Automobile armrest box processing quality automatic detection method based on computer vision

Abstract

The invention relates to the field of intelligent manufacturing, and provides an automobile armrest box processing quality automatic detection method based on computer vision, the automobile armrest box comprises a box body and a box cover, the box body and the box cover are rotatably connected through a damping structure, the method comprises the following steps: based on a first preset pressure, controlling a cylinder to open the box cover, shooting a first opening image in the opening process of the box cover; based on second preset pressure, a mechanical arm is controlled to close the box cover, and a first closing image in the box cover closing process is shot; the step S1 and the step S2 are repeatedly executed to obtain a target opening image and a target closing image; and determining a test result of the armrest box according to the first opening image, the first closing image, the target opening image and the target closing image.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing, and in particular to a method for automatically detecting the processing quality of an automobile armrest box based on computer vision. Background Art

[0002] The armrest box is a car interior component used to provide support for the driver's elbows while driving; the armrest box can also be used to install other car parts, such as throttle knobs, rocker switches, etc.; in addition, the armrest box can also provide storage, power interface and other functions, and has a high frequency of use. Therefore, the quality inspection of the armrest box is particularly important. For example, in order to improve the user experience, the cover of the armrest box usually has a damper to reduce the noise level of opening and closing and improve the smoothness of opening and closing. Therefore, it is necessary to test the normal use of the damper; in order to ensure that the appearance of the armrest box meets the requirements, the wear resistance of the armrest box also needs to be tested. However, the existing armrest box quality inspection is usually achieved through manual visual observation, which is highly subjective, involves many uncontrollable factors, and is time-consuming, resulting in affected production efficiency. Summary of the Invention

[0003] The main purpose of this application is to provide a method for automatic detection of the processing quality of automobile armrest boxes based on computer vision, aiming to improve the efficiency and objectivity of detection of the quality of armrest boxes.

[0004] In a first aspect, the present application provides a method for automatically detecting the processing quality of an automobile armrest box based on computer vision, wherein the automobile armrest box includes a box body and a box cover, and the box body and the box cover are rotationally connected via a damping structure. The method comprises the following steps:

[0005] Step S1, based on a first preset pressure, controlling the cylinder to open the box cover, and capturing a first opening image of the box cover during the opening process;

[0006] Step S2, controlling the robotic arm to close the box cover based on a second preset pressure, and capturing a first closing image of the box cover during the closing process;

[0007] Step S3, repeatedly executing step S1 and step S2 to obtain a target open image and a target closed image;

[0008] Step S4: determining a test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image.

[0009] In some embodiments, the step S1 of controlling the cylinder to open the box cover based on a first preset pressure and capturing a first opening image of the box cover during the opening process includes:

[0010] Analyzing the first opening image to determine an opening angle of the lid in the first opening image and an opening time taken to reach the opening angle;

[0011] When the opening angle and the first opening time do not meet a first preset condition, the armrest box test result is determined to be abnormal, wherein the first preset condition includes: an opening angle range and an opening time range.

[0012] In some embodiments, the target opening image includes at least one of the following: a second opening image and a third opening image; the target closing image includes at least one of the following: a second closing image and a third closing image; and step S3, repeating step S1 and step S2 to obtain a target opening image and a target closing image, includes at least one of the following:

[0013] Step 31, repeating step S1 and step S2 for a preset number of times, and using the image obtained by the last execution of step S1 and step S2 as the second opening image and the second closing image;

[0014] Step S32: Repeat step S1 and step S2, and continue to obtain the images obtained by executing step S1 and step S2 as the third opening image and the third closing image, until the third opening image and the third closing image do not meet the second preset condition, and obtain the number of executions of step S1 and step S2.

[0015] In some embodiments, step S31 further includes:

[0016] Calculating a velocity deviation index of the box lid according to the first opening image, the second opening image, the first closing image, and the second closing image;

[0017] When the speed deviation index is greater than a first preset threshold, the armrest box test result is determined to be abnormal.

[0018] In some embodiments, when the speed deviation index is greater than a first preset threshold, determining that the armrest box test result is abnormal further includes:

[0019] If the speed deviation index is greater than a second preset threshold, executing step S32 to obtain the execution count, wherein the second preset threshold is less than the first preset threshold;

[0020] When the execution times are less than the preset times, the armrest box test result is determined to be abnormal.

[0021] In some embodiments, calculating the speed deviation index of the lid according to the first opening image, the second opening image, the first closing image, and the second closing image includes:

[0022] Extracting a first standard speed, a second standard speed, and a third standard speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the first opening image and the first closing image;

[0023] Extracting a first current speed, a second current speed, and a third current speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the second opening image and the second closing image;

[0024] The velocity deviation index is calculated based on the following formula:

[0025]

[0026] Among them, d i =|v i -v′ i | / v i , v′ i Indicates the first standard speed, the second standard speed, and the third standard speed, v i represents the first current speed, the second current speed, and the third current speed; k is the sensitivity coefficient, k≥2; Σ represents the covariance matrix, d=[d1, d2, d3];

[0027] In some embodiments, the robotic arm is provided with an abrasive assembly; and step S2, based on a second preset pressure, controlling the robotic arm to close the box cover and capturing a first closing image of the box cover during closing, further comprises:

[0028] Based on a second preset pressure, controlling the robotic arm to close the box cover, and capturing a box cover closing image after the box cover is closed;

[0029] Perform a wear degree analysis on the box cover closing image, and determine the test result of the armrest box according to the wear degree obtained from the wear degree analysis.

[0030] In some embodiments, performing wear analysis on the lid closing image and determining the armrest box test result according to the wear degree obtained from the wear analysis includes:

[0031] When step S2 is performed a preset number of times, performing wear analysis on the box lid closing image obtained by the last execution of step S2; or

[0032] When the armrest box reaches a preset wear degree, the number of executions of step S2 is obtained, and the wear degree is determined according to the number of executions.

[0033] In some embodiments, the step S4 of determining the test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image further includes:

[0034] The audio in the target opening image and the target closing image is analyzed to obtain a test result of the armrest box.

[0035] In some embodiments, analyzing the audio in the target opening image and the target closing image to obtain the test result of the armrest box includes:

[0036] Novelty detection is performed on target audio information corresponding to the target open image and the target closed image to determine whether abnormal noise exists in the target audio information.

[0037] The present application provides a method for automatically detecting the processing quality of an automobile armrest box based on computer vision. The present application comprises the following steps: step S1, based on a first preset pressure, controlling a cylinder to open the box cover, and capturing a first opening image during the box cover opening process; step S2, based on a second preset pressure, controlling a robotic arm to close the box cover, and capturing a first closing image during the box cover closing process; step S3, repeatedly executing steps S1 and S2 to obtain a target opening image and a target closing image; and step S4, determining the test result of the armrest box based on the first opening image, the first closing image, the target opening image, and the target closing image. Testing the armrest box using images of the box cover opening and closing improves test efficiency and objectivity; and by repeatedly opening and closing the box cover, automated testing of the durability of the box cover's damping capacity is achieved, reducing the labor and time costs required for testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0039] Figure 1 A flowchart of a method for automatically detecting the processing quality of an automobile armrest box based on computer vision provided in one embodiment of the present application;

[0040] Figure 2A schematic diagram of a scenario for a method for automatically detecting the processing quality of an automobile armrest box based on computer vision provided in one embodiment of the present application;

[0041] Figure 3 A schematic block diagram of a computer vision-based automatic inspection device for the processing quality of an automobile armrest box provided in one embodiment of the present application;

[0042] Figure 4 This is a schematic block diagram of the structure of a computer device involved in one embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0045] An embodiment of the present application provides a method for automatically detecting the processing quality of an automobile armrest box based on computer vision.

[0046] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0047] Please refer to Figure 1 , Figure 1 A flow chart of a method for automatically detecting the processing quality of an automobile armrest box based on computer vision provided in an embodiment of the present application. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision can be used in a terminal or a server. The terminal can be an electronic device such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device; the server can be an independent server, a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0048] like Figure 1As shown, the method for automatically detecting the processing quality of an automobile armrest box based on computer vision includes steps S1 to S4.

[0049] Step S1, based on a first preset pressure, controlling the cylinder to open the box cover, and capturing a first opening image of the box cover during the opening process;

[0050] Step S2, controlling the robotic arm to close the box cover based on a second preset pressure, and capturing a first closing image of the box cover during the closing process;

[0051] Step S3, repeatedly executing step S1 and step S2 to obtain a target open image and a target closed image;

[0052] Step S4: Determine the test result of the armrest box according to the first opening image, the first closing image, the target opening image and the target closing image.

[0053] For example, a vehicle armrest box includes a box body and a cover, which are rotationally connected via a damping structure, such as a hydraulic damper, a pneumatic damper, a magnetorheological damper, a spring damper, or a friction plate damper. The damping structure ensures smooth, seamless, and silent opening and closing of the cover, ensuring that the angular velocity of the cover changes in a specific pattern when the cover is opened.

[0054] However, the damping structure is easily damaged due to repeated use, for example, due to leakage, wear, loosening, etc. Therefore, testing the durability of the damping structure has become an urgent problem that needs to be solved. The embodiment of the present application uses a cylinder and a robotic arm to automatically open and close the armrest box lid, and captures images of the lid opening and closing process. The captured images are analyzed using computer vision technology, thereby improving the automation level of armrest box testing and reducing the time and labor costs of armrest box quality inspection.

[0055] For example, an armrest box may be randomly selected from each batch of armrest boxes as a test sample, and the automatic detection method for processing quality of an automobile armrest box based on computer vision provided in an embodiment of the present application may be executed on the test sample.

[0056] For example, the first opening image, the first closing image, the target opening image, and the target closing image are captured from the side of the lid to intuitively demonstrate the opening angle and angular velocity of the lid. Compared to using an angular velocity sensor, these images can record motion information in a non-contact manner, avoiding any impact on the lid's natural movement. This also enables multi-dimensional analysis such as slow-motion playback.

[0057] In some embodiments, the step S1 of controlling the cylinder to open the box cover based on a first preset pressure and capturing a first opening image of the box cover during the opening process includes:

[0058] Analyzing the first opening image to determine an opening angle of the lid in the first opening image and an opening time taken to reach the opening angle;

[0059] When the opening angle and the first opening time do not meet a first preset condition, the armrest box test result is determined to be abnormal, wherein the first preset condition includes: an opening angle range and an opening time range.

[0060] Illustratively, in an embodiment of the present application, the first opening image and the first closing image obtained when the armrest box is opened and closed for the first time are used as the basis for subsequent analysis of the target opening image and the target closing image, for example, the target opening image is compared with the first opening image, and the target closing image is compared with the first closing image. Therefore, the first opening image and the first closing image themselves must first meet the requirements, and it is necessary to ensure that the opening and closing of the box lid are normal when steps S1 and S2 are executed for the first time.

[0061] For example, during normal use of the armrest box, the box cover will rotate to the maximum angle after being opened and hover at the maximum angle position. In the embodiment of the present application, the box cover is opened by a cylinder with a first preset pressure. The first preset pressure can ensure that the box cover is opened to the maximum allowable angle after a certain period of rotation, that is, it reaches a certain opening angle after a certain opening time. Therefore, the opening time needs to meet the preset opening time range, and the opening angle needs to meet the preset opening angle range. If the opening time is too long or too short, or the opening angle is too large or too small, it means that there is an abnormality in the armrest box cover itself, and an abnormality prompt is directly output in this case.

[0062] Exemplarily, the opening angle represents the maximum angle reached by the lid in the first opening image.

[0063] In some embodiments, the target opening image includes at least one of the following: a second opening image and a third opening image; the target closing image includes at least one of the following: a second closing image and a third closing image; and step S3, repeating step S1 and step S2 to obtain a target opening image and a target closing image, includes at least one of the following:

[0064] Step 31, repeating step S1 and step S2 for a preset number of times, and using the image obtained by the last execution of step S1 and step S2 as the second opening image and the second closing image;

[0065] Step S32: Repeat step S1 and step S2, and continue to obtain the images obtained by executing step S1 and step S2 as the third opening image and the third closing image, until the third opening image and the third closing image do not meet the second preset condition, and obtain the number of executions of step S1 and step S2.

[0066] For example, in an embodiment of the present application, the operation of opening and closing the box lid may be repeated a certain number of times according to the test requirements, such as 10 times, 100 times, 1000 times, etc., which is not limited here; and after executing step S1 and step S2 for the preset number of times, an image of the last execution of step S1 and step S2 is obtained to determine whether there is any abnormality in the opening and closing of the box lid after executing step S1 and step S2 for the preset number of times.

[0067] For example, in an embodiment of the present application, the operation of opening and closing the box lid may be repeated until an abnormality occurs in the opening and closing of the box lid, the number of times the box lid is opened and closed is obtained, and whether the number of times the box lid is opened and closed meets the requirements of relevant standards is determined.

[0068] In some embodiments, step S31 further includes:

[0069] Calculating a velocity deviation index of the box lid according to the first opening image, the second opening image, the first closing image, and the second closing image;

[0070] When the speed deviation index is greater than a first preset threshold, the armrest box test result is determined to be abnormal.

[0071] Exemplarily, whether the opening and closing of the trunk lid is abnormal is determined based on the angular velocity of the trunk lid during the opening and closing process. For example, the angular velocities of the trunk lid in the first and second opening images are compared, and the angular velocities of the trunk lid in the first and second closing images are compared. The speed deviation index between the first and Nth opening and closing of the trunk lid is calculated. If the speed deviation index is greater than a first preset threshold, indicating a significant deviation in the angular velocity of the Nth opening and closing relative to the first opening and closing, the armrest box test result is abnormal. Otherwise, the armrest box test result is normal. It will be understood that N is the value of a preset number of times.

[0072] In some embodiments, when the speed deviation index is greater than a first preset threshold, determining that the armrest box test result is abnormal further includes:

[0073] If the speed deviation index is greater than a second preset threshold, executing step S32 to obtain the execution count, wherein the second preset threshold is less than the first preset threshold;

[0074] When the execution times are less than the preset times, the armrest box test result is determined to be abnormal.

[0075] For example, in order to ensure that the service life of the armrest box meets the requirements, even when the speed offset index is less than or equal to the first preset threshold, if the speed offset index is greater than the second preset threshold, the armrest box still needs to be repeatedly opened and closed to obtain the maximum number of opening and closing times of the armrest box, that is, the number of executions in step S32.

[0076] For example, if the obtained execution times are less than the preset times, it means that the service life of the armrest box cannot meet the requirements, and the armrest box test result is abnormal.

[0077] In some embodiments, calculating the speed deviation index of the lid according to the first opening image, the second opening image, the first closing image, and the second closing image includes:

[0078] Extracting a first standard speed, a second standard speed, and a third standard speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the first opening image and the first closing image;

[0079] Extracting a first current speed, a second current speed, and a third current speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the second opening image and the second closing image;

[0080] The velocity deviation index is calculated based on the following formula:

[0081]

[0082] Among them, d i =|v i -v′ i | / v i , v′ i Indicates the first standard speed, the second standard speed, and the third standard speed, v i represents the first current speed, the second current speed, and the third current speed; k is the sensitivity coefficient, k≥2; Σ represents the covariance matrix, d=[d1, d2, d3];

[0083] For example, the angular velocity of the lid's opening and closing can be determined from the image using methods such as optical flow, inter-frame differencing, and background subtraction. The angular velocity of the lid during the first opening and closing is then compared with the angular velocity during the Nth opening and closing to obtain a velocity offset index. Specifically, multiple key points are set along the lid's opening and closing path, for example, three key points are set at a position near the closed state, a position near the fully open state, and a position midway between the two. The angular velocity of the lid at these three positions is then calculated.

[0084] For example, these key points may be marked with prominent colors in the background of the armrest image, such as on the membrane for the upper armrest.

[0085] Please refer to Figure 2 , Figure 2 A schematic diagram of a scenario for a method for automatically detecting the processing quality of an automobile armrest box based on computer vision provided in one embodiment of the present application.

[0086] like Figure 2 As shown, the dashed line represents the outline of the fetal membrane, and the dotted line represents the motion trajectory of the lid end. Markers can be placed at locations corresponding to key points on the fetal membrane, and the instantaneous velocity of the lid at the key point can be calculated based on the duration that the lid covers the mark. The number of key points can be three or more, and is not limited here.

[0087] Exemplarily, the angular velocities of the box lid when it passes through the first key point, the second key point, and the third key point in the first open image and the first closed image are calculated as the first standard speed v′1, the second standard speed v′2, and the third standard speed v′3, respectively; or the first standard speed is calculated based on the average value of the speed of the box lid passing through the first key point in the first open image and the first closed image, and so on, which are not repeated here; similarly, the corresponding first current speed v1, second current speed v2, and third current speed v3 in the second open image and the second closed image are calculated.

[0088] For example, by d i =|v i -v′ i | / v i The relative deviation of each current speed is calculated to eliminate the influence of dimension, where i = 1, 2, 3, ...; an exponential function is applied to the relative deviation to amplify the significant deviation, where the sensitivity coefficient k is used to control the degree of deviation amplification, for example, it can be 2; weights are assigned based on the size of the deviation so that the large deviation variable dominates the result, and the covariance matrix Σ between variables is introduced (the unit matrix can be used) to correct the independence hypothesis deviation. If the variables are positively correlated, the actual impact is less than the independence hypothesis, and this factor compresses the result. If negatively correlated, the result is amplified; finally, the result is normalized to the range of 0 to 100 to obtain the speed deviation index Q.

[0089] In some embodiments, the robotic arm is provided with an abrasive assembly; and step S2, based on a second preset pressure, controlling the robotic arm to close the box cover and capturing a first closing image of the box cover during closing, further comprises:

[0090] Based on a second preset pressure, controlling the robotic arm to close the box cover, and capturing a box cover closing image after the box cover is closed;

[0091] Perform a wear degree analysis on the box cover closing image, and determine the test result of the armrest box according to the wear degree obtained from the wear degree analysis.

[0092] For example, in order to further improve the testing efficiency of the armrest box, an abrasive component may be provided on the robotic arm for closing the box cover, and the wear resistance test of the outer surface of the box cover may be performed while the box cover is closed.

[0093] For example, the closed image of the trunk lid can be obtained by taking an image of the trunk lid surface under preset lighting, and the degree of wear of the closed image of the trunk lid before and after wear can be compared. For example, the grayscale similarity of the closed image of the trunk lid before and after wear can be compared to obtain the degree of wear of the armrest box.

[0094] In some embodiments, performing wear analysis on the lid closing image and determining the armrest box test result according to the wear degree obtained from the wear analysis includes:

[0095] When step S2 is performed a preset number of times, performing wear analysis on the box lid closing image obtained by the last execution of step S2; or

[0096] When the armrest box reaches a preset wear degree, the number of executions of step S2 is obtained, and the wear degree is determined according to the number of executions.

[0097] For example, the wear resistance of the box cover can be tested. Similarly, the degree of wear can be identified after N wear cycles, or the number of times the wear cycle reaches a preset degree of wear can be recorded (i.e., the number of times the box cover is closed). Please refer to the above embodiments and will not elaborate on them here.

[0098] In some embodiments, the step S4 of determining the test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image further includes:

[0099] The audio in the target opening image and the target closing image is analyzed to obtain a test result of the armrest box.

[0100] For example, damage to the damping structure of the box cover may also cause imaging when the box cover is opened and closed. The audio in the target opening image and the target closing image may also be extracted to determine whether there is noise in the audio, thereby determining the test result of the armrest box.

[0101] In some embodiments, analyzing the audio in the target opening image and the target closing image to obtain the test result of the armrest box includes:

[0102] Novelty detection is performed on target audio information corresponding to the target open image and the target closed image to determine whether abnormal noise exists in the target audio information.

[0103] For example, in order to avoid the influence of the sound of other machinery running, environmental noise, etc. in the test workshop, the target audio information can be compared with the previous audio information for novelty detection to determine whether there is a sound in the target audio information that does not exist in the first audio information, thereby determining whether there is abnormal noise in the target audio information, and in the event of abnormal noise, the detection result is judged to be abnormal.

[0104] The present application provides a method for automatically detecting the processing quality of an automobile armrest box based on computer vision. The present application comprises the following steps: step S1, based on a first preset pressure, controlling a cylinder to open the box cover, and capturing a first opening image during the box cover opening process; step S2, based on a second preset pressure, controlling a robotic arm to close the box cover, and capturing a first closing image during the box cover closing process; step S3, repeatedly executing steps S1 and S2 to obtain a target opening image and a target closing image; and step S4, determining the test result of the armrest box based on the first opening image, the first closing image, the target opening image, and the target closing image. Testing the armrest box using images of the box cover opening and closing improves test efficiency and objectivity; and by repeatedly opening and closing the box cover, automated testing of the durability of the box cover's damping capacity is achieved, reducing the labor and time costs required for testing.

[0105] See also Figure 3 , Figure 3 This is a schematic diagram of an automatic detection device for the processing quality of an automobile armrest box based on computer vision provided in one embodiment of the present application. The automatic detection device for the processing quality of an automobile armrest box based on computer vision can be configured in a server or terminal to execute the aforementioned automatic detection method for the processing quality of an automobile armrest box based on computer vision.

[0106] like Figure 3 As shown, the computer vision-based automatic detection device for the processing quality of an automobile armrest box includes: a box cover opening module 110 , a box cover closing module 120 , a repeated execution module 130 , and an image analysis module 140 .

[0107] A box cover opening module 110 is configured to control the cylinder to open the box cover based on a first preset pressure, and to capture a first opening image during the box cover opening process;

[0108] The box cover closing module 120 is used to control the robot arm to close the box cover based on the second preset pressure, and to capture a first closing image of the box cover during the closing process;

[0109] A repeating module 130 is configured to repeatedly execute step S1 and step S2 to obtain a target opening image and a target closing image;

[0110] The image analysis module 140 determines a test result of the armrest box according to the first open image, the first closed image, the target open image, and the target closed image.

[0111] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] The methods and apparatus of the present application can be used in a wide variety of general or specialized computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0113] For example, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0114] See also Figure 4 , Figure 4 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal.

[0115] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0116] The storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can enable the processor to execute any one of the computer vision-based methods for automatically detecting the processing quality of an automobile armrest box.

[0117] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0118] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any one of the automatic detection methods for the processing quality of the automobile armrest box based on computer vision.

[0119] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0120] It should be understood that 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. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0121] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0122] Step S1, based on a first preset pressure, controlling the cylinder to open the box cover, and capturing a first opening image of the box cover during the opening process;

[0123] Step S2, controlling the robotic arm to close the box cover based on a second preset pressure, and capturing a first closing image of the box cover during the closing process;

[0124] Step S3, repeatedly executing step S1 and step S2 to obtain a target open image and a target closed image;

[0125] Step S4: determining a test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image.

[0126] It should be noted that, those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working process of the computer equipment described above can refer to the corresponding process in the aforementioned embodiment of the automatic detection method for the processing quality of the automobile armrest box based on computer vision, and will not be repeated here.

[0127] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the method for automatic detection of processing quality of automobile armrest boxes based on computer vision in the present application.

[0128] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0129] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0130] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0131] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for automatically detecting the processing quality of an automobile armrest box based on computer vision, characterized in that: The automobile armrest box comprises a box body and a box cover, wherein the box body and the box cover are rotatably connected via a damping structure, and the method comprises: Step S1, based on a first preset pressure, controlling the cylinder to open the box cover, and capturing a first opening image of the box cover during the opening process; Step S2, controlling the robotic arm to close the box cover based on a second preset pressure, and capturing a first closing image of the box cover during the closing process; Step S3, repeatedly executing step S1 and step S2 to obtain a target open image and a target closed image; Step S4: determining a test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image.

2. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 1 is characterized in that: The step S1, controlling the cylinder to open the box cover based on a first preset pressure and capturing a first opening image of the box cover during the opening process, includes: Analyzing the first opening image to determine an opening angle of the lid in the first opening image and an opening time taken to reach the opening angle; When the opening angle and the first opening time do not meet a first preset condition, the armrest box test result is determined to be abnormal, wherein the first preset condition includes: an opening angle range and an opening time range.

3. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 1, characterized in that: The target opening image includes at least one of the following: a second opening image and a third opening image; the target closing image includes at least one of the following: a second closing image and a third closing image; and step S3, repeating step S1 and step S2 to obtain a target opening image and a target closing image, including at least one of the following: Step 31, repeating step S1 and step S2 for a preset number of times, and using the image obtained by the last execution of step S1 and step S2 as the second opening image and the second closing image; Step S32: Repeat step S1 and step S2, and continue to obtain the images obtained by executing step S1 and step S2 as the third opening image and the third closing image, until the third opening image and the third closing image do not meet the second preset condition, and obtain the number of executions of step S1 and step S2.

4. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 4 is characterized in that: After step S31, the following steps are further included: Calculating a velocity deviation index of the box lid according to the first opening image, the second opening image, the first closing image, and the second closing image; When the speed deviation index is greater than a first preset threshold, the armrest box test result is determined to be abnormal.

5. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 4 is characterized in that: When the speed deviation index is greater than a first preset threshold, determining that the armrest box test result is abnormal further includes: If the speed deviation index is greater than a second preset threshold, executing step S32 to obtain the execution count, wherein the second preset threshold is less than the first preset threshold; When the execution times are less than the preset times, the armrest box test result is determined to be abnormal.

6. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 4 is characterized in that: The calculating the speed deviation index of the box cover according to the first opening image, the second opening image and the first closing image, and the second closing image includes: Extracting a first standard speed, a second standard speed, and a third standard speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the first opening image and the first closing image; Extracting a first current speed, a second current speed, and a third current speed when the lid rotates to a first key point, a second key point, and a third key point from any one of the second opening image and the second closing image; The velocity deviation index is calculated based on the following formula: Among them, d i =|v i -v′ i | / v i , v′ i Indicates the first standard speed, the second standard speed, and the third standard speed, v i represents the first current speed, the second current speed, and the third current speed; k is the sensitivity coefficient, k≥2; Σ represents the covariance matrix, d=[d1, d2, d3].

7. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 1, characterized in that: The robotic arm is provided with an abrasive assembly; the step S2, based on the second preset pressure, controls the robotic arm to close the box cover and captures a first closing image of the box cover during the closing process, further comprising: Based on a second preset pressure, controlling the robotic arm to close the box cover, and capturing a box cover closing image after the box cover is closed; Perform a wear degree analysis on the box cover closing image, and determine the test result of the armrest box according to the wear degree obtained from the wear degree analysis.

8. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 7, characterized in that: The performing wear analysis on the cover closing image and determining the test result of the armrest box according to the wear degree obtained by the wear analysis includes: When step S2 is performed a preset number of times, performing wear analysis on the box lid closing image obtained by the last execution of step S2; or When the armrest box reaches a preset wear degree, the number of executions of step S2 is obtained, and the wear degree is determined according to the number of executions.

9. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to any one of claims 1 to 8, characterized in that: The step S4 of determining a test result of the armrest box according to the first opening image, the first closing image, the target opening image, and the target closing image further includes: The audio in the target opening image and the target closing image is analyzed to obtain a test result of the armrest box.

10. The method for automatically detecting the processing quality of an automobile armrest box based on computer vision according to claim 9, characterized in that: The analyzing the audio in the target opening image and the target closing image to obtain the test result of the armrest box includes: Novelty detection is performed on target audio information corresponding to the target open image and the target closed image to determine whether abnormal noise exists in the target audio information.

Images