Intelligent cabin function automatic test method and electronic equipment

Abstract

The invention provides an intelligent cabin function automatic test method and electronic equipment. According to the method, all target test cases can be executed in sequence, and in the execution process of any target test case, a target vehicle component associated with the target test case is controlled to execute a corresponding cabin function operation; controlling the panoramic camera to shoot the target vehicle part, and receiving an image of the target vehicle part shot by the panoramic camera; based on the image recognition model, recognizing whether the target vehicle part is in a working state corresponding to the cabin function operation; and according to the identification result, generating a test result corresponding to the target test case, so that the corresponding cabin function operation can be executed for the target vehicle component associated with each target test case, whether the cabin function operation is normally completed or not can be determined by shooting the image of the target vehicle component through the camera, the test coverage range is wide, and the test efficiency is improved. Manual intervention is not needed, a large amount of time cost and labor cost are saved, and reliability is high.

Description

Technical Field

[0001] This application relates to the field of vehicle automated testing technology, and in particular to an automated testing method and electronic device for intelligent cockpit functions. Background Technology

[0002] The intelligent cockpit is a concept proposed by the automotive industry under the trend of intelligentization and connectivity. It refers to upgrading the traditional car cockpit into a highly digitalized, intelligent, and interactive mobile space by integrating advanced hardware, software, and human-machine interaction technologies, which can provide drivers with an intelligent experience and promote driving safety.

[0003] Currently, before a vehicle leaves the factory, its intelligent cockpit function needs to be tested. Since the intelligent cockpit function involves multiple vehicle components (such as the dashboard, windows, sunroof, etc.), test engineers need to frequently verify the status of various vehicle components inside the vehicle, such as verifying the display status of the central control screen and dashboard, the on / off status of various indicator lights, and the opening and closing status of vehicle components such as windows, sunroof, and trunk.

[0004] Therefore, during the testing of intelligent cockpit functions, test engineers need to frequently verify the status of various components in the vehicle, including the display status of the central control screen and instrument panel, the on / off status of various indicator lights, and the opening and closing status of physical components such as windows, sunroof, and trunk. This results in a significant expenditure of time and manpower, and low reliability. Summary of the Invention

[0005] This application provides an automated testing method and electronic device for intelligent cockpit functions, which solves the problem that in the process of testing intelligent cockpit functions, test engineers need to frequently verify the status of various components in the vehicle, resulting in a large amount of time and manpower costs and low reliability.

[0006] In a first aspect, this application provides an automated testing method for intelligent cockpit functions, applied to a test terminal. The test terminal is communicatively connected to both a vehicle and a panoramic camera installed inside the vehicle. The method provided in this application includes: From a pre-defined set of test cases associated with smart cockpit functions, identify multiple target test cases; Each target test case is executed sequentially. During the execution of any target test case, the target vehicle component associated with the target test case is controlled to perform the corresponding cockpit function operation. Control the panoramic camera to shoot at the target vehicle parts, and receive the images of the target vehicle parts captured by the panoramic camera; Based on a pre-trained image recognition model, it identifies whether the target vehicle component is in the working state corresponding to the cockpit function operation. The image recognition model is trained by inputting multiple historical vehicle component images labeled with working states into the network to be trained. Based on the identification results, test results corresponding to the target test cases are generated.

[0007] In some implementations, controlling the panoramic camera to capture images of the target vehicle components includes: Based on the location of the target vehicle component associated with the pre-recorded target test case and the current orientation of the panoramic camera, determine the rotation direction and rotation angle of the panoramic camera; Based on the rotation direction and angle of the panoramic camera, control the panoramic camera to rotate toward the target vehicle component, and control the panoramic camera to shoot toward the target vehicle component.

[0008] In some implementations, before determining multiple target test cases from a pre-defined set of test cases associated with smart cockpit functions, the method provided in this application further includes: Collect historical vehicle component images at each vehicle part and mark the working status of each historical vehicle component image; Multiple historical vehicle component images labeled with their working status are input into the network to be trained, and an image recognition model is obtained.

[0009] In some implementations, historical vehicle component images of each vehicle component are acquired, including: For each vehicle component, historical images of the vehicle component are collected from different angles; And / or, for each vehicle component, historical vehicle component images are acquired under different lighting conditions.

[0010] In some implementations, after marking the operational status of each historical vehicle component image, the process includes: Preprocessing operations are performed on each historical vehicle component image marked with its working state to obtain a preprocessed historical vehicle component image. The preprocessing operations include rotation, brightness adjustment, contrast adjustment, and / or noise injection.

[0011] In some implementations, controlling the target vehicle component associated with the target test case to perform corresponding cockpit function operations includes: If the target vehicle component associated with the target test case is a window, control the window to open to the target opening degree; If the target vehicle component associated with the target test case is the sunroof, control the sunroof to open to the target opening degree; If the target vehicle component associated with the target test case is the dashboard, control the dashboard to light up.

[0012] In some implementations, the network to be trained is a YOLO v8 network.

[0013] In a second aspect, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device performs the method provided in the first aspect of this application.

[0014] Thirdly, this application also provides a storage medium storing a computer program, which, when executed by a processor, causes the computer to perform the method provided in the first aspect of this application.

[0015] Fourthly, this application also provides a computer program product, including a computer program that, when run, causes an electronic device to perform the method provided in the first aspect of this application.

[0016] This application provides an automated testing method and electronic device for intelligent cockpit functions. It can determine multiple target test cases from a pre-set set of test cases associated with intelligent cockpit functions; execute each target test case sequentially; during the execution of any target test case, control the target vehicle component associated with the target test case to perform the corresponding cockpit function operation; control a panoramic camera to capture images of the target vehicle component and receive the images captured by the panoramic camera; based on a pre-trained image recognition model, identify whether the target vehicle component is in the working state corresponding to the cockpit function operation; and generate the test result corresponding to the target test case based on the recognition result. In this way, it is possible to determine whether the cockpit function operation is successfully completed by capturing images of the target vehicle component for each target test case, achieving wide test coverage, eliminating the need for manual intervention, saving significant time and manpower costs, and ensuring high reliability. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic diagram illustrating the communication connection between the test terminal and the panoramic camera provided in an embodiment of this application; Figure 2A flowchart of an automated testing method for intelligent cockpit functions provided in an embodiment of this application; Figure 3 A functional block diagram of the automated testing device for intelligent cockpit functions provided in the embodiments of this application. Detailed Implementation

[0019] Embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0020] The accompanying drawings illustrate various structural schematics according to embodiments of the present disclosure. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0021] In the context of this disclosure, when a layer / element is referred to as being "above" another layer / element, the layer / element may be directly above the other layer / element, or there may be an intermediate layer / element between them. Additionally, if a layer / element is "above" another layer / element in one orientation, then when the orientation is reversed, the layer / element may be "below" the other layer / element.

[0022] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0023] This application provides an automated testing method for intelligent cockpit functions, applied to a testing terminal. For example... Figure 1 As shown, the test terminal communicates with both the vehicle and a panoramic camera installed inside the vehicle. For example, the test terminal can communicate with the panoramic camera via USB, serial port, or Bluetooth. During testing, all the seats in the vehicle can be folded down, and the panoramic camera can be positioned at the geometric center of the vehicle's interior space so that the camera can clearly capture images of all vehicle components. It should be noted that the panoramic camera can be rotated to any shooting angle via a motor. Figure 2 As shown, the method provided in this application embodiment includes: S201: Determine multiple target test cases from a pre-defined set of test cases associated with the smart cockpit function.

[0024] Understandably, each test case is used to test different cockpit functions, and testers can select multiple target test cases from the set of test cases associated with smart cockpit functions.

[0025] S202: Execute each target test case in sequence. During the execution of any target test case, control the target vehicle component associated with the target test case to perform the corresponding cockpit function operation.

[0026] For example, if the target vehicle component associated with the target test case is a window, the window is controlled to open to the target opening degree; if the target vehicle component associated with the target test case is a sunroof, the sunroof is controlled to open to the target opening degree; if the target vehicle component associated with the target test case is a dashboard, the dashboard is controlled to light up.

[0027] S203: Control the panoramic camera to shoot at the target vehicle component and receive the image of the target vehicle component captured by the panoramic camera.

[0028] For example, the rotation direction and rotation angle of the panoramic camera are determined based on the position of the target vehicle component associated with the pre-recorded target test case and the current orientation of the panoramic camera; based on the rotation direction and rotation angle of the panoramic camera, the panoramic camera is controlled to rotate to face the target vehicle component, and the panoramic camera is controlled to shoot towards the target vehicle component.

[0029] S204: Based on a pre-trained image recognition model, identify whether the target vehicle component is in the working state corresponding to the cockpit function operation.

[0030] For example, when the cockpit function is to control the window to open to the target opening degree, it is identified whether the window is opened to the target opening degree (e.g., 50%); when the cockpit function is to control the sunroof to open to the target opening degree, it is identified whether the sunroof is opened to the target opening degree (e.g., 50%); when the cockpit function is to control the instrument panel to light up, it is identified whether the instrument panel is lit up, and if it is lit up, it is identified whether the lit instrument panel has a distorted display.

[0031] The image recognition model described above is trained by inputting multiple historical vehicle component images labeled with their working states into a training network. For example, the training network can be, but is not limited to, a YOLO v8 network. Furthermore, leveraging the powerful general recognition capabilities of the YOLO v8 network, the network can be pre-trained using the collected historical vehicle component dataset. This allows the YOLO v8 network to acquire a preliminary understanding and localization ability of the in-vehicle environment layout and the location of common components, forming a strong feature extractor specifically for in-vehicle scenarios within the initially trained YOLO v8 network. Next, the backbone of the YOLO v8 network is frozen, and the network layers responsible for classification and bounding box regression are trained using a dedicated state dataset. This stage allows the YOLO v8 network to learn how to effectively map the general features extracted by the backbone network to newly added fine-grained state categories. Subsequently, the last few layers of the backbone network can be gradually unfrozen, and further fine-tuning can be performed with a very low learning rate to smoothly adapt to new features, further improving the performance of the final image recognition model.

[0032] Furthermore, the process of training the above image recognition model may include: Step 1: Collect historical vehicle component images of each vehicle part and mark the working status of each historical vehicle component image.

[0033] For example, for each vehicle component, historical images of the vehicle component are acquired from different angles; and / or, for each vehicle component, historical images of the vehicle component are acquired under different lighting conditions. This enhances the generalization ability of the training samples.

[0034] Additionally, preprocessing operations can be performed on each historical vehicle component image labeled with its working state to obtain preprocessed historical vehicle component images. These preprocessing operations include rotation, brightness adjustment, contrast adjustment, and / or noise injection. This further enhances the generalization ability of the training samples.

[0035] Step 2: Input multiple historical vehicle component images labeled with their working status into the network to be trained to obtain an image recognition model.

[0036] S205: Based on the identification results, generate the test results corresponding to the target test cases.

[0037] For example, when the cockpit function is operated to control the window to open to the target opening degree, if the window is identified as being opened to the target opening degree, a test result indicating that the window opening test is normal is generated; if the window is identified as not being opened to the target opening degree, a test result indicating that the window opening test is abnormal is generated.

[0038] Please see Figure 3 This application provides an automated testing device for intelligent cockpit functions, applied to a testing terminal. It should be noted that the basic principle and technical effects of the automated testing device for intelligent cockpit functions provided in this application are the same as those in the above embodiments. For the sake of brevity, any parts not mentioned in this application can be referred to the corresponding content in the above embodiments. The testing terminal is communicatively connected to the vehicle and a panoramic camera installed inside the vehicle. The device provided in this application includes a test case determination unit, a test case execution unit, an image capture control unit, a working status recognition unit, and a test result generation unit. The test case determination unit is used to determine multiple target test cases from a pre-set set of test cases associated with the smart cockpit function.

[0039] The test case execution unit is used to execute each target test case in sequence. During the execution of any target test case, it controls the target vehicle component associated with the target test case to perform the corresponding cockpit function operation.

[0040] In some implementations, the test case execution unit is specifically used to control the window to open to a target opening degree when the target vehicle component associated with the target test case is a window; to control the sunroof to open to a target opening degree when the target vehicle component associated with the target test case is a sunroof; and to control the dashboard to light up when the target vehicle component associated with the target test case is an instrument panel.

[0041] The image capture control unit is used to control the panoramic camera to capture images of the target vehicle parts and to receive images of the target vehicle parts captured by the panoramic camera.

[0042] The operational status recognition unit is used to identify whether a target vehicle component is in an operational state corresponding to a cockpit function operation, based on a pre-trained image recognition model. The image recognition model is trained by inputting multiple historical vehicle component images labeled with operational states into a training network. In some implementations, the training network is a YOLO v8 network.

[0043] The test result generation unit is used to generate test results corresponding to the target test cases based on the identification results.

[0044] In some implementations, the image capture control unit is configured to determine the rotation direction and rotation angle of the panoramic camera based on the position of the target vehicle component associated with the pre-recorded target test case and the current orientation of the panoramic camera; and to control the panoramic camera to rotate toward the target vehicle component based on the rotation direction and rotation angle of the panoramic camera, and to control the panoramic camera to capture images toward the target vehicle component.

[0045] In some embodiments, the apparatus provided in this application further includes: The sample acquisition unit is used to acquire historical vehicle component images of each vehicle part and to mark the working status of each historical vehicle component image.

[0046] The model training unit is used to input multiple historical vehicle component images labeled with their working status into the network to be trained, thereby training an image recognition model.

[0047] In some implementations, the sample acquisition unit is used to acquire historical vehicle component images of each vehicle component from different angles; and / or, for each vehicle component, to acquire historical vehicle component images under different lighting conditions.

[0048] The sample acquisition unit is also used to perform preprocessing operations on each historical vehicle component image marked with a working state to obtain a preprocessed historical vehicle component image. The preprocessing operations include rotation, brightness adjustment, contrast adjustment, and / or noise injection.

[0049] In addition, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device performs the method provided in the above embodiments of this application.

[0050] In addition, this application embodiment also provides a storage medium storing a computer program, which, when executed by a processor, causes the computer to perform the method provided in the above embodiments of this application.

[0051] In addition, this application also provides a computer program product, including a computer program that, when run, causes an electronic device to perform the method provided in the above embodiments of this application.

[0052] The above description does not provide detailed technical specifications regarding the structure of each layer. However, those skilled in the art should understand that layers and regions of desired shapes can be formed using various technical means. Furthermore, to form the same structure, those skilled in the art can also design methods that are not entirely identical to those described above. Additionally, although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be advantageously combined.

[0053] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0054] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An automated testing method for intelligent cockpit functions, characterized in that, The method, applied to a test terminal that is communicatively connected to a vehicle and a panoramic camera installed inside the vehicle, includes: From a pre-defined set of test cases associated with smart cockpit functions, identify multiple target test cases; Each of the target test cases is executed sequentially. During the execution of any target test case, the target vehicle component associated with the target test case is controlled to perform the corresponding cockpit function operation. Control the panoramic camera to shoot at the target vehicle component, and receive the image of the target vehicle component captured by the panoramic camera; Based on a pre-trained image recognition model, it is determined whether the target vehicle component is in the working state corresponding to the cockpit function operation. The image recognition model is obtained by inputting multiple historical vehicle component images labeled with working states into the network to be trained. Based on the identification results, test results corresponding to the target test cases are generated.

2. The method according to claim 1, characterized in that, Controlling the panoramic camera to capture images of the target vehicle components includes: Based on the pre-recorded location of the target vehicle component associated with the target test case and the current orientation of the panoramic camera, determine the rotation direction and rotation angle of the panoramic camera; Based on the rotation direction and rotation angle of the panoramic camera, control the panoramic camera to rotate so that it faces the target vehicle component, and control the panoramic camera to shoot towards the target vehicle component.

3. The method according to claim 1, characterized in that, Before determining multiple target test cases from a pre-defined set of test cases associated with smart cockpit functions, the method further includes: Collect historical vehicle component images at each vehicle part, and mark the working status of each historical vehicle component image; Multiple historical vehicle component images labeled with their working status are input into the network to be trained, and the image recognition model is obtained through training.

4. The method according to claim 3, characterized in that, The acquisition of historical vehicle component images at various vehicle parts includes: For each vehicle component, historical vehicle component images are acquired from different angles; And / or, for each vehicle component, historical vehicle component images are acquired under different lighting conditions.

5. The method according to claim 3, characterized in that, After marking the working status of each of the historical vehicle component images, the process includes: Preprocessing operations are performed on each of the historical vehicle component images marked with a working state to obtain a preprocessed historical vehicle component image, wherein the preprocessing operations are rotation, brightness adjustment, contrast adjustment, and / or noise injection.

6. The method according to any one of claims 1-5, characterized in that, The control of the target vehicle component associated with the target test case to perform the corresponding cockpit function operation includes: If the target vehicle component associated with the target test case is a window, control the window to open to the target opening degree; If the target vehicle component associated with the target test case is a sunroof, control the sunroof to open to the target opening degree; If the target vehicle component associated with the target test case is the dashboard, control the dashboard to light up.

7. The method according to any one of claims 1-5, characterized in that, The network to be trained is a YOLO v8 network.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to perform the method as described in any one of claims 1 to 7.

9. A storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the computer to perform the method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is run, it causes the electronic device to perform the method as described in any one of claims 1 to 7.

Images