A computer vision-based unmanned vehicle inspection method, system and unmanned vehicle

Abstract

The present invention relates to an unmanned vehicle inspection method, system and unmanned vehicle based on computer vision. The method includes: identifying the target to be inspected based on the image captured by the camera carried by the unmanned vehicle itself; fitting the line between the coordinates of the target to be inspected as the path function, saving the first coordinate of any point on the path function and the second coordinate of the intersection of the path function and the lower edge of the image; adjusting the movement direction of the unmanned vehicle based on the positional relationship between the line between the current coordinates of the unmanned vehicle and the first coordinate and the third coordinate of the intersection of the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected. The technical solution provided by the present invention identifies the target to be inspected through a target detection algorithm, combines the actual scene conditions, and uses a simple navigation algorithm to determine the action trajectory, and finally guides the unmanned vehicle to stop at a preset position, which can achieve accurate positioning of the unmanned vehicle in different environments and reduce the requirements for hardware.

Description

Technical Field

[0001] The present invention relates to the field of unmanned vehicle navigation, and in particular to an unmanned vehicle inspection method and system based on computer vision, and an unmanned vehicle. Background Art

[0002] With the development of artificial intelligence and 5G technologies, artificial intelligence has made outstanding contributions in many fields. For example, unmanned vehicle technology is needed to repair equipment or check its operating status in some small spaces or dangerous environments. The current technical solutions mainly use laser radar, infrared camera, laser ranging and other equipment technologies to design unmanned vehicle positioning and navigation algorithms, and achieve the effect of accurate fixed-point parking for unmanned vehicles, which can make unmanned vehicles park at the exact location. The algorithms of this type of solution are complex and have high requirements for equipment. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present invention provides an unmanned vehicle inspection method, system and unmanned vehicle based on computer vision.

[0004] According to a first aspect of an embodiment of the present invention, there is provided an unmanned vehicle inspection method based on computer vision, comprising:

[0005] Identify the target to be inspected based on the images collected by the camera carried by the unmanned vehicle;

[0006] Fitting a line between the coordinates of the target to be inspected as a path function, and saving a first coordinate of any point on the path function and a second coordinate of an intersection of the path function and the lower edge of the image;

[0007] The movement direction of the unmanned vehicle is adjusted according to the positional relationship between the third coordinate of the intersection point of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected.

[0008] Further, adjusting the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection point of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected specifically includes:

[0009] When the distance between the third coordinate and the second coordinate is lower than a preset range, adjusting the unmanned vehicle to move leftward;

[0010] When the distance between the third coordinate and the second coordinate exceeds a preset range, adjusting the unmanned vehicle to move rightward;

[0011] When the distance between the third coordinate and the second coordinate is within a preset range, the unmanned vehicle maintains its current forward direction.

[0012] Further, adjusting the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection point of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected, specifically also includes:

[0013] When the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified, the distance between the current position and the target is calculated according to preset parameters;

[0014] Calculate the movement time of the unmanned vehicle according to the preset distance and the current movement speed of the unmanned vehicle;

[0015] The movement of the unmanned vehicle is controlled according to the current movement speed, movement direction and movement time.

[0016] Furthermore, the method further comprises:

[0017] When the target to be inspected is not identified, the unmanned vehicle is controlled to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected.

[0018] According to a second aspect of an embodiment of the present invention, there is provided an unmanned vehicle inspection system based on computer vision, comprising:

[0019] The target recognition module is used to identify the target to be inspected based on the images collected by the camera carried by the unmanned vehicle;

[0020] A path fitting module, used for fitting the connection line between the coordinates of the objects to be inspected as a path function, and saving the first coordinate of any point on the path function and the second coordinate of the intersection of the path function and the lower edge of the image;

[0021] A motion control module is used to adjust the motion direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected.

[0022] Furthermore, the motion control module specifically includes:

[0023] A direction control unit is used to adjust the unmanned vehicle to move to the left when the distance between the third coordinate and the second coordinate is lower than a preset range; to adjust the unmanned vehicle to move to the right when the distance between the third coordinate and the second coordinate exceeds a preset range; and to maintain the current forward direction of the unmanned vehicle when the distance between the third coordinate and the second coordinate is within a preset range.

[0024] Furthermore, the motion control module specifically includes:

[0025] A first calculation unit is used to calculate the distance between the current position and the target according to preset parameters when the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified;

[0026] A second calculation unit, configured to calculate the movement time of the unmanned vehicle according to the distance between the current position and the target and the current movement speed of the unmanned vehicle;

[0027] The first motion control unit is used to control the motion of the unmanned vehicle according to the current motion speed, motion direction and motion time.

[0028] Furthermore, the motion control module specifically includes:

[0029] The second motion control unit is used to control the unmanned vehicle to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected when the target to be inspected is not identified.

[0030] According to a third aspect of an embodiment of the present invention, there is provided an unmanned vehicle, comprising a camera, a processor and a memory, wherein the memory stores an executable code, and when the executable code is executed by the processor, the processor executes the above method.

[0031] Furthermore, the unmanned vehicle also includes a laser radar.

[0032] The technical solution provided by the embodiment of the present invention identifies the target to be inspected through a target detection algorithm, and uses a simple navigation algorithm to determine the action trajectory in combination with the actual scene conditions, and finally guides the unmanned vehicle to stop at a preset position. It can achieve accurate positioning of the unmanned vehicle in different environments and reduce the requirements for hardware.

[0033] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.

[0035] Figure 1 is a flowchart of an unmanned vehicle inspection method based on computer vision according to an exemplary embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of the coordinates of each stop point of the unmanned vehicle;

[0037] Figure 3 This is a schematic diagram of the stop sign position;

[0038] Figure 4 This is an example of the recognition effect when the unmanned vehicle moves towards the first stop sign;

[0039] Figure 5 This is an example of the recognition effect when the unmanned vehicle moves towards the second stop sign;

[0040] Figure 6 It is a flowchart for precise positioning of unmanned vehicles. DETAILED DESCRIPTION

[0041] The preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0042] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0043] It should be understood that although the terms "first", "second", "third", etc. may be used to describe various information in the present invention, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0044] The technical solutions of the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0045] Figure 1 The figure is a flowchart of an unmanned vehicle inspection method based on computer vision according to an exemplary embodiment of the present invention.

[0046] In one embodiment, the main hardware equipment involved in the present invention includes an unmanned vehicle, a lidar, a high-definition camera, and an intelligent algorithm box, wherein the camera is responsible for collecting images on the unmanned vehicle's motion path, the intelligent algorithm box is responsible for identifying features in the image, and the lidar is responsible for analyzing whether there are obstacles in the surrounding environment.

[0047] See also Figure 1 , the method comprising:

[0048] 110. Identify the target to be inspected based on the image collected by the camera carried by the unmanned vehicle;

[0049] Specifically, the target detection model is trained in advance with images of the target to be inspected, and the trained model is deployed in the intelligent algorithm box to ensure that the target to be inspected can be recognized.

[0050] 120. Fitting a line between the coordinates of the target to be inspected as a path function, and saving a first coordinate of any point on the path function and a second coordinate of an intersection of the path function and a lower edge of the image;

[0051] Specifically, the unmanned vehicle can be placed near the target to be inspected in advance, and the camera on the unmanned vehicle can be aimed at the target to be inspected. The parameters of the unmanned vehicle and the camera can be adjusted in combination with the use environment. When the parameters of the camera and the unmanned vehicle are fixed, such as Figure 2 As shown, two virtual points D1 and D2 corresponding to the two inspection targets are set. By fitting the coordinates of these two virtual points, the path function of the current unmanned vehicle in the image can be automatically analyzed, and the coordinate value of one of the virtual points D1 (D) and the intersection of the path function and the lower edge of the image (F) is saved for subsequent reference. The coordinate values ​​are shown in the following formula:

[0052] D1=(x1,y1)

[0053] D2=(x2,y2)

[0054]

[0055] f(x)=kx+b

[0056]

[0057] Where D1 and D2 represent the coordinates of two virtual points, the saved virtual point is represented by D(D1), k and b represent the slope and bias of the path function respectively, f(x) represents the path function, and F represents the intersection of the path function and the lower edge of the image.

[0058] 130. Adjust the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected.

[0059] Specifically, Figure 2 As shown, by fitting the direction function of the current coordinates of the unmanned vehicle (S1) and D, the coordinates of the intersection point T1 of the function and the lower edge of the image are calculated. According to the positional relationship between T1 and F, the deviation direction of the unmanned vehicle can be determined, thereby adjusting the movement direction of the unmanned vehicle.

[0060] In a specific embodiment, the process of adjusting the movement direction of the unmanned vehicle in step 130 specifically includes:

[0061] When the distance between the third coordinate and the second coordinate is lower than a preset range, adjusting the unmanned vehicle to move leftward;

[0062] When the distance between the third coordinate and the second coordinate exceeds a preset range, adjusting the unmanned vehicle to move rightward;

[0063] When the distance between the third coordinate and the second coordinate is within a preset range, the unmanned vehicle maintains its current forward direction.

[0064] Specifically, Figure 2 As shown in the figure, when F is to the right of T1, it means that the unmanned vehicle is moving to the left; otherwise, it is moving to the right, and the direction is adjusted continuously until the error between T1 and F is less than the acceptable range. At this time, it means that the unmanned vehicle is moving in the correct trajectory and will move straight forward until the unmanned vehicle reaches the first inspection target.

[0065] After reaching the first inspection target, if the current unmanned vehicle can see the second inspection target, the unmanned vehicle's direction of movement is adjusted according to the above method until the unmanned vehicle reaches the second inspection target. This process can be repeated to reach all inspection targets and complete the inspection task.

[0066] Optionally, in this embodiment, the method further includes:

[0067] 140. When the target to be inspected is not identified, the unmanned vehicle is controlled to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected.

[0068] Specifically, if the target to be inspected cannot be identified from the camera, the coordinates of the last time the target to be inspected was identified will be used, and the direction of movement of the unmanned vehicle will continue to be adjusted according to the above method of adjusting the direction of movement until the unmanned vehicle reaches the target to be inspected.

[0069] Optionally, in this embodiment, step 130 specifically further includes:

[0070] 1301. When the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified, the distance between the current position and the target is calculated according to preset parameters;

[0071] 1302. Calculate the movement time of the unmanned vehicle according to the preset distance and the current movement speed of the unmanned vehicle;

[0072] 1303. Control the movement of the unmanned vehicle according to the current movement speed, movement direction and movement time.

[0073] Specifically, due to the camera's field of view, when the unmanned vehicle cannot see the target to be inspected, it actually has not yet completely reached the location of the target to be inspected. At this time, the distance to the target to be inspected will be calculated using the pre-set unmanned vehicle parameters and camera parameters, and then the time required to move forward will be calculated based on the vehicle's current speed, so as to accurately reach the target to be inspected.

[0074] Corresponding to the above method embodiment, an embodiment of the present invention provides an unmanned vehicle inspection system based on computer vision, comprising:

[0075] The target recognition module is used to identify the target to be inspected based on the images collected by the camera carried by the unmanned vehicle;

[0076] A path fitting module, used for fitting the connection line between the coordinates of the target to be inspected as a path function, and saving the first coordinate of any point on the path function and the second coordinate of the intersection of the path function and the lower edge of the image;

[0077] A motion control module is used to adjust the motion direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected.

[0078] Optionally, in this embodiment, the motion control module specifically includes:

[0079] A direction control unit is used to adjust the unmanned vehicle to move to the left when the distance between the third coordinate and the second coordinate is lower than a preset range; to adjust the unmanned vehicle to move to the right when the distance between the third coordinate and the second coordinate exceeds a preset range; and to maintain the current forward direction of the unmanned vehicle when the distance between the third coordinate and the second coordinate is within a preset range.

[0080] Optionally, in this embodiment, the motion control module further includes:

[0081] A first calculation unit is used to calculate the distance between the current position and the target according to preset parameters when the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified;

[0082] A second calculation unit, configured to calculate the movement time of the unmanned vehicle according to the distance between the current position and the target and the current movement speed of the unmanned vehicle;

[0083] The first motion control unit is used to control the motion of the unmanned vehicle according to the current motion speed, motion direction and motion time.

[0084] Optionally, in this embodiment, the motion control module further includes:

[0085] The second motion control unit is used to control the unmanned vehicle to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected when the target to be inspected is not identified.

[0086] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0087] An embodiment of the present invention further provides an unmanned vehicle, comprising a camera, a processor and a memory, wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the above method.

[0088] The processor may be a central processing unit (CPU), 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.

[0089] The memory may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. Among them, ROM may store static data or instructions required by the processor or other modules of the computer. The permanent storage may be a readable and writable storage device. The permanent storage may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0090] The memory stores executable codes, and when the executable codes are processed by the processor, the processor can execute part or all of the methods described above.

[0091] In addition, the method according to the present invention may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing part or all of the steps in the above method of the present invention.

[0092] Alternatively, the present invention may also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or computing device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present invention.

[0093] Example:

[0094] like Figure 3 As shown in the figure, a stop sign is placed at each of the two inspection targets as an identification feature. First, the trained model is deployed in the intelligent algorithm box to ensure that the features of the stop sign can be accurately identified. Figure 1-2 As shown. After the preparations are completed, the unmanned vehicle is placed at the starting point. The unmanned vehicle's laser radar and intelligent algorithm box will infer the current environmental obstacles and stop features in the image in real time. When the stop position is set, the unmanned vehicle will drive to the vicinity of the stop point through the obstacle avoidance algorithm so that the unmanned vehicle can recognize the stop sign.

[0095] When the unmanned vehicle recognizes the stop sign, it starts to adjust the angle. The car will choose to stop at the first relatively close stop sign. The specific method is to fit the current first stop point coordinate (S1) and the direction function of D, and calculate the coordinate point T1 of the intersection of the function and the lower edge of the image. When F is to the right of T1, it means that the unmanned vehicle is moving to the left; otherwise, it is moving to the right. The direction is continuously adjusted until the error between T1 and F is less than the acceptable range. At this time, it means that the unmanned vehicle is moving in the correct trajectory and will move straight forward. The example figure is as follows Figure 4 .

[0096] When the unmanned vehicle cannot see the first stop sign, it will calculate the distance to the stop sign using the pre-set unmanned vehicle parameters and camera parameters, and then calculate the time required to move forward based on the current speed of the vehicle, so as to accurately reach the first stop sign.

[0097] like Figure 5As shown, after reaching the first stop sign, if the current angle of the unmanned vehicle can see the second stop sign, the second angle adjustment method will be used; if the position of the second stop sign cannot be seen, the coordinates of the last time to the second stop sign will be used, and the first angle adjustment method will be used to continue adjusting. When the angle correction is completed, it starts to move forward. When the coordinates of the stop point in the picture reach the preset threshold (this threshold is calculated by simulating the on-site environment, when the unmanned vehicle is at the target stop position, the value of the second stop point on the vertical axis of the image), it means that the unmanned vehicle has actually reached the target stop point. Due to the influence of the minimum moving unit of the unmanned vehicle, it may exceed the threshold. When it exceeds the threshold, it can retreat until the difference between the two values ​​is less than the acceptable range, and then stop moving, at which time it reaches the final stop position. The overall unmanned vehicle precise positioning process is as follows. Figure 6 shown.

[0098] The scheme of the present invention has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the specification are not necessarily required by the present invention. In addition, it can be understood that the steps in the method of the embodiment of the present invention can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present invention can be merged, divided and deleted according to actual needs.

[0099] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or a combination of both.

[0100] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A computer vision-based unmanned vehicle inspection method, characterized in that: include: Identify the target to be inspected based on the images collected by the camera carried by the unmanned vehicle; Fitting the connecting line between the coordinates of the target to be inspected as a path function, and saving the first coordinate of any point on the path function and the second coordinate of the intersection of the path function and the lower edge of the image; Adjusting the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection point of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected; Let D1 and D2 represent the coordinates of the virtual points corresponding to the two inspection targets, k and b represent the slope and bias of the path function respectively, and f(x) represents the path function, where: D1=(x1,y1) D2=(x2,y2) f(x)=kx+b.

2. The method according to claim 1, characterized in that The step of adjusting the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected specifically includes: When the distance between the third coordinate and the second coordinate is lower than a preset range, adjusting the unmanned vehicle to move leftward; When the distance between the third coordinate and the second coordinate exceeds a preset range, adjusting the unmanned vehicle to move rightward; When the distance between the third coordinate and the second coordinate is within a preset range, the unmanned vehicle maintains its current forward direction.

3. The method according to claim 2, characterized in that Adjusting the movement direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection point of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate until the unmanned vehicle reaches the identified target to be inspected, specifically also includes: When the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified, the distance between the current position and the target is calculated according to preset parameters; Calculating the movement time of the unmanned vehicle according to the distance between the current position and the target and the current movement speed of the unmanned vehicle; The movement of the unmanned vehicle is controlled according to the current movement speed, movement direction and movement time.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: When the target to be inspected is not identified, the unmanned vehicle is controlled to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected.

5. An unmanned vehicle inspection system based on computer vision, characterized in that: include: The target recognition module is used to identify the target to be inspected based on the images collected by the camera carried by the unmanned vehicle; A path fitting module, used for fitting the connection line between the coordinates of the target to be inspected as a path function, and saving the first coordinate of any point on the path function and the second coordinate of the intersection of the path function and the lower edge of the image; A motion control module, used for adjusting the motion direction of the unmanned vehicle according to the positional relationship between the third coordinate of the intersection of the line between the current coordinate of the unmanned vehicle and the first coordinate and the lower edge of the image and the second coordinate, until the unmanned vehicle reaches the identified target to be inspected; Let D1 and D2 represent the coordinates of the virtual points corresponding to the two inspection targets, k and b represent the slope and bias of the path function respectively, and f(x) represents the path function, where: D1=(x1,y1) D2=(x2,y2) f(x)=kx+b.

6. The system according to claim 5, characterized in that The motion control module specifically includes: A direction control unit is used to adjust the unmanned vehicle to move to the left when the distance between the third coordinate and the second coordinate is lower than a preset range; to adjust the unmanned vehicle to move to the right when the distance between the third coordinate and the second coordinate exceeds a preset range; and to maintain the current forward direction of the unmanned vehicle when the distance between the third coordinate and the second coordinate is within a preset range.

7. The system according to claim 6, characterized in that The motion control module specifically includes: A first calculation unit is used to calculate the distance between the current position and the target according to preset parameters when the unmanned vehicle maintains the current forward direction and moves to a position where the target to be inspected cannot be identified; A second calculation unit, configured to calculate the movement time of the unmanned vehicle according to the distance between the current position and the target and the current movement speed of the unmanned vehicle; The first motion control unit is used to control the motion of the unmanned vehicle according to the current motion speed, motion direction and motion time.

8. The system according to any one of claims 5 to 7, characterized in that: The motion control module specifically includes: The second motion control unit is used to control the unmanned vehicle to move to the target to be inspected according to the pre-saved coordinates of the target to be inspected when the target to be inspected is not identified.

9. An unmanned vehicle, characterized in that: The invention comprises a camera, a processor and a memory, wherein the memory stores executable codes, and when the executable codes are executed by the processor, the processor executes the method according to any one of claims 1 to 4.

10. The unmanned vehicle according to claim 9, characterized in that: Also includes lidar.

Images