CN-121994130-A - Automatic film covering precision detection method and system for automobile lampshade

CN121994130ACN 121994130 ACN121994130 ACN 121994130ACN-121994130-A

Abstract

The invention discloses an automatic film coating precision detection method and system for an automobile lampshade, which relate to the technical field of film coating detection and comprise the following steps of acquiring a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point based on a real-time film coating front point cloud image and a real-time film coating rear point cloud image; the method comprises the steps of acquiring a first real-time midpoint and a second real-time midpoint based on a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point, acquiring a real-time tectorial membrane value based on the first real-time midpoint and the second real-time midpoint, acquiring a historical tectorial membrane value based on a three-dimensional point cloud picture before and after normal tectorial membrane, acquiring a first tectorial membrane threshold value and a second tectorial membrane threshold value based on the historical tectorial membrane value, and acquiring tectorial membrane precision detection results based on the real-time tectorial membrane value, the first tectorial membrane threshold value and the second tectorial membrane threshold value.

Inventors

WANG KUN
WANG ERHUA

Assignees

顺安(天津)塑胶制品股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260126

Claims (10)

1. An automatic film coating precision detection method for an automobile lampshade is characterized by comprising the following steps: Three-dimensional point cloud pictures before and after film coating of the automobile lampshade to be detected are obtained and marked as a real-time film coating front point cloud picture and a real-time film coating rear point cloud picture respectively; Acquiring a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point based on a point cloud image before real-time film coating and a point cloud image after real-time film coating; acquiring a first real-time midpoint and a second real-time midpoint based on the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point; acquiring a real-time film covering value based on the first real-time midpoint and the second real-time midpoint; acquiring a historical film covering value based on a three-dimensional point cloud image before and after normal film covering; acquiring a first tectorial membrane threshold value and a second tectorial membrane threshold value based on the historical tectorial membrane value; and acquiring a film covering precision detection result based on the real-time film covering value, the first film covering threshold value and the second film covering threshold value.
2. The method for automatically detecting the film coating precision of the automobile lampshade according to claim 1, wherein the step of acquiring the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point based on the point cloud image before the real-time film coating and the point cloud image after the real-time film coating comprises the following substeps: a plane rectangular coordinate system is established on a plane where the automobile lampshade is placed, and is marked as a projection coordinate system; marking three-dimensional coordinate points in the point cloud picture before the real-time film coating as first real-time three-dimensional coordinate points; marking the three-dimensional coordinate points in the point cloud picture after the real-time film coating as second real-time three-dimensional coordinate points; Projecting the first real-time three-dimensional coordinate on a projection coordinate system to obtain a two-dimensional coordinate point, and marking the two-dimensional coordinate point as the first real-time two-dimensional coordinate point; and projecting the second real-time three-dimensional coordinate on a projection coordinate system to obtain a two-dimensional coordinate point, and marking the two-dimensional coordinate point as the second real-time two-dimensional coordinate point.
3. The method for automatically detecting the film covering precision of the automobile lampshade according to claim 2, wherein the step of acquiring the first real-time midpoint and the second real-time midpoint based on the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point comprises the following sub-steps: The minimum value and the maximum value of the abscissa in the first real-time two-dimensional coordinate point are respectively marked as a first abscissa value and a second abscissa value; acquiring the average value of the first transverse value and the second transverse value, and marking the average value as a first transverse average value; The minimum value and the maximum value of the ordinate in the first real-time two-dimensional coordinate point are respectively marked as a first ordinate and a second ordinate; acquiring the average value of the first longitudinal value and the second longitudinal value, and marking the average value as a first longitudinal average value; A coordinate point with a first horizontal mean value as an abscissa value and a first vertical mean value as an ordinate value is marked as a first real-time midpoint; and taking the second real-time two-dimensional coordinate point as the first real-time two-dimensional coordinate point to acquire a first real-time midpoint, and marking the first real-time midpoint as the second real-time midpoint.
4. The automated film coating accuracy detection method for an automotive lamp shade according to claim 3, wherein the step of acquiring the real-time film coating value based on the first real-time midpoint and the second real-time midpoint comprises the following sub-steps: Marking the area formed by the first real-time two-dimensional coordinate points as a first real-time area, and marking the area formed by the second real-time two-dimensional coordinate points as a second real-time area; And (3) moving the second real-time area to enable the second real-time midpoint to coincide with the first real-time midpoint, then rotating the second real-time area by taking the second real-time midpoint as a rotation center, stopping rotating when the overlapping area of the first real-time area and the second real-time area is the largest, and obtaining the three-dimensional height difference value of the second real-time two-dimensional coordinate point and the first real-time two-dimensional coordinate point of each same coordinate at the moment, and marking the three-dimensional height difference value as a real-time tectorial membrane value.
5. The method for automatically detecting the film coating precision of the automobile lampshade according to claim 4, wherein the step of acquiring the historical film coating value based on the three-dimensional point cloud patterns before and after normal film coating comprises the following substeps: And respectively considering the three-dimensional point cloud pictures before and after normal film coating as a point cloud picture before real-time film coating and a point cloud picture after real-time film coating, then acquiring a real-time film coating value, and marking the real-time film coating value as a historical film coating value.
6. The automated film coating accuracy detection method of claim 5, wherein the step of obtaining the first film coating threshold and the second film coating threshold based on the historical film coating values comprises the following sub-steps: acquiring a first number of historical film covering values, if the same historical film covering values exist, respectively counting the number of each same historical film covering value, and marking the number as the same film covering value number; the historical film coating values are used as horizontal axis data, the same film coating value quantity is used as vertical axis data, a plane rectangular coordinate system is established, and the plane rectangular coordinate system is marked as a film coating value observation coordinate system; drawing an abscissa and an ordinate of the historical film coating value and the corresponding same film coating value number as data points on a film coating value observation coordinate system; and marking the data points in the tectorial membrane value observation coordinate system as tectorial membrane value coordinate points.
7. The automated film coating accuracy detection method of claim 6, wherein the obtaining the first film coating threshold and the second film coating threshold based on the historical film coating values further comprises the sub-steps of: acquiring the range length of a historical film coverage value in a film coverage value coordinate system, and marking as D1; Establishing two straight lines parallel to a longitudinal axis of a tectorial membrane value observation coordinate system, wherein the width between the two straight lines is D2, and marking the space between the two straight lines as a real-time search space, wherein the real-time search space can move left and right; the distribution number threshold is calculated as k=a× (d2++d1) ×s1, where K is the distribution number threshold, a is the set ratio, and S1 is the first number.
8. The automated film coating accuracy detection method of claim 7, wherein the obtaining the first film coating threshold and the second film coating threshold based on the historical film coating values further comprises the sub-steps of: marking all numbers of historical film covering values corresponding to all film covering value coordinate points in the real-time search space as real-time search numbers; Moving the real-time search space to enable the minimum abscissa of the real-time search space to be equal to the abscissa of the coordinate point of the minimum tectorial membrane value, then moving the real-time search space to the right, judging the size of the real-time search number and the distribution number threshold in real time, and stopping moving the real-time search space when the real-time search number is larger than or equal to the distribution number threshold; Moving the real-time search space to make the maximum abscissa of the real-time search space equal to the abscissa of the coordinate point of the maximum film covering value, then moving the real-time search space leftwards, judging the size of the real-time search number and the distribution number threshold in real time, stopping moving the real-time search space when the real-time search number is larger than or equal to the distribution number threshold, and acquiring the historical film covering value corresponding to the maximum abscissa of the real-time search space at the moment and marking the historical film covering value as a second film covering threshold.
9. The automated film coating accuracy detection method of claim 8, wherein the film coating accuracy detection result is obtained based on the real-time film coating value, the first film coating threshold value and the second film coating threshold value, comprising the steps of: If the real-time film coverage value is in the area between the first film coverage threshold value and the second film coverage threshold value, marking the area as a normal film coverage area; marking a region with the real-time coating value smaller than a first coating threshold value as a first abnormal region; and marking the area with the real-time coating value larger than the second coating threshold value as a second abnormal area.
10. An automatic film covering precision detection system for an automobile lampshade, which is used for realizing the automatic film covering precision detection method for the automobile lampshade according to any one of claims 1-9, and is characterized by comprising a real-time data acquisition module, a coordinate point acquisition module, a midpoint acquisition module, a real-time film covering value acquisition module, a historical film covering value acquisition module, a threshold acquisition module and a detection result acquisition module; The real-time data acquisition module is used for acquiring three-dimensional point cloud pictures before and after film coating of the automobile lampshade to be detected, and the three-dimensional point cloud pictures are respectively marked as a real-time point cloud picture before film coating and a real-time point cloud picture after film coating; the coordinate point acquisition module is used for acquiring a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point based on the point cloud image before real-time film coating and the point cloud image after real-time film coating; The midpoint acquisition module is used for acquiring a first real-time midpoint and a second real-time midpoint based on the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point; the real-time tectorial membrane value acquisition module is used for acquiring a real-time tectorial membrane value based on the first real-time midpoint and the second real-time midpoint; the historical film coverage value acquisition module is used for acquiring a historical film coverage value based on a three-dimensional point cloud picture before and after normal film coverage; The threshold value acquisition module is used for acquiring a first tectorial membrane threshold value and a second tectorial membrane threshold value based on the historical tectorial membrane value; the detection result acquisition module is used for acquiring a film covering precision detection result based on the real-time film covering value, the first film covering threshold value and the second film covering threshold value.

Description

Automatic film covering precision detection method and system for automobile lampshade Technical Field The invention relates to the technical field of film coating detection, in particular to an automatic film coating precision detection method and system for an automobile lampshade. Background In order to improve the weather resistance, scratch resistance, optical performance and visual effect of an automobile lampshade, a core process is formed by covering the surface of the lampshade with a functional film or a temporary protective film, the process requires the film to be bonded with a complex three-dimensional curved surface of the lampshade in a high-precision, defect-free and conformal manner, and any bonding deviation can directly influence the protection of a product, so that the automatic film-covering precision detection of the automobile lampshade is required; The existing film coating precision detection mainly depends on manual visual inspection or two-dimensional image comparison detection, is low in manual detection efficiency, high in labor intensity, is influenced by personnel experience, fatigue degree and subjective judgment, is poor in consistency, and is difficult to meet the strict requirements of large-scale automatic production on efficiency and quality. Disclosure of Invention The method aims at solving at least one of the technical problems in the prior art to a certain extent, and comprises the steps of obtaining a three-dimensional point cloud image before and after film coating of an automobile lamp shade to be detected, respectively marking the three-dimensional point cloud image before film coating and the three-dimensional point cloud image after film coating as a real-time film coating, obtaining a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point based on the real-time front point cloud image before film coating and the real-time film coating, obtaining a first real-time midpoint and a second real-time midpoint based on the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point, obtaining a real-time film coating value based on the first real-time midpoint and the second real-time midpoint, obtaining a historical film coating value based on the three-dimensional point cloud image before film coating and the rear film coating of a normal film coating, obtaining a first film coating threshold value and a second film coating threshold value based on the historical film coating value, and obtaining film coating accuracy detection results based on the real-time film coating value, so that in the existing film coating detection technology, due to strong reflection and light transmission characteristics exist between a film and the automobile lamp shade, and poor accuracy of film coating accuracy detection is achieved through the two-dimensional images. In order to achieve the above purpose, the application provides an automatic film covering precision detection method for an automobile lampshade, which comprises the following steps: Three-dimensional point cloud pictures before and after film coating of the automobile lampshade to be detected are obtained and marked as a real-time film coating front point cloud picture and a real-time film coating rear point cloud picture respectively; Acquiring a first real-time two-dimensional coordinate point and a second real-time two-dimensional coordinate point based on a point cloud image before real-time film coating and a point cloud image after real-time film coating; acquiring a first real-time midpoint and a second real-time midpoint based on the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point; acquiring a real-time film covering value based on the first real-time midpoint and the second real-time midpoint; acquiring a historical film covering value based on a three-dimensional point cloud image before and after normal film covering; acquiring a first tectorial membrane threshold value and a second tectorial membrane threshold value based on the historical tectorial membrane value; and acquiring a film covering precision detection result based on the real-time film covering value, the first film covering threshold value and the second film covering threshold value. Further, the method for acquiring the first real-time two-dimensional coordinate point and the second real-time two-dimensional coordinate point based on the point cloud image before the real-time film coating and the point cloud image after the real-time film coating comprises the following sub-steps: a plane rectangular coordinate system is established on a plane where the automobile lampshade is placed, and is marked as a projection coordinate system; marking three-dimensional coordinate points in the point cloud picture before the real-time film coating as first real-time three-dimensional coordinate point