A method and related device for identifying a transmission tower logo

By using the object detection model and encoder in the transmission tower image to obtain feature vectors, and combining preset relationships, the transmission tower identification is automatically identified, which solves the problem of low recognition efficiency in the prior art and achieves fast and accurate identification and detection efficiency. promote.

CN118628706BActive Publication Date: 2024-12-06HUADIAN ZHANGQIU POWER GENERATION CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411108338.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-12-06
Estimated Expiration
2044-08-13

AI Technical Summary

Technical Problem

The prior art is difficult to quickly and accurately identify the identification of the transmission tower in the transmission tower image, resulting in low detection efficiency of the power system and unable to adapt to the needs of large-scale power networks.

Method used

By obtaining the image of the transmission tower to be tested, input it to the pre-constructed target detection model and encoder, obtaining the location area and target feature vector of the transmission tower, combining the correspondence between the preset transmission tower identification and the feature vector, and finding the highest similarity with the highest similarity Identify, realize automatic identification.

Benefits of technology

It realizes rapid and accurate identification of transmission tower marks, improves the detection efficiency of power system, adapts to the needs of large-scale power networks, and improves the accuracy of automated inspections.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118628706B_ABST
    Figure CN118628706B_ABST
Patent Text Reader

Abstract

The present application discloses a method for identifying a transmission tower logo and a related device, which relate to the field of artificial intelligence, including: obtaining an image of a transmission tower to be tested; inputting the image of the transmission tower to be tested into a pre-constructed target detection model, and obtaining a first position area of ​​the transmission tower in the image of the transmission tower to be tested through the target detection model; inputting the image of the transmission tower to be tested and the first position area into a pre-constructed encoder, and obtaining a target feature vector of the image located in the first position area through the encoder. From the correspondence between the preset transmission tower logo and the transmission tower feature vector, find the target transmission tower logo corresponding to the transmission tower feature vector with the highest similarity to the target feature vector. Obtain the transmission tower logo of the transmission tower in the image of the transmission tower to be tested based on the target transmission tower logo. The embodiment of the present application can automatically determine the transmission tower logo of the transmission tower in the image of the transmission tower to be tested through the image of the transmission tower to be tested.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method for identifying a transmission tower logo and a related device. Background Art

[0002] Transmission towers are an important part of the power system, and their inspection and maintenance are crucial to ensuring the safety of power transmission. Traditional inspection methods mainly rely on manual inspections, which are inefficient and cannot meet the needs of large-scale power networks. With the advancement of technology, automated inspection methods have begun to be applied to the identification and inspection of transmission towers. The automated inspection method includes: obtaining images of transmission towers to be inspected, and inspecting transmission towers in combination with the images of transmission towers; after obtaining the images of transmission towers to be inspected, it is necessary to identify the transmission tower logo of the transmission tower in the transmission tower image, so as to determine the correspondence between the transmission tower logo and the inspection results.

[0003] Based on this, how to quickly and accurately identify the transmission tower logo of the transmission tower in the transmission tower image is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0004] In view of the above problems, the present application provides a transmission tower identification method and related devices to achieve the purpose of quickly and accurately identifying the transmission tower identification of the transmission tower in the transmission tower image. The specific scheme is as follows:

[0005] The first aspect of the present application provides a method for identifying a transmission tower mark, comprising:

[0006] Acquire the image of the transmission tower to be tested;

[0007] Inputting the transmission tower image to be tested into a pre-built target detection model, and obtaining a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model;

[0008] Inputting the transmission tower image to be tested and the first location area into a pre-built encoder, and obtaining a target feature vector of the image located in the first location area through the encoder;

[0009] The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder.

[0010] From the correspondence between the preset transmission tower identifiers and the transmission tower feature vectors, searching for the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector;

[0011] The transmission tower identifier of the transmission tower in the transmission tower image to be tested is obtained based on the target transmission tower identifier.

[0012] In a possible implementation, the step of obtaining the transmission tower identification of the transmission tower in the transmission tower image to be tested based on the target transmission tower identification includes:

[0013] Acquire, from a preset knowledge graph, a second entity connected to a first entity having the target transmission tower identifier;

[0014] The knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of a transmission tower having the transmission tower identifier, and if the transmission towers represented by two entities are connected, there is an edge between the two entities;

[0015] determining a target entity from the first entity and the second entity;

[0016] It is determined that the transmission tower identifier included in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

[0017] In a possible implementation, the step of searching, from the correspondence between the preset transmission tower identifiers and the transmission tower feature vectors, for the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector includes:

[0018] From the correspondence between the preset transmission tower identifiers and the geographical locations, searching for candidate transmission tower identifiers within a geographical location range; the geographical location range is a range within a set length from a target geographical location, and the target geographical location is the geographical location of the transmission tower in the transmission tower image to be tested;

[0019] From the preset correspondence between the candidate transmission tower identifiers and the transmission tower feature vectors, the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector is searched.

[0020] In a possible implementation, the method for constructing the knowledge graph includes:

[0021] Obtain feature vectors corresponding to a plurality of existing transmission tower images;

[0022] For each of the existing transmission tower images, the transmission tower identification of the existing transmission tower image, the feature vectors corresponding to the multiple existing transmission tower images, and the set labels are input into the matching network model; a loss function is obtained through the prediction results of the matching network model and the labeling results corresponding to the existing transmission tower images; and the matching network model is trained through the loss function;

[0023] Among them, the set label includes a first transmission tower identifier, and each of the first transmission tower identifiers is a transmission tower identifier of a transmission tower connected to the transmission tower in the existing transmission tower image; the prediction result is the similarities and differences between the predicted label and the set label, and the predicted label includes the transmission tower identifier of the transmission tower connected to the transmission tower with the transmission tower identifier obtained by the matching network model, and the annotation result is that the set label is wrong or the set label is accurate.

[0024] In a possible implementation, the step of obtaining feature vectors corresponding to a plurality of existing transmission tower images respectively includes:

[0025] Inputting the plurality of existing transmission tower images into the target detection model respectively, and obtaining third position areas respectively corresponding to the plurality of existing transmission tower images through the target detection model;

[0026] The plurality of existing transmission tower images and the third position areas respectively corresponding to the plurality of existing transmission tower images are input into the encoder, and the feature vectors respectively corresponding to the plurality of existing transmission tower images are obtained through the encoder.

[0027] A second aspect of the present application provides a transmission tower identification device, comprising:

[0028] A first acquisition module is used to acquire an image of a transmission tower to be tested;

[0029] A second acquisition module is used to input the transmission tower image to be tested into a pre-built target detection model, and obtain a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model;

[0030] A third acquisition module is used to input the image of the transmission tower to be tested and the first location area into a pre-built encoder, and obtain a target feature vector of the image located in the first location area through the encoder;

[0031] The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder.

[0032] A search module, used to search for a target transmission tower identifier corresponding to a transmission tower feature vector having the highest similarity to the target feature vector from the correspondence between preset transmission tower identifiers and transmission tower feature vectors;

[0033] The fourth acquisition module is used to obtain the transmission tower identifier of the transmission tower in the transmission tower image to be tested based on the target transmission tower identifier.

[0034] In a possible implementation, the fourth acquisition module includes:

[0035] A first acquisition unit is used to acquire, from a preset knowledge graph, a second entity connected to the first entity having the target transmission tower identifier;

[0036] The knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of a transmission tower having the transmission tower identifier, and if the transmission towers represented by two entities are connected, there is an edge between the two entities;

[0037] A first determining unit, configured to determine a target entity from the first entity and the second entity;

[0038] The second determining unit is used to determine that the transmission tower identifier included in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

[0039] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the transmission tower identification method of the first aspect or any implementation of the first aspect.

[0040] A fourth aspect of the present application provides a server, comprising at least one processor and a memory connected to the processor, wherein:

[0041] The memory is used to store computer programs;

[0042] The processor is used to execute the computer program so that the server can implement the transmission tower identification method of the above-mentioned first aspect or any implementation manner of the first aspect.

[0043] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by a server, the server can implement the transmission tower identification method of the above-mentioned first aspect or any implementation of the first aspect.

[0044] By means of the above technical scheme, the present application provides a method for identifying a transmission tower logo, obtaining an image of a transmission tower to be tested; inputting the image of the transmission tower to be tested into a pre-constructed target detection model, and obtaining a first position area of ​​the transmission tower in the image of the transmission tower to be tested through the target detection model; inputting the image of the transmission tower to be tested and the first position area into a pre-constructed encoder, and obtaining a target feature vector of the image located in the first position area through the encoder. Since the first position area is the area that prompts the encoder to mainly obtain feature vectors, the target feature vector obtained by the encoder is more accurate. From the correspondence between the preset transmission tower logo and the transmission tower feature vector, the target transmission tower logo corresponding to the transmission tower feature vector with the highest similarity to the target feature vector is searched. It can be understood that the higher the similarity between the two transmission towers, the greater the possibility that the two transmission towers are the same transmission tower, so the transmission tower logo of the transmission tower in the image of the transmission tower to be tested is obtained based on the target transmission tower logo. The embodiment of the present application can automatically determine the transmission tower logo of the transmission tower in the image of the transmission tower to be tested through the image of the transmission tower to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0046] Figure 1 A schematic diagram of a system architecture provided for this application;

[0047] Figure 2 A schematic diagram of an optional hardware structure of a terminal 100 provided in this application;

[0048] Figure 3 A schematic diagram of the structure of a server 200 provided in this application;

[0049] Figure 4 A schematic diagram of a flow chart of a method for identifying a transmission tower logo provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of a representation form of an image of a transmission tower to be tested and a first location area provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of a transmission tower provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of the structure of a transmission tower identification device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0054] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0055] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0056] See also Figure 1 , Figure 1 A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0057] Among them, an image shooting application can be installed on the terminal 100, and an image of the transmission tower to be tested of the transmission tower can be obtained through the image shooting application, and the image of the transmission tower to be tested can be sent to the server 200. The server 200 can obtain the transmission tower identification of the transmission tower in the image of the transmission tower to be tested based on the received image of the transmission tower to be tested.

[0058] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the transmission tower identification of the transmission tower in the image of the transmission tower to be tested based on the received image of the transmission tower to be tested by itself without the need for cooperation from the server, and the embodiments of the present application are not limited thereto.

[0059] Next describe Figure 1 The product form of the mid-terminal 100;

[0060] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a drone, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any restrictions on this.

[0061] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0062] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 This is merely an example of a terminal and does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0063] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the terminal. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0064] Among them, the input device 132 can receive input data and the like.

[0065] The display unit 140 may be used to display information input by the user or provided to the user, various menus of the terminal 100, interactive interfaces, file display and / or playback of any multimedia file. In the embodiment of the present application, the display unit 140 may be used to display an interface of the image of the transmission tower to be tested, processing results, etc.

[0066] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0067] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0068] Among them, the memory 120 can be used to store software codes related to the transmission tower identification method, the processor 170 can execute the steps of the transmission tower identification method, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to achieve corresponding functions.

[0069] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0070] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0071] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0072] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0073] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0074] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0075] Next describe Figure 1 The product form of the server 200;

[0076] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0077] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0078] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0079] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0080] The memory 204 may be used to store software codes related to the transmission tower identification method, and the processor 202 may execute the steps of the transmission tower identification method of the chip, and may also schedule other units to implement corresponding functions.

[0081] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0082] Reference Figure 4 , Figure 4 A schematic diagram of a method for identifying a transmission tower logo provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, a method for identifying a transmission tower logo provided in an embodiment of the present application may include steps 401 to 405, and these steps are described in detail below.

[0083] Step 401: Acquire an image of a transmission tower to be tested.

[0084] For example, a terminal such as a drone or a robot may be used to photograph transmission towers in various locations to obtain images of the transmission towers to be tested.

[0085] For example, a person may carry a terminal to various places to photograph transmission towers to obtain images of the transmission towers to be tested.

[0086] It can be understood that steps 401 to 405 provided in the embodiment of the present application can be executed once at a set time interval, thereby achieving the purpose of inspecting the transmission tower based on the image of the transmission tower to be tested.

[0087] Step 402: input the transmission tower image to be tested into a pre-built target detection model, and obtain a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model.

[0088] Exemplarily, the method for training a target detection model includes the following steps A1 to A3.

[0089] Step A1: Input the sample transmission tower image into the target detection model; obtain the predicted location area through the target detection model.

[0090] Step A2: Obtain a loss function based on the predicted location area and the annotated location area of ​​the sample transmission tower image.

[0091] Step A3: training the target detection model through a loss function until the number of iterations reaches a preset number or the accuracy of the target detection model reaches a preset accuracy.

[0092] Exemplarily, the target detection model may be a YOLOv5 (You Only Look Once version 5) model or a Faster R-CNN (faster region proposal convolutional neural network) model.

[0093] Step 403: input the transmission tower image to be tested and the first location area into a pre-built encoder, and obtain a target feature vector of the image located in the first location area through the encoder.

[0094] The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder.

[0095] Exemplarily, there are many forms of presentation of the image of the transmission tower to be tested and the first location area, and the embodiments of the present application provide but are not limited to the following forms.

[0096] The first form: Figure 5 As shown, it is a schematic diagram of a representation form of the image of the transmission tower to be tested and the first position area provided in an embodiment of the present application. Figure 5 The dotted box in the middle is the first position area. Figure 5 The area framed by the solid line is the image of the transmission tower to be tested.

[0097] The second form: an image of the transmission tower to be measured and the coordinates of the first location area.

[0098] The process of training the encoder is described in detail below. The process includes the following steps B1 to B3.

[0099] Step B1: input the sample transmission tower image and the second position area into the transmission tower recognition model; obtain the prediction result through the transmission tower recognition model.

[0100] Among them, the prediction results include the following situations: Situation 1: the image located in the second position area is a transmission tower, and the second position area completely overlaps with the transmission tower location area of ​​the sample transmission tower image; Situation 2: the image located in the second position area is a transmission tower, and the overlap degree between the second position area and the transmission tower location area of ​​the sample transmission tower image is less than 1 and greater than 0; Situation 3: the image in the second position area is not a transmission tower, and the second position area is completely different from the transmission tower location area of ​​the sample transmission tower image.

[0101] Exemplarily, the transmission tower recognition model may be a ResNet (Residual Network) model or a DenseNet (Deep residual network) model.

[0102] Exemplarily, the transmission tower recognition model includes: an encoder and a decoder. Exemplarily, the input of the encoder is the input of the transmission tower recognition model, the output of the encoder is the input vector of the decoder, and the output of the decoder is the output of the transmission tower recognition model.

[0103] Step B2: Obtain the loss function by combining the prediction result obtained in step B1 with the labeling result of the sample transmission tower image.

[0104] Step B3: Train the transmission tower recognition model using the loss function obtained in step B2 until the number of training times reaches a preset threshold, or the accuracy of the transmission tower recognition model reaches a preset accuracy.

[0105] Step 404: searching for a target transmission tower identifier corresponding to a transmission tower feature vector having the highest similarity to the target feature vector from the correspondence between preset transmission tower identifiers and transmission tower feature vectors.

[0106] Exemplarily, the similarity may be cosine similarity.

[0107] Step 405: obtaining a transmission tower identifier of a transmission tower in the transmission tower image to be tested based on the target transmission tower identifier.

[0108] It is understandable that there are multiple ways to implement step 405, and the embodiments of the present application provide but are not limited to the following two.

[0109] The first implementation of step 405 includes: determining that the target transmission tower identifier is a transmission tower identifier of a transmission tower in the transmission tower image to be measured.

[0110] The second implementation of step 405 includes the following steps C1 to C3.

[0111] It is understandable that if there is an error in the target feature vector obtained in step 403, the target transmission tower identifier obtained in step 404 is not the transmission tower identifier of the transmission tower in the transmission tower image to be tested, so further determination is required.

[0112] Step C1: Obtain, from a preset knowledge graph, a second entity connected to a first entity having the target transmission tower identifier.

[0113] Among them, the knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of the transmission tower with the transmission tower identifier, if the transmission towers represented by two entities are connected, the two entities have edges; if the transmission towers represented by two entities are not connected, there are no edges between the two entities.

[0114] The following example shows that two transmission towers are connected. Figure 6 Shown is a schematic diagram of a transmission tower provided in an embodiment of the present application.

[0115] like Figure 6 As shown, the transmission tower 61 is connected to the transmission tower 62 and the transmission tower 63 respectively.

[0116] Step C2: determining a target entity from the first entity and the second entity.

[0117] Exemplarily, an existing transmission tower image of the first entity, an existing transmission tower image of the second entity, and an image of the transmission tower to be tested may be sent to a device held by an inspector, and the inspector determines a target entity from the first entity and the second entity.

[0118] Step C3: Determine that the transmission tower identifier in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

[0119] The embodiment of the present application provides a method for identifying a transmission tower logo, which includes obtaining an image of a transmission tower to be tested; inputting the image of the transmission tower to be tested into a pre-constructed target detection model, and obtaining a first position area of ​​the transmission tower in the image of the transmission tower to be tested through the target detection model; inputting the image of the transmission tower to be tested and the first position area into a pre-constructed encoder, and obtaining a target feature vector of the image located in the first position area through the encoder. Since the first position area is an area that prompts the encoder to mainly obtain feature vectors, the target feature vector obtained by the encoder is more accurate. From the correspondence between the preset transmission tower logo and the transmission tower feature vector, the target transmission tower logo corresponding to the transmission tower feature vector with the highest similarity to the target feature vector is searched. It can be understood that the higher the similarity between the two transmission towers, the greater the possibility that the two transmission towers are the same transmission tower, so the transmission tower logo of the transmission tower in the image of the transmission tower to be tested is obtained based on the target transmission tower logo. The embodiment of the present application can automatically determine the transmission tower logo of the transmission tower in the image of the transmission tower to be tested through the image of the transmission tower to be tested.

[0120] In an optional implementation, the method for constructing a knowledge graph includes the following steps D1 to D2.

[0121] Step D1: Obtain feature vectors corresponding to multiple existing transmission tower images.

[0122] It is understandable that, before executing steps 401 to 405, existing transmission tower images corresponding to each transmission tower have been obtained. Exemplarily, the implementation method of step D1 includes the following steps D11 to D12.

[0123] Step D11: input the plurality of existing transmission tower images into the target detection model respectively, and obtain the third position areas respectively corresponding to the plurality of existing transmission tower images through the target detection model.

[0124] Step D12: input the plurality of existing transmission tower images and the third position areas respectively corresponding to the plurality of existing transmission tower images into the encoder, and obtain the feature vectors respectively corresponding to the plurality of existing transmission tower images through the encoder.

[0125] Step D2: For each of the existing transmission tower images, the transmission tower identification of the existing transmission tower image, the feature vectors corresponding to the multiple existing transmission tower images, and the set labels are input into the matching network model; a loss function is obtained through the prediction results of the matching network model and the labeling results corresponding to the existing transmission tower images; and the matching network model is trained through the loss function.

[0126] Among them, the set label includes a first transmission tower identifier, and each of the first transmission tower identifiers is a transmission tower identifier of a transmission tower connected to the transmission tower in the existing transmission tower image; the prediction result is the similarities and differences between the predicted label and the set label, and the predicted label includes the transmission tower identifier of the transmission tower connected to the transmission tower with the transmission tower identifier obtained by the matching network model, and the annotation result is that the set label is wrong or the set label is accurate.

[0127] Exemplarily, the present application can classify multiple existing transmission tower images into positive samples and negative samples, wherein the set labels of the existing transmission tower images belonging to the positive samples are correct, and the set labels of the existing transmission tower images belonging to the negative samples are wrong. An example is given below.

[0128] Assume that the positive sample includes: an existing transmission tower image A011, and the set labels corresponding to the existing transmission tower image A011 include: the transmission tower identifications of the transmission towers connected to the transmission tower in the existing transmission tower image A011 are transmission tower identification A022 and transmission tower identification A033. Then, in the real environment, the transmission towers in the existing transmission tower image A011 are indeed connected to the transmission towers with the transmission tower identification A022 and the transmission towers with the transmission tower identification A033, respectively, that is, the set labels are accurate.

[0129] For the existing transmission tower image A011, if the predicted label obtained by the matching network model is {transmission tower identification A022, transmission tower identification A033}, the prediction result is {yes, yes}. Since the existing transmission tower image A011 is a positive sample, the labeling result is yes.

[0130] Assume that the negative samples include: the existing transmission tower image A044, and the set labels corresponding to the existing transmission tower image A044 include: the transmission tower identifications of the transmission towers connected to the transmission tower in the existing transmission tower image A044 are transmission tower identification A055 and transmission tower identification A066. Then, in the real environment, the transmission towers in the existing transmission tower image A044 are not connected to the transmission towers with the transmission tower identification A055 and the transmission towers with the transmission tower identification A066, that is, the set labels are wrong.

[0131] For the existing transmission tower image A044, if the predicted label obtained by the matching network model is {transmission tower identification A021, transmission tower identification A066}, the prediction result is {no, yes}. Since the existing transmission tower image A011 is a positive sample, the labeling result is {no, no}.

[0132] Exemplarily, the matching network model may be a Siamese Network (twin neural network) model or a Triplet Networks (three-layer neural network) model.

[0133] It is understandable that different transmission towers have different geographical locations. For example, each entity in the knowledge graph also includes the geographical location of the transmission tower. For example, the geographical location of the transmission tower in the image of the transmission tower to be tested can also be obtained. Based on this, the implementation method of step 404 includes the following steps E1 to E2.

[0134] Step E1: searching for candidate transmission tower identifiers within a geographical location range from the preset correspondence between transmission tower identifiers and geographical locations; the geographical location range is a range within a set length from a target geographical location, and the target geographical location is the geographical location of the transmission tower in the transmission tower image to be tested.

[0135] Exemplarily, the set length can be set based on actual conditions and is not limited here.

[0136] Exemplarily, the target geographic location can be obtained based on the following three methods.

[0137] A first method for obtaining a target geographic location includes: determining a geographic location of a device that photographs the transmission tower to be measured as the target geographic location.

[0138] Exemplarily, the number of the transmission tower images to be tested of the same transmission tower may be one or more.

[0139] The second method for obtaining the target geographical location includes: determining the target geographical location based on the geographical location of a device that photographs the transmission tower to be measured and the photographing angle of the device.

[0140] Exemplarily, the number of the transmission tower images to be tested of the same transmission tower may be one or more, so that the target geographical location can be obtained based on the geographical location and shooting angle of each transmission tower image to be tested.

[0141] The third method for obtaining the target geographic location includes: sending a positioning signal to the transmission tower when taking an image of the transmission tower to be tested; the positioning signal is used to instruct the positioning system of the transmission tower to obtain its own geographic location.

[0142] Step E2: from the preset correspondence between the candidate transmission tower identifiers and the transmission tower feature vectors, searching for the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector.

[0143] It is understandable that considering the error of the target geographical location, the candidate transmission tower identifiers within the geographical location range are searched. Exemplarily, the more accurate the target geographical location is, the smaller the set length is; the less accurate the target geographical location is, the larger the set length is.

[0144] It can be understood that when executing step E2, since the search is limited to the candidate transmission tower identifiers, the search scope is greatly reduced, which not only improves the search speed but also improves the search accuracy.

[0145] A method for identifying a transmission tower mark provided in an embodiment of the present application is introduced above, and a device for executing the above-mentioned method for identifying a transmission tower mark will be introduced below.

[0146] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of a transmission tower identification device provided in an embodiment of the present application. Figure 7 As shown, the transmission tower identification device comprises:

[0147] The first acquisition module 701 is used to acquire an image of a transmission tower to be tested;

[0148] The second acquisition module 702 is used to input the transmission tower image to be tested into a pre-built target detection model, and obtain a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model;

[0149] A third acquisition module 703 is used to input the transmission tower image to be tested and the first location area into a pre-built encoder, and obtain a target feature vector of the image located in the first location area through the encoder;

[0150] The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder.

[0151] A search module 704 is used to search for a target transmission tower identifier corresponding to a transmission tower feature vector having the highest similarity to the target feature vector from the correspondence between preset transmission tower identifiers and transmission tower feature vectors;

[0152] The fourth acquisition module 705 is used to obtain the transmission tower identifier of the transmission tower in the transmission tower image to be tested based on the target transmission tower identifier.

[0153] In an optional implementation, the fourth acquisition module includes:

[0154] A first acquisition unit is used to acquire, from a preset knowledge graph, a second entity connected to the first entity having the target transmission tower identifier;

[0155] The knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of a transmission tower having the transmission tower identifier, and if the transmission towers represented by two entities are connected, there is an edge between the two entities;

[0156] A first determining unit, configured to determine a target entity from the first entity and the second entity;

[0157] The second determining unit is used to determine that the transmission tower identifier included in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

[0158] In an optional implementation, the search module includes:

[0159] A first search unit is used to search for a candidate transmission tower identifier within a geographical location range from a preset correspondence between a transmission tower identifier and a geographical location; the geographical location range is a range within a set length from a target geographical location, and the target geographical location is the geographical location of the transmission tower in the transmission tower image to be tested;

[0160] The second searching unit is used to search the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity with the target feature vector from the preset correspondence between the candidate transmission tower identifiers and the transmission tower feature vectors.

[0161] In an optional implementation, the method further includes:

[0162] A fifth acquisition module is used to acquire feature vectors corresponding to a plurality of existing transmission tower images;

[0163] A sixth acquisition module is used to input the transmission tower identification of the existing transmission tower image, the feature vectors corresponding to the multiple existing transmission tower images, and the set labels into the matching network model for each of the existing transmission tower images; obtain a loss function through the prediction results of the matching network model and the labeling results corresponding to the existing transmission tower images; and train the matching network model through the loss function;

[0164] Among them, the set label includes a first transmission tower identifier, and each of the first transmission tower identifiers is a transmission tower identifier of a transmission tower connected to the transmission tower in the existing transmission tower image; the prediction result is the similarities and differences between the predicted label and the set label, and the predicted label includes the transmission tower identifier of the transmission tower connected to the transmission tower with the transmission tower identifier obtained by the matching network model, and the annotation result is that the set label is wrong or the set label is accurate.

[0165] In an optional implementation, the fifth acquisition module includes:

[0166] A second acquisition unit is used to input the plurality of existing transmission tower images into the target detection model respectively, and obtain third position areas respectively corresponding to the plurality of existing transmission tower images through the target detection model;

[0167] The third acquisition unit is used to input the multiple existing transmission tower images and the third position areas respectively corresponding to the multiple existing transmission tower images into the encoder, and obtain the feature vectors respectively corresponding to the multiple existing transmission tower images through the encoder.

[0168] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on a server, the server implements any of the transmission tower identification methods provided in the embodiments of the present application.

[0169] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by a server, the server can implement any of the transmission tower identification methods provided in the embodiments of the present application.

[0170] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0171] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0172] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0173] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for identifying a transmission tower logo, characterized in that: include: Acquire the image of the transmission tower to be tested; Inputting the transmission tower image to be tested into a pre-built target detection model, and obtaining a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model; Inputting the transmission tower image to be tested and the first location area into a pre-built encoder, and obtaining a target feature vector of the image located in the first location area through the encoder; The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder; From the correspondence between the preset transmission tower identifiers and the transmission tower feature vectors, searching for the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector; Obtaining a transmission tower identifier of a transmission tower in the transmission tower image to be tested based on the target transmission tower identifier; The step of obtaining the transmission tower identification of the transmission tower in the transmission tower image to be tested based on the target transmission tower identification comprises: Acquire, from a preset knowledge graph, a second entity connected to a first entity having the target transmission tower identifier; The knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of a transmission tower having the transmission tower identifier, and if the transmission towers represented by two entities are connected, there is an edge between the two entities; determining a target entity from the first entity and the second entity; It is determined that the transmission tower identifier included in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

2. The method for identifying a transmission tower according to claim 1, characterized in that: The step of searching, from the correspondence between the preset transmission tower identifiers and the transmission tower feature vectors, for the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector comprises: From the correspondence between the preset transmission tower identifiers and the geographical locations, searching for candidate transmission tower identifiers within a geographical location range; the geographical location range is a range within a set length from a target geographical location, and the target geographical location is the geographical location of the transmission tower in the transmission tower image to be tested; From the preset correspondence between the candidate transmission tower identifiers and the transmission tower feature vectors, the target transmission tower identifier corresponding to the transmission tower feature vector having the highest similarity to the target feature vector is searched.

3. The method for identifying a transmission tower according to claim 1, characterized in that: The method for constructing the knowledge graph includes: Obtain feature vectors corresponding to a plurality of existing transmission tower images; For each of the existing transmission tower images, the transmission tower identification of the existing transmission tower image, the feature vectors corresponding to the multiple existing transmission tower images, and the set labels are input into the matching network model; a loss function is obtained through the prediction results of the matching network model and the labeling results corresponding to the existing transmission tower images; and the matching network model is trained through the loss function; Among them, the set label includes a first transmission tower identifier, and each of the first transmission tower identifiers is a transmission tower identifier of a transmission tower connected to the transmission tower in the existing transmission tower image; the prediction result is the similarities and differences between the predicted label and the set label, and the predicted label includes the transmission tower identifier of the transmission tower connected to the transmission tower with the transmission tower identifier obtained by the matching network model, and the annotation result is that the set label is wrong or the set label is accurate.

4. The method for identifying a transmission tower according to claim 3, characterized in that: The step of obtaining feature vectors corresponding to a plurality of existing transmission tower images respectively comprises: Inputting the plurality of existing transmission tower images into the target detection model respectively, and obtaining third position areas respectively corresponding to the plurality of existing transmission tower images through the target detection model; The plurality of existing transmission tower images and the third position areas respectively corresponding to the plurality of existing transmission tower images are input into the encoder, and the feature vectors respectively corresponding to the plurality of existing transmission tower images are obtained through the encoder.

5. A transmission tower identification device, characterized in that: include: A first acquisition module is used to acquire an image of a transmission tower to be tested; A second acquisition module is used to input the transmission tower image to be tested into a pre-built target detection model, and obtain a first position area where the transmission tower is located in the transmission tower image to be tested through the target detection model; A third acquisition module is used to input the image of the transmission tower to be tested and the first location area into a pre-built encoder, and obtain a target feature vector of the image located in the first location area through the encoder; The transmission tower recognition model is obtained by taking the sample transmission tower image and the second position area as inputs of the transmission tower recognition model, and taking the annotation results corresponding to the sample transmission tower image as training targets, wherein the annotation results include: whether the image located in the second position area is a transmission tower, and the degree of overlap between the second position area and the position area where the transmission tower is located in the sample transmission tower image; the transmission tower recognition model includes the encoder and the decoder, and the output of the encoder is connected to the input of the decoder; A search module, used to search for a target transmission tower identifier corresponding to a transmission tower feature vector having the highest similarity to the target feature vector from the correspondence between preset transmission tower identifiers and transmission tower feature vectors; A fourth acquisition module, configured to obtain a transmission tower identifier of a transmission tower in the transmission tower image to be tested based on the target transmission tower identifier; The fourth acquisition module includes: A first acquisition unit is used to acquire, from a preset knowledge graph, a second entity connected to the first entity having the target transmission tower identifier; The knowledge graph includes multiple entities and edges between entities, each of the entities includes a transmission tower identifier and a feature vector of a transmission tower having the transmission tower identifier, and if the transmission towers represented by two entities are connected, there is an edge between the two entities; A first determining unit, configured to determine a target entity from the first entity and the second entity; The second determining unit is used to determine that the transmission tower identifier included in the target entity is the transmission tower identifier of the transmission tower in the transmission tower image to be tested.

6. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the transmission tower identification method as claimed in any one of claims 1 to 4.

7. A server, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the server can implement the transmission tower identification method as described in any one of claims 1 to 4.

8. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by the server, the server can implement the transmission tower identification method as described in any one of claims 1 to 4.