Vehicle body paint surface detection system and method and storage medium

Abstract

The invention relates to a vehicle body paint surface detection system and method and a storage medium. The system comprises a vehicle body conveying device arranged in the first direction and used for conveying a target vehicle in the first direction; the tunnel type detection device is arranged on the vehicle body conveying device in a crossing mode in the second direction and used for collecting first image data of the side face and the top face of the target vehicle, and a preset angle is formed between the second direction and the first direction; the follow-up detection device is arranged in the first direction and used for collecting second image data of the head and the tail of the target vehicle; the central control device is connected with the tunnel type detection device and the follow-up detection device; and the processor is used for receiving the first image data and the second image data and determining paint surface defect information of the target vehicle according to the first image data and the second image data. By adopting the system, the false detection and missing detection risks caused by limited manual observation capacity, concentration degree and visual speed can be reduced, so that the accuracy of vehicle paint surface detection is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle inspection technology, and in particular to a vehicle body paint inspection system, method, central control device, computer-readable storage medium, and computer program product. Background Technology

[0002] In the automotive manufacturing industry, the detection of paint defects during the production process is a crucial step.

[0003] In existing automobile manufacturing production lines, the detection of paint defects still relies on traditional manual visual inspection methods, which involve manually identifying various paint defects such as scratches, dents, and particles.

[0004] However, the speed of manual visual inspection is limited by the physiological limits of the human body, making it difficult to keep pace with the increasing speed of automated production. Furthermore, due to eye fatigue, highly subjective judgment standards, and interference from ambient light and complex reflections from the vehicle's curved surface, it is difficult to comprehensively observe the vehicle's paint surface. Minor defects or defects at specific angles are easily overlooked, leading to a high probability of missed or false detections during the inspection process. These problems all contribute to low accuracy in vehicle paint inspection, affecting the paint quality of manufactured vehicles. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle paint surface inspection system, method, central control device, computer-readable storage medium, and computer program product that can improve the accuracy of vehicle paint surface inspection in response to the above-mentioned technical problems.

[0006] In a first aspect, this application provides a vehicle body paint inspection system, comprising:

[0007] A vehicle body conveying device arranged along a first direction is used to convey a target vehicle along the first direction;

[0008] A tunnel-type detection device straddling the vehicle body conveying device along the second direction is used to collect first image data of the side and top of the target vehicle, with the second direction forming a preset angle with the first direction.

[0009] A follow-up detection device set along the first direction is used to collect second image data of the front and rear of the target vehicle;

[0010] The central control unit connects the tunnel-type detection device and the follow-up detection device; it is used to receive first image data and second image data, and determine the paint defect information of the target vehicle based on the first image data and second image data.

[0011] In one embodiment, the tunneling detection device includes:

[0012] A tunnel mechanism spanning the vehicle body conveyor forms a tunnel-type detection space, which provides a darkroom environment for the acquisition of the first image data.

[0013] The light source, located in the tunnel-type detection space and connected to the central control device, is used to illuminate the target vehicle so that the side and top surfaces of the target vehicle produce reflective images.

[0014] Multiple first image acquisition units are connected to the central control device. Each first image acquisition unit is set in the tunnel-type detection space and is used to capture first image data of the target vehicle. The first image data includes reflective images of the side and top surfaces of the target vehicle.

[0015] In one embodiment, the light source is a structured light source used to illuminate the target vehicle so that structured light images are generated on the side and top surfaces of the target vehicle.

[0016] In one embodiment, a track is provided along a first direction;

[0017] A robotic arm mounted on a track, connected to a central control unit, is used for follow-up detection devices, including:

[0018] It moves back and forth along the first direction on the track;

[0019] The second image acquisition unit, installed on the robotic arm and connected to the central control device, is used to acquire second image data of the front and rear of the target vehicle.

[0020] In one embodiment, the robotic arm moves at the same speed as the target vehicle moves on the vehicle body conveyor.

[0021] In one embodiment, the vehicle body paint inspection system further includes:

[0022] A photoelectric sensor, connected to the central control unit, is used to detect whether the target vehicle has reached the preset inspection position and obtain the detection result;

[0023] The central control unit is also used to control the start of the tunnel-type detection device and the follow-up detection device when the target vehicle is determined to have arrived at the inspection position based on the detection results.

[0024] Secondly, this application also provides a method for detecting vehicle body paint, applied to a vehicle body paint detection system. The vehicle body paint detection system includes: a vehicle body conveying device arranged along a first direction for conveying a target vehicle along the first direction; a tunnel-type detection device straddling the vehicle body conveying device along a second direction for acquiring first image data of the side and top surfaces of the target vehicle, the second direction forming a preset angle with the first direction; and a follow-up detection device arranged along the first direction for acquiring second image data of the front and rear of the target vehicle. The method includes:

[0025] Acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle;

[0026] The paint defect information of the target vehicle is determined based on the first image data and the second image data.

[0027] In one embodiment, determining the paint defect information of the target vehicle based on the first image data and the second image data includes:

[0028] Identify a first paint defect in the first image data and a second paint defect in the second image data;

[0029] Paint defects are mapped onto a preset 3D model of the target vehicle to obtain paint defect information of the target vehicle.

[0030] In one embodiment, the first image data includes structured light images of the side and top surfaces of the target vehicle; identifying a first paint defect in the first image data includes:

[0031] Determine the pattern features of the structured pattern in the structured light image;

[0032] Determine the deviation value of the pattern features from the preset reference characteristics;

[0033] The first paint defect in the first image data is determined based on the deviation value.

[0034] Thirdly, this application also provides a central control device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0035] Acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle;

[0036] The paint defect information of the target vehicle is determined based on the first image data and the second image data.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle;

[0039] The paint defect information of the target vehicle is determined based on the first image data and the second image data.

[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0041] Acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle;

[0042] The paint defect information of the target vehicle is determined based on the first image data and the second image data.

[0043] The aforementioned vehicle body paint inspection system, method, central control device, computer-readable storage medium, and computer program product include a vehicle body conveying device arranged along a first direction for conveying a target vehicle along the first direction; a tunnel-type inspection device straddling the vehicle body conveying device along a second direction for acquiring first image data of the side and top surfaces of the target vehicle, wherein the second direction forms a preset angle with the first direction; a follow-up inspection device arranged along the first direction for acquiring second image data of the front and rear of the target vehicle; and a central control device connecting the tunnel-type inspection device and the follow-up inspection device for receiving the first image data and the second image data, and determining paint defect information of the target vehicle based on the first image data and the second image data. This application involves acquiring first image data of the side and top surfaces of the target vehicle through a tunnel-type detection device during the vehicle's transport on a vehicle body conveyor, and acquiring second image data of the front and rear surfaces of the target vehicle through a follow-up detection device, thereby obtaining comprehensive image data of the entire vehicle body. Then, the central control device determines the paint defect information of the target vehicle based on the first and second image data. Compared with manual vehicle body paint inspection, this method can reduce the risk of false detection and missed detection caused by the limited observation ability, concentration, and visual speed of humans, thereby improving the accuracy of vehicle paint inspection. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the structure of a vehicle body paint detection system in one embodiment;

[0046] Figure 2 This is a detailed structural diagram of a vehicle body paint inspection system in one embodiment;

[0047] Figure 3 This is a flowchart illustrating a method for detecting vehicle body paint in one embodiment;

[0048] Figure 4This is a detailed flowchart illustrating the steps for determining paint defect information of a target vehicle based on first image data and second image data in one embodiment.

[0049] Figure 5 This is a detailed flowchart illustrating the steps for identifying a first paint defect in a first image data in one embodiment.

[0050] Figure 6 This is a structural block diagram of a vehicle body paint inspection system device in one embodiment;

[0051] Figure 7 This is an internal structural diagram of the central control device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0054] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0055] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0056] It is understandable that "at least one" refers to one or more, and "multiple" refers to two or more. "At least a part of an element" refers to part or all of an element.

[0057] When used herein, the singular forms of “a,” “an,” and “ / the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0058] In one exemplary embodiment, such as Figure 1 As shown, a vehicle body paint inspection system is provided, including: a vehicle body conveying device 110 arranged along a first direction for conveying a target vehicle along the first direction; a tunnel-type inspection device 120 spanning the vehicle body conveying device 110 along a second direction for acquiring first image data of the side and top surfaces of the target vehicle, wherein the second direction forms a preset angle with the first direction; a follow-up inspection device 130 arranged along the first direction for acquiring second image data of the front and rear of the target vehicle; and a central control device 140 connecting the tunnel-type inspection device 120 and the follow-up inspection device 130 for receiving the first image data and the second image data, and determining paint defect information of the target vehicle based on the first image data and the second image data.

[0059] In this embodiment, the vehicle body conveying device 110 is arranged along a first direction, serving as a carrier and transport medium for the target vehicle. A tunnel-type detection device 120 is positioned above the vehicle body conveying device 110 along a second direction (at a preset angle to the first direction), forming a spatially perpendicular arrangement with the vehicle body conveying device 110. When the target vehicle moves on the vehicle body conveying device 110, it passes through the tunnel-type detection device 120 along the first direction inside the tunnel-type detection device 120. A follow-up detection device 130 is arranged along the first direction, parallel to the vehicle body conveying device 110. A central control device 140 is connected to the tunnel-type detection device 120 and the follow-up detection device 130 via wired or wireless communication, receiving first image data transmitted by the tunnel-type detection device 120 and second image data transmitted by the follow-up detection device 130.

[0060] Specifically, the vehicle body conveyor 110 is installed in the vehicle production line. It realizes the continuous or intermittent movement of the target vehicle in the first direction through a mechanical transmission mechanism (such as a chain, belt or roller), ensuring that the target vehicle passes through the detection area at a constant speed, providing a standardized motion trajectory for image acquisition, and eliminating detection errors caused by inconsistent vehicle movement.

[0061] The tunnel-type detection device 120 integrates an image acquisition unit, which acquires first image data of the side and top surfaces of the target vehicle through the principle of optical imaging. Through the layout perpendicular to the direction of movement of the target vehicle, it achieves full coverage of the side and top surfaces.

[0062] The follow-up detection device 130 can collect local image data of the front and rear of the vehicle by synchronously tracking along the direction of vehicle movement. The second image data it collects makes up for the blind spots of the tunnel device in the detection of the front and rear of the target vehicle, so that the collected image data can fully cover all the paint surfaces of the target vehicle.

[0063] The central control device 140 may include a data processing module (such as an industrial computer or an image processing chip), which acquires the first image data and the second image data collected by the tunnel detection device 120 and the follow-up detection device 130 through a communication connection, analyzes the first image data and the second image data, and finally obtains the paint defect information of the target vehicle, thereby realizing the detection of paint defects of the target vehicle.

[0064] In this application, during the process of the target vehicle being transported on the vehicle body conveying device 110, a tunnel-type detection device 120 collects first image data of the side and top surfaces of the target vehicle, and a follow-up detection device 130 collects second image data of the front and rear of the target vehicle to obtain comprehensive image data of the entire vehicle body. Then, a central control device 140 determines the paint defect information of the target vehicle based on the first and second image data. Compared with the method of manual vehicle body paint inspection, this method can reduce the risk of false detection and missed detection caused by the limited human observation ability, concentration and visual speed, thereby improving the accuracy of vehicle paint inspection.

[0065] In some exemplary embodiments, such as Figure 2 As shown, the tunnel-type detection device 120 includes:

[0066] A tunnel mechanism 210 spans the vehicle body conveying device 110, forming a tunnel-type detection space to provide a darkroom environment for the acquisition of first image data. A light source 220 is installed in the tunnel mechanism 210 and connected to the central control device 140 to illuminate the target vehicle so that the side and top surfaces of the target vehicle produce reflective images. Multiple first image acquisition units 230 are connected to the central control device 140, and each first image acquisition unit 230 is installed in the tunnel mechanism 210 to capture first image data of the target vehicle, including reflective images of the side and top surfaces of the target vehicle.

[0067] In this embodiment, the tunnel mechanism 210 spans above the vehicle body conveying device 110, including a top plate and two side plates parallel to the first direction, forming a semi-enclosed detection area resembling a tunnel. Due to the obstruction of the top and side plates, the light inside the tunnel is relatively dim. When the target vehicle moves into the tunnel and the light source 220 illuminates the target vehicle, the darkroom-like environment inside the tunnel facilitates the identification of reflections on the target vehicle's surface. The light source 220 is fixedly installed on the inner wall or top of the tunnel mechanism 210 and connected to the central control device 140. When the central control device 140 detects that the target vehicle has reached the preset inspection position, it controls the light source 220 to start. Multiple first image acquisition units 230 are distributed and installed at different positions (such as the side walls and top) of the tunnel mechanism 210, and are also connected to the central control device 140 to transmit the acquired images to the central control device 140.

[0068] Specifically, the tunnel structure 210 can be a closed environment constructed by a steel frame and an opaque protective panel, including a top plate and two side plates parallel to the first direction, used to isolate external light interference, and to ensure that different batches of vehicles are tested under the same lighting conditions through a standardized testing environment, eliminating the influence of environmental variables on the test results and providing stable lighting conditions for image acquisition.

[0069] The light source 220 can be an LED (Light Emitting Diode) light source, which provides illumination conditions for the acquisition of the first image based on the control of the central control device 140, and illuminates the target vehicle to generate reflective images on the side and top surfaces of the target vehicle.

[0070] The first image acquisition unit 230 can be a camera. Multiple cameras are distributed along the inner wall of the tunnel mechanism, ensuring that the images captured by the cameras cover the entire illuminated cross-section of the vehicle body. The fields of view between cameras need to be continuous to prevent data loss during data stitching, which would affect defect detection. Simultaneously, camera lenses with different parameters need to be used according to the actual situation to cover a wider detection area within the depth of field, and the spatial resolution of the cameras should be maximized to detect even smaller defects. Multiple cameras are densely distributed around the inner wall of the tunnel mechanism 210 to achieve full coverage imaging of the sides and top of the vehicle body (excluding the front / rear).

[0071] In another exemplary embodiment, the camera and light source 220 can be mounted on a fixed bracket or held by a robotic arm, allowing the camera to move relative to the vehicle body. The camera then captures surface images reflected from the vehicle body in real time, relative to the real-time movement of the detection system. Alternatively, a combination of fixed brackets and robotic arm 250 can be used. For example, fixed brackets can be used on the left and right sides of the vehicle body where the height is relatively fixed, while a more flexible robotic arm can be used on areas where the height changes significantly with the vehicle model, such as the roof, hood, and rear, allowing for real-time adjustment of the detection points as the vehicle body moves. Alternatively, a fixed bracket can be used to mount the camera and structured light source, which is more suitable for scenarios where the vehicle model size changes little on the production line.

[0072] The tunnel-type inspection device 120 can acquire image data of the side and top surfaces of a moving target vehicle, meeting the cycle time requirements of the vehicle production line and improving the efficiency of paint defect detection.

[0073] In some exemplary embodiments, the light source 220 is a structured light source used to illuminate the target vehicle so that structured light images are generated on the side and top surfaces of the target vehicle.

[0074] In this embodiment, the light source 220 can be a structured light source, connected to the central control device 140, to realize the control of light pattern generation; the first image data acquired by the first image acquisition unit 230 can be a structured light image captured by structured light technology. The structured light technology uses a pre-designed pattern with a special structure (such as discrete light spots, striped light, coded structured light, etc.), and then projects the pattern onto the surface of a three-dimensional object. Another camera is used to observe the distortion of the image on the three-dimensional physical surface. After the pattern is projected onto the surface of the three-dimensional object, the image of the three-dimensional object surface captured by the camera device is the structured light image carrying the projected pattern.

[0075] It should be noted that the reason for setting up a structured light source is that when the structured light source is illuminating the surface of the target vehicle, the defective area will show a more obvious change compared to the surrounding normal paint surface, which can effectively enhance the characteristics of defects such as protrusions, depressions, particles, and pinholes. Generally, structured light sources include, but are not limited to, binary stripe LED light sources 220. When the structured light source is a binary stripe LED light source 220, illuminating the surface of the target vehicle with the binary stripe LED light source 220 will produce a binary stripe-like light band.

[0076] Illuminating a target vehicle with structured light can make the distorted parts caused by defects more obvious and easier to identify, which helps to improve the accuracy of paint defects.

[0077] In some exemplary embodiments, the follow-up detection device 130 includes: a track 240 arranged along a first direction, a robotic arm 250 arranged on the track 240, and a second image acquisition unit 260 arranged on the robotic arm 250.

[0078] The robotic arm 250 is connected to the central control device 140 and is used to move back and forth along the track 240 in the first direction. The second image acquisition unit 260 is connected to the central control device 140 and is used to acquire second image data of the front and rear of the target vehicle.

[0079] In this embodiment, the number of follow-up detection devices 130 can be two. Two sets of follow-up detection devices 130 are symmetrically arranged on both sides of the vehicle body conveying device 110. One set is used to collect second image data of the front of the target vehicle, and the other set is used to collect second image data of the rear of the target vehicle. When the number of follow-up detection devices 130 is one, the follow-up detection device 130 simultaneously collects second image data of the front and rear of the target vehicle. Based on this, the specific structure of the follow-up detection device 130 is as follows: the track 240 is laid parallel to the ground, support frame, or wall on both sides of the vehicle body conveying device 110 along the first direction; the bottom of the robotic arm 250 is slidably connected to the track 240, and the drive module (such as a servo motor) of the robotic arm 250 is connected to the central control device 140; the second image acquisition unit 260 is installed at the end of the robotic arm 250 and connected to the central control device 140.

[0080] Specifically, the track 240 can provide the robotic arm 250 with long-stroke motion capability and provide the robotic arm 250 with linear motion reference. Through the control of the central control device 140, the robotic arm 250 can accurately track the detection trajectory of vehicles with different wheelbases.

[0081] The robotic arm 250 may include joint components with multiple degrees of freedom, and its end effector can be precisely positioned in three-dimensional space under the control of the central control device 140. When performing defect detection, the central control device 140 controls the robotic arm 250 to move along a first direction to follow the target vehicle. After completing the defect detection of the target vehicle, the central control device 140 controls the robotic arm 250 to move in the opposite direction to the first direction to a pre-set initial position, waiting for the next target vehicle to be detected.

[0082] The second image acquisition unit 260 may include a camera and a light source 220, which can perform high-precision scanning of key points in complex curved areas such as the front grille, the edge of the headlights, and the rear bumper, thus making up for the detection blind spots of the tunnel-type detection device 120.

[0083] The follow-up detection device 130 can supplement the defect images of the front and rear of the vehicle that the tunnel detection device 120 cannot detect, so as to realize the comprehensive inspection of the paint surface of the target vehicle and improve the accuracy of paint defect detection.

[0084] In some exemplary embodiments, the robotic arm 250 moves at the same speed on the track 240 as the target vehicle moves at the same speed on the vehicle body transfer device 110.

[0085] In this embodiment, the central control device 140 sets the moving speed of the robotic arm 250 based on the conveying speed of the vehicle body conveying device 110, so that the second image acquisition unit 260 at the end of the robotic arm 250 is relatively stationary with respect to the target vehicle. This allows the acquisition of second image data of the front and rear of the target vehicle without stopping the target vehicle, adapting to the production rhythm of the entire production line and improving the efficiency of paint defect detection.

[0086] In some exemplary embodiments, the vehicle body paint inspection system further includes:

[0087] A photoelectric sensor, connected to the central control unit 140, is used to detect whether the target vehicle has reached the preset inspection position and obtain the detection result; the central control unit 140 is also used to control the tunnel detection device 120 and the follow-up detection device 130 to start when the detection result determines that the target vehicle has reached the inspection position.

[0088] In this embodiment, the photoelectric sensor can be installed above or to the side of the position to be inspected on the vehicle body conveying device 110, without further restrictions, and its signal output terminal is connected to the central control device 140.

[0089] When the photoelectric sensor detects that the target vehicle has arrived at the inspection position, it outputs the detection result to the central control device 140. When the central control device 140 receives the detection result and recognizes that the target vehicle has arrived at the inspection position, it controls the tunnel detection device 120 and the follow-up detection device 130 to start, thereby saving energy when there is no target vehicle to be inspected.

[0090] In addition, an encoder can be installed to detect the forward distance of the target vehicle and determine its position. Existing tunnel defect detection technologies mostly use encoders to monitor the vehicle body displacement and update the relative position of the vehicle body and the camera, which is not accurate enough. This method combines encoder and camera calibration to obtain the relative position of the camera and the vehicle body at multiple moments, resulting in higher accuracy.

[0091] Based on the same inventive concept, this application also provides a method for detecting vehicle body paint, which can be applied to, for example... Figure 1 The diagram shows a vehicle body paint inspection system. The structure of the vehicle body paint inspection system will not be described in detail here.

[0092] In one exemplary embodiment, such as Figure 3 As shown, a method for inspecting vehicle body paint is provided, which is applied to... Figure 1Taking the central control device as an example, the explanation includes the following steps 302 and 304. Wherein:

[0093] Step 302: Obtain first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle;

[0094] The target vehicle refers to the car whose paint surface is to be inspected; the first image data is the image information of the side and top of the target vehicle collected by the tunnel-type inspection device, which contains data that can reflect the condition of the paint surface; the second image data is the image information of the front and rear of the target vehicle collected by the follow-up inspection device, which also contains data that can reflect the condition of the paint surface.

[0095] In this embodiment, the central control device sends a command to the tunnel-type detection device, which is mounted on top of the vehicle body conveying device along a second direction perpendicular to the first direction. During the process of the target vehicle being conveyed by the vehicle body conveying device along the first direction, the tunnel-type detection device starts its data acquisition operation, acquires first image data of the side and top surfaces of the target vehicle, and transmits it to the central control device. The central control device also sends a command to the follow-up detection device, which is set along the first direction. During the process of the target vehicle being conveyed, the follow-up detection device starts its data acquisition operation, acquires second image data of the front and rear of the target vehicle, and transmits it to the central control device.

[0096] Step 304: Determine the paint defect information of the target vehicle based on the first image data and the second image data.

[0097] Among them, paint defect information refers to information related to various problems existing on the paint surface of the target vehicle, including but not limited to specific characteristic data such as the type, location, and size of defects such as scratches, orange peel, runs, and particles.

[0098] In this embodiment, after receiving the first image data transmitted by the tunnel-type detection device and the second image data transmitted by the follow-up detection device, the central control device processes the two sets of data using a preset paint defect analysis model to identify defects in the paint surface of the target vehicle's side, top, front, and rear, and determines specific information such as the type, location, and size of the defects.

[0099] In some embodiments, such as Figure 4 As shown, step 304 above includes steps 402 and 404, wherein:

[0100] Step 402: Identify the first paint defect in the first image data and identify the second paint defect in the second image data;

[0101] Among them, paint defects refer to abnormal conditions on the paint surface of the target vehicle, such as scratches, dents, orange peel, runs, etc., that affect the quality of the paint surface.

[0102] In this embodiment, the central control device analyzes and processes the first and second image data to identify the first and second paint defects present in the images, and determines the location and approximate shape of the defects in the images. The central control device can identify paint defects in the first and second image data using a defect detection model. The defect detection model is trained using multiple image data containing defects as samples, with the defects corresponding to the image data as labels.

[0103] Step 404: Map the paint defects onto the preset target vehicle 3D model to obtain the paint defect information of the target vehicle.

[0104] The preset target vehicle 3D model is a pre-built 3D digital model that matches the actual size and shape of the target vehicle.

[0105] In this embodiment, the central control device, based on the location information of the paint defects identified in the image, combined with the spatial relationship between the first and second image acquisition devices and the target vehicle, as well as the coordinate system of the three-dimensional model, accurately maps the identified paint defects onto the preset three-dimensional model of the target vehicle through coordinate transformation and mapping. This allows the actual location of the paint defects on the target vehicle to be presented intuitively on the three-dimensional model. At the same time, combined with the information such as the shape and size of the defects identified in the image, complete information on the paint defects of the target vehicle is obtained.

[0106] In one exemplary embodiment, the first image data includes structured light images of the side and top surfaces of the target vehicle; such as Figure 5 As shown, step 402 above includes steps 502 to 508, wherein:

[0107] Step 502: Determine the pattern features of the structured pattern in the structured light image;

[0108] Among them, structured light images are images containing deformed structured light patterns collected by tunneling detection devices after projecting specific structured light (such as striped light, grid light, etc.) onto the side and top of the target vehicle; pattern features refer to parameters that describe the shape and properties of the structured light pattern in the image, such as the shape, stripe spacing, curvature, and grayscale distribution.

[0109] In this embodiment, the central control device processes the structured light image in the first image data, uses image processing algorithms, such as edge detection algorithms, to extract the edge contour of the structured light pattern, obtains the grayscale distribution of the pattern through grayscale analysis algorithms, and then combines morphological processing methods to analyze the shape and stripe spacing of the pattern, thereby comprehensively determining the pattern features of the structured light pattern in the structured light image.

[0110] Step 504: Determine the deviation value of the pattern feature from the preset reference characteristic;

[0111] Among them, the preset benchmark characteristics are the standard pattern features that the structured light pattern should have when the paint surface of the target vehicle is free of defects, including parameters such as standard shape, stripe spacing, curvature, and grayscale distribution; the deviation value refers to the difference in various parameters between the actual determined pattern features and the preset benchmark characteristics.

[0112] In this embodiment, the central control device compares the pattern features of the determined structural pattern with the preset reference characteristics one by one. By calculating the values ​​of the two in terms of shape similarity, stripe spacing difference, curvature change, gray scale distribution difference, etc., the deviation value of the pattern features compared with the preset reference characteristics is obtained.

[0113] Step 506: Determine the first paint defect in the first image data based on the deviation value;

[0114] In this embodiment, the central control device judges the obtained deviation value according to a preset deviation value threshold range. If the deviation value exceeds the normal range, it is determined that there is a paint defect in the area. Combining the magnitude and direction of the deviation value, the type and approximate extent of the paint defect can be further determined, thereby identifying the paint defect in the first image data.

[0115] By using structured light to identify vehicle paint defects, the characteristics of structured light images and image recognition technology are fully utilized, improving the accuracy and efficiency of paint defect detection.

[0116] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0117] Based on the same inventive concept, this application also provides a vehicle body paint surface inspection device for implementing the above-described vehicle body paint surface inspection method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more vehicle body paint surface inspection device embodiments provided below can be found in the limitations of the vehicle body paint surface inspection method described above, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 6 As shown, a vehicle body paint surface inspection device is provided, comprising:

[0119] The data acquisition module 601 is used to acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear of the target vehicle.

[0120] The detection module 602 is used to determine paint defect information of the target vehicle based on the first image data and the second image data.

[0121] In one embodiment, the detection module 602 is further configured to identify a first paint defect in the first image data and a second paint defect in the second image data; and to map the paint defect to a preset target vehicle 3D model to obtain paint defect information of the target vehicle.

[0122] In one embodiment, the detection module 602 is further configured to determine the pattern features of the structured pattern in the structured light image; determine the deviation value of the pattern features from a preset reference characteristic; determine a first paint defect in the first image data based on the deviation value; and identify paint defects in the second image data.

[0123] Each module in the aforementioned vehicle paint inspection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the central control unit in hardware form or independent of it, or stored in the memory of the central control unit in software form, so that the processor can call and execute the corresponding operations of each module.

[0124] In one exemplary embodiment, a central control device is provided, the internal structure of which can be shown in the following diagram. Figure 7As shown, the central control unit includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores the control data of the central control unit. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a method for detecting vehicle body paint.

[0125] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the central control device to which the present application is applied. A specific central control device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] In one exemplary embodiment, a central control device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described embodiment of the vehicle body paint detection method.

[0127] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps in the above-described embodiment of the vehicle body paint detection method.

[0128] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described vehicle body paint detection method embodiment.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0130] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0131] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle body paint inspection system, characterized in that, include: A vehicle body conveying device arranged along a first direction is used to convey a target vehicle along the first direction; A tunnel-type detection device straddling the vehicle body conveying device along the second direction is used to collect first image data of the side and top of the target vehicle, wherein the second direction forms a preset angle with the first direction; A follow-up detection device set along the first direction is used to acquire second image data of the front and rear of the target vehicle; The central control device connects the tunnel-type detection device and the follow-up detection device; It is used to receive the first image data and the second image data, and to determine the paint defect information of the target vehicle based on the first image data and the second image data.

2. The system according to claim 1, characterized in that, The tunnel-type detection device includes: A tunnel mechanism spanning the vehicle body conveying device forms a tunnel-type detection space, which provides a darkroom environment for the acquisition of the first image data. A light source located in the tunnel-type detection space is connected to the central control device and is used to illuminate the target vehicle so that the side and top surfaces of the target vehicle produce reflective images. Multiple first image acquisition units are connected to the central control device. Each first image acquisition unit is set in the tunnel-type detection space and is used to capture first image data of the target vehicle. The first image data includes reflective images of the side and top surfaces of the target vehicle.

3. The system according to claim 2, characterized in that, The light source is a structured light source, used to illuminate the target vehicle so that structured light images are generated on the side and top surfaces of the target vehicle.

4. The system according to claim 1, characterized in that, The follow-up detection device includes: A track set along the first direction; A robotic arm mounted on the track is connected to the central control device and is used to move back and forth on the track along the first direction. The second image acquisition unit, installed on the robotic arm and connected to the central control device, is used to acquire second image data of the front and rear of the target vehicle.

5. The system according to claim 4, characterized in that, The robotic arm moves at the same speed as the target vehicle moves on the vehicle body conveyor.

6. The system according to claim 1, characterized in that, The vehicle body paint inspection system also includes: A photoelectric sensor, connected to the central control device, is used to detect whether the target vehicle has reached the preset inspection position and obtain the detection result; The central control device is also used to control the tunnel-type detection device and the follow-up detection device to start when the detection result determines that the target vehicle has arrived at the inspection position.

7. A method for inspecting vehicle body paint, characterized in that, An application to a vehicle body paint inspection system, the vehicle body paint monitoring system comprising: a vehicle body conveying device arranged along a first direction for conveying a target vehicle along the first direction; a tunnel-type inspection device straddling the vehicle body conveying device along a second direction for acquiring first image data of the side and top surfaces of the target vehicle, the second direction being perpendicular to the first direction; and a follow-up inspection device arranged along the first direction for acquiring second image data of the front and rear of the target vehicle. The method includes: Acquire first image data of the side and top surfaces of the target vehicle, and second image data of the front and rear surfaces of the target vehicle; The paint defect information of the target vehicle is determined based on the first image data and the second image data.

8. The method according to claim 7, characterized in that, The step of determining the paint defect information of the target vehicle based on the first image data and the second image data includes: Identify a first paint defect in the first image data and identify a second paint defect in the second image data; The paint defects are mapped onto a preset three-dimensional model of the target vehicle to obtain the paint defect information of the target vehicle.

9. The method according to claim 8, characterized in that, The first image data includes structured light images of the side and top surfaces of the target vehicle; identifying the first paint defect in the first image data includes: Determine the pattern features of the structural pattern in the structured light image; Determine the deviation value of the pattern feature from a preset reference characteristic; The first paint defect in the first image data is determined based on the deviation value.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 7 to 9.

Images