A photographing method of a vehicle, a vehicle photographing device, and a vehicle photographing system

Abstract

The application discloses a kind of vehicle's photographing method, vehicle photographing equipment and vehicle photographing system, the vehicle photographing system includes AGV car, mechanical arm and photographing device, one end of the mechanical arm is arranged on the AGV car, the other end is connected with the photographing device, the photographing method of the vehicle includes: obtaining the vehicle model information of vehicle to be inspected;According to the vehicle model information determines the photographing task trajectory corresponding to the vehicle to be inspected, wherein the photographing task trajectory includes the running trajectory of the AGV car moving to the position to be photographed and the photographing parameter of the mechanical arm and the photographing device on the position to be photographed;According to the photographing task trajectory, photographing is carried out.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle detection, in particular to a vehicle photographing method, a vehicle photographing device and a vehicle photographing system. BACKGROUND

[0002] At present, when the appearance of a vehicle is detected and measured, a fixed camera posture and angle are basically adopted to take pictures of the detection part. When the posture and angle of the fixed camera are fixed, the vehicle needs to be in a consistent state under the camera each time to meet the shooting requirements. Therefore, the method of adopting a fixed camera posture and angle cannot be compatible with different vehicle models, especially for engineering vehicles with complex appearance structures, it is difficult to be compatible with all vehicle models. SUMMARY

[0003] Therefore, the embodiments of the present application provide a vehicle photographing method, a vehicle photographing device and a vehicle photographing system to photograph all vehicle models.

[0004] The embodiments of the present application provide a vehicle photographing method applied to a vehicle photographing system, the vehicle photographing system comprising an AGV trolley, a mechanical arm and a photographing device, one end of the mechanical arm is arranged on the AGV trolley, and the other end is connected with the photographing device, the vehicle photographing method comprising: acquiring vehicle model information of a vehicle to be detected; determining a photographing task track corresponding to the vehicle to be detected according to the vehicle model information, wherein the photographing task track comprises a running track of the AGV trolley moving to a position to be photographed and photographing parameters of the mechanical arm and the photographing device at the position to be photographed; and photographing according to the photographing task track.

[0005] The vehicle photographing method provided by the embodiments of the present application can automatically complete photographing of the parts of the vehicle to be photographed, and is compatible with all vehicle models.

[0006] Specifically, the acquisition of the vehicle model information of the vehicle to be detected comprises: after the vehicle to be detected is parked in a detection area, acquiring a first image of a characteristic component in the vehicle to be detected by the photographing device; based on the first image and motion information saved in a preset two-dimensional code task track template, controlling the AGV trolley to move to a two-dimensional code scanning position of the vehicle to be detected; after the AGV trolley moves to the two-dimensional code scanning position of the vehicle to be detected, adjusting photographing parameters of the photographing device according to photographing information saved in the two-dimensional code task track template; and scanning a two-dimensional code of the vehicle to be detected by using the photographing device with the adjusted photographing parameters to obtain the vehicle model information of the vehicle to be detected.

[0007] Specifically, the AGV car is controlled to move to the two-dimensional code scanning position of the vehicle to be inspected based on the first image and motion information saved in a preset two-dimensional code task trajectory template, including: obtaining a standard position of the AGV car relative to the vehicle to be inspected and a first state parameter when the mechanical arm is in an unfolded state in the motion information; after adjusting the mechanical arm to the first state parameter, determining a current position of the AGV car relative to the vehicle to be inspected according to the first image; controlling the AGV car to move to the standard position according to the current position and the standard position; after controlling the AGV car to move to the standard position, obtaining a first running trajectory of the AGV car in the motion information; and controlling the AGV car to move according to the first running trajectory, so that the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected.

[0008] Specifically, after the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected, the photographing parameters of the photographing device are adjusted according to the photographing information saved in the two-dimensional code task trajectory template, including: obtaining a second state parameter when the mechanical arm is in an unfolded state and a first focal length of a zoom camera in the photographing device in the photographing information; after the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected, the mechanical arm is adjusted to the second state parameter, and the zoom camera is adjusted to the first focal length.

[0009] Specifically, the method for constructing the QR code task trajectory template includes: after the first training vehicle is parked in the inspection area, controlling the AGV to move to a standby position; controlling the robotic arm to be in the undeployed state, and acquiring the first state parameters of the robotic arm in the undeployed state; after the AGV moves to the standby position, and while the robotic arm is in the undeployed state, acquiring a second image of the feature components in the first training vehicle through the binocular camera in the imaging device; calculating and determining the standard position of the AGV relative to the inspection vehicle based on the second image; and determining to move the AGV from the standard position. The first running trajectory is taken to the QR code scanning position of the first training vehicle; after the AGV moves to the QR code scanning position, the robotic arm is controlled to be in the unfolded state, and the second state parameters of the robotic arm in the unfolded state and the first focal length of the zoom camera are obtained when the recognition effect of the QR code image meets the preset first requirement; the first state parameters of the robotic arm in the unfolded state, the standard position of the AGV relative to the vehicle to be inspected, the first running trajectory of the AGV, the second state parameters of the robotic arm in the unfolded state, and the first focal length of the zoom camera are saved to obtain the QR code task trajectory template.

[0010] Specifically, determining the photographing task trajectory corresponding to the vehicle to be inspected based on the vehicle model information includes: obtaining the photographing task trajectory corresponding to the vehicle to be inspected based on the vehicle model information and using a preset correspondence between vehicle models and photographing task trajectories.

[0011] Specifically, the method for constructing the correspondence between the vehicle type and the photographing task trajectory comprises: for a second training vehicle belonging to any vehicle type, obtaining a photographing position of the second training vehicle and a photographing order of the photographing position; determining a first photographing position according to the photographing position and the photographing order of the photographing position, and taking the first photographing position as a current photographing position; moving the AGV car to the current photographing position, and taking a second running track of the AGV car moving to the current photographing position as a running track of the AGV car moving to the current photographing position; after the AGV car moves to the current photographing position, obtaining a third state parameter of the mechanical arm and a second focal length of the zoom camera when the shooting effect of the image meets a preset second requirement, and taking the third state parameter of the mechanical arm and the second focal length of the zoom camera as photographing parameters at the current photographing position; determining a next photographing position according to the photographing position and the photographing order of the photographing position until there is no next photographing position, taking the next photographing position as the current photographing position, and returning to the step of moving the AGV car to the current photographing position and recording the second running track of the AGV car moving to the current photographing position; traversing a plurality of second training vehicles belonging to a plurality of vehicle types to obtain the correspondence between the vehicle type and the photographing task trajectory.

[0012] Specifically, the photographing according to the photographing task trajectory comprises: determining a first to-be-photographed position according to the photographing position and the photographing order of the photographing position saved in the photographing task trajectory, and taking the first to-be-photographed position as a current to-be-photographed position; obtaining a second running track of moving to the current to-be-photographed position according to the running track saved in the photographing task trajectory; moving to the current to-be-photographed position according to the second running track; after moving to the current to-be-photographed position, obtaining photographing parameters at the current to-be-photographed position according to the photographing parameters saved in the photographing task trajectory, and photographing according to the photographing parameters; determining a next to-be-photographed position according to the photographing order in the photographing task trajectory, taking the next to-be-photographed position as the current to-be-photographed position, and returning to the step of obtaining the second running track of moving to the current to-be-photographed position according to the running track saved in the photographing task trajectory; after the photographing at the last photographing position in the photographing task trajectory ends, obtaining a third running track of moving to the standard position according to the running track saved in the photographing task trajectory; moving to the standard position according to the third running track.

[0013] Specifically, the moving to the current photographing position according to the second running track comprises: when there is an obstacle in the second running track, performing obstacle avoidance processing; and / or the moving to the standard position according to the third running track comprises: when there is an obstacle in the third running track, performing obstacle avoidance processing.

[0014] The embodiment of the present application further provides an electronic device, including a memory and a processor, which are connected in communication with each other, and the memory stores computer instructions, and the processor executes the computer instructions to perform the photographing method of the vehicle.

[0015] The embodiment of the present application further provides a vehicle photographing system, including an AGV, a mechanical arm, a photographing device and the electronic device, one end of the mechanical arm is arranged on the AGV, the other end is connected with the photographing device, and the AGV, the mechanical arm and the photographing device are connected with the electronic device.

[0016] The embodiment of the present application further provides a vehicle photographing device, including an AGV, a mechanical arm and a photographing device, the first end of the mechanical arm is arranged on the AGV, and the second end is connected with the photographing device, wherein the mechanical arm has at least two postures.

[0017] Specifically, the photographing device includes a camera support, a zoom camera and at least two binocular cameras, the second end of the mechanical arm is connected with the camera support, the zoom camera is arranged at the first end of the camera support, the binocular cameras are arranged at the second end of the camera support, and the at least two binocular cameras are arranged on both sides of the second end. BRIEF DESCRIPTION OF DRAWINGS

[0018] The features and advantages of the present application will be more clearly understood through the following detailed description taken in conjunction with the accompanying drawings, which are given by way of illustration and are not intended to be limiting of the present application, in which:

[0019] Figure 1 It is a structure schematic view of the vehicle photographing device in the embodiment 1 of the present application;

[0020] Figure 2 It is an ultrasonic radar installation position schematic view in the embodiment 1 of the present application;

[0021] Figure 3 It is an ultrasonic radar installation position schematic view in the embodiment 1 of the present application;

[0022] Figure 4 It is a structure schematic view of the photographing device in the embodiment 1 of the present application;

[0023] Figure 5A flowchart of a vehicle photographing method in the embodiment 2 of the present application is shown in the figure;

[0024] Figure 6 A flowchart of a method for constructing a two-dimensional code task trajectory template in the embodiment 2 of the present application is shown in the figure;

[0025] Figure 7 A flowchart of a method for constructing a correspondence between a vehicle model and a detection task in the embodiment 2 of the present application is shown in the figure;

[0026] Figure 8 A flowchart of an obstacle avoidance method in the embodiment 2 of the present application is shown in the figure;

[0027] Figure 9 A structural diagram of a vehicle photographing device in the embodiment 3 of the present application is shown in the figure;

[0028] Figure 10 A structural diagram of an electronic device in the embodiment 4 of the present application is shown in the figure;

[0029] Wherein, 1, AGV trolley; 2, box body; 3, six-degree-of-freedom mechanical arm; 4, photographing device; 2-1, ultrasonic radar; 2-2, ultrasonic radar; 2-3, ultrasonic radar; 2-4, ultrasonic radar; 4-1, binocular camera; 4-2, binocular camera; 4-3, camera support; 4-4, zoom camera. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0031] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0032] Embodiment 1

[0033] The embodiment 1 of the present application provides a vehicle photographing device, as shown in the figure. Figure 1 The vehicle photographing device includes an AGV trolley, a mechanical arm and a photographing device, wherein the first end of the mechanical arm is arranged on the AGV trolley, the second end is connected with the photographing device, and the mechanical arm has at least two postures.

[0034] Specifically, the mechanical arm can be a six-degree-of-freedom mechanical arm or a seven-degree-of-freedom mechanical arm.

[0035] In the vehicle photographing device of the embodiment 1 of the present application, since the AGV trolley is movable, and the mechanical arm has at least two postures, that is, the posture of the mechanical arm is changeable, that is, different postures of the mechanical arm can be adopted when photographing the vehicle, and thus the photographing device also has different postures and angles, so that the vehicle photographing device of the embodiment 1 of the present application can photograph vehicles of different models.

[0036] Specifically, the photographing device comprises a camera support, a zoom camera and at least two binocular cameras, the second end of the mechanical arm is connected with the camera support, the zoom camera is arranged at the first end of the camera support, the binocular cameras are arranged at the second end of the camera support, and the at least two binocular cameras are arranged on both sides of the second end.

[0037] The data obtained by the binocular cameras is three-dimensional data, and the spatial coordinates of the object can be obtained according to the photographing results of the binocular cameras, so that the position of the vehicle photographing device for photographing the two-dimensional code can be determined, so that the two-dimensional code of the vehicle of different models can be accurately photographed, and the model of the vehicle can be further determined according to the two-dimensional code. The zoom camera is used to take photos, and the appearance of the vehicle can be detected based on the photos taken by the zoom camera.

[0038] As shown in Figure 1 , the bottom of the vehicle photographing device is an AGV trolley 1, the upper surface of the AGV trolley 1 is a box body 2, the upper surface of the box body 2 is provided with a six-degree-of-freedom mechanical arm 3, and the distal end of the mechanical arm 3 is connected to the rear of a photographing device 4. The box body 2 is provided with a battery for supplying power to the mechanical arm 3, and the box body 2 can also serve as a support platform for the mechanical arm 3, thereby playing a supporting role.

[0039] As shown in Figure 4 , the photographing device 4 is composed of a binocular camera 4-1, a binocular camera 4-2, a camera support 4-3 and a zoom camera 4-4, the binocular camera 4-1 and the binocular camera 4-2 are arranged on the upper end of the camera support 4-3 in front and back, the photographing direction of the binocular camera 4-1 is towards the front, the photographing direction of the binocular camera 4-2 is towards the rear, and the zoom camera 4-4 is arranged at the lower end of the camera support 4-3, and the photographing direction is towards the front.

[0040] Further, as shown in Figure 2 and Figure 3 , four ultrasonic radars are installed around the box body 2, which are ultrasonic radar 2-1, ultrasonic radar 2-2, ultrasonic radar 2-3 and ultrasonic radar 2-4; thus, based on the detection signals of the ultrasonic radars, obstacle avoidance processing can be performed during the photographing process of the vehicle photographing device.

[0041] The vehicle photographing device of the embodiment 1 of the present application has the following advantages:

[0042] 1. High flexibility, since the AGV trolley and the mechanical arm are movable components, the target can be positioned and photographed from multiple angles, and the detection function is highly expandable;

[0043] 2. Intelligence, the system is equipped with a binocular camera, a zoom camera and an ultrasonic radar, and after the task template is completed, it can realize autonomous and automatic detection and obstacle avoidance;

[0044] 3. Traceable detection, the detection and measurement images are classified and stored according to the vehicle information, and can be traced and reviewed at any time;

[0045] 4. Can replace manual detection, and the long-term use cost is less than the labor cost.

[0046] Embodiment 2

[0047] The embodiment 1 of the present application provides a photographing method of a vehicle. The purpose of photographing the vehicle in the embodiment 1 of the present application is to automatically detect the appearance of the vehicle by analyzing the pictures obtained by photographing.

[0048] The photographing method of the vehicle is applied to the vehicle photographing system, the vehicle photographing system comprises an AGV trolley, a mechanical arm and a photographing device, one end of the mechanical arm is arranged on the AGV trolley, and the other end is connected with the photographing device. That is, the vehicle photographing system comprises a control system and the vehicle photographing device of the embodiment 1 of the present application, for example, the control system can be arranged in the box 2. Figure 1

[0049] Figure 5 The flowchart of the vehicle photographing method in the embodiment 1 of the present application is shown in Figure 5 The vehicle photographing method of the embodiment 1 of the present application comprises the following steps:

[0050] S101: Obtain the vehicle model information of the vehicle to be detected.

[0051] Different vehicle models need to be detected in different parts, so before photographing the vehicle, the vehicle model information of the vehicle to be detected needs to be determined to obtain the position of the vehicle to be detected which needs to be photographed according to the vehicle model information of the vehicle to be detected.

[0052] Specifically, the photographing device comprises a binocular camera and a zoom camera. The data obtained by the binocular camera is three-dimensional data, and the spatial coordinates of the object can be obtained; the zoom camera is used to take pictures.

[0053] ​Specifically, the obtaining of the vehicle model information of the vehicle to be inspected includes the following steps: after the vehicle to be inspected is parked in the inspection area, a first image of a feature component in the vehicle to be inspected is obtained by the photographing device; based on the first image and motion information saved in a preset two-dimensional code task trajectory template, the AGV car is controlled to move to a two-dimensional code scanning position of the vehicle to be inspected; after the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected, the photographing parameters of the photographing device are adjusted according to the photographing information saved in the two-dimensional code task trajectory template; and the two-dimensional code of the vehicle to be inspected is scanned by the photographing device after the photographing parameters are adjusted to obtain the vehicle model information of the vehicle to be inspected.

[0054] More specifically, the controlling of the AGV car to move to the two-dimensional code scanning position of the vehicle to be inspected based on the first image and the motion information saved in the preset two-dimensional code task trajectory template includes the following steps: obtaining a standard position of the AGV car relative to the vehicle to be inspected and a first state parameter when the mechanical arm is in an unfolded state in the motion information; after the mechanical arm is adjusted to the first state parameter, a current position of the AGV car relative to the vehicle to be inspected is determined according to the first image; the AGV car is controlled to move to the standard position according to the current position and the standard position; after the AGV car is controlled to move to the standard position, a first running trajectory of the AGV car in the motion information is obtained; and the AGV car is controlled to move according to the first running trajectory, so that the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected.

[0055] More specifically, the adjusting of the photographing parameters of the photographing device according to the photographing information saved in the two-dimensional code task trajectory template after the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected includes: obtaining a second state parameter when the mechanical arm is in an unfolded state and a first focal length of a zoom camera in the photographing device in the photographing information; after the AGV car moves to the two-dimensional code scanning position of the vehicle to be inspected, the mechanical arm is adjusted to the second state parameter, and the zoom camera is adjusted to the first focal length.

[0056] That is, the two-dimensional code task trajectory template saves the following information: the first state parameter of the mechanical arm in the unexpanded state, the standard position of the AGV trolley relative to the vehicle to be inspected, the first running trajectory of the AGV trolley, the second state parameter of the mechanical arm in the expanded state, and the first focal length of the zoom camera in the photographing device. Among them, the first state parameter of the mechanical arm in the unexpanded state, the standard position of the AGV trolley relative to the vehicle to be inspected, and the first running trajectory of the AGV trolley are motion information; the second state parameter of the mechanical arm in the expanded state and the first focal length of the zoom camera in the photographing device are photographing information.

[0057] Among them, the feature part is a part with obvious features at the position of the vehicle head, such as doors, windows, etc.

[0058] Among them, the construction method of the two-dimensional code task trajectory template includes: after the first training vehicle is parked in the inspection area, the AGV trolley is controlled to move to the standby position; the mechanical arm is controlled to be in the unexpanded state, and the first state parameter of the mechanical arm in the unexpanded state is obtained; after the AGV trolley moves to the standby position, the second image of the feature part in the first training vehicle is obtained by the binocular camera in the photographing device when the mechanical arm is in the unexpanded state; the standard position of the AGV trolley relative to the vehicle to be inspected is calculated and determined according to the second image; the first running trajectory of the AGV trolley from the standard position to the two-dimensional code scanning position of the first training vehicle is determined; after the AGV trolley moves to the two-dimensional code scanning position, the mechanical arm is controlled to be in the expanded state, and the second state parameter of the mechanical arm in the expanded state and the first focal length of the zoom camera when the recognition effect of the two-dimensional code image meets the preset first requirement are obtained; the first state parameter of the mechanical arm in the unexpanded state, the standard position of the AGV trolley relative to the vehicle to be inspected, the first running trajectory of the AGV trolley, the second state parameter of the mechanical arm in the expanded state, and the first focal length of the zoom camera are saved to obtain the two-dimensional code task trajectory template.

[0059] As shown in Figure 6 , Figures 1 to 4 the construction method of the two-dimensional code task trajectory template includes:

[0060] S1: The programmable AGV trolley 1 is parked to the specified parking position, that is, the standby position of the programmable AGV trolley 1 when no vehicle needs to be detected, and the mechanical arm 3 is set to the initial position of the unexpanded state. At this time, the state parameter of the mechanical arm is the first state parameter;

[0061] S2: Since the position of the vehicle relative to the programmable AGV trolley 1 cannot be guaranteed to be completely consistent each time the vehicle stops in the detection area, the relative position of the vehicle and the programmable AGV trolley 1 needs to be positioned. Specifically, after the AGV trolley moves to the standby position, when the mechanical arm is in the unfolded state, the second image of the feature part in the first training vehicle is obtained by the binocular camera in the photographing device, and the standard position of the AGV trolley relative to the vehicle to be inspected is calculated and determined according to the second image. At this time, the standard position of the programmable AGV trolley 1 relative to the vehicle to be inspected and the first state parameter of the mechanical arm 3 are recorded in the two-dimensional code task trajectory template;

[0062] S3: The programmable AGV trolley 1 is operated to the position in front of the vehicle head where the two-dimensional code can be photographed, and the first running trajectory of the programmable AGV trolley 1 is recorded in the two-dimensional code task trajectory template;

[0063] S4: The mechanical arm is unfolded so that the zoom camera 4-4 can clearly identify the vehicle information two-dimensional code, and the second state parameter of the mechanical arm 3 and the first focal length of the zoom camera 4-4 are recorded in the two-dimensional code task trajectory template;

[0064] S5: The mechanical arm 3 is set to the initial position of the unfolded state, i.e. the first state parameter, and the current programmable AGV trolley 1 is moved to the standby position.

[0065] The role of S5 is to return the system to the original position, i.e. to the initialization state, so that the system can automatically walk to the accurate two-dimensional code shooting position by calling the two-dimensional code task trajectory template that has been made, and obtain the vehicle model information.

[0066] This is because the two-dimensional code carrying the vehicle model information is pasted at a fixed position on the vehicle head. For vehicles of different models, although the vehicle models are different, the shapes of the vehicle heads are basically the same. Therefore, based on the two-dimensional code task trajectory template constructed in advance, the vehicle photographing system can photograph the two-dimensional code pasted on the vehicle head, so as to obtain the vehicle model information.

[0067] S102: Determine the photographing task trajectory corresponding to the vehicle to be inspected according to the vehicle model information, wherein the photographing task trajectory includes the running trajectory of the AGV trolley moving to the position to be photographed and the photographing parameters of the mechanical arm and the photographing device at the position to be photographed.

[0068] Specifically, determining the photographing task trajectory corresponding to the vehicle to be inspected according to the vehicle model information includes: according to the vehicle model information, using the preset correspondence between the vehicle model and the photographing task trajectory, obtaining the photographing task trajectory corresponding to the vehicle to be inspected.

[0069] Specifically, the method for constructing the correspondence between the vehicle model and the photography task trajectory includes the following steps: For a second training vehicle belonging to any vehicle model, obtain the photography position of the second training vehicle and the photography order of the photography position; determine the first photography position according to the photography position and the photography order of the photography position, and take the first photography position as the current photography position; move the AGV to the current photography position, and take the third running trajectory of the AGV to the current photography position as the running trajectory of the AGV to the current photography position; after the AGV moves to the current photography position, obtain the image shooting effect that meets the preset... The second requirement is the third deployed state of the robotic arm and the third focal length of the zoom camera, and the third deployed state of the robotic arm and the third focal length of the zoom camera are used as the shooting parameters at the current shooting position; according to the shooting position and the shooting order of the shooting positions, the next shooting position is determined until there is no next shooting position, the next shooting position is used as the current shooting position and the AGV is moved to the current shooting position, and the third running trajectory of the AGV when it moves to the current shooting position is recorded; multiple second training vehicles belonging to multiple vehicle types are traversed to obtain the correspondence between the vehicle type and the shooting task trajectory.

[0070] Specifically, for the same vehicle model, multiple photo-taking task trajectories can be obtained using the above method. Furthermore, by processing these multiple photo-taking task trajectories, such as calculating the average value, a more accurate photo-taking task trajectory for that vehicle model can be obtained.

[0071] For example, such as Figure 7 , Figures 1 to 4 As shown, the method for constructing the correspondence between vehicle models and detection tasks includes:

[0072] S1: Read the standard position of the programmable AGV 1 relative to the vehicle and the first state parameters of the robotic arm 3 from the QR code task trajectory template;

[0073] S2: The robotic arm 3 automatically adjusts to the target-grabbing posture at the front of the vehicle based on the first state parameters;

[0074] S3: The binocular camera 4-1 captures the target features at the front of the vehicle, calculates the current position of the programmable AGV 1 relative to the vehicle (specifically, the feature component in the vehicle), and calculates the position difference between the current position and the standard position based on the standard position of the programmable AGV 1 relative to the vehicle read in step S1. Based on the position difference, the AGV 1 is controlled to move to the standard position, i.e., self-orientation compensation is performed.

[0075] S4: Obtain the first running track of the AGV car saved in the two-dimensional code task track template; control the AGV car to move according to the first running track, so that the AGV car moves to the two-dimensional code scanning position of the vehicle to be detected; after the AGV car moves to the two-dimensional code scanning position of the vehicle to be detected, adjust the mechanical arm to the second state parameter, and adjust the zoom camera to the first focal length; after adjusting the mechanical arm to the second state parameter and the zoom camera to the first focal length, scan the two-dimensional code of the vehicle to be detected by using the zoom camera to obtain the vehicle model information of the vehicle to be detected. Store the vehicle model information as the template name of the detection task track;

[0076] S5: Set the mechanical arm 3 to the initial position of being not unfolded, that is, the state parameter of the mechanical arm at this time is the first state parameter, and record the standard position of the programmable AGV car 1 relative to the vehicle and the first state parameter of the mechanical arm 3 in the detection task track template;

[0077] S6: Move the programmable AGV car 1 to the next detection and measurement target, and obtain the running track of the programmable AGV car 1 moving to the next detection and measurement target to obtain the second running track; adjust the unfolded posture of the mechanical arm 3 and the focal length of the zoom camera 4-4 until the best state of target shooting, and in the best state, obtain the third state parameter of the mechanical arm and the second focal length of the zoom camera, and record the second running track of the programmable AGV car 1, the third state parameter of the mechanical arm 3, and the second focal length information of the zoom camera 4-4 in the detection task track template;

[0078] S7: Repeat step S6 until the second running track of the programmable AGV car 1, the third state parameter of the mechanical arm 3, and the second focal length information of the zoom camera 4-4 of all detection and measurement targets are recorded in the detection task track template;

[0079] S8: Set the mechanical arm 3 to the initial position of being not unfolded, and move the current programmable AGV car 1 to the above standard position, and record the running track of the programmable AGV car 1 in the detection task track template.

[0080] At this point, the detection task track template for a certain vehicle model is completed, and the detection task track template for other vehicle models can be made by referring to the detection task track template making process. In subsequent vehicle detection and measurement, the two-dimensional code task track template and the detection task track template corresponding to the vehicle model can be called to automatically complete the detection and measurement work.

[0081] It should be noted that the steps S1-S4 are a specific process of obtaining the vehicle model information of the vehicle to be detected based on the two-dimensional code task trajectory template constructed in advance. The steps S5-S8 are a construction process of the detection task trajectory template, wherein the detection task trajectory template stores the correspondence between the vehicle model and the photographing task trajectory.

[0082] S103: photographing according to the photographing task trajectory.

[0083] Specifically, the photographing according to the photographing task trajectory includes: determining a first to-be-photographed position according to the photographing position stored in the photographing task trajectory and the photographing order of the photographing position, and taking the first to-be-photographed position as a current to-be-photographed position; obtaining a second running trajectory for moving to the current to-be-photographed position according to the running trajectory stored in the photographing task trajectory; moving to the current to-be-photographed position according to the second running trajectory; after moving to the current to-be-photographed position, obtaining a photographing parameter at the current to-be-photographed position according to the photographing parameter stored in the photographing task trajectory, and photographing according to the photographing parameter; determining a next to-be-photographed position according to the photographing order in the photographing task trajectory, taking the next to-be-photographed position as the current to-be-photographed position, and returning to the step of obtaining the second running trajectory for moving to the current to-be-photographed position according to the running trajectory stored in the photographing task trajectory; after the photographing at the last to-be-photographed position in the photographing task trajectory ends, obtaining a third running trajectory for moving to the standard position according to the running trajectory stored in the photographing task trajectory; and moving to the standard position according to the third running trajectory.

[0084] Further, the moving to the current to-be-photographed position according to the second running trajectory includes: when there is an obstacle in the second running trajectory, performing obstacle avoidance processing.

[0085] Further, the moving to the standard position according to the third running trajectory includes: when there is an obstacle in the third running trajectory, performing obstacle avoidance processing.

[0086] For example, as Figure 8 described above, the embodiment of the present application is a method for automatically avoiding obstacles in an automatic detection and measurement process. In the description of the following method, the ultrasonic radar and the binocular camera are referred to as an alarm feedback system. The method includes:

[0087] S1: starting the obstacle detection function of the alarm feedback system, setting an alarm stop time threshold, and setting an alarm threshold respectively;

[0088] S2: scan the alarm data of the alarm feedback system, judge whether there is an alarm, if there is an alarm, execute step S3, otherwise, set the alarm feedback system to non-alarm state, continue to execute S2;

[0089] S3: judge whether the alarm timing has been started, if yes, execute step S6, otherwise, execute step S4;

[0090] S4: start the alarm timing;

[0091] S5: the device stops walking and sends out an alarm bell;

[0092] S6: judge whether the alarm stop time threshold is exceeded, if yes, execute step S7, otherwise, execute step S2;

[0093] S7: judge whether the alarm is in the forward direction of the task trajectory (for example, the second running trajectory), if yes, execute step S8, otherwise, execute step S12;

[0094] S8: judge whether there is a next task trajectory link node in the detection task trajectory template, if yes, execute step S9, otherwise, clear the alarm, return to the standby position and send the detection result to the terminal;

[0095] S9: link the task trajectory;

[0096] S10: set the detection and measurement system to non-alarm state, clear the alarm timing;

[0097] S11: return to the previous task trajectory node, continue to execute the detection and measurement task, and execute step S2;

[0098] S12: start the device fault alarm, and end the detection.

[0099] Therefore, the embodiment 1 of the present application can automatically complete the photographing of the vehicle parts to be photographed by constructing the corresponding relationship between the two-dimensional code task trajectory template and the vehicle model and the photographing task trajectory, and the photographing method is suitable for all vehicle models.

[0100] Embodiment 2

[0101] Corresponding to the embodiment 1 of the present application, the embodiment 2 of the present application also provides a vehicle photographing device. Figure 9 The structure diagram of the vehicle photographing device in the embodiment 2 of the present application is shown in Figure 9 The vehicle photographing device of the embodiment 2 of the present application includes an acquisition module 20, a photographing task trajectory determination module 21 and a photographing module 22.

[0102] Specifically, the acquisition module 20 is used to acquire the vehicle model information of the vehicle to be detected.

[0103] The photographing task trajectory determination module 21 is configured to determine a photographing task trajectory corresponding to the vehicle to be inspected according to the vehicle type information, wherein the photographing task trajectory comprises a running trajectory of the AGV moving to a position to be photographed and photographing parameters of the mechanical arm and the photographing device at the position to be photographed.

[0104] The photographing module 22 is configured to perform photographing according to the photographing task trajectory.

[0105] Specifically, the photographing device comprises a binocular camera and a zoom camera, and the acquisition module 20 is specifically configured to: after the vehicle to be inspected is parked in the inspection area, acquire a first image of a feature component in the vehicle to be inspected by the photographing device; control the AGV to move to a position to scan a two-dimensional code of the vehicle to be inspected based on the first image and motion information saved in a preset two-dimensional code task trajectory template; after the AGV moves to the position to scan the two-dimensional code of the vehicle to be inspected, adjust photographing parameters of the photographing device according to photographing information saved in the two-dimensional code task trajectory template; and scan the two-dimensional code of the vehicle to be inspected by the photographing device after the photographing parameters are adjusted to obtain vehicle type information of the vehicle to be inspected.

[0106] More specifically, the acquisition module 20 is configured to: acquire a standard position of the AGV relative to the vehicle to be inspected and a first state parameter when the mechanical arm is in an undeployed state in the motion information; after the mechanical arm is adjusted to the first state parameter, determine a current position of the AGV relative to the vehicle to be inspected according to the first image; control the AGV to move to the standard position according to the current position and the standard position; after the AGV is controlled to move to the standard position, acquire a first running trajectory of the AGV in the motion information; and control the AGV to move according to the first running trajectory, so that the AGV moves to the position to scan the two-dimensional code of the vehicle to be inspected.

[0107] More specifically, the acquisition module 20 is configured to: acquire a second state parameter when the mechanical arm is in a deployed state and a first focal length of a zoom camera in the photographing information; after the AGV moves to the position to scan the two-dimensional code of the vehicle to be inspected, adjust the mechanical arm to the second state parameter and adjust the zoom camera to the first focal length.

[0108] Further, the vehicle photographing device further comprises a model construction module 23. The model construction module 23 is specifically configured to: after the first training vehicle is parked in the detection area, control the AGV to move to a standby position; control the mechanical arm to be in the unfolded state, and acquire the first state parameter when the mechanical arm is in the unfolded state; after the AGV moves to the standby position, acquire a second image of a feature part in the first training vehicle through a binocular camera in the photographing device when the mechanical arm is in the unfolded state; determine a standard position of the AGV relative to the vehicle to be detected according to the second image; determine a first running track of the AGV from the standard position to a two-dimensional code scanning position of the first training vehicle; after the AGV moves to the two-dimensional code scanning position, control the mechanical arm to be in an unfolded state, acquire a second state parameter of the mechanical arm when the recognition effect of the two-dimensional code image meets a preset first requirement and a first focal length of the zoom camera; save the first state parameter of the mechanical arm in the unfolded state, the standard position of the AGV relative to the vehicle to be detected, the first running track of the AGV, the second state parameter of the mechanical arm in the unfolded state, and the first focal length of the zoom camera to obtain the two-dimensional code task track template.

[0109] Specifically, the photographing task track determination module 21 is specifically configured to: according to the vehicle type information, utilize a preset correspondence relationship between a vehicle type and a photographing task track to obtain a photographing task track corresponding to the vehicle to be detected.

[0110] Specifically, the model construction module 23 is specifically configured to: for a second training vehicle belonging to any vehicle type, obtain a photographing position of the second training vehicle and a photographing order of the photographing position; determine a first photographing position according to the photographing position and the photographing order of the photographing position, and take the first photographing position as a current photographing position; move the AGV car to the current photographing position and record a second running track of the AGV car when the AGV car moves to the current photographing position; after the AGV car moves to the current photographing position, obtain a third state parameter of the mechanical arm and a second focal length of the zoom camera when a shooting effect of an image meets a preset second requirement, record the third state parameter of the mechanical arm and the second focal length of the zoom camera, and obtain a photographing parameter at the current photographing position; after the photographing parameter at the current photographing position is obtained, determine a next photographing position according to the photographing position and the photographing order of the photographing position, when the next photographing position exists, take the next photographing position as the current photographing position and return to the step of moving the AGV car to the current photographing position and recording the second running track of the AGV car when the AGV car moves to the current photographing position; when the next photographing position does not exist, move the AGV car to a standard position of the AGV car relative to the vehicle to be detected, record a third running track of the AGV car when the AGV car moves to the standard position, and obtain a correspondence between the vehicle type of the second training vehicle and a photographing task track; traverse a plurality of second training vehicles belonging to a plurality of vehicle types, and obtain the correspondence between the vehicle type and the photographing task track.

[0111] Specifically, the photographing module 22 is specifically configured to: determine a first to-be-photographed position according to a photographing position saved in the photographing task track and a photographing order of the photographing position, and take the first to-be-photographed position as a current to-be-photographed position; obtain a second running track of moving to the current to-be-photographed position according to a running track saved in the photographing task track; move to the current to-be-photographed position according to the second running track; after moving to the current to-be-photographed position, obtain a photographing parameter at the current to-be-photographed position according to a photographing parameter saved in the photographing task track, and perform photographing according to the photographing parameter; determine a next to-be-photographed position according to a photographing order in the photographing task track, take the next to-be-photographed position as the current to-be-photographed position, and return to the step of obtaining the second running track of moving to the current to-be-photographed position according to the running track saved in the photographing task track; after photographing at a last photographing position in the photographing task track ends, obtain a third running track of moving to the standard position according to the running track saved in the photographing task track; move to the standard position according to the third running track.

[0112] The specific details of the vehicle photographing device can be referred to Figures 1 to 8 The corresponding descriptions and effects in the embodiments are not repeated here.

[0113] Embodiment 4

[0114] The embodiment of the present application also provides an electronic device, such as Figure 10 As shown, the electronic device can include a processor 31 and a memory 32, wherein the processor 31 and the memory 32 can be connected through a bus or other means.

[0115] Further, the embodiment of the present application also provides a vehicle photographing system, which includes an AGV trolley, a mechanical arm, a photographing device and the above-mentioned electronic device, one end of the mechanical arm is arranged on the AGV trolley, the other end is connected with the photographing device, and the AGV trolley, the mechanical arm and the photographing device are all connected with the electronic device.

[0116] Specifically, the processor 31 can be a central processing unit (CPU). The processor 31 can also be 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. chips, or combinations of the above various chips.

[0117] The memory 32 is a kind of non-transient computer readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules (for example, the acquisition module 20, the photographing task trajectory determination module 21, the photographing module 22 and the model construction module 23 shown in the embodiment of the present application) corresponding to the photographing method of the vehicle in the embodiment of the present application. The processor 31 executes various functions of the processor and data processing by running the non-transient software programs, instructions and modules stored in the memory 32, that is, realizes the photographing method of the vehicle in the above-mentioned method embodiment. Figure 9

[0118] ​The memory 32 can include a program storage area and a data storage area. The program storage area can store an operating system and applications required by at least one function. The data storage area can store data created by the processor 31 and the like. In addition, the memory 32 can include a high-speed random access memory, and can also include a non-transitory memory such as at least one disk storage device, a flash memory device, or other non-transitory solid state memory device. In some embodiments, the memory 32 can optionally include a memory disposed remotely from the processor 31, which can be connected to the processor 31 through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0119] The one or more modules are stored in the memory 32 and, when executed by the processor 31, perform the functions as described above. Figures 1 to 9 The photographing method of the vehicle in the illustrated embodiment.

[0120] The above-described electronic device specific details can be understood in correspondence with the above-described Figures 1 to 10 The above-described electronic device specific details can be understood in correspondence with the above-described

[0121] Those skilled in the art can understand that all or part of the processes in the above-described embodiments can be completed by a computer program instructing related hardware. The program can be stored in a computer readable storage medium, and when executed, can include the processes of the above-described embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), a solid-state drive (SSD), or the like. The storage medium can also include a combination of the above-described types of memories.

[0122] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A photographing method of a vehicle, characterized by, The application is applied to a vehicle photographing system, the vehicle photographing system comprises an AGV trolley, a mechanical arm and a photographing device, one end of the mechanical arm is arranged on the AGV trolley, the other end is connected with the photographing device, and the photographing method of the vehicle comprises: acquiring vehicle model information of a vehicle to be inspected; determining a photographing task track corresponding to the vehicle to be inspected according to the vehicle model information, wherein the photographing task track comprises a running track of the AGV trolley moving to a position to be photographed and photographing parameters of the mechanical arm and the photographing device at the position to be photographed; performing photographing according to the photographing task track; the acquiring of the vehicle model information of the vehicle to be inspected comprises: after the vehicle to be inspected is parked in an inspection area, acquiring a first image of a characteristic component in the vehicle to be inspected by the photographing device; based on the first image and movement information saved in a preset two-dimensional code task track template, controlling the AGV trolley to move to a two-dimensional code scanning position of the vehicle to be inspected; after the AGV trolley moves to the two-dimensional code scanning position of the vehicle to be inspected, adjusting photographing parameters of the photographing device according to photographing information saved in the two-dimensional code task track template; scanning a two-dimensional code of the vehicle to be inspected by using the photographing device after the photographing parameters are adjusted to obtain the vehicle model information of the vehicle to be inspected; the construction method of the two-dimensional code task track template comprises: after a first training vehicle is parked in the inspection area, controlling the AGV trolley to move to a standby position; controlling the mechanical arm to be in an undeployed state and acquiring first state parameters of the mechanical arm in the undeployed state; after the AGV trolley moves to the standby position, acquiring a second image of a characteristic component in the first training vehicle by a binocular camera in the photographing device when the mechanical arm is in the undeployed state; determining a standard position of the AGV trolley relative to the vehicle to be inspected according to the second image; determining a first running track of the AGV trolley moving from the standard position to a two-dimensional code scanning position of the first training vehicle; after the AGV trolley moves to the two-dimensional code scanning position, controlling the mechanical arm to be in a deployed state, acquiring second state parameters of the mechanical arm in the deployed state and a first focal length of a zoom camera when the recognition effect of the two-dimensional code image meets a preset first requirement; saving the first state parameters of the mechanical arm in the undeployed state, the standard position of the AGV trolley relative to the vehicle to be inspected, the first running track of the AGV trolley, the second state parameters of the mechanical arm in the deployed state and the first focal length of the zoom camera to obtain the two-dimensional code task track template.

2. The method of claim 1, wherein, the controlling of the AGV trolley to move to the two-dimensional code scanning position of the vehicle to be inspected based on the first image and the movement information saved in the preset two-dimensional code task track template comprises: acquiring the standard position of the AGV trolley relative to the vehicle to be inspected and the first state parameters of the mechanical arm in the undeployed state in the movement information; After adjusting the mechanical arm to the first state parameter, a current position of the AGV vehicle relative to the vehicle to be inspected is determined according to the first image; According to the current position and the standard position, the AGV vehicle is controlled to move to the standard position; After controlling the AGV vehicle to move to the standard position, a first running track of the AGV vehicle in the motion information is obtained; The AGV vehicle is controlled to move according to the first running track, so that the AGV vehicle moves to a two-dimensional code scanning position of the vehicle to be inspected.

3. The method of claim 2, wherein, After the AGV vehicle moves to the two-dimensional code scanning position of the vehicle to be inspected, the photographing parameters of the photographing device are adjusted according to the photographing information saved in the two-dimensional code task track template, which comprises: A second state parameter when the mechanical arm is in an unfolded state and a first focal length of a zoom camera in the photographing device in the photographing information are obtained; After the AGV vehicle moves to the two-dimensional code scanning position of the vehicle to be inspected, the mechanical arm is adjusted to the second state parameter, and the zoom camera is adjusted to the first focal length.

4. The method according to any one of claims 1 to 3, characterized in that, According to the vehicle type information, a preset correspondence between vehicle types and photographing task tracks is used to obtain the photographing task track corresponding to the vehicle to be inspected.

5. The method of claim 4, wherein, The method for constructing the correspondence between vehicle types and photographing task tracks comprises: For a second training vehicle belonging to any vehicle type, a photographing position of the second training vehicle and a photographing order of the photographing position are obtained; A first photographing position is determined according to the photographing position and the photographing order of the photographing position, and the first photographing position is taken as a current photographing position; The AGV vehicle is moved to the current photographing position, and a second running track when the AGV vehicle moves to the current photographing position is recorded; After the AGV vehicle moves to the current photographing position, a third state parameter of the mechanical arm and a second focal length of the zoom camera when a shooting effect of an image meets a preset second requirement are obtained, the third state parameter of the mechanical arm and the second focal length of the zoom camera are recorded, and photographing parameters at the current photographing position are obtained; After the photographing parameters at the current photographing position are obtained, a next photographing position is determined according to the photographing position and the photographing order of the photographing position, when the next photographing position exists, the next photographing position is taken as the current photographing position, and the step of moving the AGV vehicle to the current photographing position and recording the second running track when the AGV vehicle moves to the current photographing position is returned; when the next photographing position does not exist, the AGV vehicle is moved to a standard position of the AGV vehicle relative to the vehicle to be inspected, and a third running track when the AGV vehicle moves to the standard position is recorded, and a correspondence between the vehicle type and the photographing task track of the second training vehicle is obtained; The second training vehicle belongs to a plurality of vehicle models, and a corresponding relationship between the vehicle models and the photographing task trajectory is obtained.

6. The method of claim 5, wherein, The photographing according to the photographing task trajectory comprises: A first to-be-photographed position is determined according to the photographing position saved in the photographing task trajectory and the photographing order of the photographing position, and the first to-be-photographed position is taken as a current to-be-photographed position; A second running trajectory for moving to the current to-be-photographed position is obtained according to the running trajectory saved in the photographing task trajectory; The second running trajectory is used to move to the current to-be-photographed position; After moving to the current to-be-photographed position, a photographing parameter at the current to-be-photographed position is obtained according to the photographing parameter saved in the photographing task trajectory, and photographing is performed according to the photographing parameter; A next to-be-photographed position is determined according to the photographing order in the photographing task trajectory, the next to-be-photographed position is taken as the current to-be-photographed position, and the step of obtaining the second running trajectory for moving to the current to-be-photographed position according to the running trajectory saved in the photographing task trajectory is returned; After the photographing at the last photographing position in the photographing task trajectory ends, a third running trajectory for moving to the standard position is obtained according to the running trajectory saved in the photographing task trajectory; The third running trajectory is used to move to the standard position.

7. The method of claim 6, wherein, The moving to the current to-be-photographed position according to the second running trajectory comprises: When there is an obstacle in the second running trajectory, obstacle avoidance processing is performed; And / or, the moving to the standard position according to the third running trajectory comprises: When there is an obstacle in the third running trajectory, obstacle avoidance processing is performed.

8. An electronic device, comprising: It comprises: A memory and a processor, which are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the photographing method of the vehicle in any one of claims 1-7.

9. A vehicle photographing system, characterized by comprising: It comprises an AGV, a mechanical arm, a photographing device and the electronic device in claim 8, one end of the mechanical arm is arranged on the AGV, the other end is connected with the photographing device, and the AGV, the mechanical arm and the photographing device are connected with the electronic device.

10. The vehicle photographing system of claim 9, wherein, The mechanical arm has at least two postures; The photographing device comprises a camera support, a zoom camera and at least two binocular cameras, the other end of the mechanical arm is connected with the camera support, the zoom camera is arranged at a first end of the camera support, the binocular cameras are arranged at a second end of the camera support, and the at least two binocular cameras are arranged on both sides of the second end.

Images