is larger, the calculation capability of the monitoring equipment is higher, and the hardware cost of the monitoring equipment is increased.
Disclosure of Invention
In order to solve the technical problems, the embodiment of the invention is expected to provide a water meter reading method and a water meter reading system, and the combined identification of water meter monitoring equipment and a server on a water meter dial can reduce the image uploading power consumption and the image identification processing calculated amount of the water meter monitoring equipment.
The technical scheme of the invention is realized as follows:
the embodiment of the invention provides a water meter reading method, which comprises the following steps:
the water meter monitoring equipment shoots the water meter dial for the 1 st time to obtain the 1 st water meter image; uploading the 1 st water meter image to a server;
The server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and a rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position;
the water meter monitoring equipment obtains an ith water meter image by carrying out ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1;
and the server obtains the reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information.
In an embodiment of the present invention, the pointer position information includes: coordinates and pointer shape data of each pointer of the water meter;
the pointer position change information includes: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
In an embodiment of the present invention, each pointer of the water meter includes: a bit pointer, a ten-bit pointer, a hundred-bit pointer, and a kilobit pointer.
In the embodiment of the invention, the pointer shape data is image data of a pointer or modeling description data of the pointer, and the modeling description data of the pointer is used for representing the description data of the pointer in a pre-established data model.
In the embodiment of the invention, the method further comprises the following steps: the dial angle identification of the dial of the water meter is determined in advance, the server carries out image identification on the 1 st water meter image, and coordinates and shape data of the dial angle identification in the 1 st water meter image are obtained; transmitting the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image to the water meter monitoring equipment; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial;
The image recognition of the ith water meter image comprises the following steps: and according to the ith water meter image, the rotation angle of the 1 st water meter image and the coordinate and shape data of the dial angle mark in the 1 st water meter image, determining that the ith water meter image is matched with the 1 st water meter image, and carrying out image identification on the ith water meter image.
In the embodiment of the invention, the method further comprises the following steps: and according to the ith water meter image, the rotation angle of the 1 st water meter image and the coordinate and shape data of the dial angle mark in the 1 st water meter image, determining that the ith water meter image is not matched with the 1 st water meter image, and ignoring the 1 st water meter image to the ith water meter image.
In the embodiment of the invention, the shape data of the dial angle mark is image data of the dial angle mark or modeling description data of the dial angle mark, and the modeling description data of the dial angle mark is used for representing the description data of the dial angle mark in a pre-established data model.
In the embodiment of the present invention, the server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image, including:
The server converts the 1 st water meter image into a gray level image, and detects pointer position information in the 1 st water meter image in the gray level image by utilizing a preset standard pointer shape based on a generalized Hough transformation algorithm.
In the embodiment of the present invention, the server performs image recognition on the 1 st water meter image to obtain the rotation angle of the 1 st water meter image, and the method includes:
determining dial angle marks of a water meter dial; converting the 1 st water meter image into a gray scale image; detecting and obtaining coordinates and shape data of the dial angle mark in the 1 st water meter image in the gray level diagram based on a generalized Hough transform algorithm by utilizing a standard shape of the preset dial angle mark; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial; the rotation angle of the dial angle mark is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
And obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
The embodiment of the invention also provides a water meter reading system, which comprises a water meter monitoring device and a server; wherein,,
the water meter monitoring equipment is used for shooting a water meter dial for the 1 st time to obtain a 1 st water meter image; uploading the 1 st water meter image to a server;
the server is used for carrying out image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and the rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position;
the water meter monitoring equipment is also used for obtaining an ith water meter image by carrying out ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1;
The server is further configured to obtain a reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information.
In an embodiment of the present invention, the pointer position information includes: coordinates and pointer shape data of each pointer of the water meter;
the pointer position change information includes: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
In the embodiment of the invention, the server is further used for pre-determining dial angle identification of a water meter dial, and carrying out image identification on the 1 st water meter image to obtain coordinate and shape data of the dial angle identification in the 1 st water meter image; transmitting the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image to the water meter monitoring equipment; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial;
correspondingly, the water meter monitoring equipment is specifically configured to perform image recognition on the ith water meter image when determining that the ith water meter image is matched with the 1 st water meter image according to the ith water meter image, the rotation angle of the 1 st water meter image, and coordinates and shape data of a dial angle identifier in the 1 st water meter image.
In the embodiment of the invention, the server is specifically configured to convert the 1 st water meter image into a gray level image, and detect pointer position information in the 1 st water meter image in the gray level image based on a generalized hough transform algorithm by using a preset standard pointer shape.
In the embodiment of the invention, the server is specifically used for determining the dial angle mark of the water meter dial; converting the 1 st water meter image into a gray scale image; detecting and obtaining coordinates and shape data of the dial angle mark in the 1 st water meter image in the gray level diagram based on a generalized Hough transform algorithm by utilizing a standard shape of the preset dial angle mark; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial; the rotation angle of the dial angle mark is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
And obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
In the embodiment of the invention, the water meter monitoring equipment shoots the water meter dial for the 1 st time to obtain the 1 st water meter image; uploading the 1 st water meter image to a server; the server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and a rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position; the water meter monitoring equipment obtains an ith water meter image by carrying out ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1; and the server obtains the reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information.
According to the technical scheme, the water meter monitoring equipment and the server are used for jointly identifying the water meter dial, so that the image uploading power consumption and the image identification processing calculated amount of the water meter monitoring equipment can be reduced.
Drawings
FIG. 1 is a flow chart of a water meter reading method according to an embodiment of the invention;
FIG. 2 is a schematic illustration of a 1 st water meter image according to an embodiment of the present invention;
FIG. 3 is a schematic illustration of a water meter image corresponding to FIG. 2 at a predetermined reference position;
fig. 4 is a schematic structural diagram of a water meter reading system according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
The embodiment of the invention can realize remote meter reading of the non-intelligent water meter by utilizing the water meter monitoring equipment and the server; the water meter monitoring equipment has image shooting capability and image recognition capability, and in practical application, the water meter monitoring equipment can comprise equipment such as a camera, a processor and the like, and the camera can be connected with the processor; the server and the water meter monitoring equipment can form wireless communication connection, the server can perform data interaction with the water meter monitoring equipment, and the embodiment of the invention does not limit the communication mode of the server and the water meter monitoring equipment; the server has image recognition capability; the embodiment of the invention does not limit the distance between the server and the water meter monitoring equipment.
Based on the above-described water meter monitoring device and server, the following embodiments are presented.
First embodiment
In a first embodiment of the present invention, a water meter reading method is provided, and fig. 1 is a flowchart of a water meter reading method in an embodiment of the present invention, as shown in fig. 1, the flowchart may include:
step 101: the water meter monitoring equipment shoots the water meter dial for the 1 st time to obtain the 1 st water meter image; uploading the 1 st water meter image to a server;
illustratively, the meter includes a plurality of pointers, for example, each pointer of the meter includes at least one integer bit pointer, which may be a bit pointer, a ten bit pointer, a hundred bit pointer, or a kilobit pointer.
Optionally, each pointer of the water meter may further include at least one split pointer, where the split pointer may be a tenth pointer, a percentile pointer, a thousandth pointer, or a ten thousandth pointer. Here, the index of the index is small and can be ignored. Note that the color of the integer bit pointer and the split bit pointer may be the same or different.
Step 102: the server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and a rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position.
Illustratively, the pointer location information includes: coordinates and pointer shape data of each pointer of the water meter; for example, the pointer shape data is image data of a pointer or modeling description data of a pointer, which is used to represent description data of the pointer in a pre-established data model.
For example, the modeling description data of the pointer may be a stretch size of the pointer or a stretch coefficient acquired when the pointer is identified.
It will be appreciated that the location information of each pointer of the meter in the meter image may be determined in combination with the coordinates of each pointer and the pointer shape data of the meter.
For the implementation manner of obtaining the pointer position information in the 1 st water meter image, in an optional example, the server converts the 1 st water meter image into a gray scale image, and detects the pointer position information in the 1 st water meter image in the gray scale image based on a generalized hough transform algorithm and by using a preset standard pointer shape.
Here, the standard pointer shape may be input into the server in advance by the user.
For example, the 4 integer bit pointers of the water meter may be a unit pointer, a ten bit pointer, a hundred bit pointer, or a kilobit pointer; the color of the integer pointer in the water meter is different from that of the split pointer, and the color of the split pointer is red; when the server performs image recognition on the 1 st water meter image, firstly shielding a red pointer in the 1 st water meter image (one implementation way is to convert red in the 1 st water meter image into white by using color mapping), and then converting the 1 st water meter image into a gray scale image;
Traversing the stretching coefficient, the pointer angle and the coordinates in the gray level map based on a generalized Hough transformation algorithm by utilizing a preset standard pointer shape, finding candidate pointer positions and stretching coefficients, forming a candidate set by the stretching coefficients obtained when the candidate pointer positions and the pointers are identified, merging the candidate set into 4 types of sub-candidate sets based on a distance threshold, and selecting 4 pointer positions with highest peak values output by using the Hough transformation algorithm when the stretching coefficients are consistent in the 4 types of sub-candidate sets; thus, pointer position information in the 1 st water meter image can be obtained.
Here, for the water meter image, the preset reference position may be preset as needed; fig. 2 is a schematic diagram of a 1 st water meter image according to an embodiment of the present invention, fig. 3 is a schematic diagram of a water meter image corresponding to fig. 2 at a preset reference position, in fig. 3, four pointers on the right side are red pointers, and four pointers on the left side are black pointers. It can be seen that when the direction in which the 0 reading of each pointer in the water meter is located is the vertical direction (perpendicular to the horizontal direction), the water meter is located at a preset reference position; while the 1 st meter image shown in fig. 2 is not in the reference position.
For the implementation manner of obtaining the rotation angle of the 1 st water meter image, in one example, a dial angle identifier of a water meter dial is predetermined, wherein the dial angle identifier is an identifier capable of indicating the rotation angle of the 1 st water meter image in the water meter dial; in actual implementation, an object at a fixed position of a water meter dial can be selected in advance to be used as a dial angle mark; for example, for the water meter dial shown in fig. 2, the "m" letter may be identified as the dial angle.
After the dial angle identification is determined, the server performs image identification on the 1 st water meter image to obtain the coordinate and shape data of the dial angle identification in the 1 st water meter image.
Optionally, the server may detect, in the gray map, coordinate and shape data of the dial angle identifier in the 1 st water meter image based on a generalized hough transform algorithm and using a preset standard shape of the dial angle identifier; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; wherein, the rotation angle of dial plate angle sign is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
And obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
Here, the standard shape of the dial angle identification may be input into the server in advance by the user; for example, for the water meter dial shown in fig. 2, when the "m" letter can be identified as the dial angle, the standard shape of the "m" letter can be input into the server.
In the specific implementation, after determining the dial angle mark, the server searches through the traversing coordinate and the rotating angle in the picture based on a generalized Hough transformation algorithm and by utilizing the standard shape of the preset dial angle mark and the stretching coefficient obtained during pointer identification, and obtains the rotating angle of the dial angle mark, namely the rotating angle of the 1 st water meter image.
For example, when the "m" character can be used as the dial angle sign, the rotation angle of the "m" character shown in fig. 2 with respect to the "m" character shown in fig. 3 is the rotation angle of the dial angle sign.
Here, the shape data of the dial angle indicator is image data of the dial angle indicator or modeling description data of the dial angle indicator, which is used to represent description data of the dial angle indicator in a pre-established data model.
For example, the modeling description data of the dial angle indicator may be a stretch size of the dial angle indicator or a stretch coefficient acquired when the dial angle indicator is identified.
Optionally, after the rotation angle of the 1 st water meter image is obtained, the numerical values corresponding to the unit pointer, the ten-bit pointer, the hundred-bit pointer and the kilo-bit pointer can be determined according to the rotation angle.
It should be noted that the above-mentioned image recognition algorithm is only an exemplary algorithm, and in practical application, other image recognition algorithms may be used to recognize the effects of the pointer position, the stretch shape, the dial angle identification position, the stretch shape and the rotation angle, for example, the effect may be recognized by using a convolutional neural network; which image recognition algorithm is specifically adopted can be determined according to actual conditions.
Step 103: the method comprises the steps that a water meter monitoring device obtains an ith water meter image by carrying out ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1.
In actual implementation, the water meter monitoring equipment can shoot the water meter dial again after receiving pointer position information of the 1 st water meter image; for example, the water meter monitoring device may periodically photograph the water meter face after receiving pointer position information of the 1 st water meter image.
Here, the implementation manner of image recognition on the ith water meter image is the same as the implementation manner of image recognition on the 1 st water meter image, and will not be repeated here.
It can be understood that as the water consumption of the user increases, each pointer in the water meter dial is continuously rotated; on this basis, the pointer position change information includes: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image; specifically, when each pointer of the water meter image includes a unit pointer, a tens pointer, a hundreds pointer, and a thousands pointer, the above pointer position change information includes: the rotation angle of the unit pointer of the ith water meter image relative to the unit pointer of the 1 st water meter image, the rotation angle of the ten-bit pointer of the ith water meter image relative to the ten-bit pointer of the 1 st water meter image, the rotation angle of the hundred-bit pointer of the ith water meter image relative to the hundred-bit pointer of the 1 st water meter image, and the rotation angle of the thousand-bit pointer of the ith water meter image relative to the thousand-bit pointer of the 1 st water meter image.
It will be appreciated that when the pointer position information includes the coordinates and pointer shape data of each pointer of the water meter, by comparing the pointer position information in the 1 st water meter image with the pointer position information in the i-th water meter image, pointer position change information of the i-th water meter image with respect to the 1 st water meter image can be obtained.
In an alternative example, the meter monitoring device may convert the ith meter image to a gray scale; when the pointer shape data is the stretch coefficient obtained when the pointer is identified, the water meter monitoring device can search the rotation angle with the minimum total difference between the actual pointer shape and the gray level map at the coordinate position of each pointer according to the received coordinate and the stretch coefficient of each pointer of the water meter, and determine the rotation angle obtained by searching as the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
Optionally, in an implementation manner of performing image recognition on the ith water meter image, the server may send the rotation angle of the 1 st water meter image and coordinate and shape data of the dial angle identifier in the 1 st water meter image to the water meter monitoring device; and then judging whether the ith water meter image is matched with (matched with) the 1 st water meter image according to the ith water meter image, the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image.
And when the ith water meter image is determined to be matched with the 1 st water meter image, performing image recognition on the ith water meter image.
When it is determined that the i-th water meter image does not match the 1-th water meter image, the 1-th to i-th water meter images are ignored, and the process returns to step 101.
In actual implementation, the water meter monitoring device can convert the ith water meter image into a gray scale image; when the shape data of the dial angle mark is the stretching coefficient obtained when the dial angle mark is identified, the water meter monitoring equipment can obtain an image of the dial angle mark according to the received coordinate and stretching coefficient of the dial angle mark; then, carrying out overlap difference operation on the converted gray level pictures by utilizing the coordinate positions of the dial angle marks to obtain a total difference; if the obtained total difference is smaller than the set threshold, executing the step of performing image recognition on the ith water meter image, otherwise, returning to the step 101.
That is, the water meter monitoring device needs to determine whether the ith water meter image is matched with the 1 st water meter image, and then, only when the ith water meter image is matched with the 1 st water meter image, the ith water meter image is subjected to image recognition, so that timely correction errors can be reduced, erroneous results are avoided, and accuracy and reliability of water meter reading can be improved.
Step 104: and the server obtains the reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information.
In practical implementation, the server may sum the rotation angle of the 1 st water meter image with the rotation angle corresponding to each pointer in the pointer position change information, so as to obtain the angle of each pointer in the i-th water meter image when the water meter dial is at the preset reference position, and further obtain the reading corresponding to each pointer in the i-th water meter image.
It can be seen that in the embodiment of the invention, when the reading corresponding to each pointer in one water meter image needs to be determined, only the 1 st water meter image is uploaded by the water meter monitoring equipment, and the water meter monitoring equipment is not required to upload each photographed water meter image.
In addition, in the embodiment of the invention, when the reading corresponding to each pointer in one water meter image is required to be determined each time, the water meter monitoring equipment only needs to obtain the pointer position change information of one water meter image through image recognition, and other image processing and image recognition processes are realized in the server, so that compared with the existing meter reading scheme 2), the image recognition calculation amount of the water meter monitoring equipment is reduced, and the calculation power consumption and hardware cost of the water meter monitoring equipment can be reduced.
In summary, by applying the water meter reading method of the embodiment of the invention, the image uploading power consumption and the image recognition calculated amount of the water meter monitoring equipment are reduced by the combined calculation and interaction method of the server side and the water meter monitoring equipment, so that the service life and the hardware cost of the water meter monitoring equipment can be well balanced.
Second embodiment
On the basis of the water meter reading method provided by the first embodiment of the invention, the second embodiment of the invention provides a water meter reading system.
Fig. 4 is a schematic structural diagram of a water meter reading system according to an embodiment of the present invention, as shown in fig. 4, the system may include: a water meter monitoring device 401 and a server 402; wherein,,
the water meter monitoring device 401 is configured to perform 1 st shooting on a water meter dial to obtain a 1 st water meter image; uploading the 1 st water meter image to a server;
the server 402 is configured to perform image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and a rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position;
The water meter monitoring device 401 is further configured to obtain an ith water meter image by performing an ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1;
the server 402 is further configured to obtain a reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information.
Optionally, the pointer position information includes: coordinates and pointer shape data of each pointer of the water meter;
the pointer position change information includes: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
Optionally, each pointer of the water meter includes: a bit pointer, a ten-bit pointer, a hundred-bit pointer, and a kilobit pointer.
Optionally, the pointer shape data is image data of a pointer or modeling description data of the pointer, and the modeling description data of the pointer is used for representing description data of the pointer in a pre-established data model.
Optionally, the server 402 is further configured to determine a dial angle identifier of a dial of the water meter in advance, perform image recognition on the 1 st water meter image, and obtain coordinate and shape data of the dial angle identifier in the 1 st water meter image; transmitting the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image to the water meter monitoring equipment; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial;
correspondingly, the water meter monitoring device 401 is specifically configured to perform image recognition on the ith water meter image when determining that the ith water meter image is matched with the 1 st water meter image according to the ith water meter image, the rotation angle of the 1 st water meter image, and the coordinate and shape data of the dial angle identifier in the 1 st water meter image.
Optionally, the water meter monitoring device 401 is further configured to determine, according to the i-th water meter image, the rotation angle of the 1 st water meter image, and the coordinate and shape data of the dial angle identifier in the 1 st water meter image, to ignore the 1 st water meter image to the i-th water meter image when the i-th water meter image is not matched with the 1 st water meter image.
Optionally, the shape data of the dial angle identifier is image data of the dial angle identifier or modeling description data of the dial angle identifier, and the modeling description data of the dial angle identifier is used for representing the description data of the dial angle identifier in a pre-established data model.
Optionally, the server 402 is specifically configured to convert the 1 st water meter image into a gray scale image, and detect pointer position information in the 1 st water meter image in the gray scale image based on a generalized hough transform algorithm by using a preset standard pointer shape.
Optionally, the server 402 is specifically configured to determine a dial angle identifier of a dial of the water meter; converting the 1 st water meter image into a gray scale image; detecting and obtaining coordinates and shape data of the dial angle mark in the 1 st water meter image in the gray level diagram based on a generalized Hough transform algorithm by utilizing a standard shape of the preset dial angle mark; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial; the rotation angle of the dial angle mark is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
And obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
The technical schemes described in the embodiments of the present invention may be arbitrarily combined without any collision.
In several embodiments provided by the present invention, it should be understood that the disclosed method and intelligent device may be implemented in other manners. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described as separate units may or may not be physically separate, and units 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one second processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention.
Claims (14)
1. A method of reading a meter of a water meter, the method comprising:
the water meter monitoring equipment shoots the water meter dial for the 1 st time to obtain the 1 st water meter image; uploading the 1 st water meter image to a server;
the server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and a rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position;
The water meter monitoring equipment obtains an ith water meter image by carrying out ith shooting on a water meter dial; the water meter monitoring equipment performs image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; the water meter monitoring equipment obtains pointer position change information of the ith water meter image relative to the 1 st water meter image according to the pointer position information in the 1 st water meter image and the pointer position information in the ith water meter image; the water meter monitoring equipment sends the pointer position change information to the server; wherein i is an integer greater than 1;
the server obtains the reading corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information;
wherein the pointer position information includes: coordinates of each pointer and pointer shape data of the water meter.
2. The method of claim 1, wherein the pointer position change information comprises: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
3. The method of claim 2, wherein each pointer of the meter comprises: a bit pointer, a ten-bit pointer, a hundred-bit pointer, and a kilobit pointer.
4. The method according to claim 2, wherein the pointer shape data is image data of a pointer or modeling description data of a pointer, the modeling description data of the pointer being used to represent description data of the pointer in a pre-established data model.
5. The method according to claim 1, wherein the method further comprises: the dial angle identification of the dial of the water meter is determined in advance, the server carries out image identification on the 1 st water meter image, and coordinates and shape data of the dial angle identification in the 1 st water meter image are obtained; transmitting the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image to the water meter monitoring equipment; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial;
the image recognition of the ith water meter image comprises the following steps: and according to the ith water meter image, the rotation angle of the 1 st water meter image and the coordinate and shape data of the dial angle mark in the 1 st water meter image, determining that the ith water meter image is matched with the 1 st water meter image, and carrying out image identification on the ith water meter image.
6. The method of claim 5, wherein the method further comprises: and according to the ith water meter image, the rotation angle of the 1 st water meter image and the coordinate and shape data of the dial angle mark in the 1 st water meter image, determining that the ith water meter image is not matched with the 1 st water meter image, and ignoring the 1 st water meter image to the ith water meter image.
7. The method according to claim 5, wherein the shape data of the dial angle indicator is image data of the dial angle indicator or modeling description data of the dial angle indicator, and the modeling description data of the dial angle indicator is used for representing description data of the dial angle indicator in a pre-established data model.
8. The method of claim 1, wherein the server performs image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image, including:
the server converts the 1 st water meter image into a gray level image, and detects pointer position information in the 1 st water meter image in the gray level image by utilizing a preset standard pointer shape based on a generalized Hough transformation algorithm.
9. The method of claim 1, wherein the server performs image recognition on the 1 st water meter image to obtain a rotation angle of the 1 st water meter image, comprising:
determining dial angle marks of a water meter dial; converting the 1 st water meter image into a gray scale image; detecting and obtaining coordinates and shape data of the dial angle mark in the 1 st water meter image in the gray level diagram based on a generalized Hough transform algorithm by utilizing a standard shape of the preset dial angle mark; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial; the rotation angle of the dial angle mark is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
and obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
10. A water meter reading system, which is characterized by comprising a water meter monitoring device and a server; wherein,,
the water meter monitoring equipment is used for shooting a water meter dial for the 1 st time to obtain a 1 st water meter image; uploading the 1 st water meter image to a server;
the server is used for carrying out image recognition on the 1 st water meter image to obtain pointer position information in the 1 st water meter image and the rotation angle of the 1 st water meter image; transmitting the pointer position information of the 1 st water meter image to water meter monitoring equipment; the rotation angle of the 1 st water meter image is used for representing the rotation angle of the 1 st water meter image relative to the water meter image at a preset reference position;
the water meter monitoring equipment is also used for obtaining an ith water meter image by carrying out ith shooting on a water meter dial; performing image recognition on the ith water meter image to obtain pointer position information in the ith water meter image; according to the pointer position information in the 1 st water meter image and the pointer position information in the i th water meter image, obtaining pointer position change information of the i th water meter image relative to the 1 st water meter image; transmitting the pointer position change information to the server; wherein i is an integer greater than 1;
The server is further used for obtaining readings corresponding to each pointer in the ith water meter image according to the rotation angle of the 1 st water meter image and the pointer position change information;
wherein the pointer position information includes: coordinates of each pointer and pointer shape data of the water meter.
11. The system of claim 10, wherein the pointer position change information comprises: the rotation angle of each pointer of the ith water meter image relative to the corresponding pointer of the 1 st water meter image.
12. The system of claim 10, wherein the server is further configured to pre-determine a dial angle identifier of a water meter dial, and perform image recognition on the 1 st water meter image to obtain coordinates and shape data of the dial angle identifier in the 1 st water meter image; transmitting the rotation angle of the 1 st water meter image and coordinate and shape data of dial angle marks in the 1 st water meter image to the water meter monitoring equipment; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial;
correspondingly, the water meter monitoring equipment is specifically configured to perform image recognition on the ith water meter image when determining that the ith water meter image is matched with the 1 st water meter image according to the ith water meter image, the rotation angle of the 1 st water meter image, and coordinates and shape data of a dial angle identifier in the 1 st water meter image.
13. The system according to claim 10, wherein the server is specifically configured to convert the 1 st water meter image into a gray scale image, and detect pointer position information in the 1 st water meter image in the gray scale image based on a generalized hough transform algorithm and using a preset standard pointer shape.
14. The system according to claim 10, wherein the server is specifically configured to determine a dial angle identification of a water meter dial; converting the 1 st water meter image into a gray scale image; detecting and obtaining coordinates and shape data of the dial angle mark in the 1 st water meter image in the gray level diagram based on a generalized Hough transform algorithm by utilizing a standard shape of the preset dial angle mark; obtaining the rotation angle of the dial angle mark according to the coordinate and shape data of the dial angle mark in the 1 st water meter image and the coordinate and shape data of the dial angle mark in the water meter image at a preset reference position; the dial angle mark is a mark which can indicate the rotation angle of the 1 st water meter image in the water meter dial; the rotation angle of the dial angle mark is used for representing: the dial angle mark of the 1 st water meter image is relative to the rotation angle of the dial angle mark in the water meter image at the preset reference position;
And obtaining the rotation angle of the 1 st water meter image, wherein the rotation angle of the 1 st water meter image is the rotation angle of the dial angle mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711443684.2A CN109977725B (en) | 2017-12-27 | 2017-12-27 | Water meter reading method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711443684.2A CN109977725B (en) | 2017-12-27 | 2017-12-27 | Water meter reading method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109977725A CN109977725A (en) | 2019-07-05 |
| CN109977725B true CN109977725B (en) | 2023-10-31 |
Family
ID=67072218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711443684.2A Active CN109977725B (en) | 2017-12-27 | 2017-12-27 | Water meter reading method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109977725B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542905A (en) * | 2013-10-23 | 2014-01-29 | 福建省计量科学研究院 | Water meter flow identifying method |
| CN103955694A (en) * | 2014-04-09 | 2014-07-30 | 广州邦讯信息系统有限公司 | Image recognition meter reading system and method |
| CN105260709A (en) * | 2015-09-28 | 2016-01-20 | 北京石油化工学院 | Water meter detecting method, apparatus, and system based on image processing |
| CN105300482A (en) * | 2015-09-28 | 2016-02-03 | 北京石油化工学院 | Water meter calibration method, apparatus and system based on image processing |
| CN106682674A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | Pointer type meter automatic reading method based on intelligent tour-inspection robot |
| CN107220645A (en) * | 2017-05-24 | 2017-09-29 | 河北省计量监督检测研究院 | Water meter recognition methods based on dynamic image pro cess |
| CN107463931A (en) * | 2017-07-06 | 2017-12-12 | 国家电网公司 | A kind of real-time pointer instrument reading method and device based on ARM platforms |
-
2017
- 2017-12-27 CN CN201711443684.2A patent/CN109977725B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542905A (en) * | 2013-10-23 | 2014-01-29 | 福建省计量科学研究院 | Water meter flow identifying method |
| CN103955694A (en) * | 2014-04-09 | 2014-07-30 | 广州邦讯信息系统有限公司 | Image recognition meter reading system and method |
| CN105260709A (en) * | 2015-09-28 | 2016-01-20 | 北京石油化工学院 | Water meter detecting method, apparatus, and system based on image processing |
| CN105300482A (en) * | 2015-09-28 | 2016-02-03 | 北京石油化工学院 | Water meter calibration method, apparatus and system based on image processing |
| CN106682674A (en) * | 2016-12-23 | 2017-05-17 | 浙江大学 | Pointer type meter automatic reading method based on intelligent tour-inspection robot |
| CN107220645A (en) * | 2017-05-24 | 2017-09-29 | 河北省计量监督检测研究院 | Water meter recognition methods based on dynamic image pro cess |
| CN107463931A (en) * | 2017-07-06 | 2017-12-12 | 国家电网公司 | A kind of real-time pointer instrument reading method and device based on ARM platforms |
Non-Patent Citations (1)
| Title |
|---|
| 张宝印.图像校正.《基于矢量的时序图形图像处理技术研究与实践》.2008, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109977725A (en) | 2019-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
| CN102663360B (en) | Method for automatic identifying steel slab coding and steel slab tracking system | |
| CN110569856B (en) | Sample labeling method and device, and damage category identification method and device | |
| CN103955694A (en) | Image recognition meter reading system and method | |
| CN104899609B (en) | A kind of mechanical meter recognition methods based on image registration | |
| CN111950396B (en) | Meter reading neural network identification method | |
| CN109934108B (en) | Multi-target and multi-type vehicle detection and distance measurement system and implementation method | |
| CN112183367B (en) | Vehicle data error detection method, device, server and storage medium | |
| CN115294145B (en) | Method and system for measuring sag of power transmission line | |
| CN110634138A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| CN114279433A (en) | Map data automatic production method, related device and computer program product | |
| CN116338608B (en) | Method, device, equipment and storage medium for adjusting detection angle of microwave radar | |
| CN106682579B (en) | Unmanned aerial vehicle binocular vision image processing system for detecting icing of power transmission line | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| CN109903308B (en) | Method and device for acquiring information | |
| CN109977725B (en) | Water meter reading method and system | |
| CN112329666A (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN113763466A (en) | Loop detection method and device, electronic equipment and storage medium | |
| CN116091470A (en) | Intelligent industrial control method and device based on 5G technology, electronic equipment and storage medium | |
| CN116310263A (en) | Pointer type aviation horizon instrument indication automatic reading implementation method | |
| CN113239922B (en) | Virtual reality space positioning feature point recognition system and recognition method | |
| WO2015086076A1 (en) | Method for determining a similarity value between a first image and a second image | |
| CN114782852A (en) | Reading method, reading device and reading system of pointer type industrial instrument | |
| CN111539329B (en) | Self-adaptive substation pointer instrument identification method | |
| CN110516647A (en) | Moving objects location method and system based on image recognition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |