JP3259624B2 - Surface condition inspection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a surface condition inspection apparatus, and more particularly to a method for irradiating a surface to be inspected with light, forming a light-receiving image from light reflected from the surface to be inspected, and inspecting the object to be inspected based on the light-receiving image. The present invention relates to a surface state inspection apparatus for performing an inspection such as a determination as to whether the surface state is good or bad.

[0002]

2. Description of the Related Art As a conventional surface condition inspection apparatus, there is one disclosed, for example, in Japanese Patent Application Laid-Open No. Hei 3-10150.
This involves irradiating the surface of a vehicle (body) conveyed in the painting process with light, and detecting defects (so-called dust spots) on the painted surface from an image obtained by capturing an image of the illumination area with an image sensor. Things. Specifically, when a vehicle is detected by the vehicle detection sensor, a predetermined defect detection process is started, and when the vehicle stops passing, the process ends.

[0003]

However, the conventional surface condition inspection apparatus requires a dedicated sensor for detecting the presence or absence of a vehicle as described above. In addition, since an image of a conveyed object surface is simply taken without distinction, when a plurality of image sensors are installed so as to image the entire surface of the vehicle, the inside of a tire house or a window ( Since the inside of the tire house is rough painted, spot detection is not required, and a portion that does not need to be inspected, such as the window portion being empty during painting), is imaged and processed, so that there is a problem in that there is much waste and inefficiency.

The present invention has been made to solve the above problems, and a first object of the present invention is to provide a surface condition inspection capable of detecting the presence or absence of an object to be inspected without requiring a dedicated sensor. A second object is to provide a surface condition inspection apparatus capable of performing a defect detection process only on a surface to be inspected (a portion to be inspected) of an object to be inspected.

[0005]

Means for Solving the Problems In order to achieve the above object, the present invention is configured as described in the claims. That is, according to the first aspect of the present invention, a conveyor for moving an object to be inspected, and an irradiation light that is arranged adjacent to the conveyor and irradiates the surface to be inspected with light having a predetermined light and dark pattern. Lighting means;
An imaging unit that creates a light-receiving image based on the reflected light from the inspection surface irradiated with the light from the illumination unit and outputs the image as an image signal, and detects a defect on the inspection surface based on the light-receiving image from the imaging unit. Surface condition inspection means to be detected, and a plurality of light reception images formed along the moving direction of the conveyor, which are predetermined based on the shape of the inspection object or the position of the inspection object projected on the light reception image. based on the luminance value and a recognition means for recognizing whether the inspected surface is present in the field of view of the imaging means, the surface shape
Condition test means, only when recognizing that the surface to be inspected is present, in the absence of the inspected object within the field of view of the detection processing line stomach, further the imaging unit of the defect of the inspection surface, within its field of view The imaging means and the lighting means are arranged in an arch shape above the conveyor so that light from the lighting means and others does not enter. As described above, in the present invention, it is configured to recognize the presence or absence of a surface to be inspected based on a luminance value of a predetermined location in a received light image obtained by using an illuminating unit and an imaging unit used for a defect detection process. Therefore, it is possible to recognize whether or not the surface to be inspected exists in the field of view of the imaging means without using a dedicated sensor.

Claims 2 and 3 show the detailed configuration of the recognizing means, and show a detection position of a luminance value used for recognition processing and a processing method therefor.

[0007]

According to the present invention, it is possible to recognize whether or not a surface is to be inspected without requiring a dedicated sensor for detecting the presence or absence of an object to be inspected, and it is possible to perform defect detection processing only on the surface to be inspected. The surface state can be inspected efficiently, and the cost can be reduced.

[0008]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the drawings. 1 to 3 are views showing an embodiment of the present invention. First, FIG. 1 is a block diagram showing a basic configuration of a surface condition inspection apparatus according to the present invention. In FIG. 1, reference numeral 1 denotes an illuminating device, which is arranged so as to irradiate the surface 3 to be inspected with light having a predetermined light and dark pattern. Reference numeral 2 denotes a video camera (for example, a CCD camera or the like), which is arranged to capture an image of the inspection target surface 3 on which the light and dark pattern is projected. The positions of the illumination device 1 and the video camera 2 are
Is arranged so that the light and dark pattern of the illumination device 1 is incident on the video camera 2 when the light exists, and when the surface 3 to be inspected does not exist, the light of the illumination device 1 is not incident on the video camera 2. ing. Reference numeral 4 denotes a camera control unit, which generates an image signal of a received image picked up by the video camera 2 and outputs the image signal to the image processing device 5. Reference numeral 6 denotes a host computer, which has a function of controlling the image processing apparatus 5 and displaying or outputting processing results to the outside. Reference numeral 7 denotes a monitor which displays a screen captured by the video camera 2 and the like. The illumination pattern of the illumination device 1 is, for example, a light and dark stripe (same as FIG. 4A described later) as shown on the monitor 7.

Next, FIG. 2 is a block diagram showing a configuration of the image processing apparatus 5. As shown in FIG. In FIG. 2, an image signal from the camera control unit 4 is converted into a digital value by an A / D converter 9 via a buffer amplifier 8. Further, an MPU (microprocessor) 10 performs a predetermined operation, processing, and the like on the image data. Reference numeral 11 denotes a memory for storing image data and processing results.
It can be output to the monitor 7 via the / A converter 12 and displayed.

Next, FIG. 3 is a perspective view showing an example in which the apparatus shown in FIG. 1 is applied to the inspection of a coating defect called "garbage spots" in a coating line of an automobile. In FIG. 3, the painted automobile body 14 flows along the paint inspection line in the direction of the arrow. On a part of the painted surface of this body 14,
The lighting device 1 and the video camera 2 are configured to project a predetermined light-dark pattern and to capture an image of a part where the light-dark pattern is projected.
Are arranged in a state of being fixed in an arch shape.
Therefore, while the body 14 moves on the painting inspection line by the conveyor 15 and passes under the video camera 2 arranged in an arch shape and under the stripe illumination, the surface 3 to be inspected 3
Is detected.

Next, the operation will be described. A received light image obtained by imaging the inspected surface 3 on which the light and dark stripes are projected is, for example, as shown in FIG. A / D conversion of the image signal from the video camera 2 to adjust the luminance level to 8 bi
When converted to a digital value of t, 255
Is white at the maximum value and 0 is black, and one screen is 512 × 480.
When the data is captured at the pixel resolution, the horizontal axis is 0 to 511.
And the number of pixels becomes as shown in FIG.

Here, as shown in FIG.
In 3 ', light is irregularly reflected due to the unevenness, so that the defect portion is reflected as a point (region) having a brightness different from the surroundings.
In other words, a dark point (defect 13) appears in a bright portion of a stripe, and a bright point (13 ') appears in a dark portion of a stripe. FIG. 4B shows a luminance (density) cross section of the defects 13 and 13 ′ (portion on the line marked with *).

The received light image shown in FIG. 4 is taken into the image processing device 5 as an original image S0, and an isolated point extraction process using, for example, a differentiation process is performed to perform a defect detection process. In addition,
The details of the defect detection processing are out of the scope of the present invention, and therefore will not be described. However, any defect detection processing including an illumination device and an imaging device can be generally combined with the present invention.

Next, a description will be given of a process of recognizing the presence or absence of a surface to be inspected, which is a feature of the present invention. FIG. 5 is a top view of the portion of the body 14 and the conveyor 15 in FIG. 3 (the lighting device 1, the video camera 2, and the like are omitted). Any one of the video cameras 2 for imaging the upper surface (roof, hood, etc.) of the body 14
Assuming that one field of view is in a range as shown by a hatched portion 16, the video camera 2 has a painted surface of the body 14 (the surface 3 to be inspected) and a floor or a window mounting portion (a black portion in the drawing, There is no glass during painting, it is hollow)
Of course, it is reflected. Such portions other than the painted surface are collectively referred to as "background". The recognition processing of the present invention is to automatically recognize (determine) the painted portion (the surface 3 to be inspected) and the background using the image obtained from the video camera 2.

[0015] As shown in FIG.
And moves in the direction of the arrow, the images of the video camera 2 having the field of view as described above are shown in FIGS. 6 (a), 6 (b) and 6 (c).
As shown in (2), first, the inspection target surface 3 is reflected from the background, and an image is formed in which the background is reflected again. The luminance cross section in the x direction (the line marked with * in the figure) of the image at this time is shown in FIG.
(B ′) and (c ′) are obtained. In FIG. 6, (a ′) is (a), (b ′) is (b), (c ′)
Respectively correspond to (c).

As described with reference to FIG. 1, the positions of the illumination device 1 and the video camera 2 are such that when the surface 3 to be inspected is present, the light / dark pattern of the illumination device 1 is incident on the video camera 2;
When there is no surface 3 to be inspected, the light of the illumination device 1 is not incident on the video camera 2. Therefore, the background luminance value Y _B in (a portion which is not the inspected surface 3) is almost 0, because the illumination light stripe pattern at the point with the inspected surface 3 is irradiated, the luminance value in the stripe light portion Y _{SH has} a luminance value Y _{SL in} a stripe dark portion. Therefore, if there is an area having a luminance value higher than the luminance value Y _B in the background in the image, it is determined that the body 14 is within the field of view of the video camera 2 and that the inspected surface 3 is imaged ( Recognition).

Next, details of the recognition processing will be described.
First, the first method will be described. In the case of the field of view of the video camera 2 shown by oblique lines in FIG. 5, the received light image is such that the body 14 appears from the right end of the screen as shown in FIG. 6, the body is reflected on the entire screen, and passes to the left end of the screen. Reflected.
In such a case, the presence or absence of the body may be recognized from the luminance value of the entire screen (512 × 480 pixels).
As shown in the figure, using the brightness value of an arbitrary part (hereinafter referred to as a point: ● mark in the figure) that divides the screen equally as the representative value of the image, and recognizing the presence or absence of the body, the processing time is better. Short and efficient. For example, the maximum value Y _MAX of the luminance value Y at the point in the image is obtained, and if the value is larger than the reference value Y _REF , it can be determined that “there is a body (the surface to be inspected 3)”. If the reference value Y _REF is, for example, a value such as (Y _SL + Y _B ) / 2 in FIG. 6A, the background and the body can be reliably separated and recognized.

However, even when only the background appears in the field of view of the video camera 2, a point having a large luminance value may exist due to noise or some other cause. May be mistakenly recognized. In such a case, if the maximum value Y _MAX itself is not used, and either the second value from the maximum value Y _MAX or the value calculated from the luminance value such as the third value or the average value is used, erroneous recognition is performed. Can be prevented. However, it is possible to recognize in a short time after entering the body into the field of view of the video camera 2 as used value close to the maximum value Y _MAX. Therefore, as the value of the luminance value Y and the value of the reference value Y _REF at the point used for the determination, optimal values are experimentally selected in advance.

Next, as a second method of the recognition processing, FIG.
The presence or absence of a body can be recognized based on the number of points equal to or greater than a predetermined value among the luminance values of the points in the image. For example, the predetermined value is set as a reference value Y _REF, and if the number of points N of the luminance value equal to or more than Y _REF is larger than a preset value N _REF , it is determined that “there is a body”. The reference value Y _REF and the value N _REF may be determined in advance through experiments or the like.

Next, a third method of the recognition processing will be described.
This method divides a plurality of points in an image into several regions (groups), calculates a maximum value or the like from a luminance value for each group, and recognizes the presence or absence of a body based on the value. is there. For example, in FIG. 8, one column in the x direction is divided into three groups as one group, and the maximum luminance values Y _MAX 1, Y _MAX 2, and Y _MAX in each group.
_MAX3 is calculated and compared with the reference value _YREF . Then, the number of groups having the maximum value Y _MAX larger than the reference value Y _REF is
If it is larger than a predetermined number G _REF , it is determined that “there is a body”.

Next, a fourth method of the recognition processing will be described. In this method, a plurality of points in an image are divided into several regions (groups), and the brightness value and a reference value Y _{REF are obtained.}
Is compared with the reference value Y _REF in each group.
The number of groups in which a luminance value greater than
If there is more than _REF, it is determined that "there is a body". In this method, since the calculated value such as the maximum value is not used, the processing speed is faster than the first to third methods. However, although the influence of noise and the like increases, the reduction of the recognition ability can be prevented by adjusting the number and position of the groups and points.

Next, a fifth method of the recognition processing will be described. This method uses a video camera 2 as shown in FIG.
This is a recognition method in a case where only a part of the body is reflected in the field of view, and the background and the inspected surface 3 are reflected together at the same position on the x-axis. As shown in FIGS. 9A, 9B, and 9C, when the body passes through the lower side of the screen, the point at which the luminance value is read is set as shown in FIG. 9D. By arranging it on the lower side of the screen, recognition processing can be performed in the same manner as in the first to fourth methods.

Next, a sixth method of the recognition processing will be described. When an image of a pillar portion narrower than the visual field is taken in the visual field (hatched portion 17) of the video camera 2 as shown in FIG. 10C, an image as shown in FIG. 10A is obtained.
In order to recognize a portion narrower than such a visual field, if the luminance value reading point is set according to the shape of the inspected object as shown in FIG. it can. Note that in FIG.
8 is a cart.

Next, a seventh method of the recognition processing will be described. This method is a processing method when two video cameras are installed at opposing positions. FIG. 11 is a schematic top view of the apparatus of FIG. The body 14 is within the field of view of the two video cameras 2, 2 'installed at opposing positions.
In the case where there is a virtual image of the illuminating devices 1 and 1 ′ reflected on the surface 3 to be inspected, the visual fields of the video cameras 2 and 2 ′ are as shown by solid lines in the figure. If there is no body 14,
The visual fields of the video cameras 2 and 2 ′ are as indicated by dotted lines, and the background is imaged. In the present invention, since the presence or absence of a body is recognized using the luminance value of the received light image, when the body 14 is not shown in the field of view of the video camera 2, the luminance value of the luminance value not illuminated to the lighting device is It is desirable to have a low background. Therefore, as shown in the figure, when the illuminating devices 1, 1 'and the video cameras 2, 2' on both sides of the body 14 face each other, the arrangement is such that the illumination of each video camera does not appear in the field of view of each video camera (for example, (The angle shown in FIG. 11). That is, when the body 14 is not in the field of view of the video cameras 2 and 2 ', the video cameras 2 and 2' and the lighting apparatus 1,
Set the position of 1 '.

The presence or absence of the surface to be inspected can be detected by various methods as described above. However, the image processing apparatus 5 shown in FIG. The above defect detection processing is performed. With this configuration, the defect detection processing is performed only when there is a surface to be inspected, so that the inspection can be performed efficiently without wasteful processing.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a basic configuration of a surface condition inspection apparatus according to the present invention.

FIG. 2 is a block diagram showing a configuration of an image processing apparatus 5.

FIG. 3 is a perspective view showing an example in which the apparatus of FIG. 1 is applied to the inspection of a coating defect in a coating line of an automobile.

FIG. 4 is a diagram showing an example of a light-receiving image and an image signal obtained by imaging a surface to be inspected on which light and dark stripes are projected.

FIG. 5 is a top view of a body 14 and a conveyor 15 in FIG.

FIG. 6 is a diagram showing an example of a received light image and an image signal in FIG. 3;

FIG. 7 is a view showing an example of points at which a screen is equally divided as points for performing determination for recognizing the presence or absence of a body.

FIG. 8 is a diagram showing an example of positions of other points obtained by dividing the screen.

FIG. 9 is a diagram showing an example of a point position in a case where a background and a surface to be inspected appear together in a visual field of a video camera.

FIG. 10 is a view showing an example of a point position for recognizing a portion narrower than the field of view of the video camera and a side surface of the body.

FIG. 11 is a schematic top view of the apparatus showing an arrangement in a case where two video cameras are installed at opposing positions.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Illumination device 2 ... Video camera 3 ... Surface to be inspected (painted surface) 4 ... Camera control unit 5 ... Image processing device 6 ... Host computer 7 ... Monitor 8 ... Buffer amplifier 9 ... A / D converter 10 ... MPU 11 ... Memory 12 ... D / A converter 13, 13 '... Defect 14 ... Body 15 ... Conveyor 16, 17 ... Video camera field of view 18 ... Dolly

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Chinori Norimune 2 Takaracho, Kanagawa-ku, Yokohama, Kanagawa Prefecture Nissan Motor Co., Ltd. (56) References JP-A-5-60514 (JP, A) (58) Field surveyed (Int.Cl. ⁷ , DB name) G01N 21/84-21/958 G01B 11/00-11/30 G06T 1/00-9/40

Claims (3)

(57) [Claims] 1. A conveyor for moving an object to be inspected, and a predetermined light disposed on the conveyor and adjacent to the conveyor.
Illumination that irradiates irradiation light like irradiating dark pattern light
Means, and reflection from the surface to be inspected irradiated with light from the illumination means
Creates a received light image with light and outputs it as an image signal
Imaging means; and a defect on the surface to be inspected based on a light reception image from the imaging means.
Surface condition inspection to detect defectsmeansAnd the shape of the object to be inspected or projected on the received light image
Predetermined based on the position of the object to be inspected,
Light reception at multiple locations formed along the direction of conveyor movement
Inspection within the visual field of the imaging means based on the brightness value of the image
A recognition means for recognizing whether or not a surface exists;With The above surface condition inspection means, Recognizes that the surface to be inspected exists
Only when a defect is detected on the surface to be inspected.I further When there is no object to be inspected in the field of view of the imaging means
In the field of view, light from the illumination means and others
In order not to enter, the imaging means and the illumination means
Characterized by being arranged in an arch above the conveyor.tableSurface condition inspection device. 2. The apparatus according to claim 1, wherein said recognition means recognizes the presence or absence of a surface to be inspected based on a result of comparing a luminance value at a plurality of predetermined positions of the received light image or a value calculated from these luminance values with a preset value. The surface condition inspection apparatus according to claim 1, wherein: 3. The recognizing means divides a plurality of predetermined portions of the received light image into predetermined ranges, and based on a result of comparing a predetermined value with a luminance value or a value calculated from the luminance value in each range. 2. The surface condition inspection apparatus according to claim 1, wherein the presence or absence of the surface to be inspected is recognized.