CN111351441A - Vision-based thickness measurement device and method - Google Patents

Abstract

Vision-based thickness measurement apparatus and methods are disclosed. The thickness measuring device comprises a thickness measuring sensor, a first image acquisition device, a second image acquisition device and a second strip light source, wherein the two first strip light sources and the first image acquisition device are positioned on one side of a reference plane, and the two second strip light sources and the second image detection device are positioned on the other side of the reference plane; and an image processing unit which receives the image from the image pickup device and obtains the thickness of the detected object from the image, wherein the image processing unit determines the distance between the image pickup device and the detected object from the bar patterns of one side and the other side of the detected object, and obtains the thickness of the detected object by subtracting the distance from the distance between the two image pickup devices. The thickness measuring method includes moving an object to be detected along a reference plane; emitting strip-shaped light rays towards two sides of the detected object; capturing bar patterns on two sides of a detected object; and determining the thickness of the detected object according to the bar pattern.

Description

Vision-based thickness measurement device and method

technical field

The present invention relates to the field of thickness measurement, in particular, to a vision-based thickness measurement method and device.

Background technique

The measurement of workpiece thickness is generally divided into contact and non-contact measurement methods. In the current measurement, the thickness is basically obtained at a certain measurement point, and it is difficult to obtain the thickness distribution in a larger measurement area. At the same time, in the current non-contact measurement method, there is still measurement deviation caused by the vibration of the detected object itself. Therefore, there is a high need for an apparatus and method that can obtain the thickness distribution within a larger measurement area.

SUMMARY OF THE INVENTION

The present invention has been made to overcome the above-mentioned problems and other unsolved technical problems.

An object of the present invention is to provide a vision-based thickness measurement device and method, which can obtain the thickness distribution in a larger measurement area, that is, a single measurement can obtain the thickness of a curved surface area.

Another object of the present invention is to provide a vision-based thickness measurement device and method, which can measure the thickness of the entire workpiece with high precision and have the characteristics of anti-interference and vibration.

Another object of the present invention is to provide a vision-based thickness measurement device and method, which can detect the 3D thickness of the entire workpiece, so as to analyze the 3D surface information for the bag, pit and dimensional deviation in the workpiece. detection.

According to one aspect of the present invention, there is provided a vision-based thickness measurement device, comprising:

a thickness measurement sensor comprising two first strip light sources and a first image acquisition device on one side of a virtual reference plane, and two second strips on opposite sides of the reference plane shape light source and a second image detection device, wherein the two first strip light sources are inclined to the reference plane at a predetermined first tilt angle and a second tilt angle respectively with respect to a plane perpendicular to the reference plane One side of the light source emits strip light, and the two second strip light sources are directed to the other side of the reference plane at a predetermined third and fourth inclination angles with respect to the plane perpendicular to the reference plane. A strip light is emitted, the first image acquisition device is located between the two first strip light sources to capture an image of one side of the reference plane, and the second image acquisition device is located between the two first strip light sources. between two light bars to capture an image of the other side of the reference plane; and

an image processing unit, the image processing unit receives images from the first image acquisition device and the second image acquisition device, and obtains the thickness of the detected object according to the images,

Wherein, when the detected object moves through the thickness measurement sensor along the direction of the reference plane, the bar-shaped rays of the two first bar-shaped light sources form a first bar on one side of the detected object The strip light of the two second strip light sources forms a second strip pattern on the other side of the detected object;

Wherein, the image processing unit determines a first distance between the first image acquisition device and the one side of the detected object according to the first strip pattern and the second strip pattern, and a second distance between the second image capture device and the other side of the detected object, and by subtracting the distance between the first image capture device and the second image capture device The thickness of the detected object is obtained from the first distance and the second distance.

Preferably, the first inclination angle and the second inclination angle are the same, and the third inclination angle and the fourth inclination angle are the same. Further preferably, the first inclination angle, the second inclination angle, the third inclination angle and the fourth inclination angle are the same.

Preferably, at least two of the first inclination angle, the second inclination angle, the third inclination angle and the fourth inclination angle are different. That is, the light emission angle of each bar-shaped light source with respect to the reference plane or the above-mentioned plane perpendicular to the reference plane may be different from other bar-shaped light sources.

Preferably, the first stripe light source and the second stripe light source are multi-stripe light sources to improve the applicability of thickness measurement.

Preferably, a plurality of the thickness measurement sensors are provided, and the plurality of thickness measurement sensors are arranged in parallel on both sides of the reference plane, so that the strip light rays emitted by the plurality of thickness measurement sensors are parallel to each other .

Preferably, a plurality of the thickness measurement sensors are provided, and the plurality of thickness measurement sensors are arranged at an angle to each other, so that the plurality of thickness measurement sensors can simultaneously detect the thicknesses of the plurality of surfaces of the detected object.

Preferably, a plurality of the thickness measurement sensors are provided, and the plurality of thickness measurement sensors are arranged in a matrix form in a plurality of directions.

Preferably, the two first bar-shaped light sources respectively emit light of different colors, and the two second bar-shaped light sources respectively emit light of different colors.

Preferably, the intersection point of the strip light rays of the two first strip light sources coincides with the intersection point of the strip light rays of the two second strip light sources.

Preferably, the intersections of the bar rays of the two first bar light sources and the intersections of the bar rays of the two second bar light sources are spaced apart from each other by a specified distance.

Preferably, the thickness measurement sensor is mounted on a bracket, and a temperature compensation unit is provided on the bracket, wherein the image processing unit receives the compensation value from the temperature compensation unit to determine the detected object thickness of.

Preferably, the first strip pattern includes two light patterns formed by the two first strip light sources, and the second strip pattern includes two light patterns formed by the two second strip light sources. a ray pattern, the image processing unit determines the first image according to the distance between the two ray patterns in the first strip pattern and the distance between the two ray patterns in the second strip pattern, respectively A first distance between the acquisition device and the one side of the detected object and a second distance between the second image acquisition device and the other side of the detected object.

According to another aspect of the present invention, a vision-based thickness measurement method is provided, comprising:

Make the detected object move along the virtual reference plane;

With the movement of the detected object, two first bar-shaped light sources located on one side of the reference plane are used at predetermined first and second inclination angles with respect to a plane perpendicular to the reference plane. A strip light is emitted toward one side of the detected object, and at the same time, two second strip light sources located on the other side of the reference plane are used to emit light at a predetermined third relative to the plane perpendicular to the reference plane. The inclination angle and the fourth inclination angle emit strip light toward the other side of the detected object;

A first stripe pattern on one side of the detected object is captured with a first image acquisition device located on one side of the reference plane, and captured with a second image acquisition device located on the other side of the reference plane a second bar pattern on the other side of the detected object; and

A first distance between the first image capturing device and one side of the detected object and a first distance between the second image capturing device and the detected object are determined according to the first bar pattern and the second bar pattern. the second distance between the other side of the detected object, and by subtracting the first distance and the second distance from the distance between the first image capturing device and the second image capturing device Then, the thickness of the detected object is obtained.

Preferably, the first inclination angle and the second inclination angle are the same, and the third inclination angle and the fourth inclination angle are the same. Further preferably, the first inclination angle, the second inclination angle, the third inclination angle and the fourth inclination angle are the same.

Preferably, at least two of the first inclination angle, the second inclination angle, the third inclination angle and the fourth inclination angle are different.

Preferably, the first stripe light source and the second stripe light source are multi-stripe light sources.

Preferably, a plurality of pairs of the two first bar-shaped light sources arranged in parallel are used to emit bar-shaped light toward one side of the detected object, and at the same time, a plurality of pairs of the two second bar-shaped light sources arranged in parallel are used to emit light toward the detected object. The other side of the detected object emits strip light; and corresponding to the plurality of pairs of the two first strip light sources arranged in parallel, a plurality of the first image acquisition devices are used to capture a portion of the detected object. The first strip pattern on the side, and corresponding to the plurality of pairs of the two second strip light sources arranged in parallel, a plurality of the second image acquisition devices are used to capture the second image on the other side of the detected object bar pattern.

Preferably, multiple pairs of the two first strip light sources arranged at an angle are used to emit strip light toward multiple surfaces of the detected object, and at the same time, multiple pairs of the two second strips arranged at an angle are used. The light source emits strip light toward a plurality of opposite surfaces of the detected object; and corresponding to a plurality of pairs of the two first strip light sources arranged at an angle, the plurality of first image acquisition devices are used to capture the A first strip pattern on a plurality of surfaces of a detected object, and corresponding to a plurality of pairs of the two second bar light sources arranged at an angle, the detected object is captured by a plurality of the second image acquisition devices A second stripe pattern of a plurality of opposite surfaces.

Preferably, after capturing the first strip pattern and the second strip pattern, the first strip pattern and the second strip pattern are first matched according to time.

Preferably, according to the distance between the two light patterns of the first strip pattern and the distance between the two light patterns in the second strip pattern, the distance between the first image capturing device and the target is determined. A first distance between the one side of the detected object and a second distance between the second image capturing device and the other side of the detected object.

Preferably, a database of correspondence between the first distance and the second distance and the first stripe pattern and the second stripe pattern is pre-stored.

Preferably, a compensation value is received from the temperature compensation unit to perform data compensation for the detected thickness of the detected object.

Preferably, the first image acquisition device and the second image acquisition device capture images at predetermined time intervals, and transmit the acquired image data to the image processing unit.

Preferably, the two first bar-shaped light sources respectively emit light of different colors, and the two second bar-shaped light sources respectively emit light of different colors.

Description of drawings

The accompanying drawings illustrate preferred embodiments of the present disclosure, and together with the foregoing disclosure serve to provide a further understanding of the technical spirit of the present disclosure. However, the present disclosure should not be construed as limited to the embodiments shown in the accompanying drawings.

In the attached image:

FIG. 1 is an exemplary schematic diagram of a vision-based thickness measurement apparatus according to a first embodiment of the present invention.

FIG. 2 is an oblique perspective view of the thickness measuring apparatus shown in FIG. 1 .

FIG. 3 schematically shows a bar-shaped ray pattern formed on the left surface of the detected object.

FIG. 4 is a flow chart of a thickness measurement method according to the present invention.

5 is an oblique perspective view of a thickness measuring apparatus according to a second embodiment of the present invention.

6 is a schematic view of a thickness measuring apparatus according to a third embodiment of the present invention.

Detailed ways

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Before the description, it should be understood that the terms used in this specification and the appended claims should not be construed as limited to ordinary meanings and dictionary meanings, but based on meanings corresponding to technical aspects of the present disclosure and concepts based on principles that allow the inventor to define terms appropriately for best explanation.

Furthermore, the descriptions set forth herein are preferred examples for illustrative purposes only and are not intended to limit the scope of the present disclosure, therefore, it should be understood that the present disclosure may be made without departing from the spirit and scope of the present disclosure at the time of filing this application. Other equivalents and modifications are made below.

1 is an exemplary schematic diagram of a vision-based thickness measurement apparatus according to a first embodiment of the present invention, and FIG. 2 is an oblique perspective view of the thickness measurement apparatus shown in FIG. 1 . The thickness measurement apparatus according to the present invention may include a thickness measurement sensor and an image processing unit. 1 , a first left light source 10R, a second left light source 10G, a left image capture device 10C, a first right light source 20R, a second right light source 20G, and a right image capture device 20C. The above-mentioned light sources are respectively strip light sources. Preferably, the above-mentioned light source is a laser light source. The above image acquisition device may be a camera. However, the present invention is not limited to this.

According to the embodiments shown in FIGS. 1 and 2 , the detected object 100 is exemplarily shown as being substantially plate-shaped, however, the detected object 100 may have various shapes. The plane on which the detected object 100 is located can be regarded as a virtual reference plane. The first left light source 10R and the second left light source 10G are arranged on the left side of the reference plane. The first left light source 10R and the second left light source 10G emit strip-shaped light to one side of the reference plane at predetermined first and second inclination angles with respect to a vertical plane perpendicular to the reference plane. The first inclination angle and the second inclination angle may be the same or different. Preferably, the first left light source 10R and the second left light source 10G emit light of different colors. In the first embodiment, the first left light source 10R emits red light, and the second left light source 10G emits green light. Preferably, the bar-shaped rays of the first and second left-hand light sources 10R and 10G are parallel to each other in the longitudinal direction, that is, when the bar-shaped rays of the first and second left-hand light sources 10R and 10G are emitted to the reference When flat, the bar light patterns are parallel or coincident. The left-side image pickup device 10C is arranged between the first left-side light source 10R and the second left-side light source 10G, and preferably at a central position therebetween. Preferably, the left-side image capturing device 10C acquires images facing the left side of the reference plane.

Preferably, the first left light source 10R, the second left light source 10G and the left image capturing device 10C are fixedly arranged on the left bracket. A temperature compensation unit is provided on the left bracket to eliminate errors caused by temperature during thickness measurement.

Similarly, the first right light source 20R and the second right light source 20G are arranged on the right side of the reference plane. The first right light source 20R and the second right light source 20G emit strip light to the other side of the reference plane at a predetermined third inclination angle and a fourth inclination angle with respect to the above-mentioned plane perpendicular to the reference plane, respectively. The intersection of the bar rays of the side light source 20R and the second right light source 20G is in the same plane as the intersection of the bar rays of the first left light source 10R and the second left light source 10G. Preferably, the predetermined inclination angles of the first right light source 20R and the second right light source 20G are the same as the first left light source 10R and the second left light source 10G. However, the present invention is not limited thereto, for example, the predetermined inclination angles of the first and second right light sources 20R and 20G may be different from those of the first and second left light sources 10R and 10G. Likewise, the third inclination angle and the fourth inclination angle may be the same or different, and the first right light source 20R and the second right light source 20G emit light of different colors. In the first embodiment, the first right light source 20R emits red light, and the second right light source 20G emits green light. Preferably, the strip light rays of the first right light source 20R and the second right light source 20G are parallel to each other in the longitudinal direction, and are in the longitudinal direction with the strip light rays of the first left light source 10R and the second left light source 10G Also parallel. The right-side image pickup device 20C is arranged between the first right-side light source 20R and the second right-side light source 20G, and preferably at a central position therebetween. Preferably, the right-side image capturing device 20C also acquires images directly facing the right side of the reference plane.

Preferably, the first right light source 20R, the second right light source 20G and the right image capturing device 20C are fixedly arranged on the right bracket. At this time, the distance between the left image capturing device 10C and the right image capturing device 20C is relatively fixed. A temperature compensation unit is also provided on the right bracket to eliminate errors caused by temperature during thickness measurement.

Referring to FIG. 1 , the intersection of the bar rays of the first left light source 10R and the second left light source 10G coincides with the intersection of the bar rays of the first right light source 20R and the second right light source 20G, that is, the first A left-side light source 10R and a second right-side light source 20G are arranged exactly opposite to each other, and the intersection of the second left-side light source 10G and the first right-side light source 20R are arranged exactly opposite. However, the present invention is not limited to this. For example, the intersection of the bar rays of the first left light source 10R and the second left light source 10G may be spaced apart from the intersection of the bar rays of the first right light source 20R and the second right light source 20G, as desired. The distance corresponding to the approximate thickness of the detected object.

Referring to FIG. 1 , the strip light emitted by the first left light source 10R and the second left light source 10G forms two strip patterns on the left surface _Sa of the detected object 100, and the two strip patterns are The distance between them is D _a . The strip light emitted by the first right light source 20R and the second right light source 20G forms two strip patterns on the right side surface S _b of the detected object 100 , and the distance between the two strip patterns is D _b . For example, FIG. 3 schematically shows a bar-shaped light pattern formed on the left side surface of the detected object. However, the present invention is not limited thereto, for example, the strip light source in the present application may be a multi-stripe light source.

Preferably, since the two light sources on the left and right sides in the present application emit strip light of different colors, the two strip patterns formed on the detected object are of different colors. The above-mentioned distances D _a and D _b can be accurately obtained by identifying patterns of different colors by the image processing unit. The positions of the different color patterns presented when the two bar-shaped ray patterns are formed before the intersection and after the intersection are different. For example, the position indicated by D _b2 shown in FIG. 6 is the ray pattern formed after the intersection, which is obviously different from the ray pattern formed before the intersection. In the present invention, light of different colors can be used to easily identify the difference of the above-mentioned distances.

FIG. 4 is a flow chart of a thickness measurement method according to the present invention. Hereinafter, the process of using the thickness measuring apparatus of the first embodiment of the present invention to measure the thickness of the detected object will be described with reference to FIG. 4 .

First, the detected object is moved into the detection area along the direction of the reference plane (S1). When an object is detected, the thickness measuring apparatus of the present invention starts detection (S2). At this time, the first left light source 10R and the second right light source 20G emit strip light toward one side of the detected object 100 , while the first right light source 20R and the second right light source 20G are directed toward the other side of the detected object 100 . One side emits a bar-shaped light, and the left image pickup device 10C and the right image pickup device 20C simultaneously capture images of the left and right surfaces of the detected object 100 (S3, S4). Preferably, the moving direction of the detected object 100 is perpendicular to the longitudinal direction of the bar light.

As the detected object moves, the left image pickup device 10C and the right image pickup device 20C capture images at predetermined time intervals, and transmit the acquired image data to the image processing unit (S5).

At the image processing unit, the data of the distance D _a on the left image and the data of the distance D _b on the right image are obtained according to the bar-shaped ray pattern on the left image and the right image, and the left image is divided according to time. The data of the side image and the right image are matched (S6).

Based on the matched data D _a and D _b of the left and right images, the image processing unit can calculate the thickness of the detected object at the corresponding position ( S7 ). In particular, the distances between the left and right image capture devices 10C, 20C and the corresponding bar-shaped ray intersections are specified, and the distance between the left image capture device 10C and the right image capture device 20C is specific. Therefore, according to the distance _Da obtained from the left image, the image processing unit can obtain the distance of the left surface of the detected object relative to the left image acquisition device 10C. Likewise, according to the distance D _b obtained from the right image, the image processing unit can obtain the distance of the right surface of the detected object relative to the right image acquisition device 20C. By removing the distances of the left and right surfaces of the detected object with respect to the left image pickup device 10C and the right image pickup device 20C from the distance between the left image pickup device 10C and the right image pickup device 20C, The thickness of the detected object at the predetermined position can be obtained.

When the detected object moves out of the detection area, the detection ends (S8).

5 is an oblique perspective view of a thickness measuring apparatus according to a second embodiment of the present invention. For the sake of convenience, reference numerals similar to those of the first embodiment are used in the second embodiment of the present invention for the same or equivalent components, and detailed descriptions thereof will be omitted.

The thickness measurement apparatus according to the second embodiment of the present invention may include a plurality of sets of thickness measurement sensors arranged in parallel. For example, FIG. 5 includes two groups of thickness measurement sensors, that is, the first group of thickness measurement sensors includes a first left light source 11R, a second left light source 11G, a left image acquisition device 11C, a first right light source 21R, The second right light source 21G and the right image capturing device 21C. The second group of thickness measurement sensors includes a first left light source 12R, a second left light source 12G, a left image capture device 12C, a first right light source 22R, a second right light source 22G, and a right image capture device 22C. However, the number of thickness measurement sensors may be more than two groups as required.

Similar to the first embodiment, the configurations of the first group of thickness measurement sensors and the second group of thickness measurement sensors are similar to the arrangement and type of the thickness measurement sensors in the first embodiment. Therefore, for the sake of simplicity, the specific configurations of the first group of thickness measurement sensors and the second group of thickness measurement sensors will not be described in detail.

Different from the first embodiment, since multiple sets of thickness measurement sensors are arranged side by side, when detecting a detection object with a larger width, a narrower strip light source can be used in a limited space to realize the thickness of the entire detection object. Measurement. Therefore, the structure of the thickness measurement sensor of the present invention can be made more compact.

6 is a schematic view of a thickness measuring apparatus according to a third embodiment of the present invention. The thickness measurement apparatus according to the third embodiment of the present invention may include a plurality of sets of thickness measurement sensors arranged at an angle to each other. For example, Figure 6 includes two sets of thickness measurement sensors arranged perpendicular to each other.

Referring to FIG. 6 , the detected object 100 has a vertically curved shape, that is, a horizontal portion and a vertical portion. The first group of thickness measurement sensors includes a first left light source 13R, a second left light source 13G, a left image capture device 13C, a first right light source 23R, a second right light source 23G, and a right image capture device 23C. The second group of thickness measurement sensors includes a first upper light source 24R, a second upper light source 24G, an upper image capture device 24C, a first lower light source 23R, a second lower light source 23G, and a lower image capture device 23C. The first group of thickness measurement sensors is used to measure the thickness of the vertical portion of the detected object 100 , and the second group of thickness measurement sensors is used to measure the thickness of the horizontal portion of the detected object 100 .

However, the number and arrangement of the thickness measurement sensors may be different depending on the shape of the detected object. For example, the thickness measurement sensors can be arrayed in different directions, so as to detect the thickness of the detected object in different directions and with different accuracy.

Since the plurality of sets of thickness measurement sensors are arranged at an angle, the present invention can easily detect the thickness of a detected object having a plurality of planes.

Although the present invention has been described in conjunction with the above-described embodiments, it is apparent that the scope of the present invention is not limited to the above-described embodiments. Certain components of the above-described embodiments of the invention can be recombined to form new embodiments. Accordingly, those skilled in the art will recognize that various modifications, additions and substitutions are possible, without departing from the spirit and scope of the invention as disclosed in the appended claims.

Claims (24)

1. A vision-based thickness measuring apparatus, comprising:

a thickness measuring sensor including two first bar-shaped light sources and one first image pickup device located at one side of a virtual reference plane, and two second bar-shaped light sources and one second image detection device located at an opposite side of the reference plane, wherein the two first bar-shaped light sources emit bar-shaped light to one side of the reference plane at predetermined first and second inclination angles with respect to a plane perpendicular to the reference plane, respectively, the two second bar-shaped light sources emit bar-shaped light to the other side of the reference plane at predetermined third and fourth inclination angles with respect to the plane perpendicular to the reference plane, the first image pickup device is located between the two first bar-shaped light sources to capture an image of one side of the reference plane, and the second image pickup device is located between the two second bar-shaped light sources to capture the image of one side of the reference plane An image of the other side of the face; and

an image processing unit which receives the images from the first image acquisition device and the second image acquisition device and obtains the thickness of the detected object according to the images,

when the detected object moves through the thickness measuring sensor along the direction of the reference plane, the strip light rays of the two first strip light sources form a first strip pattern on one side of the detected object, and the strip light rays of the two second strip light sources form a second strip pattern on the other side of the detected object;

wherein the image processing unit determines a first distance between the first image pickup device and the one side of the detected object and a second distance between the second image pickup device and the other side of the detected object from the first bar pattern and the second bar pattern, and obtains the thickness of the detected object by subtracting the first distance and the second distance from the distance between the first image pickup device and the second image pickup device.

2. The vision-based thickness measurement device of claim 1, wherein the first and second tilt angles are the same, and the third and fourth tilt angles are the same.

3. The vision-based thickness measurement apparatus of claim 1, wherein at least two of the first, second, third, and fourth tilt angles are different.

4. The vision-based thickness measurement apparatus of claim 1, wherein the first and second stripe light sources are multiple stripe light sources.

5. The vision-based thickness measurement apparatus according to claim 1, wherein a plurality of the thickness measurement sensors are provided, the plurality of thickness measurement sensors being arranged in parallel on both sides of the reference plane such that the emitted strip-shaped light rays of the plurality of thickness measurement sensors are parallel to each other.

6. The vision-based thickness measurement apparatus of claim 1, wherein a plurality of the thickness measurement sensors are provided, the plurality of thickness measurement sensors being arranged at an angle to each other such that the plurality of thickness measurement sensors can simultaneously detect the thickness of a plurality of surfaces of the inspected object.

7. The vision-based thickness measurement apparatus of claim 1, wherein a plurality of the thickness measurement sensors are provided, the plurality of thickness measurement sensors being arranged in a matrix form in a plurality of directions.

8. The vision-based thickness measurement device of any one of claims 1-7, wherein the two first bar light sources each emit light of a different color and the two second bar light sources each emit light of a different color.

9. The vision-based thickness measurement device of claim 8, wherein the intersection of the bar rays of the two first bar light sources coincides with the intersection of the bar rays of the two second bar light sources.

10. The vision-based thickness measurement apparatus of claim 8, wherein the intersection points of the bar light rays of the two first bar light sources and the intersection points of the bar light rays of the two second bar light sources are spaced apart from each other by a specified distance.

11. The vision-based thickness measurement device of any one of claims 1-7, wherein the thickness measurement sensor is mounted on a support and a temperature compensation unit is disposed on the support, wherein the image processing unit receives compensation values from the temperature compensation unit to determine the thickness of the inspected object.

12. The vision-based thickness measuring apparatus of any one of claims 1 to 7, wherein the first bar pattern includes two light patterns formed by the two first bar light sources, the second bar pattern includes two light patterns formed by the two second bar light sources, and the image processing unit determines a first distance between the first image capturing device and the one side of the detected object and a second distance between the second image capturing device and the other side of the detected object from a distance between the two light patterns of the first bar pattern and a distance between the two light patterns of the second bar pattern, respectively.

13. A vision-based thickness measurement method, comprising:

moving the detected object along a virtual reference plane;

emitting, with the movement of the detected object, a bar light toward one side of the detected object at predetermined first and second inclination angles with respect to a plane perpendicular to the reference plane using two first bar light sources located on one side of the reference plane, while emitting a bar light toward the other side of the detected object at predetermined third and fourth inclination angles with respect to the plane perpendicular to the reference plane using two second bar light sources located on the other side of the reference plane;

capturing a first bar pattern of one side of the detected object with a first image capturing device located at one side of the reference plane, and capturing a second bar pattern of the other side of the detected object with a second image capturing device located at the other side of the reference plane; and

and determining a first distance between the first image acquisition device and one side of the detected object and a second distance between the second image acquisition device and the other side of the detected object according to the first bar-shaped pattern and the second bar-shaped pattern, and obtaining the thickness of the detected object by subtracting the first distance and the second distance from the distance between the first image acquisition device and the second image acquisition device.

14. The vision-based thickness measurement method of claim 13, wherein the first and second tilt angles are the same, and the third and fourth tilt angles are the same.

15. The vision-based thickness measurement method of claim 13, wherein at least two of the first, second, third, and fourth tilt angles are different.

16. The vision-based thickness measurement apparatus of claim 13, wherein the first and second stripe light sources are multiple stripe light sources.

17. The vision-based thickness measurement method as claimed in claim 13, wherein a plurality of pairs of the two first bar light sources arranged in parallel are used to emit bar light toward one side of the inspected object, while a plurality of pairs of the two second bar light sources arranged in parallel are used to emit bar light toward the other side of the inspected object; and is

Capturing a first bar pattern of one side of the detected object with a plurality of the first image pickup devices corresponding to a plurality of pairs of the two first bar light sources arranged in parallel, and capturing a second bar pattern of the other side of the detected object with a plurality of the second image pickup devices corresponding to a plurality of pairs of the two second bar light sources arranged in parallel.

18. The vision-based thickness measurement method of claim 13, wherein a plurality of pairs of the two first bar light sources arranged at an angle are used to emit bar light rays toward a plurality of surfaces of the inspected object, and a plurality of pairs of the two second bar light sources arranged at an angle are used to emit bar light rays toward a plurality of opposite surfaces of the inspected object; and is

Capturing a first bar pattern of a plurality of surfaces of the inspected object with a plurality of the first image capturing devices corresponding to a plurality of pairs of the two first bar light sources arranged at an angle, and capturing a second bar pattern of a plurality of opposite surfaces of the inspected object with a plurality of the second image capturing devices corresponding to a plurality of pairs of the two second bar light sources arranged at an angle.

19. The vision-based thickness measurement method of any one of claims 13-18, wherein after capturing the first and second bar patterns, the first and second bar patterns are first matched as a function of time.

20. The vision-based thickness measurement method of any one of claims 13-18, wherein a first distance between the first image capture device and the one side of the inspected object and a second distance between the second image capture device and the other side of the inspected object are determined according to a distance between two light patterns of the first bar pattern and a distance between two light patterns of the second bar pattern.

21. The vision-based thickness measurement method of claim 20, wherein a database of correspondences between the first and second distances and the first and second bar patterns is pre-stored.

22. The vision-based thickness measurement method of any one of claims 13-18, wherein a compensation value is received from a temperature compensation unit to perform data compensation on the detected thickness of the inspected object.

23. The vision-based thickness measurement method of any one of claims 13-18, wherein the first image capture device and the second image capture device capture images at predetermined time intervals and transmit the acquired image data to an image processing unit.

24. The vision-based thickness measurement method of any one of claims 13-18, wherein the two first bar light sources each emit light of a different color and the two second bar light sources each emit light of a different color.

Images