Instrument detection method, device and storage medium for wheeled inspection robot

Abstract

The present invention discloses an instrument detection method for a wheeled inspection robot, the method comprising: controlling the wheeled inspection robot to start driving according to a preset motion trajectory at a trajectory starting point; arranging a natural light source or an adjustable light source at a preset position in a space where a plurality of instrument walls are located; controlling the wheeled inspection robot to take pictures, and obtaining an instrument wall image at each first point; encoding the instrument position of each instrument wall image, and obtaining an instrument position code of each instrument; identifying the instrument reading of each instrument in each instrument wall image, and obtaining an identification reading of each instrument; comparing each identification reading with a standard reading, and obtaining an identification deviation of each reading identification reading, and outputting an identification reading with an identification deviation greater than a first threshold value and a corresponding instrument position code, so as to realize the detection of the instrument recognition accuracy of the wheeled inspection robot under different illuminations and shooting angles.

Description

Technical Field

[0001] The present invention relates to the technical field of instrument recognition, and in particular to an instrument detection method, device and storage medium of a wheeled inspection robot. Background Art

[0002] At present, the inspection robots used in Guangdong Power Grid include three categories: substation inspection robots, cable tunnel inspection robots, and transmission line inspection robots. Among them, substation inspection robots include outdoor wheeled inspection robots and indoor track-type inspection robots. The former is mainly used for infrared temperature measurement and instrument status reading of outdoor equipment in substations, while the latter is mainly used for status monitoring of indoor switch cabinets. Since the height of wheeled inspection robots is usually below 1m, but the position of the instruments of outdoor equipment in substations to be read is usually higher (the height will be greater than 1.2m), the visible light camera cannot shoot the instruments vertically. For digital instruments, non-vertical pictures can also achieve a high recognition rate through visual recognition algorithms; but for traditional pointer instruments, non-vertical pictures are usually difficult to correctly obtain instrument readings. However, the current requirements for the accuracy of robot instrument recognition in the procurement technical specifications are as follows: excluding factors such as light and shooting angle, the instrument and status recognition rate shall not be less than 90%, the error of correctly identifying the reading data of pointer instruments shall not be greater than ±2%, the accuracy of digital instrument reading data shall reach 100%, and the status accuracy shall reach 100%. The reason for the difference between the procurement requirements and the actual situation is the lack of a unified instrument recognition algorithm accuracy detection method. At present, third-party testing agencies usually only have the ability to exclude factors such as light and shooting angles, that is, general detection methods, and will not provide special detection methods or customized special devices for robots used in power grids. Therefore, robot manufacturers can only provide general detection reports constructed by third parties during the bidding stage. This recognition accuracy that excludes factors such as light and shooting angles has no practical significance for power grid users. Summary of the invention

[0003] The invention provides an instrument detection method for a wheeled inspection robot, so as to realize the detection of the instrument recognition accuracy of the wheeled inspection robot under different illumination intensities and shooting angles.

[0004] The embodiment of the present invention provides an instrument detection method for a wheeled inspection robot, comprising: controlling the wheeled inspection robot to start driving according to a preset motion trajectory at a trajectory starting point, so that the wheeled inspection robot drives around a plurality of instrument walls; a natural light source or an adjustable light source is arranged at a preset position in a space where the plurality of instrument walls are located; during driving, when the wheeled inspection robot drives to a first point, controlling the wheeled inspection robot to take a photo, and obtaining an image of the instrument wall at each first point; the first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments;

[0005] The instrument position of each of the instrument wall images is encoded to obtain the instrument position code of each instrument; the instrument indication of each instrument in each of the instrument wall images is identified to obtain the identification indication of each instrument; each of the identified indications is compared with the standard indication to obtain the identification deviation of each identification indication, and the identification indication whose identification deviation is greater than the first threshold and the corresponding instrument position code are output.

[0006] As a preferred solution, the present invention uses a wheeled inspection robot to shoot and identify the indications of the instruments on the instrument wall according to a preset inspection track, and arranges the light source position so that different positions on the instrument wall have different lighting conditions, calculates the deviation between the identification indication of the wheeled inspection robot and the standard indication, and realizes the accuracy detection of the wheeled inspection robot for instrument recognition under different shooting angles and different illumination conditions. And by encoding each instrument position, the instrument position can be quickly located, and the position and lighting conditions of the instrument with unqualified instrument recognition accuracy can be quickly determined, which improves the detection efficiency of repeated tests.

[0007] As a preferred solution, when the wheeled inspection robot travels to the first point, before controlling the wheeled inspection robot to take photos, the method further includes:

[0008] The starting position of each instrument wall is set as the second position in the driving direction of the wheeled inspection robot; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

[0009] As a preferred solution, the wheeled inspection robot of the present invention travels around several instrument walls. The wheeled inspection robot needs to change its shooting direction during travel to face the instrument wall that needs to be photographed. The present invention sets a starting position for each instrument wall in the travel direction of the wheeled inspection robot, and controls the shooting direction of the wheeled inspection robot to face the corresponding instrument wall when the wheeled inspection robot travels to the starting position of the instrument wall, thereby photographing the instrument wall that needs to be photographed, thereby enabling the wheeled inspection robot to follow a preset inspection trajectory and to change the shooting direction to photograph and identify the indications of the instruments on the instrument wall, thereby realizing the wheeled inspection robot's instrument recognition accuracy detection under different shooting angles and different illumination conditions.

[0010] As a preferred solution, when the wheeled inspection robot travels to the first point, the wheeled inspection robot is controlled to take pictures to obtain the instrument wall image of each first point, specifically:

[0011] When the wheeled inspection robot travels to the first point, the wheeled inspection robot is controlled to take photos to obtain an instrument wall image of each column of instruments on each of the instrument walls.

[0012] As a preferred solution, each instrument wall of the present invention is provided with m rows and n columns of instruments. The wheeled inspection robot photographs and identifies the instrument readings of each column of instruments on each instrument wall, calculates the deviation between the identified readings and the standard readings of each column of instruments, and realizes the instrument recognition accuracy detection of the wheeled inspection robot under different shooting angles and different illumination conditions.

[0013] As a preferred solution, the instrument position of each of the instrument wall images is encoded to obtain the instrument position code of each instrument, specifically:

[0014] According to the relative position of each instrument wall and the wall direction of each instrument wall, the instrument wall number is obtained;

[0015] Obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position;

[0016] The instrument location code of each instrument is constructed according to the instrument wall number where the current instrument is located and the instrument number of the current instrument.

[0017] As a preferred solution, the present invention numbers each instrument wall, the wall direction of each instrument wall, the coordinate position of each instrument and the number of instruments at the same coordinate position to obtain a unique position code for each instrument, which can quickly locate the instrument position, and can quickly determine the position and lighting conditions of instruments that fail to meet the instrument recognition accuracy, thereby improving the detection efficiency of repeated tests.

[0018] As a preferred solution, outputting the identification indication whose identification deviation is greater than the first threshold value and the corresponding instrument position code also includes:

[0019] The illuminance value of the meter position corresponding to the identification indication whose identification deviation is greater than the first threshold is obtained and outputted.

[0020] As a preferred scheme, after calculating the deviation between the identification indication of the wheeled inspection robot and the standard indication for each instrument, the present invention obtains the identification indication with an identification deviation greater than a first threshold value and the position code and light intensity value of the corresponding instrument position, thereby obtaining the instrument position and light intensity value conditions where the wheeled inspection robot's instrument identification accuracy is unqualified, thereby realizing the instrument identification accuracy detection of the wheeled inspection robot under different shooting angles and different light intensity conditions.

[0021] Correspondingly, the present invention also provides an instrument detection device for a wheeled inspection robot, comprising: a wheeled inspection robot control module and a data processing module;

[0022] The wheeled inspection robot control module is used to control the wheeled inspection robot to start driving according to a preset motion trajectory from the starting point of the trajectory, so that the wheeled inspection robot drives around several instrument walls; natural light sources or adjustable light sources are set at preset positions in the space where several of the instrument walls are located; during driving, when the wheeled inspection robot drives to the first point, the wheeled inspection robot is controlled to take pictures to obtain the image of the instrument wall at each first point; the first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments;

[0023] The data processing module is used to encode the instrument position of each instrument wall image to obtain the instrument position code of each instrument; identify the instrument indication of each instrument in each instrument wall image to obtain the identification indication of each instrument; compare each identification indication with the standard indication to obtain the identification deviation of each identification indication, and output the identification indication whose identification deviation is greater than the first threshold and the corresponding instrument position code.

[0024] As a preferred solution, the present invention controls the wheeled inspection robot through a wheeled inspection robot control module to shoot and identify the indications of instruments on the instrument wall according to a preset inspection trajectory, and arranges the light source positions so that different positions of the instrument wall have different lighting conditions; the data processing module calculates the deviation between the identification indications of the wheeled inspection robot and the standard indication, thereby realizing the accuracy detection of the wheeled inspection robot for instrument recognition under different shooting angles and different illumination conditions; and by encoding the position of each instrument, the position of the instrument can be quickly located, and the position and lighting conditions of instruments with unqualified instrument recognition accuracy can be quickly determined, thereby improving the detection efficiency of repeated tests.

[0025] As a preferred solution, the wheeled inspection robot control module includes: a driving track control unit, a direction control unit and a shooting control unit;

[0026] The driving track control unit is used to control the wheeled inspection robot to start driving along a preset motion track from the starting point of the track, so that the wheeled inspection robot drives around a plurality of instrument walls; a natural light source or an adjustable light source is arranged at a preset position of the space where the plurality of instrument walls are located;

[0027] The shooting control unit is used to control the wheeled inspection robot to take pictures when the wheeled inspection robot drives to the first point, so as to obtain the instrument wall image of each column of instruments on each instrument wall;

[0028] The direction control unit is used to set the starting position of each instrument wall in the driving direction of the wheeled inspection robot as the second position; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

[0029] As a preferred solution, the driving track control unit of the present invention controls the wheeled inspection robot to drive around several instrument walls. The wheeled inspection robot is required to change the shooting direction during driving to face the instrument wall that needs to be photographed. The direction control unit sets the starting position of each instrument wall in the driving direction of the wheeled inspection robot. When the wheeled inspection robot drives to the starting position of the instrument wall, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall. The shooting control unit shoots the instrument wall that needs to be photographed, so that the wheeled inspection robot follows the preset inspection track and can shoot and identify the indications of the instruments on the instrument wall by changing the shooting direction, thereby realizing the instrument recognition accuracy detection of the wheeled inspection robot under different shooting angles and different illumination conditions.

[0030] As a preferred solution, the data processing module includes an encoding unit, an identification unit and an output unit;

[0031] The encoding unit is used to obtain the instrument wall number according to the relative position of each instrument wall and the wall direction of each instrument wall; obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position; construct the instrument position code of each instrument according to the instrument wall number where the current instrument is located and the instrument number of the current instrument;

[0032] The recognition unit is used to recognize the instrument reading of each instrument in each instrument wall image to obtain the recognition reading of each instrument; compare each recognition reading with the standard reading to obtain the recognition deviation of each recognition reading;

[0033] The output unit is used to output an identification indication whose identification deviation is greater than a first threshold and a corresponding instrument position code.

[0034] As a preferred embodiment, the encoding unit of the present invention numbers each instrument wall, the wall direction of each instrument wall, the coordinate position of each instrument, and the number of instruments at the same coordinate position to obtain a unique position code for each instrument, which can quickly locate the instrument position and quickly determine the position and lighting conditions of instruments that fail to meet the requirements for instrument recognition accuracy. After the recognition unit calculates the deviation between the recognition indication of each instrument and the standard indication of the wheeled inspection robot, the output unit obtains the recognition indication with a recognition deviation greater than a first threshold value and the position code and illumination value of the corresponding instrument position, thereby obtaining the instrument position and illumination value conditions for instruments that fail to meet the wheeled inspection robot's instrument recognition accuracy, thereby realizing the instrument recognition accuracy detection of the wheeled inspection robot under different shooting angles and different illumination conditions.

[0035] Correspondingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute an instrument detection method for a wheeled inspection robot as described in the content of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of an embodiment of an instrument detection method of a wheeled inspection robot provided by the present invention;

[0037] Figure 2 It is a schematic diagram of a top view of a layout of a space where a wheeled inspection robot is located in a method for detecting an instrument of a wheeled inspection robot provided in an embodiment of the present invention;

[0038] Figure 3 It is a structural schematic diagram of an embodiment of a wall mounting track of an instrument wall of an instrument detection method of a wheeled inspection robot provided in an embodiment of the present invention;

[0039] Figure 4 It is a structural schematic diagram of an embodiment of an instrument detection device of a wheeled inspection robot provided by the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Embodiment 1

[0042] Please refer to Figure 1 , an instrument detection method for a wheeled inspection robot provided by an embodiment of the present invention, comprising steps S101-S104:

[0043] Step S101: Control the wheeled inspection robot to start running along a preset motion trajectory from a trajectory starting point, so that the wheeled inspection robot runs around a number of instrument walls; natural light sources or adjustable light sources are arranged at preset positions in the space where the several instrument walls are located.

[0044] In this embodiment, please refer to Figure 2 , which is a schematic diagram of a top view of an embodiment of the layout of a space where a wheeled inspection robot is located in a method for detecting an instrument of a wheeled inspection robot provided by an embodiment of the present invention, wherein the wheeled inspection robot and four instrument walls (instrument wall A, instrument wall B, instrument wall C and instrument wall D) are placed in a room, and there is a window on the right side of the room for collecting natural light; instrument wall A, instrument wall B, instrument wall C and instrument wall D are placed side by side in the room from left to right, instrument wall A is a single-sided instrument wall, placed against the left wall of the room, instrument walls B, instrument wall C and instrument wall D are double-sided instrument walls, and instrument wall D is placed at a preset distance from the right window;

[0045] A light source track is installed on the indoor roof. Each light source track is located on the mid-vertical line of the center position of each two instrument walls. The adjustable light source is installed on the light source track and the position is adjusted by moving on the track.

[0046] In this embodiment, the adjustable light source between the instrument wall A and the instrument wall B is placed at the bottom of the track; the adjustable light source between the instrument wall B and the instrument wall C is placed at the top of the track; the adjustable light source between the instrument wall C and the instrument wall D is placed at the bottom of the track;

[0047] In this embodiment, the starting point of the trajectory of the wheeled inspection robot is set at the upper left corner of the room, and the end point of the trajectory is set at the lower right corner of the room; after the wheeled inspection robot reaches the starting point of the trajectory, the wheeled inspection robot is controlled to start from the starting point of the trajectory in sequence according to L 1 , L 2 , L 3 , L 4 , L 5 , L 6 and L 7 The vehicle drives along the motion trajectory, and drives around the left wall of instrument wall B, the right wall of instrument wall A, the left wall of instrument wall C, the right wall of instrument wall B, the left wall of instrument wall D, the right wall of instrument wall C and the right wall of instrument wall D in turn, until it reaches the end point.

[0048] In this embodiment, please refer to Figure 3 , which is a structural schematic diagram of an embodiment of a wall mounting track of an instrument wall of an instrument detection method for a wheeled inspection robot provided in an embodiment of the present invention, wherein 6 rows and 6 columns of mounting tracks are arranged on the wall of each instrument wall for placing instruments, namely rows 1-5 and columns af.

[0049] Step S102: During the driving process, when the wheeled inspection robot drives to the first point, the wheeled inspection robot is controlled to take pictures to obtain the image of the instrument wall at each first point. The first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments.

[0050] In this embodiment, when the wheeled inspection robot travels to the first point, before controlling the wheeled inspection robot to take a photo, the method further includes:

[0051] The starting position of each instrument wall is set as the second position in the driving direction of the wheeled inspection robot; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

[0052] In this embodiment, the L of the wheeled inspection robot 1 , L 2 , L 3 , L 4 , L 5 , L 6 and L 7 A second position is set on the motion trajectory respectively. When the wheeled inspection robot travels from the starting point of the trajectory to each second position in sequence, the shooting direction of the wheeled inspection robot is controlled to face the corresponding left wall of instrument wall B, right wall of instrument wall A, left wall of instrument wall C, right wall of instrument wall B, left wall of instrument wall D, right wall of instrument wall C or right wall of instrument wall D in sequence.

[0053] In this embodiment, when the wheeled inspection robot travels to the first point, the wheeled inspection robot is controlled to take pictures to obtain the instrument wall image of each first point, specifically:

[0054] When the wheeled inspection robot travels to the first point, the wheeled inspection robot is controlled to take photos to obtain an instrument wall image of each column of instruments on each of the instrument walls.

[0055] In this embodiment, when the wheeled inspection robot travels to the vertical plane corresponding to the installation track af columns, it takes pictures of each column of instruments on the instrument wall, and takes 6 pictures on each wall of each instrument wall, corresponding to the af columns respectively.

[0056] In this embodiment, the height h of the camera of the wheeled inspection robot from the ground is measured, and the height of the instrument is adjusted on the installation track of the instrument wall according to the value of h, so that there is an angle deviation between it and the camera of the wheeled inspection robot. The maximum angle deviation is: θ = arctan ((Hh) / L);

[0057] Among them, L is the vertical distance between the wheeled inspection robot and the instrument wall, H is the height of the instrument on the instrument wall, and h is the height of the wheeled inspection robot body camera from the ground.

[0058] Step S103: Encode the instrument position of each of the instrument wall images to obtain an instrument position code of each instrument.

[0059] In this embodiment, the instrument position of each of the instrument wall images is encoded to obtain the instrument position code of each instrument, specifically:

[0060] According to the relative position of each instrument wall and the wall direction of each instrument wall, the instrument wall number is obtained;

[0061] Obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position;

[0062] The instrument location code of each instrument is constructed according to the instrument wall number where the current instrument is located and the instrument number of the current instrument.

[0063] In this embodiment, the coding rule of the instrument position code is: instrument wall number + instrument wall direction number + instrument wall horizontal coordinate + instrument wall vertical coordinate + quantity number;

[0064] The instrument walls are numbered A, B, C or D; the wall direction of the left wall of the instrument wall is numbered L; the wall direction of the left wall of the instrument wall is numbered R; the horizontal coordinates of the instrument wall are af; the vertical coordinates of the instrument wall are 0-5. For example, the second instrument in the second row and the c column on the right wall of the instrument wall B is numbered BR2c2.

[0065] Step S104: Identify the instrument reading of each instrument in each of the instrument wall images to obtain the identification reading of each instrument; compare each of the identification readings with the standard reading to obtain the identification deviation of each identification reading, and output the identification reading whose identification deviation is greater than the first threshold and the corresponding instrument position code.

[0066] In this embodiment, outputting the identification indication whose identification deviation is greater than the first threshold value and the corresponding instrument position code also includes:

[0067] The illuminance value of the meter position corresponding to the identification indication whose identification deviation is greater than the first threshold is obtained and outputted.

[0068] In this embodiment, during the detection process, the window is opened to introduce natural light so that the right wall of the instrument wall D is illuminated by natural light. At the same time, the adjustable light source is turned on to record the illuminance x at each instrument position.

[0069] In this embodiment, the correct readings of all instruments with coordinates in AR0a-DR5f are input into the background system to obtain Form 1. The identification readings of all instruments with coordinates in AR0a-DR5f obtained by the wheeled inspection robot are taken as Form 2. Form 2 is compared with Form 1. For digital instruments, the accuracy is required to be 100%; for pointer instruments, a reading deviation of ±2% is allowed.

[0070] In this embodiment, for digital instruments, the instrument position code corresponding to the identification indication with an identification deviation greater than 0 and the illuminance value at the instrument position are obtained and output; for pointer instruments, the instrument position code corresponding to the identification indication with an identification deviation greater than ±2% and the illuminance value at the instrument position are obtained and output.

[0071] For digital instruments, the number of instruments with a recognition deviation not greater than 0 is counted as the number of correctly recognized instruments; for pointer instruments, the number of instruments with a recognition deviation not greater than ±2% is counted as the number of instruments within the deviation range. Calculate the recognition accuracy: η = n / N*100%;

[0072] Where n is the number of instruments identified correctly or the number of instruments within the deviation range, and N is the total number of instruments.

[0073] Implementing the embodiments of the present invention has the following effects:

[0074] The present invention uses a wheeled inspection robot to shoot and identify the indications of instruments on the instrument wall according to a preset inspection track, and arranges the light source position so that different positions of the instrument wall have different lighting conditions, calculates the deviation between the identification indication of the wheeled inspection robot and the standard indication, and realizes the accuracy detection of the wheeled inspection robot on the instrument recognition under different shooting angles and different illumination conditions. In addition, by encoding each instrument position, the instrument position can be quickly located, and the position and lighting conditions of the instrument with unqualified instrument recognition accuracy can be quickly determined, thereby improving the detection efficiency of repeated tests.

[0075] Embodiment 2

[0076] Please refer to Figure 3 , an instrument detection device for a wheeled inspection robot provided by an embodiment of the present invention, comprising: a wheeled inspection robot control module 201 and a data processing module 202;

[0077] The wheeled inspection robot control module 201 is used to control the wheeled inspection robot to start driving according to a preset motion trajectory from the starting point of the trajectory, so that the wheeled inspection robot drives around several instrument walls; natural light sources or adjustable light sources are set at preset positions in the space where several of the instrument walls are located; during driving, when the wheeled inspection robot drives to the first point, the wheeled inspection robot is controlled to take pictures to obtain the image of the instrument wall at each first point; the first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments;

[0078] The data processing module 202 is used to encode the instrument position of each instrument wall image to obtain the instrument position code of each instrument; identify the instrument indication of each instrument in each instrument wall image to obtain the identification indication of each instrument; compare each identification indication with the standard indication to obtain the identification deviation of each identification indication, and output the identification indication whose identification deviation is greater than the first threshold and the corresponding instrument position code.

[0079] The wheeled inspection robot control module 201 includes: a driving track control unit, a direction control unit and a shooting control unit;

[0080] The driving track control unit is used to control the wheeled inspection robot to start driving along a preset motion track from the starting point of the track, so that the wheeled inspection robot drives around a plurality of instrument walls; a natural light source or an adjustable light source is arranged at a preset position of the space where the plurality of instrument walls are located;

[0081] The shooting control unit is used to control the wheeled inspection robot to take pictures when the wheeled inspection robot drives to the first point, so as to obtain the instrument wall image of each column of instruments on each instrument wall;

[0082] The direction control unit is used to set the starting position of each instrument wall in the driving direction of the wheeled inspection robot as the second position; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

[0083] The data processing module 202 includes an encoding unit, a recognition unit and an output unit;

[0084] The encoding unit is used to obtain the instrument wall number according to the relative position of each instrument wall and the wall direction of each instrument wall; obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position; construct the instrument position code of each instrument according to the instrument wall number where the current instrument is located and the instrument number of the current instrument;

[0085] The recognition unit is used to recognize the instrument reading of each instrument in each instrument wall image to obtain the recognition reading of each instrument; compare each recognition reading with the standard reading to obtain the recognition deviation of each recognition reading;

[0086] The output unit is used to output an identification indication whose identification deviation is greater than a first threshold and a corresponding instrument position code.

[0087] The above-mentioned wheeled inspection robot instrument detection device can implement the wheeled inspection robot instrument detection method of the above-mentioned method embodiment. The options in the above-mentioned method embodiment are also applicable to this embodiment and will not be described in detail here. The rest of the contents of the embodiment of this application can refer to the contents of the above-mentioned method embodiment, and will not be repeated in this embodiment.

[0088] Implementing the embodiments of the present invention has the following effects:

[0089] The present invention controls the wheeled inspection robot by a wheeled inspection robot control module to shoot and identify the indications of instruments on the instrument wall according to a preset inspection trajectory, and arranges the positions of light sources so that different positions of the instrument wall have different lighting conditions; the data processing module calculates the deviation between the identification indication of the wheeled inspection robot and the standard indication, so as to realize the accuracy detection of the wheeled inspection robot on the instrument recognition under different shooting angles and different illumination conditions; and by encoding the position of each instrument, the position of the instrument can be quickly located, and the position and lighting conditions of the instrument with unqualified instrument recognition accuracy can be quickly determined, thereby improving the detection efficiency of repeated tests.

[0090] Embodiment 3

[0091] Correspondingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the instrument detection method of the wheeled inspection robot as described in any one of the above embodiments.

[0092] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0093] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0094] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0095] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (SecureDi gita l, SD) card, a flash card (F l ash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0096] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0097] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An instrument detection method for a wheeled inspection robot, characterized in that: include: Controlling the wheeled inspection robot to start traveling along a preset motion trajectory at a trajectory starting point, so that the wheeled inspection robot travels around a plurality of instrument walls; A natural light source or an adjustable light source is arranged at a preset position of the space where the several instrument walls are located; during driving, when the wheeled inspection robot drives to the first point, the wheeled inspection robot is controlled to take pictures to obtain an image of the instrument wall at each first point; The first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments; wherein m and n are positive integers; The instrument position of each of the instrument wall images is encoded to obtain the instrument position code of each instrument; the instrument indication of each instrument in each of the instrument wall images is identified to obtain the identification indication of each instrument; each of the identified indications is compared with the standard indication to obtain the identification deviation of each identification indication, and the identification indication whose identification deviation is greater than the first threshold and the corresponding instrument position code are output.

2. The instrument detection method of a wheeled inspection robot according to claim 1, characterized in that: When the wheeled inspection robot travels to the first point, before controlling the wheeled inspection robot to take photos, the method further includes: The starting position of each instrument wall is set as the second position in the driving direction of the wheeled inspection robot; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

3. The instrument detection method of a wheeled inspection robot according to claim 1, characterized in that: The instrument position of each instrument wall image is encoded to obtain the instrument position code of each instrument, specifically: According to the relative position of each instrument wall and the wall direction of each instrument wall, the instrument wall number is obtained; Obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position; The instrument location code of each instrument is constructed according to the instrument wall number where the current instrument is located and the instrument number of the current instrument.

4. The instrument detection method of a wheeled inspection robot according to claim 1, characterized in that: The output identification deviation is greater than the first threshold identification indication and the corresponding instrument position code, and also includes: The illuminance value of the meter position corresponding to the identification indication whose identification deviation is greater than the first threshold is obtained and outputted.

5. An instrument detection device for a wheeled inspection robot, characterized in that: include: Wheeled inspection robot control module and data processing module; The wheeled inspection robot control module is used to control the wheeled inspection robot to start driving according to a preset motion trajectory from the starting point of the trajectory, so that the wheeled inspection robot drives around several instrument walls; natural light sources or adjustable light sources are set at preset positions in the space where several of the instrument walls are located; during driving, when the wheeled inspection robot drives to the first point, the wheeled inspection robot is controlled to take pictures to obtain the image of the instrument wall at each first point; the first point is the position of each column of instruments on each instrument wall; each of the instrument walls is provided with m rows and n columns of instruments; wherein m and n are positive integers; The data processing module is used to encode the instrument position of each instrument wall image to obtain the instrument position code of each instrument; identify the instrument indication of each instrument in each instrument wall image to obtain the identification indication of each instrument; compare each identification indication with the standard indication to obtain the identification deviation of each identification indication, and output the identification indication whose identification deviation is greater than the first threshold and the corresponding instrument position code.

6. The instrument detection device of a wheeled inspection robot according to claim 5, characterized in that: The wheeled inspection robot control module includes: a travel track control unit, a direction control unit and a shooting control unit; The driving track control unit is used to control the wheeled inspection robot to start driving along a preset motion track from the starting point of the track, so that the wheeled inspection robot drives around a plurality of instrument walls; a natural light source or an adjustable light source is arranged at a preset position of the space where the plurality of instrument walls are located; The shooting control unit is used to control the wheeled inspection robot to take pictures when the wheeled inspection robot drives to the first point, so as to obtain the instrument wall image of each column of instruments on each instrument wall; The direction control unit is used to set the starting position of each instrument wall in the driving direction of the wheeled inspection robot as the second position; when the wheeled inspection robot drives to the second position, the shooting direction of the wheeled inspection robot is controlled to face the corresponding instrument wall.

7. The instrument detection device of a wheeled inspection robot according to claim 5, characterized in that: The data processing module includes an encoding unit, an identification unit and an output unit; The encoding unit is used to obtain the instrument wall number according to the relative position of each instrument wall and the wall direction of each instrument wall; obtain the instrument number according to the coordinate position of each instrument and the number of instruments at the same coordinate position; construct the instrument position code of each instrument according to the instrument wall number where the current instrument is located and the instrument number of the current instrument; The recognition unit is used to recognize the instrument reading of each instrument in each instrument wall image to obtain the recognition reading of each instrument; compare each recognition reading with the standard reading to obtain the recognition deviation of each recognition reading; The output unit is used to output an identification indication whose identification deviation is greater than a first threshold and a corresponding instrument position code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is run, it controls the device where the computer-readable storage medium is located to execute the instrument detection method of a wheeled inspection robot as described in any one of claims 1 to 4.

Images