Infrared servo method, system and robot for inspection robot with dual cameras

Abstract

The application belongs to the technical field of substation equipment inspection robots, and provides an infrared servo method and system for an inspection robot with dual cameras and the robot, and the technical scheme is to determine a servo type of a to-be-inspected point according to the environment and characteristics of different inspection points; based on the determined servo mode, a corresponding servo process is executed to generate a gimbal correction control instruction, which significantly improves the inspection efficiency and accuracy, provides flexible servo mode selection, meets the needs of different inspection scenes, and avoids the problem of low inspection efficiency and insufficient accuracy caused by the continuous adjustment of the focal length of the camera when a single camera collects data.

Description

Technical Field

[0001] This invention belongs to the technical field of substation equipment inspection robots, and particularly relates to an infrared servo method, system and substation inspection robot with dual cameras. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] When performing inspection tasks, traditional inspection robots directly call the preset gimbal angle and camera parameters based on the image acquisition configuration preset in the equipment template library. When locating the equipment to be inspected, the system performs gimbal angle correction through the visible light camera. This process requires frequent adjustment of zoom and focus values. This operation mode not only increases the mechanical wear of the visible light camera's optical components and shortens the camera's lifespan, but also increases the time spent on single-point inspection due to the continuous adjustment of the camera, ultimately resulting in a decrease in overall inspection efficiency. Summary of the Invention

[0004] To address at least one of the technical problems mentioned in the background section, this invention provides an infrared servo method and system for substation inspection robots. This system utilizes an innovative dual-camera setup combined with infrared servo functionality to significantly improve inspection efficiency and accuracy. Furthermore, it offers flexible servo mode selection to meet the needs of various inspection scenarios.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides an infrared servo method for an inspection robot using dual cameras, comprising the following steps: The servo type of the inspection point is determined based on the environment and characteristics of different inspection points; Based on the determined servo mode, the corresponding servo process is executed to generate gimbal calibration control commands, including: If there is no servo, the visible light image will be acquired directly after the pan-tilt unit is positioned according to the preset parameters and the visible light camera parameters are adjusted. If the servo mode is visible light servo, then control the visible light servo to perform visible light image acquisition; If the servo mode is infrared servo or hybrid servo, then control the infrared servo image acquisition, perform registration based on the infrared servo image acquisition result and infrared servo template, determine the position and attitude information of the inspection target according to the registration result, convert the position and attitude information in the image coordinate system into the coordinate information corresponding to the gimbal control, and generate control commands corresponding to the angle and position that the gimbal needs to adjust.

[0006] Furthermore, if the servo mode is hybrid servo, when the infrared servo fails, the visible light servo will continue to be executed.

[0007] Furthermore, if the servo mode is infrared servo, the infrared servo focus magnification value is read. If the read infrared focus value is less than the set value, the infrared servo image is controlled for the first acquisition. The infrared servo template and the first acquired infrared image are registered, and the first registration deviation is recorded. The infrared servo image is controlled for the second acquisition. The infrared servo template and the second acquired infrared image are registered, and the second registration deviation is recorded. If the difference between the second registration deviation and the first registration deviation is greater than the set difference, the next infrared servo image acquisition continues. The infrared image obtained from the next acquisition is compared with the infrared servo template until the difference between the current registration deviation and the previous registration deviation is less than the set difference. The gimbal offset is calculated based on the registration deviation of the last acquisition. A gimbal correction control command is generated based on the gimbal offset, and visible light images are acquired based on the corrected gimbal.

[0008] Furthermore, the angles that the gimbal needs to be adjusted include pitch and azimuth, and the positions include horizontal and vertical displacement.

[0009] Furthermore, the generation and acquisition of the infrared servo template includes: According to the requirements of the inspection task, control the pan-tilt unit to rotate to the designated position so that the infrared camera is aimed at the inspection target and the infrared image of the inspection target is obtained. The infrared image of the inspection servo target is processed to extract the feature information of the inspection target and generate a parameter file containing image data, feature information and template information as an infrared servo template.

[0010] Furthermore, registration is performed based on the results of infrared servo image acquisition and the infrared servo template, specifically including: Preprocess the infrared image; Based on the preprocessed infrared image, key feature points are extracted from the infrared image; The key feature points extracted from the infrared image are matched with the feature points in the template image; The matching results are verified, false matches are eliminated, and the final matching feature point pairs are obtained. By combining matching feature point pairs, the transformation model between images is estimated, and the infrared image is registered with the template image.

[0011] A second aspect of the present invention provides an infrared servo system for an inspection robot with dual cameras, comprising: The servo type determination module is used to determine the servo type of the inspection point based on the environment and characteristics of different inspection points. The gimbal calibration module is used to execute corresponding servo processes based on a defined servo mode and generate gimbal calibration control commands, including: If there is no servo, the visible light image will be acquired directly after the pan-tilt unit is positioned according to the preset parameters and the visible light camera parameters are adjusted. If the servo mode is visible light servo, then control the visible light servo to perform visible light image acquisition; If the servo mode is infrared servo or hybrid servo, then infrared servo image acquisition is controlled. Registration is performed based on the infrared servo image acquisition results and the infrared servo template. The position and attitude information of the inspection target are determined according to the registration result. The position and attitude information in the image coordinate system is converted into coordinate information corresponding to the gimbal control, and control commands corresponding to the angle and position that the gimbal needs to adjust are generated. A third aspect of the present invention provides a robot, which includes a processor and a memory. The memory stores a computer program, which is loaded and executed by the processor to implement the above-described infrared servo method for an inspection robot with dual-camera cooperation.

[0012] A fourth aspect of the present invention provides a computer-readable storage medium.

[0013] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the infrared servo method for an inspection robot with dual cameras as described above.

[0014] A fifth aspect of the present invention provides a computer device.

[0015] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the infrared servo method for a dual-camera inspection robot as described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are: This invention implements an innovative dual-camera solution with infrared servo functionality. It determines the servo type based on the servo configuration of different inspection points, executes the corresponding servo process based on the determined servo mode, and generates gimbal correction control commands. This significantly improves inspection efficiency and accuracy, provides flexible servo mode selection to meet the needs of different inspection scenarios, and avoids the problem of low efficiency and insufficient accuracy caused by constantly adjusting the camera's focal length when collecting data with a single camera.

[0017] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0018] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0019] Figure 1 This is a flowchart of the infrared servo method for an inspection robot with dual cameras provided in an embodiment of the present invention; Figure 2 This is the process for performing gimbal calibration using an infrared servo, as provided in this embodiment of the invention. Figure 3 This is a block diagram of the infrared servo system for an inspection robot with dual cameras provided in an embodiment of the present invention; Figure 4 This is a structural block diagram of the robot provided in an embodiment of the present invention. Detailed Implementation

[0020] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0021] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] Figure 1 An exemplary embodiment of the present invention provides an infrared servo method for a substation inspection robot, comprising the following steps: Step 1: Determine the servo type of the inspection point based on its environment and characteristics; In this embodiment, when determining the servo type based on the servo configuration method of different inspection points, servo configuration is performed for different inspection points according to the inspection requirements under different inspection scenarios. The servo modes of the inspection points include no servo, visible light servo, infrared servo, or hybrid servo.

[0024] Among them, the servo-free method uses a fixed position or angle to collect data, which is suitable for points where the target is fixed, the environment is stable, and the accuracy requirements are not high.

[0025] Visible light servoing: Target recognition, localization, and tracking based on visible light camera images. Suitable for points with good lighting and clearly visible target features.

[0026] Infrared servo: Based on infrared thermal imagery, this function performs temperature identification, location, and tracking. It is suitable for detecting abnormal temperatures and for identifying targets whose thermal features are still identifiable under low light, smoke, or obstruction conditions.

[0027] Hybrid servo: Simultaneous or time-division multiplexing of visible light and infrared information for servo control. Suitable for critical points requiring dual verification, complex environments, high-precision positioning, or comprehensive condition assessment.

[0028] Those skilled in the art can select a suitable servo mode and configure it accordingly based on actual needs. Specifically, the configuration information includes the selection of the servo mode and the setting of servo parameters. By adjusting the configuration parameters, different inspection scenarios can be flexibly adapted to, improving the flexibility and adaptability of inspections.

[0029] For example, during power transmission and transformation inspections, if the inspection point is a high-voltage line insulator string, the purpose of the inspection is to detect damage, contamination, and overheating points. For long-distance inspections requiring precise defect location, a hybrid servo system can be configured. Visible light is used to identify physical damage and contamination, while infrared light is used to precisely locate abnormal heating points (corona discharge, degradation). This hybrid approach ensures that physical and thermal defects are simultaneously captured and correlated.

[0030] If the inspection point is a transformer bushing joint, the purpose of the inspection is to detect heat points caused by poor contact; for close-range, critical equipment, an infrared servo can be configured. If the inspection point is the appearance / indicator lights of the substation switchgear, the purpose of the inspection is to check the status of the cabinet door, the instrument readings, and the status of the indicator lights; since the ambient light may change, a visible light servo can be configured. If the inspection point is the foundation of a power transmission tower or a large-scale environment, the purpose of the inspection is to check for foundation settlement, theft of tower materials, and large foreign objects (such as kites) in the passageway; for large-scale scanning, it can be configured to be without a servo.

[0031] To adapt to different servo modes, this invention executes different servo processes based on the servo node parameters configured at the inspection points. When the visible light servo mode is selected, the task execution process uses visible light images for servo control; when the infrared servo mode is selected, the task execution process uses infrared images for servo control; and when the hybrid servo mode is selected, the task execution process utilizes both visible light and infrared images for servo control. By adjusting the task execution process, the smooth execution of inspection tasks can be ensured, and the accuracy and efficiency of inspections can be improved.

[0032] Step 2: Based on the determined servo mode, execute the corresponding servo process to generate the corresponding servo results for the points to be inspected; To ensure the compatibility and stability of the infrared servo function, this invention adjusts the servo service interface. Specifically, it calculates the pan-tilt offset by calling the corresponding coefficient file based on the camera type. When using a visible light camera for servo control, the visible light camera's coefficient file is called; when using an infrared camera for servo control, the infrared camera's coefficient file is called. This adjustment to the servo service interface ensures the accuracy and stability of servo control across different camera types.

[0033] Specifically, the steps include the following: If there is no servo, the pan-tilt unit will be controlled to position according to the preset parameters. After the visible light camera parameters are adjusted, visible light image acquisition will be performed directly. If the servo mode is visible light servo, then control the visible light servo, and after the visible light servo is completed, perform visible light image acquisition.

[0034] It should be noted that the visible light servo process is not the focus of this application; it can be implemented using existing control processes, such as the patent with publication number CN106125744B.

[0035] If the servo mode is infrared servo, the infrared servo is executed. If the infrared focus value read is less than the set value, the infrared servo image acquisition is controlled. Based on the infrared servo image acquisition result and the infrared servo template, the registration is performed. Based on the registration result, the position and attitude information of the inspection target are determined. The position and attitude information in the image coordinate system are converted into the coordinate information corresponding to the PTZ control. The control commands corresponding to the angle (including pitch angle and azimuth angle) and position (including horizontal displacement and vertical displacement) that the PTZ needs to adjust are generated. If the infrared servo fails, and the servo mode is hybrid servo, then the visible light servo will continue. If the detection point is only configured with infrared servo, then image acquisition will proceed directly.

[0036] In this embodiment, the resolution of the infrared camera used for testing is 640*480, and the gimbal angle corresponds to a pixel coefficient of 0.039 degrees / pixel.

[0037] Please refer to Figure 2 To achieve flexible deployment and configuration of the infrared servo function, this invention imports servo templates into the pattern recognition configuration tool. Specifically, debugging personnel can import pre-collected infrared templates into the pattern recognition configuration tool and perform template annotation and configuration information generation. The generated configuration information database can be distributed to the robot body, enabling flexible deployment and configuration of the infrared servo function. Through infrared servo configuration adjustments, inspection needs in different scenarios can be met, improving the flexibility and adaptability of inspections. Taking three infrared servo cycles as an example, the gimbal calibration process is explained.

[0038] The infrared servo focus zoom value is read. If the read infrared focus value is less than the set value, the infrared servo image is acquired for the first time. The infrared servo template is called and the first acquired infrared image is registered, and the first registration deviation is recorded. The infrared servo image is acquired for the second time. The infrared servo template is called and the second acquired infrared image is registered, and the second registration deviation is recorded. If the difference between the second registration deviation and the first registration deviation is greater than the set difference, the infrared servo image is acquired for the third time. The infrared servo template is called and the third acquired infrared image is registered, and the third registration deviation is recorded. It is determined whether the difference between the third registration deviation and the second registration deviation is less than the set difference. Otherwise, the next infrared servo image acquisition continues. The infrared image obtained from the next acquisition is compared with the infrared servo template until the difference between the current registration deviation and the previous registration deviation is less than the set difference. The gimbal offset is calculated based on the registration deviation of the last acquisition. A gimbal correction control command is generated based on the gimbal offset, and visible light images are acquired based on the corrected gimbal. Specifically, the generation and acquisition of the infrared servo template includes: According to the requirements of the inspection task, control the pan-tilt unit to rotate to the designated position so that the infrared camera is aimed at the inspection target and the infrared image of the inspection target is obtained. The infrared image of the patrol servo target is processed to extract the feature information of the patrol target and generate a parameter file containing image data, feature information and template information as an infrared servo template. This invention enables the robot to flexibly deploy and configure infrared servo functions through the generated infrared servo template. By adjusting the infrared servo configuration, it can meet the inspection needs in different scenarios, improving the flexibility and adaptability of inspections.

[0039] Specifically, registration is performed based on the results of infrared servo image acquisition and the infrared servo template, including: In this embodiment, to improve the accuracy and robustness of infrared image matching, an infrared image matching algorithm is designed. This algorithm, based on feature extraction and matching methods, extracts feature points from the infrared image and matches them with feature points in a template image to determine the position and orientation of the inspection target.

[0040] To improve the accuracy and robustness of the algorithm, this invention employs multiple feature extraction and matching methods, combined with preprocessing techniques such as image enhancement and filtering. The infrared image matching algorithm can improve the accuracy and reliability of inspections.

[0041] Specifically, the steps include the following: Preprocessing of infrared images includes noise reduction and contrast enhancement. Based on the preprocessed infrared image, a hotspot-based feature extraction method is used to extract key feature points in the infrared image. The extracted feature points are matched with feature points in the template image to improve the accuracy and robustness of the matching.

[0042] In this embodiment, when matching the extracted feature points with the feature points in the template image, a matching algorithm based on local feature descriptors is used.

[0043] Matching result verification: Verify the matching results, eliminate false matches, and ensure the accuracy of the matching.

[0044] Based on the successfully matched feature point pairs, the transformation model between images is estimated to achieve accurate registration between the infrared image and the template image.

[0045] Figure 3 This application provides an exemplary embodiment of an infrared servo system for an inspection robot with dual cameras, comprising: The servo type determination module 301 is used to determine the servo type of the inspection point based on the environment and characteristics of different inspection points. The gimbal calibration module 302 is used to execute corresponding servo processes based on a determined servo mode and generate gimbal calibration control commands, including: If there is no servo, the visible light image will be acquired directly after the pan-tilt unit is positioned according to the preset parameters and the visible light camera parameters are adjusted. If the servo mode is visible light servo, then control the visible light servo to perform visible light image acquisition; If the servo mode is infrared servo or hybrid servo, then control the infrared servo image acquisition, perform registration based on the infrared servo image acquisition result and infrared servo template, determine the position and attitude information of the inspection target according to the registration result, convert the position and attitude information in the image coordinate system into the coordinate information corresponding to the gimbal control, and generate control commands corresponding to the angle and position that the gimbal needs to adjust.

[0046] It should be noted that the specific implementation of the dual-camera cooperative inspection robot infrared servo system in this embodiment of the invention is similar to the specific implementation of the dual-camera cooperative inspection robot infrared servo method in this embodiment of the invention. Please refer to the description in the method section for details. To reduce redundancy, it will not be repeated here.

[0047] like Figure 4 , Figure 4 This is a structural block diagram of a robot 400 provided in an exemplary embodiment of this application. The robot 400 may include: a lifting component 401, a robotic arm body 402, a drive motor 403, a processor 404, and a memory 405.

[0048] Processor 404 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 404 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array).

[0049] The memory 405 may include one or more computer-readable storage media, which may be non-transitory. The memory 405 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 405 is used to store at least one instruction, which is executed by the processor 405 to implement the dual-camera coordinated inspection robot infrared servo method provided in the method embodiments of this application.

[0050] In some embodiments, the robot 400 may also optionally include a peripheral device interface and at least one peripheral device. The processor 404, memory 405, and peripheral device interface can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface via a bus, signal line, or circuit board. Specifically, the peripheral device may include at least one of the following: radio frequency circuitry, a display screen, a camera assembly, audio circuitry, and a power supply.

[0051] The peripheral interface can be used to connect at least one peripheral device associated with I / O (Input / Output) to the processor 404 and the memory 405.

[0052] Camera components can be used to capture images or videos.

[0053] In some embodiments, the robot 400 further includes one or more sensors. These sensors include, but are not limited to, accelerometers, gyroscopes, pressure sensors, optical sensors, and proximity sensors.

[0054] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on robot 400 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0055] Embodiments of this application also provide a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the dual-camera coordinated inspection robot infrared servo method provided in the above-described method embodiments.

[0056] Embodiments of this application also provide a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device (such as a robot) reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the dual-camera coordinated inspection robot infrared servo methods described in the above embodiments.

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0058] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0062] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An infrared servo method for an inspection robot using dual cameras, characterized in that, Includes the following steps: The servo type of the inspection point is determined based on the environment and characteristics of different inspection points; Based on the determined servo mode, the corresponding servo process is executed to generate gimbal calibration control commands, including: If there is no servo, the visible light image will be acquired directly after the pan-tilt unit is positioned according to the preset parameters and the visible light camera parameters are adjusted. If the servo mode is visible light servo, then control the visible light servo to perform visible light image acquisition; If the servo mode is infrared servo or hybrid servo, then control the infrared servo image acquisition, perform registration based on the infrared servo image acquisition result and infrared servo template, determine the position and attitude information of the inspection target according to the registration result, convert the position and attitude information in the image coordinate system into the coordinate information corresponding to the gimbal control, and generate control commands corresponding to the angle and position that the gimbal needs to adjust. If the servo mode is hybrid servo, and the infrared servo fails, the visible light servo will continue to be executed; If the servo mode is infrared servo, the infrared servo focus zoom value is read. If the read infrared focus value is less than the set value, the infrared servo image is acquired for the first time. The infrared servo template and the first acquired infrared image are registered together, and the first registration deviation is recorded. The infrared servo image is acquired for the second time. The infrared servo template and the second acquired infrared image are registered together, and the second registration deviation is recorded. If the difference between the second registration deviation and the first registration deviation is greater than the set difference, the next infrared servo image acquisition continues. The infrared image obtained from the next acquisition is compared with the infrared servo template until the difference between the current registration deviation and the previous registration deviation is less than the set difference. The gimbal offset is calculated based on the last registration deviation. A gimbal correction control command is generated based on the gimbal offset, and visible light images are acquired based on the corrected gimbal.

2. The infrared servo method for an inspection robot with dual cameras as described in claim 1, characterized in that, The angles that the gimbal needs to be adjusted include pitch and azimuth, and the positions include horizontal and vertical displacement.

3. The infrared servo method for an inspection robot with dual cameras as described in claim 1, characterized in that, The generation and acquisition of the infrared servo template includes: According to the requirements of the inspection task, control the pan-tilt unit to rotate to the designated position so that the infrared camera is aimed at the inspection target and the infrared image of the inspection target is obtained. The infrared image of the inspection servo target is processed to extract the feature information of the inspection target and generate a parameter file containing image data, feature information and template information as an infrared servo template.

4. The infrared servo method for an inspection robot with dual cameras as described in claim 1, characterized in that, Registration is performed based on the results of infrared servo image acquisition and the infrared servo template, specifically including: Preprocess the infrared image; Based on the preprocessed infrared image, key feature points are extracted from the infrared image; The key feature points extracted from the infrared image are matched with the feature points in the template image; The matching results are verified, false matches are eliminated, and the final matching feature point pairs are obtained. By combining matching feature point pairs, the transformation model between images is estimated, and the infrared image is registered with the template image.

5. An infrared servo system for an inspection robot with dual cameras, characterized in that, include: The servo type determination module is used to determine the servo type of the inspection point based on the environment and characteristics of different inspection points. The gimbal calibration module is used to execute corresponding servo processes based on a defined servo mode and generate gimbal calibration control commands, including: If there is no servo, the visible light image will be acquired directly after the pan-tilt unit is positioned according to the preset parameters and the visible light camera parameters are adjusted. If the servo mode is visible light servo, then control the visible light servo to perform visible light image acquisition; If the servo mode is infrared servo or hybrid servo, then control the infrared servo image acquisition, perform registration based on the infrared servo image acquisition result and infrared servo template, determine the position and attitude information of the inspection target according to the registration result, convert the position and attitude information in the image coordinate system into the coordinate information corresponding to the gimbal control, and generate control commands corresponding to the angle and position that the gimbal needs to adjust. If the servo mode is hybrid servo, and the infrared servo fails, the visible light servo will continue to be executed; If the servo mode is infrared servo, the infrared servo focus zoom value is read. If the read infrared focus value is less than the set value, the infrared servo image is acquired for the first time. The infrared servo template and the first acquired infrared image are registered together, and the first registration deviation is recorded. The infrared servo image is acquired for the second time. The infrared servo template and the second acquired infrared image are registered together, and the second registration deviation is recorded. If the difference between the second registration deviation and the first registration deviation is greater than the set difference, the next infrared servo image acquisition continues. The infrared image obtained from the next acquisition is compared with the infrared servo template until the difference between the current registration deviation and the previous registration deviation is less than the set difference. The gimbal offset is calculated based on the last registration deviation. A gimbal correction control command is generated based on the gimbal offset, and visible light images are acquired based on the corrected gimbal.

6. A robot, characterized in that, The robot includes a processor and a memory, the memory storing a computer program, which is loaded and executed by the processor to implement the infrared servo method for a dual-camera coordinated inspection robot as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the infrared servo method for inspection robots with dual-camera cooperation as described in any one of claims 1 to 4.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the infrared servo method for inspection robots with dual-camera cooperation as described in any one of claims 1 to 4.

Images