CN114596431A - Information determination method and device and electronic equipment - Google Patents
Information determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN114596431A CN114596431A CN202210230599.2A CN202210230599A CN114596431A CN 114596431 A CN114596431 A CN 114596431A CN 202210230599 A CN202210230599 A CN 202210230599A CN 114596431 A CN114596431 A CN 114596431A
- Authority
- CN
- China
- Prior art keywords
- dial plate
- information
- dial
- determining
- point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000013598 vector Substances 0.000 claims description 114
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 238000003062 neural network model Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The utility model provides an information determination method, an information determination device and an electronic device, which relate to the technical field of artificial intelligence, in particular to the technical field of intelligent inspection, visual identification and deep learning in artificial intelligence, and the concrete implementation scheme comprises the following steps: acquiring a target image; determining the area of a dial plate in the target image, and detecting the range information of the dial plate; detecting position information of key points of an area of the dial plate; and determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the field of intelligent inspection, visual recognition, and deep learning technologies in artificial intelligence, and in particular, to an information determination method and apparatus, and an electronic device.
Background
With the continuous development of dial plate technology, the application range of the mode of displaying information on the dial plate and reading the information on the dial plate in the life of people is wider and wider, and currently, when the information on the dial plate is read, the template graph is generally matched with the dial plate to be read, and the reading of the dial plate is realized according to the matching result.
Disclosure of Invention
The disclosure provides an information determination method and device and electronic equipment.
According to a first aspect of the present disclosure, there is provided an information determination method, including:
acquiring a target image;
determining the area of a dial plate in the target image, and detecting the range information of the dial plate;
detecting position information of key points of the dial plate area;
and determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
According to a second aspect of the present disclosure, there is provided an information determining apparatus including:
the acquisition module is used for acquiring a target image;
the first determining module is used for determining the area of the dial plate in the target image and detecting the range information of the dial plate;
the detection module is used for detecting the position information of key points in the dial plate area;
and the second determination module is used for determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any one of the methods of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform any one of the methods of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements any of the methods of the first aspect.
In the embodiment of the disclosure, the dial plate area in the target image is determined, and the reading information of the dial plate is determined according to the range information of the dial plate and the position information of the key point of the dial plate area, so that the intelligent degree of the determination mode of the reading information of the dial plate is improved; meanwhile, the reading information of the dial can be determined only by determining the range information and the position information of the key point, and the position information of each position on the dial is not required to be determined, so that the determination rate of the reading information of the dial is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
Fig. 1 is a flowchart of an information determination method provided by an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a first neural network model provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a plurality of network structures provided by embodiments of the present disclosure;
fig. 4 is one of schematic structural diagrams of a dial provided by an embodiment of the present disclosure;
fig. 5 is a second schematic structural diagram of the dial provided in the embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an information determination apparatus provided in an embodiment of the present disclosure;
fig. 7 is a second schematic structural diagram of an information determining apparatus provided in the embodiment of the present disclosure;
fig. 8 is a third schematic structural diagram of an information determination apparatus provided in the embodiment of the present disclosure;
fig. 9 is a fourth schematic structural diagram of an information determination apparatus provided in an embodiment of the present disclosure;
fig. 10 is a fifth schematic structural diagram of an information determination apparatus provided in the embodiment of the present disclosure;
FIG. 11 is a schematic block diagram of an example electronic device used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Referring to fig. 1, fig. 1 is a flowchart of an information determining method provided by an embodiment of the present disclosure, as shown in fig. 1, including the following steps:
and step S101, acquiring a target image.
The specific manner of acquiring the target image is not limited herein, and for example: the target image can be acquired by the camera in real time, or the target image sent by other electronic equipment can be received, and the target image can be acquired by the other electronic equipment, or the target image can be acquired from the server, and the target image can be uploaded to the server by the other electronic equipment.
And S102, determining the area of the dial in the target image, and detecting the range information of the dial.
As an alternative embodiment, the target detection technique may first identify the shape of each region in the target image, and then determine, as a candidate region, a region in each region having a matching degree with the shape of the dial that is greater than a preset matching degree, where the candidate region may also be referred to as a region of the dial.
In addition to the above embodiments, the target feature recognition may be further performed on the candidate area, and the target feature may refer to a feature specific to the dial, for example: the target feature may include at least one of a pointer and a scale mark, and thus, by further performing target feature recognition on the candidate region, the candidate region including the target feature is determined as a region of the dial, and the candidate region not including the target feature is determined as a region other than the dial, thereby further improving the accuracy of the determination result of the region of the dial.
As another optional implementation, the determining, in the target image, an area of a dial plate includes:
extracting features of the target image to obtain a plurality of first feature vectors;
clustering at least part of the first feature vectors in the plurality of first feature vectors to obtain second feature vectors;
and predicting according to the second feature vector to obtain a first target feature vector, wherein the first target feature vector is used for representing the area of the dial plate.
When the feature extraction is performed on the target image, first feature vectors of different scales can be extracted, wherein the scales can refer to any one of length, width and height. Therefore, the first feature vectors with different scales are extracted, so that the extracted first feature vectors can more comprehensively and fully reflect the features of different dimensions of each region in the target image.
It should be noted that, when the feature extraction is performed on the target image, the feature extraction may be performed on each region in the target image, and then a first feature vector is obtained by screening from the extracted feature vectors; or, the region of the target image may be preliminarily screened to obtain a candidate region, and then feature extraction may be performed on the candidate region, so that consumption of computing resources may be reduced.
Wherein, the plurality of first feature vectors may include a plurality of feature vector sets, the first feature vectors belonging to different sets have different scales, and the scales of the first feature vectors belonging to the same set may be the same, for example: the plurality of first feature vectors may include a first set and a second set, the first feature vectors in the first set may have different scales from the first feature vectors in the second set, and the scales of the first feature vectors in the first set may be the same.
In addition, when clustering at least a part of the first feature vectors in the plurality of first feature vectors, the first feature vectors with the same scale may be clustered, that is to say: the first feature vectors belonging to the same set may be clustered. Therefore, the first feature vectors with the same scale are clustered, so that the number of the first feature vectors can be reduced, and meanwhile, the second feature vector can keep the details of different first feature vectors as much as possible, so that the accuracy in the subsequent prediction of the first target feature vector according to the second feature vector is higher.
The first target feature vector for representing the area of the dial is obtained by performing prediction based on the second feature vector, and may be understood as: and determining the area of the dial plate in the target image according to the first target feature vector.
In the embodiment of the disclosure, feature extraction is performed on the target image to obtain a plurality of first feature vectors, and the scales of the first feature vectors can be different, so that the extracted first feature vectors can more comprehensively and fully reflect the features of different dimensions of each region in the target image. In addition, the first feature vectors with the same scale are clustered, so that the number of the first feature vectors can be reduced, meanwhile, the second feature vectors obtained through clustering can keep details of different first feature vectors as much as possible, the accuracy when the first target feature vectors are obtained through subsequent prediction according to the second feature vectors is higher, and the dial area can be predicted more accurately.
It should be noted that, alternatively, each step in the above embodiment may be performed by a first neural network model, and the first neural network model may be a neural network model trained in advance for identifying the area of the dial plate in the target image. In this way, the first neural network model can enable the obtained first target feature vector to predict the area of the dial plate more accurately, namely, the accuracy of the prediction result of the area of the dial plate is improved.
Optionally, referring to fig. 2, the first neural network model may include a first network structure 201, a second network structure 202, and a third network structure 203, which are connected in sequence, the first network structure 201 may be configured to perform a step of performing feature extraction on the target image to obtain a plurality of first feature vectors, the second network structure 202 may be configured to perform a step of clustering at least a part of the first feature vectors in the plurality of first feature vectors to obtain second feature vectors, and the third network model 203 may be configured to perform prediction according to the second feature vectors to obtain first target feature vectors, where the first target feature vectors are used to represent regions of the dial.
It should be noted that, referring to fig. 2, the first network model structure may further include an input layer connected to the first network structure 201, and configured to input the target image to the first network structure 201.
The first network structure 201 may adopt a cross-stage local network, so that the cross-stage local network may solve a problem of gradient information repetition of network optimization in a neural network model, and integrate a change of a gradient into a feature map (i.e., a first feature vector obtained by extraction) from beginning to end, thereby reducing parameters of the model and floating point operation times per second, ensuring reasoning speed and accuracy, and reducing the size of the model.
The second network structure 202 may be referred to as a Feature fusion network, and has a good adaptability to the scale of the Feature vector, and the second network structure 202 may adopt a new Feature Pyramid Networks (FPN) structure for enhancing the bottom-up path, so as to improve the propagation of the low-level Feature vector.
It should be noted that the second network structure 202 may include a plurality of branch networks, and each branch network may cluster the first feature vector on the branch network to obtain a second feature vector, and may also use the obtained second feature vector as an input vector of a next branch network, and the next branch network may cluster the second feature vector obtained by the previous branch network and the first feature vector having the same scale as the second feature vector, and output the second feature vector corresponding to the branch network, and may also use the second feature vector corresponding to the branch network as an input vector of another branch network. In this way, a plurality of second Feature vectors of different scales can be output sequentially, and at the same time, each second Feature vector on each Feature level (i.e. each scale level) can be aggregated by using Adaptive Feature Pooling (AFP) to recover corrupted information paths between the second Feature vector and all Feature levels (i.e. all scale levels) on each scale level.
The third network structure 203 may perform prediction according to the second feature vector, so as to generate a first target feature vector with information such as class probability, object score, and bounding box.
And step S103, detecting the position information of the key points in the dial area.
As an alternative implementation, the position information of the key points can be directly identified by using a point identification algorithm, which can be referred to as the idea of a Top-Down (Top-Down) human key point detection algorithm.
As another optional implementation, the detecting the position information of the key point of the area of the dial plate includes:
inputting image areas corresponding to the areas of the dial plate in the target image into a plurality of network structures to extract feature vectors;
and fusing the feature vectors extracted by different network structures to obtain a second target feature vector, wherein the second target feature vector is used for representing the position information of the key points of the dial area.
Referring to fig. 3, a plurality of network structures 301 may be connected in parallel, and of course, a plurality of network structures may also be connected in series. It should be noted that the network structure composed of the plurality of network structures 301 may also be referred to as a second neural network model, and the second network structure may be a network model for executing a target algorithm, which is not specifically limited herein, for example: the target algorithm may be the YOLOV5 algorithm.
In addition, when a plurality of network structures 301 are connected in parallel, each network structure 301 may include a plurality of sub-networks 3011, and the sub-networks 3011 in different network structures 301 may be connected to each other, so that information exchange may be performed, and thus fusion of feature vectors of different scales may be achieved. Specific connection structure patterns can be seen in fig. 3.
Wherein, the plurality of network structures 301 may be ordered according to a decreasing resolution, that is: referring to fig. 3, the resolution of the network structure 301 gradually decreases from top to bottom, so that the finally determined second target feature vector can retain details of the feature vector extracted by the high-resolution network structure and retain the abstraction rate of the feature vector extracted by the low-resolution network structure by fusing the feature vectors extracted by the network structures 301 with different resolutions.
In the embodiment of the present disclosure, through the fusion of the feature vectors extracted by different network structures, information exchange of different feature vectors can be realized, and further, fusion of feature vectors of different scales can be realized, that is, better position accuracy can be obtained, so that the obtained second target feature vector can more accurately represent position information of key points in the area of the dial plate.
And step S104, determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
As an alternative embodiment, the key points include a rotation center point of a pointer, an end point of the pointer, a start point of a scale mark of the dial plate, and an end point of the scale mark of the dial plate; the step of determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point comprises the following steps:
determining the rotation angle proportion of the pointer in the scale marks of the dial plate according to the rotation central point, the end point of the pointer, the starting point of the scale marks of the dial plate and the end point of the scale marks of the dial plate;
and determining the reading information of the dial plate according to the rotation angle ratio and the range information of the dial plate.
Referring to fig. 4, the rotation center point 401 is respectively connected with the end point 402 of the pointer, the start point 403 of the scale mark of the dial and the end point 404 of the scale mark of the dial, so as to obtain the rotation angle of the pointer rotating in the dial 40, and the occupation ratio of the rotation angle of the pointer between the start point 403 of the scale mark of the dial 40 and the end point 404 of the scale mark of the dial can be determined according to the rotation angle, for example: the starting point 403 of the scale marks of the dial 40 and the end point 404 of the scale marks of the dial 40 are located on the same horizontal plane, the angle between the starting point 404 of the scale marks of the dial 40 and the end point 404 of the scale marks of the dial 40 is 180 degrees, and the rotation angle of the pointer rotating in the dial 40 determined as above is 150 degrees, the rotation angle occupancy ratio is 150/180 ═ 5/6, and the reading information of the dial 40 can be equal to the product of the rotation angle occupancy ratio and the range information, such as: if the whole range information is 120, the reading information of the dial plate is 5/6 × 120 — 100, that is, the reading information is 100.
In addition, referring to fig. 5, as an alternative embodiment, the schematic position diagram of the dial and the key point may be as shown in fig. 5, and the key point may include a rotation center point 501, an end point 502 of the pointer, a start point 503 of the scale mark of the dial 50, and an end point 504 of the scale mark of the dial 50, and may further include a plurality of intermediate scale marks 505.
In the embodiment of the disclosure, the rotation angle ratio is determined only according to the position information of the key point, then the reading information of the dial plate can be accurately determined according to the rotation angle ratio and the range information, compared with the mode that the position information of each scale mark of the dial plate needs to be determined, then a certain scale mark points according to a pointer, and the reading information of the dial plate is determined according to the reading information of the scale mark, the position information required to be determined in the embodiment is less, when the information of the dial plate is incomplete, the reading information can be accurately determined according to the position information of the key point and the range information, the requirement for the dial plate is reduced, and the use scene of the dial plate is enlarged.
As another alternative, the key point may include reading information of a scale mark pointed by the pointer, so that the reading information of the scale mark pointed by the pointer may be directly read, and the reading information may be verified according to the range information, and if the reading information is smaller than the range information, the reading information may be determined as the reading information of the dial. Therefore, under the condition that the information of the dial plate is complete, the reading information of the dial plate can be directly read according to the reading information of the scale marks pointed by the pointer.
As another alternative, referring to fig. 4, the key points further include a plurality of middle tick marks 405, and the middle tick marks 405 are located between the start point 403 of the tick marks and the end point 404 of the tick marks; the method further comprises the following steps:
and correcting the position information of the rotating central point of the pointer according to the plurality of middle scale marks.
When the instrument is inclined and the like, and the rotation center point of the marked pointer and the plane where the scale mark is located are not on the same plane, the identified rotation center point of the pointer has a large offset error, and at this time, the rotation center point needs to be corrected.
In the embodiment of the present disclosure, a plurality of middle scale marks 405 may be determined, and when the confidence of the plurality of middle scale marks 405 is greater than the preset confidence, the middle scale marks 405 may be determined as the scale marks 405 with a higher confidence, so that the rotation center point of the pointer may be fitted according to the position information of the middle scale marks 405, and then the center point obtained by fitting may be determined as the rotation center point after correction, so that the accuracy of the position of the rotation center point may be improved, and the accuracy of the reading information of the dial plate that may be determined according to the position information of the rotation center point and other key points may be higher.
When the rotation center point of the pointer is fitted based on the position information of the middle scale marks 405, extension lines may be formed in the same direction along the straight line where each middle scale mark 405 is located, and the intersection point of the extension lines may be determined as the corrected rotation center point, and when there are a plurality of intersection points, the intersection point where the number of the extension lines collected is the largest may be determined as the corrected rotation center point.
In the embodiment of the disclosure, according to the steps S101 to S104, the area of the dial plate in the target image is determined, and the reading information of the dial plate is determined according to the range information of the dial plate and the position information of the key point of the dial plate area, so that the intelligent degree of the determination mode of the reading information of the dial plate is improved; meanwhile, the reading information of the dial can be determined only by determining the range information and the position information of the key point, and the position information of each position on the dial is not required to be determined, so that the determination rate of the reading information of the dial is improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an information determining apparatus according to an embodiment of the present disclosure, and as shown in fig. 6, an information determining apparatus 600 includes:
an obtaining module 601, configured to obtain a target image;
a first determining module 602, configured to determine an area of a dial in the target image, and detect range information of the dial;
a detection module 603, configured to detect position information of a key point in an area of the dial;
and a second determining module 604, configured to determine reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
Optionally, referring to fig. 7, the first determining module 602 includes:
a first feature extraction submodule 6021, configured to perform feature extraction on the target image to obtain a plurality of first feature vectors;
a clustering submodule 6022, configured to cluster at least part of the first feature vectors in the plurality of first feature vectors to obtain second feature vectors;
the prediction submodule 6023 is configured to perform prediction according to the second feature vector to obtain a first target feature vector, where the first target feature vector is used to represent an area of the dial.
Optionally, referring to fig. 8, the detecting module 603 includes:
a second feature extraction submodule 6031, configured to input an image area corresponding to the area of the dial in the target image into a plurality of network structures to extract a feature vector;
and a fusion submodule 6032 for fusing the feature vectors extracted by different network structures to obtain a second target feature vector, where the second target feature vector is used to represent the position information of the key point in the area of the dial.
Optionally, referring to fig. 9, the key points include a rotation center point of a pointer, an end point of the pointer, a start point of a scale mark of the dial plate, and an end point of the scale mark of the dial plate; the second determining module 604, comprising:
a first determining submodule 6041, configured to determine, according to the rotation center point, the end point of the pointer, a start point of a scale line of the dial, and an end point of the scale line of the dial, a rotation angle proportion of the pointer in the scale line of the dial;
and the second determining submodule 6042 is configured to determine reading information of the dial according to the rotation angle ratio and the range information of the dial.
Optionally, referring to fig. 10, the key points further comprise a plurality of intermediate tick marks, the intermediate tick marks located between the start point of the tick mark and the end point of the tick mark; the information determining apparatus 600 further includes:
and a correcting module 605, configured to correct the position information of the rotation center point of the pointer according to the plurality of middle scale marks.
The information determining apparatus 600 provided in the present disclosure can implement each process implemented by the information determining method embodiment, and can achieve the same beneficial effects, and for avoiding repetition, the details are not repeated here.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 11 shows a schematic block diagram of an example electronic device 1100 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 11, the device 1100 comprises a computing unit 1101, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data necessary for the operation of the device 1100 may also be stored. The calculation unit 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.
A number of components in device 1100 connect to I/O interface 1105, including: an input unit 1106 such as a keyboard, a mouse, and the like; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108 such as a magnetic disk, optical disk, or the like; and a communication unit 1109 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 1101 can be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the respective methods and processes described above, such as the information determination method. For example, in some embodiments, the information determination method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When a computer program is loaded into RAM 1103 and executed by computing unit 1101, one or more steps of the information determination method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the information determination method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (13)
1. An information determination method, comprising:
acquiring a target image;
determining the area of a dial plate in the target image, and detecting the range information of the dial plate;
detecting position information of key points of the dial plate area;
and determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
2. The method of claim 1, wherein said determining a region of a dial in said target image comprises:
extracting features of the target image to obtain a plurality of first feature vectors;
clustering at least part of the first feature vectors in the plurality of first feature vectors to obtain second feature vectors;
and predicting according to the second feature vector to obtain a first target feature vector, wherein the first target feature vector is used for representing the area of the dial plate.
3. The method of claim 1, wherein the detecting location information of key points of an area of the dial plate comprises:
inputting image areas corresponding to the areas of the dial plate in the target image into a plurality of network structures to extract feature vectors;
and fusing the feature vectors extracted by different network structures to obtain a second target feature vector, wherein the second target feature vector is used for representing the position information of the key points of the dial area.
4. The method of any one of claims 1 to 3, wherein the key points include a center point of rotation of a pointer, an end point of the pointer, a start point of a tick mark of the dial, and an end point of a tick mark of the dial; the step of determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point comprises the following steps:
determining the rotation angle proportion of the pointer in the scale marks of the dial plate according to the rotation central point, the end point of the pointer, the starting point of the scale marks of the dial plate and the end point of the scale marks of the dial plate;
and determining the reading information of the dial plate according to the rotation angle ratio and the range information of the dial plate.
5. The method of claim 4, wherein the keypoints further comprises a plurality of intermediate tick marks located between the start point of the tick mark and the end point of the tick mark; the method further comprises the following steps:
and correcting the position information of the rotating central point of the pointer according to the plurality of middle scale marks.
6. An information determining apparatus comprising:
the acquisition module is used for acquiring a target image;
the first determining module is used for determining the area of the dial plate in the target image and detecting the range information of the dial plate;
the detection module is used for detecting the position information of key points in the area of the dial plate;
and the second determination module is used for determining the reading information of the dial plate according to the range information of the dial plate and the position information of the key point.
7. The information determination apparatus of claim 6, wherein the first determination module comprises:
the first feature extraction submodule is used for extracting features of the target image to obtain a plurality of first feature vectors;
the clustering submodule is used for clustering at least part of the first characteristic vectors in the plurality of first characteristic vectors to obtain second characteristic vectors;
and the predicting submodule is used for predicting according to the second characteristic vector to obtain a first target characteristic vector, and the first target characteristic vector is used for representing the area of the dial plate.
8. The information determination apparatus of claim 6, wherein the detection module comprises:
the second feature extraction submodule is used for inputting the image area corresponding to the area of the dial plate in the target image into a plurality of network structures to extract feature vectors;
and the fusion submodule is used for fusing the feature vectors extracted by different network structures to obtain a second target feature vector, and the second target feature vector is used for representing the position information of the key points of the dial area.
9. The information determination apparatus according to any one of claims 6 to 8, wherein the key points include a rotation center point of a pointer, an end point of the pointer, a start point of a graduation mark of the dial, and an end point of a graduation mark of the dial; the second determining module includes:
the first determining submodule is used for determining the rotation angle proportion of the pointer in the scale marks of the dial plate according to the rotation central point, the end point of the pointer, the starting point of the scale marks of the dial plate and the end point of the scale marks of the dial plate;
and the second determining submodule is used for determining the reading information of the dial plate according to the rotation angle ratio and the range information of the dial plate.
10. The information determination apparatus of claim 9, wherein the keypoints further comprise a plurality of intermediate tick marks located between a start point of the tick mark and an end point of the tick mark; the information determination apparatus further includes:
and the correcting module is used for correcting the position information of the rotating center point of the pointer according to the plurality of middle scale marks.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210230599.2A CN114596431A (en) | 2022-03-10 | 2022-03-10 | Information determination method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210230599.2A CN114596431A (en) | 2022-03-10 | 2022-03-10 | Information determination method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114596431A true CN114596431A (en) | 2022-06-07 |
Family
ID=81808737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210230599.2A Pending CN114596431A (en) | 2022-03-10 | 2022-03-10 | Information determination method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114596431A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311469A (en) * | 2022-08-08 | 2022-11-08 | 北京百度网讯科技有限公司 | Image labeling method, training method, image processing method and electronic equipment |
| CN115797934A (en) * | 2022-12-01 | 2023-03-14 | 北京百度网讯科技有限公司 | Instrument number indicating method and device, electronic equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130070099A1 (en) * | 2011-09-20 | 2013-03-21 | Honeywell International Inc. | Image based dial gauge reading |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
| CN110110733A (en) * | 2019-05-15 | 2019-08-09 | 深圳供电局有限公司 | Pointer instrument reading method and device, computer equipment and storage medium |
| CN111027531A (en) * | 2019-12-10 | 2020-04-17 | 联想(北京)有限公司 | Pointer instrument information identification method and device and electronic equipment |
| CN111259903A (en) * | 2020-01-13 | 2020-06-09 | 深圳供电局有限公司 | Identification table counting method and device, readable storage medium and computer equipment |
| CN112115893A (en) * | 2020-09-24 | 2020-12-22 | 深圳市赛为智能股份有限公司 | Instrument panel pointer reading identification method and device, computer equipment and storage medium |
| WO2021017000A1 (en) * | 2019-08-01 | 2021-02-04 | 西门子股份公司 | Method and apparatus for acquiring meter reading, and memory, processor and terminal |
| CN112508098A (en) * | 2020-12-08 | 2021-03-16 | 南京理工大学 | Dial plate positioning and automatic reading pointer type meter value identification method and system |
| CN112651326A (en) * | 2020-12-22 | 2021-04-13 | 济南大学 | Driver hand detection method and system based on deep learning |
| CN113343969A (en) * | 2021-06-21 | 2021-09-03 | 重庆科技学院 | GBS-YOLOv5 s-based pointer instrument intelligent digital display method |
| US20210295088A1 (en) * | 2020-12-11 | 2021-09-23 | Beijing Baidu Netcom Science & Technology Co., Ltd | Image detection method, device, storage medium and computer program product |
| CN113537075A (en) * | 2021-07-19 | 2021-10-22 | 中国电信股份有限公司 | Pointer instrument reading identification method and device, storage medium and electronic equipment |
| CN113780087A (en) * | 2021-08-11 | 2021-12-10 | 同济大学 | Postal parcel text detection method and equipment based on deep learning |
| CN113780152A (en) * | 2021-09-07 | 2021-12-10 | 北京航空航天大学 | Remote sensing image ship small target detection method based on target perception |
| CN113822372A (en) * | 2021-10-20 | 2021-12-21 | 中国民航大学 | Unmanned aerial vehicle detection method based on YOLOv5 neural network |
-
2022
- 2022-03-10 CN CN202210230599.2A patent/CN114596431A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130070099A1 (en) * | 2011-09-20 | 2013-03-21 | Honeywell International Inc. | Image based dial gauge reading |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
| CN110110733A (en) * | 2019-05-15 | 2019-08-09 | 深圳供电局有限公司 | Pointer instrument reading method and device, computer equipment and storage medium |
| WO2021017000A1 (en) * | 2019-08-01 | 2021-02-04 | 西门子股份公司 | Method and apparatus for acquiring meter reading, and memory, processor and terminal |
| CN111027531A (en) * | 2019-12-10 | 2020-04-17 | 联想(北京)有限公司 | Pointer instrument information identification method and device and electronic equipment |
| CN111259903A (en) * | 2020-01-13 | 2020-06-09 | 深圳供电局有限公司 | Identification table counting method and device, readable storage medium and computer equipment |
| CN112115893A (en) * | 2020-09-24 | 2020-12-22 | 深圳市赛为智能股份有限公司 | Instrument panel pointer reading identification method and device, computer equipment and storage medium |
| CN112508098A (en) * | 2020-12-08 | 2021-03-16 | 南京理工大学 | Dial plate positioning and automatic reading pointer type meter value identification method and system |
| US20210295088A1 (en) * | 2020-12-11 | 2021-09-23 | Beijing Baidu Netcom Science & Technology Co., Ltd | Image detection method, device, storage medium and computer program product |
| CN112651326A (en) * | 2020-12-22 | 2021-04-13 | 济南大学 | Driver hand detection method and system based on deep learning |
| CN113343969A (en) * | 2021-06-21 | 2021-09-03 | 重庆科技学院 | GBS-YOLOv5 s-based pointer instrument intelligent digital display method |
| CN113537075A (en) * | 2021-07-19 | 2021-10-22 | 中国电信股份有限公司 | Pointer instrument reading identification method and device, storage medium and electronic equipment |
| CN113780087A (en) * | 2021-08-11 | 2021-12-10 | 同济大学 | Postal parcel text detection method and equipment based on deep learning |
| CN113780152A (en) * | 2021-09-07 | 2021-12-10 | 北京航空航天大学 | Remote sensing image ship small target detection method based on target perception |
| CN113822372A (en) * | 2021-10-20 | 2021-12-21 | 中国民航大学 | Unmanned aerial vehicle detection method based on YOLOv5 neural network |
Non-Patent Citations (2)
| Title |
|---|
| 张华 等: "《遥感数据可靠性分类方法研究》", 31 March 2016, 北京：测绘出版社, pages: 116 * |
| 李祖胜;孙玉秋;胡维;黎雄;: "基于数字图像处理技术的双指针机械仪表读数自动识别方法", 长江大学学报(自科版), no. 31, 5 November 2016 (2016-11-05), pages 36 - 41 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311469A (en) * | 2022-08-08 | 2022-11-08 | 北京百度网讯科技有限公司 | Image labeling method, training method, image processing method and electronic equipment |
| CN115797934A (en) * | 2022-12-01 | 2023-03-14 | 北京百度网讯科技有限公司 | Instrument number indicating method and device, electronic equipment and storage medium |
| CN115797934B (en) * | 2022-12-01 | 2023-12-01 | 北京百度网讯科技有限公司 | Meter registration method, apparatus, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657390B (en) | Training method of text detection model and text detection method, device and equipment | |
| CN113971751A (en) | Training feature extraction model, and method and device for detecting similar images | |
| CN112560862B (en) | Text recognition method and device and electronic equipment | |
| CN114596431A (en) | Information determination method and device and electronic equipment | |
| CN112800915A (en) | Building change detection method, building change detection device, electronic device, and storage medium | |
| CN114419035B (en) | Product identification method, model training device and electronic equipment | |
| CN113642583B (en) | Deep learning model training method for text detection and text detection method | |
| CN113537192B (en) | Image detection method, device, electronic equipment and storage medium | |
| CN113705628B (en) | Determination method and device of pre-training model, electronic equipment and storage medium | |
| CN112966744A (en) | Model training method, image processing method, device and electronic equipment | |
| CN113205041A (en) | Structured information extraction method, device, equipment and storage medium | |
| CN113420727A (en) | Training method and device of form detection model and form detection method and device | |
| CN114283343B (en) | Map updating method, training method and device based on remote sensing satellite image | |
| CN115359308A (en) | Model training method, apparatus, device, storage medium, and program for identifying difficult cases | |
| CN114926849A (en) | Text detection method, device, equipment and storage medium | |
| CN116468985B (en) | Model training method, quality detection device, electronic equipment and medium | |
| CN116935368A (en) | Deep learning model training method, text line detection method, device and equipment | |
| CN114724113B (en) | Road sign recognition method, automatic driving method, device and equipment | |
| CN115861809A (en) | Rod detection and training method and device for model thereof, electronic equipment and medium | |
| CN114187574A (en) | Method for identifying change point, method and device for training change point detection network | |
| CN114596442A (en) | Image identification method, device, equipment and storage medium | |
| CN113807391A (en) | Task model training method and device, electronic equipment and storage medium | |
| CN113032071A (en) | Page element positioning method, page testing method, device, equipment and medium | |
| CN115809687A (en) | Training method and device for image processing network | |
| CN116051925B (en) | Training sample acquisition method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |