KR101136388B1 - A Device For Inspecting Automobile Parts Using Vision System - Google Patents

Abstract

The present invention relates to an apparatus for inspecting automobile parts using a vision system, comprising: a nut supply pipe to which a nut is supplied; Nut drawer; Welding means for welding the drawn nut to an automobile part; An input unit for receiving an input of a part model name, an operator ID, and a work order from an operator; At least one light source for irradiating light and a photographing means for photographing the automotive parts, the light detecting unit for photographing the welding position of the automotive parts when the nut is introduced by the nut inserter, or the welding means completes the welding operation; A histogram generator that generates a histogram by counting the number of pixel levels of the photographed image, and when the histogram is biased in the brightness region of a specific part of the photographed image, according to a comparison result between the preset reference value and the extracted distribution value. An image correction unit including a histogram stretching unit which expands the histogram of the gray scale value distribution of the photographed image to have an expanded gray scale value distribution; Receive the captured image and compare the coordinate value of the captured image or the image corrected by histogram stretching after shooting with the image coordinate value of the quality screen of the inspection subject corresponding to the input part model and work order. A control unit for discriminating; And a display means for outputting a photographed image of the object and related information on a screen, and the control unit is configured to perform the histogram stretching when the histogram is biased in a brightness region of a specific portion of the image photographing the inlet state of the nut. After the completion of the irradiation of light to the welding point characterized in that it can be controlled to adjust the amount of light to be irradiated according to the bias of the histogram.

 Vision inspection system, image correction, histogram stretching

Description

A Part For Inspecting Automobile Parts Using Vision System

The present invention relates to an apparatus for inspecting automobile parts using a vision system, and more particularly, productivity can be improved by eliminating an inspection process by inspecting a nut's drawn state and weld state using a vision system in real time during assembly work. If the image captured using the vision system cannot be determined due to light saturation or light deficiency, the histogram of the captured image can be analyzed and the image can be corrected by stretching the histogram. The present invention relates to an inspection apparatus capable of preventing light saturation or light deficiency of an image by adjusting the amount of light to be irradiated according to the histogram's bias.

In general, more than 20,000 parts need to be assembled to make a car, and if the parts are large, it is easy to see if they are missing, but missing very small parts such as nuts.

In addition, products with a large number of holes add fatigue to the operator's eyes when they are visually inspected. Therefore, it is very difficult to find defects in a continuous operation. Missing parts can lead to serious accidents.

In order to solve the above problems, conventionally, after inspecting whether a vehicle part is defective by using a separate inspection jig for each part after producing parts, the defect rate is reduced by introducing an inspection apparatus using a separate jig. All the accessories cannot be inspected by using the product, and the production time is increased due to the addition of an inspection process.

In addition, in the case of the inspection apparatus using a conventional vision system, there is a problem in that the image taken due to light saturation or light saturation due to light reflection is impossible to compare, and it is difficult to determine the welding position only by comparing the shapes. As a result, the more the number of holes in a part, the more the inspection time increases.

The present invention has been made to solve the above problems, the object of the present invention is to check the incoming state and weld state of the nut in real time during the assembly operation by using a vision system to omit the inspection process can be improved productivity If the image captured using the vision system cannot be determined due to light saturation or light deficiency, the histogram of the captured image can be analyzed and the image can be corrected by stretching the histogram. The present invention provides an apparatus for accurately and quickly inspecting the nut insertion state and welding state of automobile parts by adjusting the amount of light to be irradiated according to the histogram's bias during the shooting to prevent light saturation or light shortage of the image.

The present invention for achieving the above object, the nut supply pipe is supplied with a nut; A nut drawer connected to the nut supply pipe and configured to seat the supplied nut at a welding position on an automobile part; Welding means for welding the drawn nut to the automobile part; An input unit for receiving an input of a part model name, an operator ID, and a work order from an operator; At least one light source for irradiating light and a photographing means for photographing the automotive parts, the light detecting unit for photographing the welding position of the automotive parts when the nut is introduced by the nut inserter, or the welding means completes the welding operation Wow; A result of comparing a histogram generator that generates a histogram by calculating the number of each pixel level of the photographed image and a preset reference value and a extracted distribution value when the histogram is biased in a brightness region of a specific portion of the photographed image An image correction unit including a histogram stretching unit which expands the histogram of the gray scale value distribution of the photographed image to have an expanded gray scale value distribution; Receiving the photographed image, and comparing the coordinate value of the photographed image or the image corrected by the histogram stretching after the photographing and the image coordinate value of the good photographing screen of the inspection subject corresponding to the input part model and the work order A control unit for determining whether or not a defect; And a display means for outputting the photographed image and related information of the object to the screen, wherein the controller is configured to perform histogram stretching when the histogram is biased in the brightness region of a specific portion of the image photographing the inlet state of the nut. After the welding operation is completed, it is possible to control to adjust the amount of light to be irradiated according to the bias of the histogram when irradiating light to the welding point.

In addition, the light source is preferably a plurality of LEDs having a light emitting color of R, G, B is arranged in a predetermined manner, it is characterized in that the LED array which can adjust the illumination of each LED.

In addition, the light source is a plurality of LEDs having a light emitting color of R, G, B is arranged in a predetermined manner, and the LED array that can adjust the light emission color of each LED so that the contrast of the color and contrast of the car parts and nuts to be photographed It is preferable to characterize.

According to the present invention as described above, it is possible to omit the inspection process by inspecting the inlet state and welding state of the nut in real time during the assembly operation using the vision system to improve the productivity, inspection of all parts with one vision inspection equipment This eliminates the need for a separate inspection jig when adding parts.

In addition, if the captured image cannot be judged as defective due to light saturation or light deficiency, the histogram of the captured image can be analyzed and the histogram can be corrected by stretching the histogram. By controlling the amount of light to be irradiated according to the bias of the has the advantage of preventing light saturation or light shortage of the image.

In addition, there is an advantage to reduce the defective rate by controlling the welder when the nut is poorly inserted, and there is an advantage of preventing the omission by checking the type and quantity of nuts by model as well as the badness of the nut introduced state. .

Hereinafter, with reference to the accompanying drawings will be described in detail a preferred embodiment of the present invention.

1 is a schematic diagram of a vehicle parts inspection device using the vision system of the present invention.

An automobile parts inspection apparatus using the vision system of the present invention includes a nut supply pipe 10 to which a nut is supplied as shown in FIG. 1; A nut introducer 20 for seating the supplied nut at the welding position 101 on the vehicle part 100; Welding means (30) for welding the drawn nut to the automobile part (100); An input unit 40 for receiving an input of a part model name, an operator ID, and a work order from an operator; A photodetector 50 including at least one light source 51 for irradiating light and a photographing means 52 for photographing automobile parts; A histogram generating unit 61 for generating a histogram of the captured image and a histogram stretching unit 62 for making the photographed image have an expanded gray scale value distribution when the histogram is biased in a brightness region of a specific portion. An image compensator 60 comprising; Receiving the photographed image, and comparing the coordinate value of the photographed image or the image corrected by the histogram stretching after the photographing and the image coordinate value of the good photographing screen of the inspection subject corresponding to the input part model and the work order A control unit 70 for determining whether there is a defect; And display means (80) for outputting the captured image and the related information of the object on the screen.

The nut supply pipe 10 serves to supply a nut, and the nut introducer 20 is connected to the nut supply pipe, and serves to seat the supplied nut at a welding position on an automobile part.

Welding means 30 serves to weld the drawn nut to the vehicle parts.

The input unit 40 serves to receive an input of a part model name, an operator ID, and a work order from an operator.

The light detector 50 includes one or more light sources 51 for irradiating light and photographing means 52 for photographing automobile parts, and the nut is inserted by the nut introducer 20 or the welding means ( 30) When the welding operation is completed, the welding position of the vehicle parts is photographed.

A fluorescent lamp or an infrared lamp may be used as the light source 51 for irradiating the light, and a CCD camera or an IR camera may be used as the photographing means 52.

The image compensator 60 is composed of a histogram generator 61 and a histogram stretcher 62 which redistributes pixels of image data to improve contrast characteristics.

The histogram generator 61 generates a histogram by calculating the number for each pixel level of the image. The histogram refers to displaying the number of pixels corresponding to the brightness value of each gray scale pixel in the image in a form of a function. The function can be expressed as h (g) = Ng, where g is the brightness value of the gray scale pixel, Ng is the number of pixels corresponding to the gray scale, and the range that g can have is 0 to 255. (The brightness value of the gray scale pixel). In this case, since the result value of the function may become larger or smaller depending on the image size, Ng is divided by the total number of pixels of the image and normalized, and then represented as a histogram. In this case, the histogram may also be expressed as a concept of the probability of generating the brightness value of such gray scale pixels, and may be expressed as in the following equation. p (g) = Ng / M where M is the total number of pixels of the projection, and p is the probability. The normalized histogram formula satisfies 1 when the function value of the brightness values of all gray scale pixels is added. The histogram can extract the maximum frequency value and the average value from the information about the gradations distributed throughout the digital image data through the calculation of discrete functions.

The histogram stretching unit 62 expands the histogram of the gray scale value distribution of the photographed image according to a comparison result of a preset reference value and the extracted distribution value when the histogram is biased in the brightness region of the specific portion of the photographed image. It has an expanded gray scale value distribution.

The reference value may be arbitrarily set according to the resolution, and the histogram stretching operation is a method of multiplying or dividing all pixel values by a constant value. The stretching method of the histogram is to stretch the brightness value of the input image data, and to expand the histogram on one side to all regions.

New pixel value = old pixel value-minimum pixel value / maximum pixel value-minimum pixel value * 255

In the above equation, subtracting the minimum pixel value is sliding the histogram to the left, and then each pixel value is stretched such that the maximum pixel value is 255 and the minimum pixel value is zero. Such sliding calculation and stretching method may use any one or more calculation methods.

The controller 70 receives the photographed image, coordinates of the photographed image or the image corrected by the histogram stretching after the photographing, and the image of the quality photographing screen of the inspection subject corresponding to the input part model and the work order. Compare the coordinates to determine if there is any defect. When power is supplied to the light source 51 to generate light of a constant illuminance, the photographing means 52 photographs the inspection object to generate an image. At this time, the general plane of the inspection object appears brightly by reflecting light, and in the case of the hole or nut side formed in the automotive part 100, the light is not reflected, and the black surface is slightly darkened. The contrast is different. The image photographed by the photographing means is transmitted to the controller, and the coordinate values of the photographed image of the good quality preset by the controller and the image transmitted from the photographing means are compared and it is determined whether the contrast is consistent. That is, the positions of the plurality of holes required for the automobile part 100 are defined by the X-axis and Y-axis values, and the value of the intensity corresponding to each position in the good-quality photographed image is numerically calculated and the image transmitted from the photographing means 52. Compares the value indicating the intensity of the contrast at the X and Y axis positions of the hole, and checks whether the intensity is consistent or not. Flipping, poor entry, missing)).

In addition, when the histogram is stretched because the histogram is biased in the brightness region of a specific portion of the image taken in the nut, the irradiation is performed according to the bias of the histogram when irradiating light to the welding point after completion of the welding operation. It controls the amount of light to be controlled.

As described above, the histogram is a bar graph that counts the number of pixels corresponding to each contrast value from 0 to 255. As the brightness value approaches 0, a dark image appears, and the brightness value approaches 255. The brighter picture will appear. Therefore, when the previously photographed image is concentrated at a value close to 0 or 255, the brightness of the light source 51 is adjusted to compare the image coordinate values because the contrast cannot be distinguished due to light saturation or lack of light. Prevent it from going away. As the brightness value of the histogram approaches 0 by the preset ratio, the light of the light source 51 is brightly adjusted. As the brightness value approaches 255, the light of the light source 51 is brightly adjusted.

The display means 80 outputs the screen of the determination result whether the inspection object is defective or the photographed image of the object with information such as an inspection date and time, a product number, and the like.

The light source 51 is a plurality of LEDs having a light emitting color of R, G, B is disposed in a predetermined manner, it is preferable that the LED array is capable of adjusting the illumination of each LED.

In addition, the light source 51 is a plurality of LEDs having a light emitting color of R, G, B is arranged in a predetermined manner, and the light emitting color of the LED can be adjusted so that the contrast between the color and contrast of the car parts and nuts to be photographed It is preferable that it is an array.

Unlike conventional fluorescent lamps or infrared lamps, the LED array can adjust the illuminance of the light and the color of the emitted light, thereby improving accuracy in determining whether the parts are drawn or welded.

That is, for example, when determining whether the nut is in poor condition, the illumination value of the LED array is increased by adjusting the illuminance so as not to reflect light, so that the side portion of the nut which is darker than the general plane is more highlighted and welded. In determining whether a spot is defective, a weld point that is relatively brighter than that of a side part may be more highlighted by reducing the illumination value of the LED array.

The illumination control may also be suitably adopted according to the inspection object for determining the light emission illumination by adjusting the light output and may be manually controlled.

In addition, each of the R, G, B LEDs of the LED array is to control the light output according to the emission color control, this method allows to adopt the optimal screening light color according to the screening target.

The color setting of the emission color control may be manually controlled by the user like the illumination control, and for this purpose, a separate operation unit may be further provided.

The operation of the vehicle parts inspection device using the vision system of the present invention having the configuration as described above will be described.

Auto parts inspection method using a vision system, first, if the operator receives the car parts model name, the operator ID and one or more welding points to the input unit 10 (S100). The input information is categorized and stored for each part model name and worker ID so that the categorized information can be easily retrieved by inputting a worker ID or inputting a part model name for the next work.

When the automotive part is placed on the workbench after the input step (S100), the nut is supplied to the nut introducer 30 through the nut supply pipe 20, and when the supplied nut is drawn into the welding position on the automotive part 100, (S110) The light is irradiated to the place where the nut is inserted to photograph the state of the nut on the vehicle parts (S120).

The histogram generator 61 generates a histogram by calculating the number of the pixel levels of the image in the histogram generator 61 (S130).

When the histogram is biased in the brightness region of the specific part, the histogram stretching unit 62 expands and expands the histogram of the gray scale value distribution of the photographed image according to a comparison result of the preset reference value and the extracted distribution value. The histogram stretching is performed to have a gray scale value distribution (S150).

The controller 70 compares the coordinate values of the photographed image or the image corrected by the histogram stretching after the photographing with the image coordinate values of the good photographing screen of the inspection subject corresponding to the input part model and the work order. It is determined whether the state is bad (S160). When it is determined that the nut pulled-in state is good, it outputs a control signal to the welding means 30 to weld the drawn nut and the component (S170). When the histogram stretches the image photographed by the histogram stretching unit 62, a control signal is output to adjust an amount of light to be irradiated according to the histogram's bias.

The light source 51 receiving the control signal irradiates the light adjusted appropriately to the welding spot to which the automobile part and the nut are welded, and the photographing unit 52 photographs the welding spot (S190).

The controller 70 compares the coordinate values of the photographed image with the image coordinate values of the good photographing screen of the inspection target corresponding to the input part model and the work order to determine whether welding is defective (S200).

The determination result of the defect is output through the display unit 80 (S210).

1 is a schematic diagram of a vehicle parts inspection device using a vision system according to an embodiment of the present invention.

2 is a graph showing a histogram and a stretched histogram of an input image according to an exemplary embodiment of the present invention.

Figure 3 is a flow chart showing the inspection process of the vehicle parts inspection device using a vision system according to an embodiment of the present invention.

<Description of main drawing code>

10: nut supply pipe 20: nut inlet

30: welding means 40: input means

50: light detector 51: light source

52: recording means 60: video compensation

61: histogram generating unit 62: histogram stretching unit

70: control unit 80: display unit

Claims (3)

In the inspection device for inspecting the defect of the automotive parts using the vision system, A nut supply pipe to which the nut is supplied; A nut drawer connected to the nut supply pipe and configured to seat the supplied nut at a welding position on an automobile part; Welding means for welding the drawn nut to the automobile part; An input unit for receiving an input of a part model name, an operator ID, and a work order from an operator; At least one light source for irradiating light and a photographing means for photographing the automotive parts, the light detecting unit for photographing the welding position of the automotive parts when the nut is introduced by the nut inserter, or the welding means completes the welding operation Wow; A result of comparing a histogram generator that generates a histogram by calculating the number of each pixel level of the photographed image and a preset reference value and a extracted distribution value when the histogram is biased in a brightness region of a specific portion of the photographed image An image correction unit including a histogram stretching unit which expands the histogram of the gray scale value distribution of the photographed image to have an expanded gray scale value distribution; Receiving the photographed image, and comparing the coordinate value of the photographed image or the image corrected by the histogram stretching after the photographing and the image coordinate value of the good photographing screen of the inspection subject corresponding to the input part model and the work order A control unit for determining whether or not a defect; Display means for outputting the photographed image and the related information generated by the light detector on the screen, When the histogram is stretched because the histogram is biased in the brightness region of a specific part of the image photographing the inlet state of the nut, the control unit according to the bias of the histogram when irradiating light to the welding point after completion of the welding operation Auto parts inspection device using a vision system, characterized in that it can be controlled to adjust the amount of light to be irradiated. The method of claim 1, The light source is a plurality of LEDs having a light emitting color of R, G, B is arranged in a predetermined manner, the automotive parts inspection device using a vision system, characterized in that the LED array capable of adjusting the illumination of each LED. The method of claim 1, The light source is a plurality of LEDs having a light emitting color of R, G, B is arranged in a predetermined manner, characterized in that the LED array capable of adjusting the light emission color of each LED so that the contrast of the color and contrast of the car parts and nuts to be photographed Automotive parts inspection device using a vision system.

Images