CN112115893A - Instrument panel pointer reading identification method and device, computer equipment and storage medium - Google Patents
Instrument panel pointer reading identification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112115893A CN112115893A CN202011016452.0A CN202011016452A CN112115893A CN 112115893 A CN112115893 A CN 112115893A CN 202011016452 A CN202011016452 A CN 202011016452A CN 112115893 A CN112115893 A CN 112115893A
- Authority
- CN
- China
- Prior art keywords
- pointer
- key point
- scale
- information
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention relates to a reading identification method, a reading identification device, computer equipment and a storage medium for a pointer of a dashboard, wherein the method comprises the steps of acquiring an image of the dashboard to obtain an initial image; inputting the initial image into a target detection model for target detection to obtain a target detection result; cutting an initial image according to a target detection result to obtain an instrument image; inputting the instrument image into a key point detection model to detect a pointer key point so as to obtain key point information; inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information; acquiring a pointer angle by combining the key point information and the scale digital information; determining a scale numerical value corresponding to the pointer according to the pointer angle to obtain a reading result; and feeding back the reading result to the terminal so as to display the reading result at the terminal. The invention realizes the identification of various instrument panels, has high identification accuracy, adopts OCR (optical character recognition) scales, realizes the end-to-end pointer angle identification and has high universality.
Description
Technical Field
The invention relates to a reading method of an instrument panel, in particular to a reading identification method and device of an instrument panel pointer, computer equipment and a storage medium.
Background
The pointer instrument is an instrument commonly used in the power industry, however, in view of the influence of links such as electromagnetic radiation and high temperature in the power industry, manual inspection faces many challenges, and meanwhile, an advanced automatic pointer instrument recognition scheme is very meaningful in order to improve the automation and intellectualization of a work flow and improve the work efficiency of an overall power grid.
At present, algorithms related to automatic identification of the pointer instrument in the market mainly adopt image processing, and in recent years, with the rapid development of deep learning, the deep learning gradually infiltrates into the application field of automatic identification of the pointer instrument. Chinese patent CN201611257983.2 discloses a meter scale recognition method, which is characterized in that an edge intensity graph and an edge directional diagram are obtained by processing an image to be recognized by utilizing an edge filtering convolution kernel; extracting a single-pixel outline from the edge intensity graph and the edge directional diagram; screening candidate scales meeting the conditions from the single-pixel outline; serially connecting the single candidate scales into a continuous scale queue; completing the missing scales in the scale queue; the longer scale queue is analyzed to judge whether the longer scale queue meets the characteristics of the instrument panel scale, the patent can be matched with a pointer identification algorithm to obtain the meter reading by using a distance method, but the method uses morphological characteristics to carry out scale detection, a plurality of threshold values need to be manually and finely adjusted, and for different types of meters, the threshold values need to be readjusted and set; even if the tables are of the same type, the thresholds need to be reset if the images are shot from different distances and different angles, besides, the method has another limitation that the first and the last scales are determined by the relative positions in the scale queue, if the single-pixel outline of the first and the last scales is not detected due to interference factors, the scale completion mechanism in the method can only complete the scales positioned at the middle positions, but cannot complete the scales positioned at the head and the tail, and the final reading can generate deviation. China CN201910153856.5 discloses an automatic inspection robot instrument detection and identification method based on deep learning, which is a practical deep learning model for instrument detection and identification, but the used model structure is backward, and when reading is performed, the pointer registration identification is performed through a configuration file by combining the types of instruments, so that the end-to-end identification cannot be performed, and the universality is lacked.
Therefore, a new method is needed to be designed, multiple instrument panels can be identified, the identification accuracy rate is high, end-to-end pointer angle identification is realized, and the universality is high.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a device for identifying the reading of an instrument panel pointer, computer equipment and a storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme: the instrument panel pointer reading identification method comprises the following steps:
acquiring an image of a dashboard to obtain an initial image;
inputting the initial image into a target detection model for target detection to obtain a target detection result;
cutting the initial image according to the target detection result to obtain an instrument image;
inputting the instrument image into a key point detection model to detect a pointer key point so as to obtain key point information;
inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information;
acquiring a pointer angle by combining the key point information and the scale digital information;
determining a scale numerical value corresponding to the pointer according to the pointer angle to obtain a reading result;
feeding back the reading result to a terminal so as to display the reading result on the terminal;
wherein, the target detection model is obtained by training a Yolov3 network by using a plurality of images with instrument coordinates and class labels as a sample set;
the key point detection model is obtained by training a CenterNet network by using a plurality of images with key point coordinates and class labels as a sample set;
the scale recognition model is obtained by training an OCR network by taking a plurality of images with scale numerical value coordinate information labels as a sample set.
The further technical scheme is as follows: the key point information comprises position information of a dial scale zero point, position information of a dial scale end point, position information of a pointer central point and position information of a pointer tip.
The further technical scheme is as follows: inputting the instrument image into the key point detection model to perform pointer key point detection so as to obtain key point information, wherein the method comprises the following steps:
preprocessing an instrument image to obtain a processed image;
inputting the processed image into a key point detection model for feature map calculation to obtain a three-dimensional feature map;
and processing the three-dimensional characteristic graph to obtain key point information.
The further technical scheme is as follows: the processing the three-dimensional feature map to obtain the key point information includes:
filtering the positions of the key points with response values smaller than a threshold value in the three-dimensional characteristic diagram to obtain information to be processed;
judging whether each channel of the three-dimensional feature map has a key point;
if the key points do not exist in each channel of the three-dimensional feature map, returning null notification information to the terminal;
and traversing each channel local maximum value of the three-dimensional feature map to obtain key point information if each channel of the three-dimensional feature map has key points.
The further technical scheme is as follows: the acquiring of the pointer angle by combining the key point information and the scale digital information includes:
connecting lines according to the key points of the center of the pointer and the key points of the end of the pointer in the key point information to obtain the pointer;
determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information;
and calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information to obtain the angle of the pointer.
The further technical scheme is as follows: the scale digital information comprises coordinate information and numerical information of numbers on the dial scale.
The invention also provides a reading identification device for the instrument panel pointer, which is characterized by comprising the following components:
the device comprises an initial image acquisition unit, a display unit and a display unit, wherein the initial image acquisition unit is used for acquiring an image of a dashboard to obtain an initial image;
the target detection unit is used for inputting the initial image into the target detection model for target detection so as to obtain a target detection result;
the cutting unit is used for cutting the initial image according to the target detection result to obtain an instrument image;
the key point detection unit is used for inputting the instrument image into the key point detection model to detect the key point of the pointer so as to obtain key point information;
the identification unit is used for inputting the instrument image into the scale identification model to identify the scale position so as to obtain scale digital information;
the angle acquisition unit is used for acquiring a pointer angle by combining the key point information and the scale digital information;
the reading acquisition unit is used for determining a scale value corresponding to the pointer according to the pointer angle so as to obtain a reading result;
and the feedback unit is used for feeding back the reading result to the terminal so as to display the reading result on the terminal.
The further technical scheme is as follows: the key point detecting unit includes:
the preprocessing subunit is used for preprocessing the instrument image to obtain a processed image;
the characteristic diagram calculation subunit is used for inputting the processed image into the key point detection model to perform characteristic diagram calculation so as to obtain a three-dimensional characteristic diagram;
and the processing subunit is used for processing the three-dimensional characteristic diagram to obtain the key point information.
The invention also provides computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor realizes the method when executing the computer program.
The invention also provides a storage medium storing a computer program which, when executed by a processor, is operable to carry out the method as described above.
Compared with the prior art, the invention has the beneficial effects that: according to the method, after the initial image of the instrument is obtained, the target detection model is adopted for detection, the initial image is cut according to the target detection result, the cut image is input into the key point detection model to obtain the information of each key point, the cut image is input into the scale recognition model to recognize the scale digital information, the reading number of the pointer is determined by combining the key point information and the scale digital information, various instrument panels can be recognized by adopting a deep learning technology, the recognition accuracy rate is high, the pointer angle recognition from end to end is realized by adopting OCR recognition scales, and the universality is high.
The invention is further described below with reference to the accompanying drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of a reading identification method for a dashboard pointer according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for identifying a reading of an instrument panel pointer according to an embodiment of the present invention;
fig. 3 is a schematic sub-flow chart of a method for identifying a reading of a pointer of an instrument panel according to an embodiment of the present invention;
fig. 4 is a schematic sub-flow chart of a method for identifying a reading of a pointer of an instrument panel according to an embodiment of the present invention;
fig. 5 is a schematic sub-flow chart of a method for identifying a reading of a pointer of an instrument panel according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of an instrument panel pointer reading identification apparatus provided in an embodiment of the present invention;
FIG. 7 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a dashboard pointer reading identification method according to an embodiment of the present invention. Fig. 2 is a schematic flow chart of a dashboard pointer reading identification method according to an embodiment of the present invention. The instrument panel pointer reading identification method is applied to a server, the server performs data interaction with a robot and a terminal, corresponding instrument images are shot through a camera on the robot, target detection is performed through a target detection model by the server, an initial image is cut according to a target detection result, the initial image is input into a key point detection model for detection and is input into a scale identification model, and reading determination is performed according to acquired key point information and scale digital information.
Fig. 2 is a schematic flow chart of a method for identifying a reading of a pointer of an instrument panel according to an embodiment of the present invention. As shown in fig. 2, the method includes the following steps S110 to S180.
And S110, acquiring an image of the instrument panel to obtain an initial image.
In the present embodiment, the initial image refers to an image of a pointer instrument.
The robot moves the robot to a designated position through positioning, and collects color pictures of a cabinet containing the pointer instrument through a cradle head of the robot.
And S120, inputting the initial image into a target detection model for target detection to obtain a target detection result.
In this embodiment, the target detection result refers to coordinate information of the meter, a corresponding confidence level, and a type of the pointer meter; the coordinate information where the meter is located may constitute a prediction box.
Wherein the target detection model is obtained by training a Yolov3 network by using a plurality of images with instrument coordinates and class labels as a sample set. Specifically, by using a Yolov3 network structure and downloading pre-training parameters completed based on ImageNet for initialization, such transfer learning can help the network to quickly converge and improve the network precision.
And S130, cutting the initial image according to the target detection result to obtain a meter image.
In the present embodiment, the meter image refers to a picture including only the meter area.
Specifically, the initial image is cut according to the obtained coordinate information of the instrument, and a high-definition instrument image is obtained.
And S140, inputting the instrument image into the key point detection model to detect the key points of the pointer so as to obtain key point information.
In this embodiment, the key point information includes position information of a dial scale zero point, position information of a dial scale end point, position information of a pointer center point, and position information of a pointer tip.
Specifically, the keypoint detection model is obtained by training a centret network by using a plurality of images with keypoint coordinates and class labels as a sample set.
In an embodiment, referring to fig. 3, the step S140 may include steps S141 to S143.
And S141, preprocessing the instrument image to obtain a processed image.
In this embodiment, the processed image is an image that is adjusted to 384 × 384 in image size and is unified and normalized.
And S142, inputting the processed image into the key point detection model for feature map calculation to obtain a three-dimensional feature map.
In this embodiment, the three-dimensional characteristic diagram is 96 × 4 and has 4 pieces of channel information, which respectively represent characteristic diagrams of information of a dial scale zero point, a dial scale end point, a pointer center point, and a pointer tip. The response value of each pixel in these profiles is between 0, 255.
And S143, processing the three-dimensional characteristic graph to obtain key point information.
In an embodiment, referring to fig. 4, the step S143 may include steps S1431 to S1434.
S1431, filtering the positions of the key points with the response values smaller than the threshold value in the three-dimensional characteristic diagram to obtain information to be processed.
In this embodiment, the information to be processed refers to the information of the key point position whose response value is smaller than the threshold value.
S1432, judging whether each channel of the three-dimensional feature map has a key point;
s1433, if the key points do not exist in each channel of the three-dimensional feature map, returning null notification information to the terminal;
s1434, if each channel of the three-dimensional feature map has a key point, traversing each channel local maximum value of the three-dimensional feature map to obtain key point information.
Detecting the three-dimensional characteristic diagram, searching the position information of the key point with the maximum response value, judging whether the response value is greater than 90, and if not, filtering the position information of the key point; otherwise, judging whether each channel of the three-dimensional characteristic diagram has a key point, if one channel has no key point, returning a null value result, reminding the robot to collect an initial image again, acquiring the coordinate position of the key point by traversing the local maximum value under the condition that each channel has a key point response result, combining the key point at the center of the pointer and the key point at the end of the pointer into a pointer, determining the angle range of the pointer by the dial scale zero point, the dial scale end point and the pointer center point, and then calculating the deflection angle of the pointer.
Aiming at the characteristic of few types of key points in the current application scene, the method optimizes the commonly used difficult sample online mining technology in key point detection, optimizes the channel-based difficult sample online mining technology into the key point field loss-based difficult sample online mining technology, focuses more on the difficult key points rather than all key points of a certain specific type, and greatly improves the identification accuracy rate of instruments with a plurality of pointers, especially under the special condition that some pointers are shielded. Aiming at the angle detection of the instrument pointer, the sample mining technology with the loss difficulty in the labeling field can be conveniently embedded into other detection technology frames based on the deep learning key point.
Specifically, in the process of training the key point detection model, the picture is preprocessed, and the data preprocessing mainly comprises picture adjustment operation, common pixel value standardization operation of data augmentation operation, and common marking gauss processing operation of key point detection, wherein the augmentation operation comprises rotation, affine transformation, noise, shelter, mirror image and the like. And (3) performing labeling gauss processing operation, namely performing convolution on the labeling characteristic diagram by using convolution kernels with different kernel sizes to obtain the gaussed labeling characteristic diagram, wherein the processing enhances the robustness of the model and is beneficial to the convergence of loss values.
Under the calculation of the key point detection model, each picture correspondingly outputs a 1 × 96 × 4 three-dimensional characteristic diagram, and the three-dimensional characteristic diagram has 4 pieces of channel information which respectively represent dial scale zero points, dial scale end points, pointer center points and pointer tip position information. Normalization is performed by multiplying the three-dimensional feature maps by 255, and finally the response value of each pixel in the feature maps is between [0, 255 ].
In the training process, statistics is carried out on loss information of the corresponding field ranges of all labels by using labeled neighborhood loss difficult sample mining in each batch processing, and the loss information is sequenced. The first 30 generations of training are performed, all the calculations are accumulated and returned, and the last 10 generations of training are performed, only the first 30% loss information in the loss value sequencing is accumulated and returned, so that the detection effect of the loss value sequencing on difficult key points is optimized, and a common Adam optimizer is used for training.
The network prototype used by the key point detection model is a CenterNet network structure, the network structure has a small number of parameters, and because the output three-dimensional feature map is 4 channels, the network parameters are further reduced, 720 × 720 picture output sizes can be supported for training, and the large size can obviously improve the key point detection accuracy.
And S150, inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information.
In this embodiment, the scale numerical information includes coordinate information and numerical information of numbers on the dial scale.
Specifically, the scale Recognition model is obtained by training an OCR (Optical Character Recognition) network by using a plurality of images with scale numerical value coordinate information labels as a sample set.
OCR refers to a process in which an electronic device such as a scanner or a digital camera checks characters printed on paper, determines the shape thereof by detecting dark and light patterns, and then translates the shape into computer characters by a character recognition method, and obtains recognition results and coordinate information of scale numbers using a FOTS (Fast organized Text pointing with a Unified Network) model, and coordinate information and numerical value information of numbers on a dial scale using the technology. An OCR technology is introduced, dial scale numbers and position information can be accurately and automatically identified, and end-to-end pointer angle identification is realized by combining key point detection. OCR recognition technology was introduced so that reading pointer readings is no longer dependent on the configuration file. The model service is more universal.
And S160, acquiring the pointer angle by combining the key point information and the scale numerical information.
In this embodiment, the pointer angle refers to the deflection radian of the pointer, and the deflection radian of the pointer is added to the scale value, so that the reading result can be determined.
In an embodiment, referring to fig. 5, the step S160 may include steps S161 to S163.
And S161, connecting lines according to the key points of the center of the pointer and the key points of the end of the pointer in the key point information to obtain the pointer.
And S162, determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information.
In this embodiment, the angle range of the pointer refers to an angle corresponding to the pointing direction of the pointer.
And S163, calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information to obtain the angle of the pointer.
The dial angle can be calculated by combining key point information and scale digital coordinates, according to scale digital coordinate information identified by OCR, the scale value corresponding to the radian can be obtained by combining the pointer center, the scale zero point and the scale end point identified by the key point, and then the radian of the pointer can be obtained according to the pointer tip, the pointer center point and the scale zero point, so that the value of the pointer scale can be correspondingly obtained.
S170, determining a scale value corresponding to the pointer according to the pointer angle to obtain a reading result.
In this embodiment, the reading result refers to the reading of the pointer.
S180, feeding back the reading result to a terminal so as to display the reading result on the terminal
According to the instrument panel pointer reading identification method, after the initial image of the instrument is obtained, the target detection model is used for detecting, the initial image is cut according to the target detection result, the cut image is input into the key point detection model to obtain the information of each key point, the cut image is input into the scale identification model to identify the scale digital information, the reading of the pointer is determined by combining the key point information and the scale digital information, the multiple instrument panels can be identified by adopting a deep learning technology, the identification accuracy is high, the OCR is adopted to identify the scale, the end-to-end pointer angle identification is realized, and the universality is high.
Fig. 6 is a schematic block diagram of an instrument panel pointer reading identification apparatus 300 according to an embodiment of the present invention. As shown in fig. 6, the present invention also provides a device 300 for identifying the reading of the dashboard pointer, corresponding to the above method for identifying the reading of the dashboard pointer. The instrument panel pointer reading recognition apparatus 300 includes a unit for performing the above-described instrument panel pointer reading recognition method, and the apparatus may be configured in a server. Specifically, referring to fig. 6, the instrument panel pointer reading identification apparatus 300 includes an initial image acquisition unit 301, a target detection unit 302, a cropping unit 303, a key point detection unit 304, an identification unit 305, an angle acquisition unit 306, a reading acquisition unit 307, and a feedback unit 308.
An initial image obtaining unit 301, configured to obtain an image of a dashboard to obtain an initial image; the target detection unit 302 is configured to input the initial image into a target detection model for target detection to obtain a target detection result; a clipping unit 303, configured to clip the initial image according to the target detection result to obtain an instrument image; a key point detection unit 304, configured to input the meter image into the key point detection model to perform pointer key point detection, so as to obtain key point information; the identification unit 305 is used for inputting the instrument image into a scale identification model to identify the scale position so as to obtain scale numerical information; an angle obtaining unit 306, configured to obtain a pointer angle by combining the key point information and the scale number information; a reading obtaining unit 307, configured to determine a scale value corresponding to the pointer according to the pointer angle to obtain a reading result; and the feedback unit 308 is configured to feed back the reading result to the terminal, so as to display the reading result at the terminal.
In one embodiment, the keypoint detection unit 304 comprises a preprocessing subunit, a feature map calculation subunit, and a processing subunit.
The preprocessing subunit is used for preprocessing the instrument image to obtain a processed image; the characteristic diagram calculation subunit is used for inputting the processed image into the key point detection model to perform characteristic diagram calculation so as to obtain a three-dimensional characteristic diagram; and the processing subunit is used for processing the three-dimensional characteristic diagram to obtain the key point information.
In one embodiment, the processing subunit includes a filtering module, a determining module, a returning module, and a traversing module.
The filtering module is used for filtering the positions of the key points with response values smaller than a threshold value in the three-dimensional characteristic diagram to obtain information to be processed; the judging module is used for judging whether each channel of the three-dimensional characteristic diagram has a key point or not; the return module is used for returning null notification information to the terminal if each channel of the three-dimensional feature map does not have a key point; and the traversing module is used for traversing each channel local maximum value of the three-dimensional feature map to obtain the key point information if each channel of the three-dimensional feature map has the key point.
In an embodiment, the angle obtaining unit 306 includes a connecting line subunit, a range determining subunit, and an angle calculating subunit.
The link subunit is used for connecting the link according to the key point of the center of the pointer and the key point of the end of the pointer in the key point information to obtain the pointer; the range determining subunit is used for determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information; and the angle calculating subunit is used for calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information so as to obtain the angle of the pointer.
It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of the instrument panel pointer reading identification apparatus 300 and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.
The above-described instrument panel pointer reading identification means 300 may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 7, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer programs 5032 include program instructions that, when executed, cause the processor 502 to perform a dashboard pointer reading identification method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 can be caused to execute a dashboard pointer reading identification method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:
acquiring an image of a dashboard to obtain an initial image; inputting the initial image into a target detection model for target detection to obtain a target detection result; cutting the initial image according to the target detection result to obtain an instrument image; inputting the instrument image into a key point detection model to detect a pointer key point so as to obtain key point information; inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information; acquiring a pointer angle by combining the key point information and the scale digital information; determining a scale numerical value corresponding to the pointer according to the pointer angle to obtain a reading result; and feeding back the reading result to the terminal so as to display the reading result on the terminal.
Wherein, the target detection model is obtained by training a Yolov3 network by using a plurality of images with instrument coordinates and class labels as a sample set; the key point detection model is obtained by training a CenterNet network by using a plurality of images with key point coordinates and class labels as a sample set; the scale recognition model is obtained by training an OCR network by taking a plurality of images with scale numerical value coordinate information labels as a sample set.
The key point information comprises position information of a dial scale zero point, position information of a dial scale end point, position information of a pointer central point and position information of a pointer tip.
The scale digital information comprises coordinate information and numerical information of numbers on the dial scale.
In an embodiment, when implementing the step of inputting the meter image into the key point detection model for pointer key point detection to obtain key point information, the processor 502 specifically implements the following steps:
preprocessing an instrument image to obtain a processed image; inputting the processed image into a key point detection model for feature map calculation to obtain a three-dimensional feature map; and processing the three-dimensional characteristic graph to obtain key point information.
In an embodiment, when the processor 502 implements the step of processing the three-dimensional feature map to obtain the keypoint information, the following steps are specifically implemented:
filtering the positions of the key points with response values smaller than a threshold value in the three-dimensional characteristic diagram to obtain information to be processed; judging whether each channel of the three-dimensional feature map has a key point; if the key points do not exist in each channel of the three-dimensional feature map, returning null notification information to the terminal; and traversing each channel local maximum value of the three-dimensional feature map to obtain key point information if each channel of the three-dimensional feature map has key points.
In an embodiment, when the processor 502 implements the step of obtaining the pointer angle by combining the key point information and the scale number information, the following steps are specifically implemented:
connecting lines according to the key points of the center of the pointer and the key points of the end of the pointer in the key point information to obtain the pointer; determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information; and calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information to obtain the angle of the pointer.
It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the steps of:
acquiring an image of a dashboard to obtain an initial image; inputting the initial image into a target detection model for target detection to obtain a target detection result; cutting the initial image according to the target detection result to obtain an instrument image; inputting the instrument image into a key point detection model to detect a pointer key point so as to obtain key point information; inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information; acquiring a pointer angle by combining the key point information and the scale digital information; determining a scale numerical value corresponding to the pointer according to the pointer angle to obtain a reading result; and feeding back the reading result to the terminal so as to display the reading result on the terminal.
Wherein, the target detection model is obtained by training a Yolov3 network by using a plurality of images with instrument coordinates and class labels as a sample set; the key point detection model is obtained by training a CenterNet network by using a plurality of images with key point coordinates and class labels as a sample set; the scale recognition model is obtained by training an OCR network by taking a plurality of images with scale numerical value coordinate information labels as a sample set.
The key point information comprises position information of a dial scale zero point, position information of a dial scale end point, position information of a pointer central point and position information of a pointer tip.
The scale digital information comprises coordinate information and numerical information of numbers on the dial scale.
In an embodiment, when the processor executes the computer program to implement the step of inputting the meter image into the key point detection model for pointer key point detection to obtain key point information, the processor specifically implements the following steps:
preprocessing an instrument image to obtain a processed image; inputting the processed image into a key point detection model for feature map calculation to obtain a three-dimensional feature map; and processing the three-dimensional characteristic graph to obtain key point information.
In an embodiment, when the processor executes the computer program to implement the step of processing the three-dimensional feature map to obtain the keypoint information, the following steps are specifically implemented:
filtering the positions of the key points with response values smaller than a threshold value in the three-dimensional characteristic diagram to obtain information to be processed; judging whether each channel of the three-dimensional feature map has a key point; if the key points do not exist in each channel of the three-dimensional feature map, returning null notification information to the terminal; and traversing each channel local maximum value of the three-dimensional feature map to obtain key point information if each channel of the three-dimensional feature map has key points.
In an embodiment, when the processor executes the computer program to implement the step of obtaining the pointer angle by combining the key point information and the scale numerical information, the following steps are specifically implemented:
connecting lines according to the key points of the center of the pointer and the key points of the end of the pointer in the key point information to obtain the pointer; determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information; and calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information to obtain the angle of the pointer.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The instrument panel pointer reading identification method is characterized by comprising the following steps:
acquiring an image of a dashboard to obtain an initial image;
inputting the initial image into a target detection model for target detection to obtain a target detection result;
cutting the initial image according to the target detection result to obtain an instrument image;
inputting the instrument image into a key point detection model to detect a pointer key point so as to obtain key point information;
inputting the instrument image into a scale recognition model for scale position recognition to obtain scale digital information;
acquiring a pointer angle by combining the key point information and the scale digital information;
determining a scale numerical value corresponding to the pointer according to the pointer angle to obtain a reading result;
feeding back the reading result to a terminal so as to display the reading result on the terminal;
wherein, the target detection model is obtained by training a Yolov3 network by using a plurality of images with instrument coordinates and class labels as a sample set;
the key point detection model is obtained by training a CenterNet network by using a plurality of images with key point coordinates and class labels as a sample set;
the scale recognition model is obtained by training an OCR network by taking a plurality of images with scale numerical value coordinate information labels as a sample set.
2. The instrument panel pointer reading identification method of claim 1, wherein the key point information includes position information of a dial scale zero point, position information of a dial scale end point, position information of a pointer center point, and position information of a pointer tip.
3. The method for recognizing the reading of the instrument panel pointer as claimed in claim 2, wherein the inputting the instrument image into the key point detection model for detecting the pointer key point to obtain the key point information comprises:
preprocessing an instrument image to obtain a processed image;
inputting the processed image into a key point detection model for feature map calculation to obtain a three-dimensional feature map;
and processing the three-dimensional characteristic graph to obtain key point information.
4. The method for reading and identifying a dashboard pointer as recited in claim 3, wherein the processing the three-dimensional feature map to obtain the key point information comprises:
filtering the positions of the key points with response values smaller than a threshold value in the three-dimensional characteristic diagram to obtain information to be processed;
judging whether each channel of the three-dimensional feature map has a key point;
if the key points do not exist in each channel of the three-dimensional feature map, returning null notification information to the terminal;
and traversing each channel local maximum value of the three-dimensional feature map to obtain key point information if each channel of the three-dimensional feature map has key points.
5. The method for identifying reading of instrument panel pointer as claimed in claim 4, wherein said obtaining of pointer angle in combination with said key point information and scale number information comprises:
connecting lines according to the key points of the center of the pointer and the key points of the end of the pointer in the key point information to obtain the pointer;
determining the angle range of the pointer according to the dial scale zero point, the dial scale end point and the pointer center point in the key point information;
and calculating the deflection angle of the pointer according to the angle range of the pointer and the scale numerical information to obtain the angle of the pointer.
6. The method of identifying reading of a dashboard pointer as in claim 1 wherein the scale numerical information comprises coordinate information and numerical information of the numbers on the dial scale.
7. Instrument board pointer reading recognition device, its characterized in that includes:
the device comprises an initial image acquisition unit, a display unit and a display unit, wherein the initial image acquisition unit is used for acquiring an image of a dashboard to obtain an initial image;
the target detection unit is used for inputting the initial image into the target detection model for target detection so as to obtain a target detection result;
the cutting unit is used for cutting the initial image according to the target detection result to obtain an instrument image;
the key point detection unit is used for inputting the instrument image into the key point detection model to detect the key point of the pointer so as to obtain key point information;
the identification unit is used for inputting the instrument image into the scale identification model to identify the scale position so as to obtain scale digital information;
the angle acquisition unit is used for acquiring a pointer angle by combining the key point information and the scale digital information;
the reading acquisition unit is used for determining a scale value corresponding to the pointer according to the pointer angle so as to obtain a reading result;
and the feedback unit is used for feeding back the reading result to the terminal so as to display the reading result on the terminal.
8. The instrument panel pointer reading identification device of claim 7, wherein the key point detection unit comprises:
the preprocessing subunit is used for preprocessing the instrument image to obtain a processed image;
the characteristic diagram calculation subunit is used for inputting the processed image into the key point detection model to perform characteristic diagram calculation so as to obtain a three-dimensional characteristic diagram;
and the processing subunit is used for processing the three-dimensional characteristic diagram to obtain the key point information.
9. A computer device, characterized in that the computer device comprises a memory, on which a computer program is stored, and a processor, which when executing the computer program implements the method according to any of claims 1 to 6.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011016452.0A CN112115893A (en) | 2020-09-24 | 2020-09-24 | Instrument panel pointer reading identification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011016452.0A CN112115893A (en) | 2020-09-24 | 2020-09-24 | Instrument panel pointer reading identification method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112115893A true CN112115893A (en) | 2020-12-22 |
Family
ID=73801579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011016452.0A Pending CN112115893A (en) | 2020-09-24 | 2020-09-24 | Instrument panel pointer reading identification method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115893A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700430A (en) * | 2021-01-11 | 2021-04-23 | 重庆市劢齐医疗科技有限责任公司 | Orthodontic image picture intelligent identification method based on deep learning |
| CN112861867A (en) * | 2021-02-01 | 2021-05-28 | 北京大学 | Pointer type instrument panel identification method, system and storage medium |
| CN112966719A (en) * | 2021-02-05 | 2021-06-15 | 深圳市优必选科技股份有限公司 | Method and device for recognizing meter panel reading and terminal equipment |
| CN113076941A (en) * | 2021-04-20 | 2021-07-06 | 上海阿莱夫信息技术有限公司 | Single pointer dial reading identification method based on video frame fusion |
| CN113283466A (en) * | 2021-04-12 | 2021-08-20 | 开放智能机器（上海）有限公司 | Instrument reading identification method and device and readable storage medium |
| CN113408551A (en) * | 2021-05-25 | 2021-09-17 | 深圳市富能新能源科技有限公司 | Pointer instrument reading identification method, system, equipment and computer storage medium |
| CN113435300A (en) * | 2021-06-23 | 2021-09-24 | 国网智能科技股份有限公司 | Real-time identification method and system for lightning arrester instrument |
| CN113449633A (en) * | 2021-06-27 | 2021-09-28 | 齐丰科技股份有限公司 | Pointer type meter counting value identification method based on object detection and key point positioning |
| CN113537153A (en) * | 2021-08-20 | 2021-10-22 | 杭州灵伴科技有限公司 | Meter image identification method and device, electronic equipment and computer readable medium |
| CN113705350A (en) * | 2021-07-28 | 2021-11-26 | 广州中科云图智能科技有限公司 | Pointer instrument reading identification method and device for transformer substation, medium and electronic equipment |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
| CN114140678A (en) * | 2021-11-23 | 2022-03-04 | 北京东方国信科技股份有限公司 | Scale recognition method and device, electronic equipment and storage medium |
| CN114155452A (en) * | 2021-11-29 | 2022-03-08 | 江苏红光仪表厂有限公司 | Information identification method for industrial automation instrument |
| CN114565911A (en) * | 2022-02-28 | 2022-05-31 | 上海商汤科技开发有限公司 | Instrument reading method and device, computer equipment and storage medium |
| CN115565164A (en) * | 2022-11-17 | 2023-01-03 | 深圳市北电仪表有限公司 | Instrument panel numerical value identification method, device, equipment and storage medium |
| 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 |
| CN115980116A (en) * | 2022-11-22 | 2023-04-18 | 宁波博信电器有限公司 | High-temperature-resistant detection method and system for instrument panel, storage medium and intelligent terminal |
| CN116012828A (en) * | 2022-12-02 | 2023-04-25 | 长扬科技(北京)股份有限公司 | Pointer instrument identification method and device, electronic equipment and storage medium |
| CN116363688A (en) * | 2023-03-23 | 2023-06-30 | 嘉洋智慧安全科技(北京)股份有限公司 | Image processing method, device, equipment, medium and product |
| CN116563631A (en) * | 2023-05-12 | 2023-08-08 | 深圳普菲特信息科技股份有限公司 | AI-based instrument panel visual identification method, system and storage medium |
| CN117437450A (en) * | 2023-12-12 | 2024-01-23 | 北京蒙帕信创科技有限公司 | Rotary switch identification method and system based on deep learning |
-
2020
- 2020-09-24 CN CN202011016452.0A patent/CN112115893A/en active Pending
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700430A (en) * | 2021-01-11 | 2021-04-23 | 重庆市劢齐医疗科技有限责任公司 | Orthodontic image picture intelligent identification method based on deep learning |
| CN112861867A (en) * | 2021-02-01 | 2021-05-28 | 北京大学 | Pointer type instrument panel identification method, system and storage medium |
| CN112966719A (en) * | 2021-02-05 | 2021-06-15 | 深圳市优必选科技股份有限公司 | Method and device for recognizing meter panel reading and terminal equipment |
| CN112966719B (en) * | 2021-02-05 | 2023-12-15 | 深圳市优必选科技股份有限公司 | Method and device for recognizing instrument panel reading and terminal equipment |
| CN113283466A (en) * | 2021-04-12 | 2021-08-20 | 开放智能机器（上海）有限公司 | Instrument reading identification method and device and readable storage medium |
| CN113076941A (en) * | 2021-04-20 | 2021-07-06 | 上海阿莱夫信息技术有限公司 | Single pointer dial reading identification method based on video frame fusion |
| CN113408551A (en) * | 2021-05-25 | 2021-09-17 | 深圳市富能新能源科技有限公司 | Pointer instrument reading identification method, system, equipment and computer storage medium |
| CN113435300A (en) * | 2021-06-23 | 2021-09-24 | 国网智能科技股份有限公司 | Real-time identification method and system for lightning arrester instrument |
| CN113435300B (en) * | 2021-06-23 | 2022-10-14 | 国网智能科技股份有限公司 | Real-time identification method and system for lightning arrester instrument |
| CN113449633A (en) * | 2021-06-27 | 2021-09-28 | 齐丰科技股份有限公司 | Pointer type meter counting value identification method based on object detection and key point positioning |
| CN113705350A (en) * | 2021-07-28 | 2021-11-26 | 广州中科云图智能科技有限公司 | Pointer instrument reading identification method and device for transformer substation, medium and electronic equipment |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
| CN113537153A (en) * | 2021-08-20 | 2021-10-22 | 杭州灵伴科技有限公司 | Meter image identification method and device, electronic equipment and computer readable medium |
| CN114140678A (en) * | 2021-11-23 | 2022-03-04 | 北京东方国信科技股份有限公司 | Scale recognition method and device, electronic equipment and storage medium |
| CN114155452A (en) * | 2021-11-29 | 2022-03-08 | 江苏红光仪表厂有限公司 | Information identification method for industrial automation instrument |
| CN114155452B (en) * | 2021-11-29 | 2022-11-15 | 江苏红光仪表厂有限公司 | Information identification method for industrial automation instrument |
| CN114565911A (en) * | 2022-02-28 | 2022-05-31 | 上海商汤科技开发有限公司 | Instrument reading method and device, computer equipment and storage medium |
| CN115565164A (en) * | 2022-11-17 | 2023-01-03 | 深圳市北电仪表有限公司 | Instrument panel numerical value identification method, device, equipment and storage medium |
| CN115980116A (en) * | 2022-11-22 | 2023-04-18 | 宁波博信电器有限公司 | High-temperature-resistant detection method and system for instrument panel, storage medium and intelligent terminal |
| CN115980116B (en) * | 2022-11-22 | 2023-07-14 | 宁波博信电器有限公司 | High-temperature-resistant detection method and system for instrument panel, storage medium and intelligent terminal |
| 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 |
| CN116012828A (en) * | 2022-12-02 | 2023-04-25 | 长扬科技(北京)股份有限公司 | Pointer instrument identification method and device, electronic equipment and storage medium |
| CN116012828B (en) * | 2022-12-02 | 2023-07-25 | 长扬科技(北京)股份有限公司 | Pointer instrument identification method and device, electronic equipment and storage medium |
| CN116363688A (en) * | 2023-03-23 | 2023-06-30 | 嘉洋智慧安全科技(北京)股份有限公司 | Image processing method, device, equipment, medium and product |
| CN116563631A (en) * | 2023-05-12 | 2023-08-08 | 深圳普菲特信息科技股份有限公司 | AI-based instrument panel visual identification method, system and storage medium |
| CN117437450A (en) * | 2023-12-12 | 2024-01-23 | 北京蒙帕信创科技有限公司 | Rotary switch identification method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115893A (en) | Instrument panel pointer reading identification method and device, computer equipment and storage medium | |
| CN110046529B (en) | Two-dimensional code identification method, device and equipment | |
| CN111178250B (en) | Object identification positioning method and device and terminal equipment | |
| US11699283B2 (en) | System and method for finding and classifying lines in an image with a vision system | |
| CN106980856B (en) | Formula identification method and system and symbolic reasoning calculation method and system | |
| CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
| CN108573471B (en) | Image processing apparatus, image processing method, and recording medium | |
| KR102649930B1 (en) | Systems and methods for finding and classifying patterns in images with a vision system | |
| WO2022151658A1 (en) | Defect detection method and apparatus, and computer device and computer-readable storage medium | |
| CN111382740B (en) | Text picture analysis method, text picture analysis device, computer equipment and storage medium | |
| CN111033563A (en) | Image analysis method and system for immunochromatography detection | |
| Lauridsen et al. | Reading circular analogue gauges using digital image processing | |
| CN113095292A (en) | Gesture recognition method and device, electronic equipment and readable storage medium | |
| CN110288040B (en) | Image similarity judging method and device based on topology verification | |
| CN111507957A (en) | Identity card picture conversion method and device, computer equipment and storage medium | |
| CN111221996A (en) | Instrument screen visual detection method and system | |
| JP2022009474A (en) | System and method for detecting lines in vision system | |
| CN114936997A (en) | Detection method, detection device, electronic equipment and readable storage medium | |
| CN114846513A (en) | Motion analysis system and motion analysis program | |
| US20160253570A1 (en) | Feature vector extraction device | |
| CN110689556A (en) | Tracking method and device and intelligent equipment | |
| CN115457585A (en) | Processing method and device for homework correction, computer equipment and readable storage medium | |
| CN112308836B (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN112508925A (en) | Electronic lock panel quality detection method, system, computer device and storage medium | |
| CN112559342A (en) | Method, device and equipment for acquiring picture test image 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 |