CN116503719A - Method and device for identifying connection relation of circuit experimental device - Google Patents

Abstract

The invention discloses a method for identifying the connection relationship of circuit experiment devices, comprising: obtaining circuit experiment pictures; performing target detection and instance segmentation on the circuit experiment pictures, and obtaining target recognition results including circuit experiment devices and connected terminal posts and connected The instance segmentation result of the wire; construct the directed graph corresponding to the circuit experiment according to the target recognition result and the instance segmentation result; and judge the series-parallel connection relationship between the circuit experiment devices based on the directed path of each experimental device in the directed graph. The solution can improve the accuracy of identifying the connection relationship between electrical experimental devices in complex scenarios.

Description

A method and device for identifying the connection relationship of circuit experiment devices

technical field

The invention relates to the technical field of circuit detection, in particular to a method, device, computing device and storage medium for identifying the connection relationship of circuit experimental devices.

Background technique

In the teaching or examination of physics and electricity experiments in middle schools, wires are commonly used experimental devices. In related experimental examinations and evaluations, the current direction in the circuit and the series-parallel relationship between electrical experimental equipment are the focus of investigation. Therefore, it is very important to be able to correctly judge the series-parallel connection relationship between devices and devices in the circuit.

At present, methods such as image-based object detection and semantic segmentation are mainly used to directly detect the connection relationship between circuit devices. However, this scheme has the problem of low recognition accuracy when the number of electrical experimental equipment is large and the connection relationship is diverse.

Therefore, it is necessary to provide a method for identifying the connection relationship between circuit experiment devices, which can accurately identify the connection relationship between circuit experiment devices in complex scenarios, so as to solve the problems existing in the prior art.

Contents of the invention

In view of the above problems, the present invention proposes a method, device, computing device and storage medium for identifying the connection relationship of circuit experiment devices that overcome the above problems or at least partially solve the above problems, by combining target detection, instance segmentation and directed graph The combination of construction can dynamically construct a directed graph based on the experimental circuit, and traverse the directed path of the experimental device according to the constructed directed graph data, so as to accurately judge the series-parallel connection relationship between the circuit experimental devices, which can be applied to complex identification The detection of the connection state of the experimental circuit in the scene.

According to the first aspect of the present invention, a method for identifying the connection relationship of circuit experiment devices is provided. First, the circuit experiment picture is obtained; The target recognition result and the instance segmentation result of the connected wire; then, construct the directed graph corresponding to the circuit experiment according to the target recognition result and the instance segmentation result; finally, based on the directed path of each experimental device in the directed graph, judge The series-parallel connection relationship between circuit experiment devices.

Through the above technical solution, by performing more fine-grained target detection and instance segmentation on the circuit experiment picture, the positional relationship of each experimental device, terminal and wire in the experiment picture can be determined more accurately. And according to the target recognition results and instance segmentation results, the directed graph data between each experimental device can be constructed, which can express the true description of the circuit experiment more vividly, so that the connection relationship between the circuit experimental devices can be more accurately determined according to the directed graph data .

Optionally, in the above method, the circuit test picture can be input into the pre-trained first target detection model to obtain the circuit test device detection frame; the circuit test picture containing the circuit test device detection frame can be input into the pre-trained In the second target detection model, the connected terminal detection frame is obtained; and the circuit experiment picture including the circuit experiment device detection frame and the connected terminal detection frame is input into the pre-trained instance segmentation model, and the connected wire recognition result is obtained .

Through finer-grained target detection and instance segmentation, the difficulty of feature extraction for deep learning models can be reduced, and the accuracy of different target recognition can be improved.

Optionally, in the above method, the first target detection model and the second target detection model are any of Faster-RCNN, YOLO, SSD, and Cornernet, and the instance segmentation model is any of mask RCNN and cascade RCNN.

Optionally, in the above method, the circuit experimental device is used as the vertex of the directed graph; the current direction in the wire is determined according to the connected terminal and the connected wire as the edge of the directed graph.

Optionally, in the above method, the terminals include the connected red terminal, the connected black terminal, and the connected terminal, and the direction of the wire from the connected black terminal to the connected red terminal can be determined as the current direction ; Determine the direction of the wire from the connected black terminal to the connected terminal as the current direction; determine the direction of the wire from the connected terminal to the connected red terminal as the current direction, and generate an initial directed graph.

Optionally, in the above method, if both ends of the wire are connected to red binding posts, perform a reverse query on the initial directed graph; if both ends of the wire are connected to black binding posts, perform a reverse query on the initial directed graph Positive query; if both ends of the wire are connected terminals, add a bi-directional edge between circuit experimental devices.

Optionally, in the above method, the path query is performed on the experimental device in the directed graph until the query path returns to the experimental device; if the query path of the first experimental device does not include the second experimental device, then the first experimental device is determined It is in a parallel relationship with the second experimental device; if the query path of the first experimental device includes the second experimental device, it is determined that the first experimental device and the second experimental device are in a serial relationship.

According to the second aspect of the present invention, there is provided a device for identifying the connection relationship of circuit experimental devices, including: an acquisition module, a detection module, a construction module and a judgment module.

Among them, the acquisition module is used to obtain the circuit experiment picture; the detection module is used to perform target detection and instance segmentation on the circuit experiment picture, and obtain the target recognition result including the circuit experiment device, the connected terminal post and the instance segmentation result of the connected wire ; a building module, used to construct a directed graph corresponding to the circuit experiment according to the target recognition result and the instance segmentation result; Parallel connections.

According to a third aspect of the present invention, there is provided a computing device, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions comprising Execute the instructions of the method for identifying the connection relationship of the above-mentioned circuit experiment devices.

According to a fourth aspect of the present invention, there is provided a readable storage medium storing program instructions. When the program instructions are read and executed by a computing device, the computing device executes the above-mentioned method for identifying the connection relationship of circuit experimental devices.

According to the solution of the present invention, by performing more fine-grained target detection and instance segmentation on the circuit experiment picture, the difficulty of feature extraction can be reduced, which is conducive to improving the recognition accuracy; constructing a directed graph according to the recognition result can express the electrical experiment more vividly In the description of the connection relationship of the circuit diagram, compared with the identification of the connection relationship directly using the deep learning model, this scheme can improve the accuracy of the connection relationship identification between electrical equipment, and can be applied to the accurate connection relationship of circuit experiment devices in complex scenarios. identify.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a structural block diagram of a computing device 100 according to an embodiment of the present invention;

FIG. 2 shows a schematic flow diagram of a method 200 for identifying connection relationships of circuit experiment devices according to an embodiment of the present invention;

Fig. 3 shows a schematic diagram of a circuit experiment picture according to an embodiment of the present invention;

Fig. 4 shows a schematic diagram of the identification result of the circuit experiment device according to one embodiment of the present invention;

Fig. 5 shows a schematic diagram of a recognition result of a terminal according to an embodiment of the present invention;

Fig. 6 shows a schematic diagram of a connected wire identification result according to an embodiment of the present invention;

Figure 7 shows a schematic diagram of an initial directed graph of a circuit experiment according to an embodiment of the present invention;

FIG. 8 shows a schematic diagram of a directed graph corresponding to a circuit experiment according to an embodiment of the present invention;

FIG. 9 shows a schematic structural diagram of an apparatus 900 for identifying connection relationships of circuit experiment devices according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

In middle school physics and electricity experiments, connecting the circuit according to the circuit diagram is the focus of investigation, such as using an ammeter to measure current, using a voltmeter to measure voltage, and using a sliding rheostat to change the current in the circuit and other experiments. Among them, it is necessary to judge the accuracy of the connection between the wire and the positive and negative poles of the ammeter, whether the series and parallel connection mode between the electrical devices is correct, and whether the line connection is complete.

At present, in the prior art, the area where there is a connection relationship between two electrical devices is used as the target detection frame, and the target detection technology is used to perform model training on the above detection frame, and the target detection model obtained by training is directly tested for the connection relationship between the circuit devices. identification. Since the difference between the details of the target detection frame in the series relationship and the parallel relationship is not obvious, it will lead to difficulty in feature extraction and low recognition accuracy.

In order to improve the accuracy of identifying the series-parallel relationship between circuit experimental devices, this scheme provides a method for identifying the connection relationship between circuit experimental devices, by using a finer-grained target detection frame for target detection, combined with dynamic directed graphs The construction of the connection relationship between devices can more accurately identify the connection relationship between experimental devices.

FIG. 1 shows a block diagram of a computing device 100 according to an embodiment of the present invention. As shown in FIG. 1 , in a basic configuration 102 , computing device 100 typically includes system memory 106 and one or more processors 104 . A memory bus 108 may be used for communication between the processor 104 and the system memory 106 .

Depending on the desired configuration, processor 104 may be any type of processor including, but not limited to, a microprocessor (µP), microcontroller (µC), digital information processor (DSP), or any combination thereof. Processor 104 may include one or more levels of cache such as L1 cache 110 and L2 cache 112 , processor core 114 and registers 116 . Exemplary processor core 114 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. An example memory controller 118 may be used with the processor 104 or, in some implementations, the memory controller 118 may be an internal part of the processor 104 .

Depending on the desired configuration, system memory 106 may be any type of memory including, but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. The physical memory in the computing device usually refers to the volatile memory RAM, and the data in the disk needs to be loaded into the physical memory before being read by the processor 104 . System memory 106 may include an operating system 120 , one or more applications 122 , and program data 124 .

In some implementations, applications 122 may be arranged to execute instructions on an operating system with program data 124 by one or more processors 104 . The operating system 120 may be, for example, Linux, Windows, etc., which includes program instructions for handling basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for realizing various user-desired functions. The application 122 may be, for example, a browser, instant messaging software, software development tools (such as an integrated development environment IDE, a compiler, etc.), but is not limited thereto. When the application 122 is installed into the computing device 100 , a driver module may be added to the operating system 120 .

When the computing device 100 starts to run, the processor 104 reads program instructions of the operating system 120 from the memory 106 and executes them. The application 122 runs on the operating system 120, and utilizes the interface provided by the operating system 120 and the underlying hardware to realize various user-desired functions. When the user starts the application 122 , the application 122 is loaded into the memory 106 , and the processor 104 reads and executes the program instructions of the application 122 from the memory 106 .

Computing device 100 also includes storage device 132 , which includes removable storage 136 and non-removable storage 138 , both of which are connected to storage interface bus 134 .

Computing device 100 may also include interface bus 140 to facilitate communication from various interface devices (eg, output devices 142 , peripheral interfaces 144 , and communication devices 146 ) to base configuration 102 via bus/interface controller 130 . Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150 . They may be configured to facilitate communication with various external devices such as a display or speakers via one or more A/V ports 152 . Example peripherals interfaces 144 may include serial interface controller 154 and parallel interface controller 156, which may be configured to facilitate communication via one or more I/O ports 158 and input devices such as (e.g., keyboard, mouse, pen) , voice input device, touch input device) or other peripherals (such as printers, scanners, etc.) to communicate with external devices. The example communication device 146 may include a network controller 160 , which may be arranged to facilitate communication with one or more other computing devices 162 over a network communication link via one or more communication ports 164 .

A network communication link may be one example of a communication medium. Communication media typically embodies computer readable instructions, data structures, program modules in a modulated data signal such as a carrier wave or other transport mechanism and may include any information delivery media. A "modulated data signal" may be a signal that has one or more of its data sets or changes thereof in such a manner as to encode information in the signal. By way of non-limiting example, communication media may include wired media such as a wired network or a dedicated-line network, and various wireless media such as acoustic, radio frequency (RF), microwave, infrared (IR) or other wireless media. The term computer readable media as used herein may include both storage media and communication media. In the computing device 100 according to the present invention, the application 122 includes instructions for executing the method 200 for identifying the connection relationship of circuit experimental devices of the present invention.

The intelligent experimental evaluation system judges whether the circuit is connected correctly by judging the connection status of the wire and the experimental device. However, in the actual evaluation process, it is difficult to accurately identify the experimental device using the deep learning algorithm due to problems such as crossed wire connections and disorderly placement. between series and parallel connections. Therefore, this solution provides a method for identifying the connection relationship of electrical experimental devices, which can accurately identify the series-parallel connection state between the circuit experimental devices.

FIG. 2 shows a schematic flowchart of a method 200 for identifying connection relationships of circuit experiment devices according to an embodiment of the present invention. As shown in FIG. 2 , the method starts at step S210 , obtaining a picture of a circuit experiment.

According to an embodiment of the present invention, a camera can be set up above the experimental operation table, so that the camera can overlook and shoot the experimental operation table top, and ensure that the entire circuit diagram connected can be fully presented in the image captured by the camera.

After obtaining the circuit experiment pictures collected by the camera, the pictures can be screened, and the pictures that do not meet the recognition conditions such as blurred shooting, insufficient light, and jittering can be removed, and the circuit experiment pictures with clear pictures can be selected as subsequent pictures to be recognized.

Fig. 3 shows a schematic diagram of a picture of a circuit experiment according to an embodiment of the present invention. As shown in Figure 3, the circuit experiment picture includes a voltmeter, an ammeter, a small light bulb, a sliding rheostat, a battery, a switch, and wires used to connect various devices.

Then step S220 is executed to perform object detection on the circuit experiment picture to obtain a recognition result including the experimental device, the connected terminal and the connected wire.

Target detection and instance segmentation can be performed on the circuit experiment pictures respectively, and then the target detection results and instance segmentation recognition results are superimposed for the construction of subsequent directed graphs.

According to an embodiment of the present invention, the obtained circuit test pictures can be input into the pre-trained first target detection model to obtain the recognition result of the circuit test device. For example, the power supply, switch, sliding rheostat, bulb base, voltmeter, and ammeter in the circuit experiment picture can be detected as targets to be identified, and the detection frames of the power supply, switch, sliding rheostat, bulb base, voltmeter, and ammeter can be obtained.

Then, continue to input the circuit test picture including the detection frame of each circuit test device into the pre-trained second target detection model, and output the detection frame connected to the terminal. For example, the terminal can be detected as the target to be recognized in the second target detection model, and the detection frame of the connected terminal can be obtained.

Wherein, the first target detection model and the second target detection model can be any one of Faster-RCNN, YOLO series, SSD, and Cornernet. Taking the YOLOv5 model as an example, the wiring points of all experimental devices can be uniformly identified as binding posts. According to the spatial position relationship between the binding post and the experimental device, it can be judged which connecting post belongs to the experimental device, and whether the connecting post is connected to the wire. The wire connection then identifies this terminal as a connected terminal, resulting in a callout box for each connected terminal.

It should be noted that, in order to obtain the trained first target detection model and the second target detection model, an image annotation tool can be used to mark the experimental device and the terminal of the experimental device. The content of the label includes the name and the color of the terminal (red means Positive pole, black for negative pole, blue for no positive and negative pole) and coordinates of the labeled frame, as the training data set. The YOLOv5 model is used to train and verify the training data set, and the trained first target detection model and the second target detection model are obtained.

Fig. 4 shows a schematic diagram of device identification results of a circuit experiment according to an embodiment of the present invention. As shown in Figure 4, the recognition results output by the first target detection model include the category label and detection frame of the voltmeter, the category label and detection frame of the ammeter, the category label and detection frame of the sliding rheostat, the label and detection frame of the switch, The category label and check box of the power supply, the category label and check box of the bulb base.

Fig. 5 shows a schematic diagram of a recognition result of a terminal according to an embodiment of the present invention. As shown in Figure 5, the recognition results output by the second target detection model include the label and detection frame of the connected red terminal, the label and detection frame of the connected black terminal, and the label and detection frame of the connected terminal. Wherein the connected terminal refers to the terminal of unidentifiable color and the connected terminal on the sliding rheostat.

In complex scenarios with many circuit experimental devices, different types of experimental devices or connected terminals can be marked with different colors. For example, use red for voltmeters, blue for ammeters, etc., yellow for connected terminals, and purple for connected red terminals.

For a target object in the shape of a thin strip such as a wire, in order to improve the accuracy of recognition, the circuit experiment picture including the detection frame of the circuit experiment device and the detection frame of the connected terminal can be input into the pre-trained instance segmentation model to obtain the connected Wire identification results.

The instance segmentation model can be mask RCNN. First, feature maps of different scales are obtained based on the model's basic network backbone, and then based on the region proposal network RPN, each point on the feature map generates rectangular frames of different scales, and rough classification and rough classification are performed through the network. Positioning, based on confidence and non-maximum value suppression, a large number of rectangular boxes are screened out, and the remaining rectangular boxes are input into the subsequent network. Then the rectangular frames of different sizes and scales are output through the ROI Align layer to output a fixed-size feature map. Finally, the fixed-size feature map is used as the input of the classification branch, coordinate regression branch and Mask branch to further determine the category of the rectangular frame, determine which pixels in the rectangular frame are objects, and which pixels are the background, so as to obtain the second dimension of the wire through instance segmentation. Valued mask image.

The instance segmentation model can also be an HTC model, a cascade maskRCNN model, etc., which is not limited in this solution.

Fig. 6 shows a schematic diagram of an identification result of connected wires according to an embodiment of the present invention. As shown in Figure 6, each wire in the circuit experiment picture is marked. It can also identify the wires in the picture based on image processing methods such as mean filter migration and edge detection. Then determine the connected wire according to the positional relationship between the wire and the experimental device and the connected terminal.

After the above target recognition result and instance segmentation result are superimposed, step S230 can be performed to construct a directed graph corresponding to the circuit experiment according to the target recognition result and the instance segmentation result.

According to one embodiment of the present invention, first determine the current direction in the wire according to the identified connected terminal and the connected wire instance, that is, the direction of the wire from "connected black terminal" to "connected red terminal" is the current direction. Direction, the direction from "connected black terminal" to "connected terminal" is the direction of current, and the direction from "connected terminal" to "connected red terminal" is the direction of current.

For example, the direction from the connected post on the base of the small light bulb to the connected red post on the ammeter is the direction of current flow. The entire dynamic directed graph construction can take the direction of current as the direction of the edges in the graph data (power supply—>switch, switch—>sliding rheostat, sliding rheostat—>small light bulb base, small light bulb base—>ammeter, ammeter—>power supply), Circuit experimental devices are used as graph vertices. For the case where both ends of the wire are "connected to the black terminal" or "connected to the red terminal" (the direction of the current cannot be determined), the initial directed graph can be automatically generated.

Fig. 7 shows a schematic diagram of an initial directed graph of a circuit experiment according to an embodiment of the present invention. As shown in Figure 7, the voltmeter, ammeter, small light bulb base, sliding rheostat, power supply and switch are the vertices of the directed graph, the current direction from the voltmeter to the ammeter, the current direction from the small light bulb base to the ammeter, and the sliding rheostat to the small light bulb The current direction of the base, the current direction of the switch to the sliding rheostat, the current direction of the power supply to the switch, and the current direction of the ammeter to the power supply are used as the edges of the directed graph.

For the case where both ends of the wire are connected to the red terminal at the same time, perform a reverse query according to the initial directed graph shown in Figure 7, that is, the last device at the base of the small light bulb, that is, the sliding rheostat, so that the sliding rheostat adds a line to the voltmeter There is an edge. Similarly, if both ends of the wire are connected to black terminals at the same time, the next device of the corresponding device is queried according to the initial directed graph shown in FIG. 7 . If both ends of the wire are connected terminals of an unidentifiable color at the same time, a bidirectional edge is added between the two ends of the device.

Fig. 8 shows a schematic diagram of a directed graph corresponding to a circuit experiment according to an embodiment of the present invention. As shown in Figure 8, compared with the initial directed graph established in Figure 7, the finally established directed graph adds the sliding rheostat to the directed edge of the voltmeter.

Finally, step S240 is executed, based on the directed path of each experimental device in the directed graph, the series-parallel connection relationship between the circuit experimental devices is judged.

Specifically, the path query can be performed for each experimental device in the directed graph, that is, the connection path is queried from a certain experimental device until the query path returns to the experimental device;

If the query path of the first experimental device does not include the second experimental device, it is determined that the first experimental device and the second experimental device are in parallel relationship; if the query path of the first experimental device contains the second experimental device, then determine There is a series relationship between the first experimental device and the second experimental device.

In one embodiment of the present invention, the directed edge path query can be performed on the graph nodes where the voltmeter and the small light bulb base are located, until the specified query device is returned. If there is an opposite device in each other's path, it means two devices It is a series relationship. If there is no other device in the path of each other, it means that the two devices queried are in a parallel relationship.

For example, perform a directed path query on a voltmeter: voltmeter—>ammeter—>power supply—>switch—>sliding rheostat—voltmeter. Perform directed path query on the small light bulb base: small light bulb base—>ammeter—>power supply—>switch—>sliding rheostat—>small light bulb base. It can be seen that there is no small light bulb base in the directed path of the voltmeter, and there is no voltmeter in the directed path of the small light bulb base, indicating that there is a parallel connection between the small light bulb base and the voltmeter.

According to the above method, the connection relationship between every two circuit experimental devices is judged, and finally the series-parallel connection relationship between each circuit experimental device in the whole circuit is obtained.

FIG. 9 shows a schematic structural diagram of an apparatus 900 for identifying connection relationships of circuit experiment devices according to an embodiment of the present invention. As shown in FIG. 9 , the apparatus 900 may include: an acquisition module 910 , a detection module 920 , a construction module 930 and a judgment module 940 .

Wherein, the acquiring module 910 can acquire the circuit experiment pictures. The circuit experiment pictures can be collected through the camera above the experiment console, and the collected pictures can be screened or preprocessed to obtain the circuit experiment pictures to be recognized that can meet the recognition conditions of the target detection model.

The detection module 920 can perform object detection and instance segmentation on the circuit experiment pictures acquired by the acquisition module 910, and obtain object recognition results including circuit experiment devices, connected terminals, and instance segmentation results of connected wires.

According to an embodiment of the present invention, the YOLOv5 network and mask RCNN network can be constructed by using the pytorch library, and the circuit experiment picture is first input into the pre-trained first YOLOv5 network to obtain the detection frame of the circuit experiment device; Input the circuit experiment picture of the frame into the pre-trained second YOLOv5 network to obtain the connected terminal detection frame; and input the circuit experiment picture into the pre-trained mask RCNN network to obtain the connected wire recognition result.

The construction module 930 may construct a directed graph according to the object recognition result and the instance segmentation result obtained by the detection module 920 . For example, take the circuit experimental device as the vertex of the directed graph; determine the direction of the current in the wire according to the terminal and the connected wire as the edge of the directed graph.

You can first determine the direction of the wire from the connected black terminal to the connected red terminal as the current direction; determine the direction of the wire from the connected black terminal to the connected terminal as the current direction; The direction to the connected red terminal is determined as the current direction, generating an initial directed graph.

Then, the initial directed graph is corrected, that is, if both ends of the wire are connected to red terminals, reverse query is performed on the initial directed graph; if both ends of the wire are connected to black terminals, then the initial directed graph is Make a forward query to the graph; if both ends of the wire are connected terminals, add a bidirectional edge between the circuit experiment devices. Finally, the directed graph corresponding to the whole circuit experiment graph is obtained.

The judging module 940 can judge the series-parallel connection relationship between the circuit experimental devices based on the directed path of each experimental device in the directed graph obtained by the construction module 930 .

Specifically, path query is performed for each experimental device in the directed graph until the query path returns to the experimental device; if the query path of the first experimental device does not include the second experimental device, then determine the first experimental device and the second experimental device The devices are in a parallel relationship; if the query path of the first experimental device includes the second experimental device, it is determined that the first experimental device and the second experimental device are in a serial relationship.

Through the above scheme, by performing more fine-grained target detection and instance segmentation on the circuit experiment pictures, the difficulty of feature extraction can be reduced, which is conducive to improving the recognition accuracy; constructing a directed graph based on the recognition results can more vividly express the circuit diagram in the electrical experiment For the description of the connection relationship, compared with directly using the deep learning model to identify the connection relationship, this scheme can improve the accuracy of the connection relationship identification between electrical equipment, and can be applied to the accurate identification of the connection relationship of circuit experiment devices in complex scenarios.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will understand that the modules or units or components of the devices in the examples disclosed herein may be arranged in the device as described in this embodiment, or alternatively may be located in a different location than the device in this example. in one or more devices. The modules in the preceding examples may be combined into one module or furthermore may be divided into a plurality of sub-modules.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings), as well as any method or method so disclosed, may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

Furthermore, some of the described embodiments are described herein as a method or combination of method elements that may be implemented by a processor of a computer system or by other means for performing the described function. Thus, a processor with the necessary instructions for carrying out the described method or element of a method forms a means for carrying out the method or element of a method. Furthermore, elements described herein of an apparatus embodiment are examples of means for carrying out the function performed by the element for the purpose of carrying out the invention.

As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe generic objects merely means referring to different instances of similar objects and is not intended to imply such The described objects must have a given order temporally, spatially, sequentially or in any other way.

While the invention has been described in terms of a limited number of embodiments, it will be apparent to a person skilled in the art having the benefit of the above description that other embodiments are conceivable within the scope of the invention thus described. In addition, it should be noted that the language used in the specification has been chosen primarily for the purpose of readability and instruction rather than to explain or define the inventive subject matter. Accordingly, many modifications and alterations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative rather than restrictive with respect to the scope of the present invention, which is defined by the appended claims.

Claims (10)

1. A method for identifying connection relationship of circuit experiment devices, characterized in that, comprising: Obtain the circuit experiment picture; Carrying out target detection and instance segmentation on the circuit experiment picture, and obtaining the object recognition result including the circuit experiment device, the connected terminal and the instance segmentation result of the connected wire; Constructing a directed graph corresponding to the circuit experiment according to the target recognition result and the instance segmentation result; and Based on the directed path of each experimental device in the directed graph, the series-parallel connection relationship between the circuit experimental devices is judged. 2. identification method according to claim 1, is characterized in that, described described circuit test picture is carried out target detection and instance segmentation, obtains the target recognition result that comprises circuit test device, connected binding post and connected lead. The steps for instance segmentation results include: Inputting the circuit experiment picture into the pre-trained first target detection model to obtain the circuit experiment device detection frame; Inputting the circuit experiment picture containing the detection frame of the circuit experiment device into the pre-trained second target detection model to obtain the connected terminal detection frame; and Inputting the circuit experiment picture containing the detection frame of the circuit experiment device and the detection frame of the connected terminal into the pre-trained instance segmentation model to obtain the recognition result of the connected wire. 3. The recognition method according to claim 2, wherein the first target detection model and the second target detection model are any one of Faster-RCNN, YOLO, SSD, and Cornernet, and the instance segmentation model is Any one of mask RCNN and cascade RCNN. 4. The identification method according to claim 1, wherein the step of constructing a directed graph corresponding to a circuit experiment according to the target identification result and the instance segmentation result comprises: Take the circuit experimental device as the vertex of the directed graph; Determines the direction of current flow in wires based on the terminals and connected wires as edges of a directed graph. 5. The identification method according to claim 4, characterized in that, the binding post includes a connected red binding post, a connected black binding post, and a connected binding post, and it is determined according to the binding post and the connected wire The current direction steps include: Determine the direction of the wire from the connected black terminal to the connected red terminal as the current direction; Determine the direction of the wire from the connected black terminal to the connected terminal as the current direction; Determine the direction of the wire from the connected terminal to the connected red terminal as the direction of the current flow, generating an initial directed graph. 6. The identification method according to claim 5, wherein the step of determining the direction of current in the wire according to the binding post and the connected wire further comprises: If both ends of the wire are connected to the red terminal, perform a reverse query on the initial directed graph; If both ends of the wire are connected to black terminals, perform a forward query on the initial directed graph; If both ends of the wire are connected terminals, add a bidirectional edge between the circuit experiment devices. 7. identification method according to claim 1, is characterized in that, described based on the directional path of each experimental device in described directed graph, the step of judging the series-parallel connection relationship between circuit experimental devices comprises: Perform path query for each experimental device in the directed graph until the query path returns to the experimental device; If the query path of the first experimental device does not include the second experimental device, it is determined that the first experimental device and the second experimental device are in a parallel relationship; If the query path of the first experimental device includes the second experimental device, it is determined that the relationship between the first experimental device and the second experimental device is in series. 8. A device for identifying the connection relationship of circuit experiment devices, characterized in that it comprises: The acquisition module is used to acquire circuit experiment pictures; The detection module is used to perform target detection and instance segmentation on the circuit experiment picture, and obtain the object recognition result including the circuit experiment device, the connected terminal and the instance segmentation result of the connected wire; A construction module, configured to construct a directed graph corresponding to a circuit experiment according to the target recognition result and the instance segmentation result; and The judging module is configured to judge the series-parallel connection relationship between the circuit experimental devices based on the directed path of each experimental device in the directed graph. 9. A computing device comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions comprising instructions for performing any one of claims 1-7 Instructions for the identification method of the circuit experiment device connection relationship described in the item. 10. A readable storage medium storing program instructions, when the program instructions are read and executed by a computing device, the computing device is made to execute the circuit experimental device according to any one of claims 1-7 The identification method of connection relationship.