Automatic vehicle light detection method and system based on vision

Abstract

The invention relates to an automatic vehicle light detection method and system based on vision, and belongs to the technical field of automobile automatic detection, and the method comprises the following steps: obtaining a vehicle VIN number of a vehicle; initiating a query request according to the VIN number of the whole vehicle to obtain configuration information of a lamp of the whole vehicle; issuing a diagnosis instruction based on the configuration information, sequentially lightening each light of the vehicle to obtain a current and voltage signal when the light is lightened, and meanwhile, detecting and verifying the vehicle light to obtain a light acquisition signal; and checking and comparing the current and voltage signals and the light acquisition signal to obtain a detection result and uploading the detection result. According to the invention, the advanced visual detection technology is used to carry out comprehensive detection on the lighting system, the system has high-precision identification capability, multi-dimensional parameters such as the lighting state and the brightness of the vehicle light can be rapidly detected, and potential defects such as non-lighting of the light, wrong loading and neglected loading can be effectively identified.

Description

TECHNICAL FIELD

[0001] The present disclosure belongs to the technical field of automobile automation detection, and particularly relates to a vision-based automated vehicle light detection method and system. BACKGROUND

[0002] Under the background of the vigorous development of the automobile industry, the process of automobile production line automation is continuously expanding and deepening with an irresistible momentum. With the increasingly stringent requirements of consumers for automobile quality and the increasingly fierce market competition, how to further improve the overall quality of automobile products and reduce the error detection rate caused by manual detection has become a key issue that automobile manufacturing enterprises need to solve. In the vehicle production process, the light system is an important part of ensuring driving safety and vehicle function integrity, and its accurate detection is crucial.

[0003] Traditional vehicle light detection relies on manual visual inspection, however, manual detection is not only inefficient, but also prone to errors due to human factors such as fatigue and lack of concentration. At the same time, visual detection technology is also undergoing steady and powerful improvement and perfection.

[0004] Therefore, it is necessary to provide a new vision-based automated vehicle light detection method and system to solve the above technical problems. SUMMARY

[0005] The purpose of the present disclosure is to provide a vision-based automated vehicle light detection method and system to solve the above problems.

[0006] The present disclosure achieves the above-mentioned purpose through the following technical solutions: A vision-based automated vehicle light detection method, comprising the following steps: Obtaining the VIN number of the vehicle; Initiating a query request according to the VIN number of the vehicle to obtain the configuration information of the vehicle lamps; Based on the configuration information, issuing a diagnosis instruction to light up each light of the vehicle in turn, obtaining the current voltage signal when the light is on, and simultaneously detecting and verifying the vehicle light to obtain the light collection signal; Verifying and comparing the current voltage signal and the light collection signal to obtain the detection result and upload it.

[0007] As a further optimization scheme of the present disclosure, obtaining the VIN number of the vehicle comprises: Sending a diagnosis instruction to the body domain controller through a data acquisition instrument to obtain the VIN number of the vehicle.

[0008] As a further optimization of the present disclosure, the query request is initiated according to the VIN number of the whole vehicle to obtain the configuration information of the whole vehicle lamp, which comprises: The data acquisition instrument initiates a query request to the manufacturing execution system (MES) according to the VIN number of the whole vehicle to obtain the detailed configuration information of the whole vehicle lamp.

[0009] As a further optimization of the present disclosure, the detailed configuration information comprises lamp type and function configuration.

[0010] As a further optimization of the present disclosure, the lamp type comprises halogen lamp and LED lamp; and the function configuration comprises whether it has the welcome light function.

[0011] As a further optimization of the present disclosure, the industrial camera detects and verifies the vehicle light, and the industrial camera transmits the collected image data to the visual algorithm server for processing to obtain the light collection signal.

[0012] An automated vehicle light detection system based on vision, for implementing the automated vehicle light detection method based on vision, characterized in that it comprises a manufacturing execution system (MES), an industrial camera, a visual algorithm server, a data acquisition instrument and a body domain controller; the manufacturing execution system (MES), the visual algorithm server and the body domain controller are connected to the data acquisition instrument; the industrial camera is connected to the visual algorithm server; The data acquisition instrument sends a diagnostic instruction to the body domain controller to obtain the VIN number of the whole vehicle; The data acquisition instrument initiates a query request to the manufacturing execution system (MES) according to the VIN number of the whole vehicle to obtain the configuration information of the whole vehicle lamp; When the data acquisition instrument obtains the configuration information, it issues a diagnostic instruction to the body domain controller to light up each light of the vehicle in turn, and the data acquisition instrument receives the current and voltage signals of the light-on time fed back by the body domain controller; at the same time, the data acquisition instrument sends an instruction to the visual algorithm server to drive the industrial camera to detect and verify the vehicle light, and the industrial camera transmits the collected image data to the visual algorithm server, which processes the image data to obtain a light collection signal and feeds it back to the data acquisition instrument; The data acquisition instrument checks and compares the current and voltage signals and the light collection signal to obtain a detection result. The data acquisition instrument reports the detection result and related detection data to the manufacturing execution system (MES) system.

[0013] As a further optimization scheme of the present disclosure, the manufacturing execution system MES and the visual algorithm server are both connected with the data acquisition instrument through a wireless network; the vehicle body domain controller is connected with the data acquisition instrument through CAN; the industrial camera is connected with the visual algorithm server through an Ethernet network; and the vehicle body domain controller is connected with the automobile lamps through a hard-wire connection.

[0014] An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus; A memory for storing a computer program; A processor for executing the program stored in the memory to realize the visual-based automated vehicle light detection method.

[0015] A computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to realize the visual-based automated vehicle light detection method.

[0016] The present disclosure has the following beneficial effects: The present disclosure uses advanced visual detection technology to comprehensively detect the light system, has high-precision recognition ability, can quickly detect the lighting state, brightness and other multi-dimensional parameters of the vehicle light, effectively identifies potential defects such as light not lighting, misloading and missing loading, and further seamlessly connects with the production line MES system, realizes real-time feedback and automatic processing of detection data, thereby significantly reduces the quality defects caused by light problems, and improves the quality stability of the whole vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a method flowchart in the embodiment of the present disclosure; Figure 2 is a system structure block diagram in the embodiment of the present disclosure; Figure 3 is a device structure block diagram in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following further describes the present application in combination with the drawings, and it is necessary to point out here that the following detailed description is only used to further describe the present application, and cannot be understood as limiting the protection scope of the present application, and the skilled in the art can make some non-essential improvements and adjustments to the present application according to the above application content.

[0019] As shown in Figure 1 A visual-based automated vehicle light detection method, comprising the following steps: Obtaining a vehicle VIN (Vehicle Identification Number) number; Initiating a query request according to the vehicle VIN number to obtain configuration information of a vehicle lamp; Based on the configuration information, a diagnostic instruction is issued to sequentially light up each light of the vehicle, and a current voltage signal when the light is lit up is obtained, while the vehicle light is detected and verified to obtain a light collection signal; The current voltage signal and the light collection signal are checked and compared to obtain a detection result and upload.

[0020] Obtaining a vehicle VIN number specifically includes: The data acquisition instrument sends a diagnostic instruction to the body domain controller to obtain the vehicle VIN number.

[0021] Initiating a query request according to the vehicle VIN number to obtain configuration information of a vehicle lamp includes: The data acquisition instrument initiates a query request to the manufacturing execution system MES according to the obtained vehicle VIN number to obtain detailed configuration information of the vehicle lamp; the detailed configuration information includes lamp type and function configuration; the lamp type includes halogen lamp and LED lamp; the function configuration includes whether it has a welcome light function.

[0022] The industrial camera detects and verifies the vehicle light, and the industrial camera transmits the collected image data to the visual algorithm server for processing to obtain a light collection signal.

[0023] As shown in Figure 2 The embodiment of the present disclosure provides a visual-based automated vehicle light detection system, which comprises a manufacturing execution system MES (Manufacturing Execution System), an industrial camera, a visual algorithm server, a data acquisition instrument and a body domain controller; the manufacturing execution system MES, the visual algorithm server and the body domain controller are connected with the data acquisition instrument; the industrial camera is connected with the visual algorithm server; the manufacturing execution system MES and the visual algorithm server are connected with the data acquisition instrument through a wireless network; the body domain controller is connected with the data acquisition instrument through CAN; the industrial camera is connected with the visual algorithm server through an Ethernet network; and the body domain controller is connected with the vehicle lamp through a hardwire.

[0024] First, the on-site staff connects the data acquisition instrument to the vehicle OBD (On-Board Diagnostics) port and clicks the "Start Detection" button to start the detection process.

[0025] The data acquisition instrument sends a diagnostic instruction to the vehicle body domain controller to obtain the vehicle VIN number; The data acquisition instrument initiates a query request to the manufacturing execution system MES according to the obtained vehicle VIN number, obtains the configuration information of the vehicle lamps, including the lamp type (such as halogen lamp or LED lamp) and the function configuration (such as whether it has the welcome light function, etc.); When the data acquisition instrument obtains the configuration information, it issues a diagnostic instruction to the vehicle body domain controller, and sequentially lights up each light of the vehicle. The data acquisition instrument receives the current and voltage signals of the light when it is lit, and at the same time, the data acquisition instrument sends an instruction to the visual algorithm server to drive the industrial camera to detect and verify the vehicle light. The industrial camera transmits the collected image data to the visual algorithm server, which processes the image data to obtain the light collection signal and feeds it back to the data acquisition instrument. The data acquisition instrument verifies and compares the current and voltage signals and the light collection signal to obtain the detection result. The data acquisition instrument reports the detection result and related detection data to the manufacturing execution system MES system, completing the entire detection process.

[0026] The present disclosure aims to solve the problem of low efficiency and high error rate caused by subjective factors in the existing automobile production detection link. The system uses advanced visual detection technology to comprehensively detect the light system at the key node before the vehicle enters the warehouse. The system has high precision recognition ability and can quickly detect the lighting state, brightness and other multi-dimensional parameters of the vehicle light, effectively identify potential defects such as light not lighting, misloading and missing loading, etc. In addition, the system can be seamlessly connected with the production line MES system to realize real-time feedback and automatic processing of detection data, thereby significantly reducing the quality defects caused by light problems, improving the stability of the vehicle quality, and ensuring that the vehicle meets the strict quality standards before delivery.

[0027] The implementation process of the functions and roles of each module in the above system is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.

[0028] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts are referred to the part of the method embodiments. The above described system embodiments are only illustrative, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, i.e., can be located in one place or distributed to multiple network modules. Part or all of the modules can be selected to achieve the purpose of the present disclosure according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0029] Referring to Figure 3 The electronic device provided by the embodiments of the present disclosure includes a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 complete mutual communication through the communication bus 1140. The memory 1130 is configured to store a computer program. The processor 1110 is configured to execute the program stored in the memory 1130 to implement the above-mentioned visual-based automated vehicle light detection method. The above-mentioned communication bus 1140 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus.

[0030] The communication interface 1120 is configured to communicate between the above-mentioned electronic device and other devices.

[0031] The memory 1130 can include a random access memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory 1130 can also be at least one storage device located away from the above-mentioned processor 1110.

[0032] The embodiments of the present disclosure also provide a computer readable storage medium. The above-mentioned computer readable storage medium stores a computer program, and the above-mentioned computer program is executed by a processor to implement the above-mentioned visual-based automated vehicle light detection method.

[0033] The above-described embodiments are merely illustrative of several embodiments of the present disclosure, which are described in a relatively specific and detailed manner, but should not be construed as limiting the scope of the patent of the present disclosure. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure.

Claims

1. A vision-based automated vehicle light detection method, characterized in that, Includes the following steps: Obtain the vehicle's VIN number; Initiate a query request based on the vehicle's VIN number to obtain the configuration information of the vehicle's lights; Based on the configuration information, a diagnostic command is issued to sequentially illuminate each of the vehicle's lights, obtaining the current and voltage signals when the lights are illuminated. At the same time, the vehicle lights are detected and verified to obtain the light acquisition signal. The current and voltage signals and the light acquisition signals are verified and compared to obtain the detection results, which are then uploaded.

2. The vision-based automated vehicle light detection method according to claim 1, characterized in that, Obtaining the vehicle's VIN number includes: The data acquisition unit sends diagnostic commands to the vehicle domain controller to obtain the vehicle's VIN number.

3. The vision-based automated vehicle light detection method according to claim 1, characterized in that, Initiating a query request based on the vehicle's VIN number to obtain the configuration information of the vehicle's lighting fixtures includes: The data acquisition device initiates a query request to the Manufacturing Execution System (MES) based on the acquired vehicle VIN number to obtain detailed configuration information of the vehicle's lighting fixtures.

4. The vision-based automated vehicle light detection method according to claim 1, characterized in that, The detailed configuration information includes the type of lighting fixture and its functional configuration.

5. The vision-based automated vehicle light detection method according to claim 4, characterized in that, The types of lamps include halogen lamps and LED lamps; the functional configurations include whether or not they have a welcome light message function.

6. The vision-based automated vehicle light detection method according to claim 1, characterized in that, The vehicle lights are detected and verified using an industrial camera. The industrial camera transmits the acquired image data to a vision algorithm server for processing to obtain the light acquisition signal.

7. A vision-based automated vehicle headlight detection system, used to implement the vision-based automated vehicle headlight detection method as described in any one of claims 1-6, characterized in that, The system includes a Manufacturing Execution System (MES), an industrial camera, a vision algorithm server, a data acquisition device, and a vehicle body domain controller; the MES, the vision algorithm server, and the vehicle body domain controller are all connected to the data acquisition device; the industrial camera is connected to the vision algorithm server. The data acquisition unit sends a diagnostic command to the vehicle domain controller to obtain the vehicle's VIN number; The data acquisition device initiates a query request to the Manufacturing Execution System (MES) based on the obtained vehicle VIN number to obtain the configuration information of the vehicle's lighting fixtures; After the data acquisition device obtains the configuration information, it sends a diagnostic command to the vehicle domain controller to sequentially illuminate each of the vehicle's lights. The data acquisition device receives the current and voltage signals from the vehicle domain controller when the lights are illuminated. Simultaneously, the data acquisition device sends a command to the vision algorithm server to drive the industrial camera to detect and verify the vehicle lights. The industrial camera transmits the acquired image data to the vision algorithm server, which processes the image data to obtain the light acquisition signal and feeds it back to the data acquisition device. The data acquisition instrument verifies and compares the current and voltage signals with the light acquisition signals to obtain the detection results; The data acquisition device reports the detection results and related detection data to the Manufacturing Execution System (MES).

8. The vision-based automated vehicle lighting detection system according to claim 7, characterized in that, The Manufacturing Execution System (MES) and the vision algorithm server are both connected to the data acquisition device via a wireless network; the vehicle body domain controller is connected to the data acquisition device via CAN; the industrial camera is connected to the vision algorithm server via an Ethernet network; and the vehicle body domain controller is connected to the automotive lighting system via a hardwired connection.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor for executing a program stored in a memory to implement the vision-based automated vehicle light detection method according to any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the vision-based automated vehicle light detection method according to any one of claims 1-6.

Images