JP2012101874A - Outline detection system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect the outline of an object carried by carrying devices in a predetermined direction.SOLUTION: The outline detection system includes: a first carrying device 110 configured to carry the object M in the predetermined direction D; a second carrying device 120 arranged at a distance from the installation position of the first carrying device 110 in the predetermined direction D, and configured to receive the object M carried by the first carrying device 110 and carry the object M in the predetermined direction D; a plate body 130 arranged between the first and second carrying devices 110 and 120, and located lower than the carrying surface of each of the first and second carrying devices 110 and 120, and having a pattern of stripes arranged in a direction perpendicular to the predetermined direction D provided on the top surface thereof; an imaging device 140 provided above the plate body 130, and located higher than the carrying surface of each of the first and second carrying devices 110 and 120, and configured to image an imaging area extending in the direction perpendicular to the predetermined direction D; and an outline detection device 200 configured to detect the outline of the object M based on image data imaged by the imaging device 140.

Description

  The present invention relates to an outer shape detection system. In particular, the present invention relates to an outer shape detection system that detects the outer shape of an object conveyed in a predetermined direction by a conveying device.

  In a general method for detecting the outer shape of an object, after performing edge enhancement using a density difference such as a Sobel filter on a grayscale image obtained by imaging the object, the object is subjected to image processing such as binarization. Detect object edges. However, such a method is not effective when there is no difference in color between the object and the background, because the boundary between the object and the background cannot be identified in a monochrome binary image.

  FIG. 8 shows an example of a monochrome binary image captured by a known technique. In the case of the example shown in FIG. 8A, the difference between the color of the object and the background is large, and therefore the boundary between the object and the background can be easily detected by image processing. On the other hand, in the example shown in FIGS. 8B and 8C, the difference between the color of the object and the background is small, so that the boundary between the object and the background can be detected by image processing. difficult.

  As a method for solving such a problem, there is a method of detecting the edge of the object by creating a density difference between the object and the background by irradiating light from below the object. Although this method has the feature that it is not affected by the concentration of the object, it is necessary to install an optical system device such as illumination from the back, and such changes are often difficult to apply to existing devices. Even when applied to a newly developed device, the cost has been increased.

  In addition, as a method of optically detecting the presence / absence, position, and shape of an object, a striped pattern consisting of portions having different reflectances is positioned on the background of the object, and a light spot is scanned in a direction intersecting with the stripe, A technique for alternately detecting the presence / absence, position, and shape of an object based on the level change of the reflected light is known (for example, see Patent Document 1).

JP-A-61-272680

  According to the technique described in Patent Document 1, since a light spot is projected and scanned on an object with a background member such as a dish on the back, the presence or absence of the reflected light level can be detected based on whether the change in the reflected light level is regular or not. .

  However, in the technique described in Patent Document 1, if the plate is placed on a conveyor and moved in a direction parallel to the stripes, sub-scanning is performed in the moving direction. The outline of the object cannot be accurately detected unless the moving speed of the object by the conveyor is reduced. Therefore, in the technique described in Patent Literature 1, if the outer shape of the object is detected with high accuracy, the conveyance efficiency of the object is deteriorated.

  In order to solve the above-described problem, according to a first aspect of the present invention, there is provided an outer shape detection system for detecting an outer shape of an object conveyed in a predetermined direction by a conveying device, wherein the object is conveyed in a predetermined direction. 1st conveying apparatus and the 2nd conveying apparatus which is arrange | positioned at intervals in the predetermined direction rather than the installation position of the 1st conveying apparatus, and the target object conveyed by the 1st conveying apparatus is delivered and conveyed in a predetermined direction And between the first transport device and the second transport device, a striped pattern arranged at a position lower than the transport surfaces of the first transport device and the second transport device and arranged in a direction orthogonal to a predetermined direction is an upper surface. And an image pickup region that is disposed at a position higher than the transfer surfaces of the first transfer device and the second transfer device and extends in a direction orthogonal to a predetermined direction above the plate body. Device and images captured by the imaging device Based on over data, and a contour detecting unit that detects a contour of the object.

  In addition, as described above, the summary of the invention does not enumerate all necessary features of the present invention, and sub-combinations of these feature groups can also be the invention.

  As is clear from the above description, in the present invention, in the process of transporting the object, a plate body having a striped pattern provided on the upper surface is installed below the object, and the transport direction of the object from above is set. By adopting an inexpensive method of imaging an orthogonal imaging region, the outer shape of the object imaged by the imaging device can be detected regardless of the color density of the object.

It is a figure which shows an example of the utilization environment of the external shape detection system 100 which concerns on one Embodiment. It is a figure which shows an example of the block configuration of the external shape detection apparatus. It is a figure which shows an example of the monochrome binary image which the image generation part 210 produces | generates. It is a figure which shows an example of the operation | movement flow of the external shape detection apparatus. It is a figure which shows an example of the operation | movement flow of the external shape detection apparatus. It is a figure which shows an example of the operation | movement flow of the external shape detection apparatus. It is a figure which shows an example of the operation | movement flow of the external shape detection apparatus. It is a figure which shows an example of the monochrome binary image imaged with the known technique.

  Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the scope of claims, and are combinations of features described in the embodiments. Not all are essential to the solution of the invention.

  FIG. 1 shows an example of a usage environment of an outline detection system 100 according to an embodiment. The outer shape detection system 100 detects the outer shape of the postal matter M conveyed in the predetermined direction D by the belt conveyor. The belt conveyor may be an example of the “conveying device” in the present invention. The mail M may be an example of the “object” in the present invention.

  The contour detection system 100 includes a belt conveyor 110, a belt conveyor 120, a plate body 130, a line imaging device 140, and a contour detection device 200. The line imaging device 140 and the outer shape detection device 200 are electrically connected. The belt conveyor 110 may be an example of the “first transport device” in the present invention. The belt conveyor 120 may be an example of the “second transport device” in the present invention. The line imaging device 140 may be an example of the “imaging device” in the present invention.

  The belt conveyor 110 conveys the postal matter M in the predetermined direction D. Specifically, the belt conveyor 110 rotates a wide belt 111 in a ring shape by a roller 112 and moves the mail M on the belt 111.

  The belt conveyor 120 is arranged at a distance from the belt conveyor 110 in the predetermined direction D. The belt conveyor 120 receives the postal matter M conveyed by the belt conveyor 110 and conveys it in the predetermined direction D. Specifically, the belt conveyor 120 rotates the wide belt 121 in the form of a ring by a roller 122 so that the postal matter M is placed on the belt 121 and moved.

  The plate body 130 is disposed between the belt conveyor 110 and the belt conveyor 120 at a position lower than the conveyor surfaces of the belt conveyor 110 and the belt conveyor 120. A striped pattern arranged in a direction orthogonal to the predetermined direction D is provided on the upper surface of the plate body 130.

  The line imaging device 140 is disposed above the plate body 130 at a position higher than the conveyor surfaces of the belt conveyor 110 and the belt conveyor 120. Then, the line imaging device 140 captures an imaging region extending in a direction orthogonal to the predetermined direction D.

  The contour detection device 200 detects the contour of the postal matter M based on the image data captured by the line imaging device 140.

  FIG. 2 shows an example of a block configuration of the outer shape detection apparatus 200. The outer shape detection apparatus 200 includes an image generation unit 210 and an outer shape detection unit 220. The function and operation of each component will be described below.

  The image generation unit 210 combines the image data captured by the line imaging device 140 to generate a monochrome binary image. Specifically, when the image generation unit 210 continuously receives input of image data from the line imaging device 140, the image generation unit 210 combines the image data and generates a monochrome binary image. Then, the image generation unit 210 sends the generated monochrome binary image data to the outer shape detection unit 220.

  The outer shape detection unit 220 detects the outer shape of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, when receiving the monochrome binary image data from the image generation unit 210, the outer shape detection unit 220 detects the outer shape of the postal matter M in the monochrome binary image. Then, the outer shape detection unit 220 outputs information indicating the outer shape of the detected postal matter M.

  The image generation unit 210 includes a wide area image generation unit 211 and a binarization processing unit 212. The function and operation of each component will be described below.

  The wide area image generation unit 211 synthesizes the image data captured by the line imaging device 140, and generates an image of an imaging area wider than the imaging area of each image data. Specifically, when the wide-area image generation unit 211 continuously receives input of image data from the line imaging device 140, the wide-area image generation unit 211 synthesizes the respective image data, and captures an image capturing area wider than the image capturing area of the image data. Generate an image. Then, the wide area image generation unit 211 sends the generated image data to the binarization processing unit 212.

  The binarization processing unit 212 binarizes the image generated by the wide area image generation unit 211. Specifically, when the binarization processing unit 212 receives image data from the wide area image generation unit 211, the binarization processing unit 212 binarizes the image. Then, the binarization processing unit 212 sends the binarized monochrome binary image data to the outer shape detection unit 220.

  The outer shape detection unit 220 includes a left end edge detection unit 221, a right end edge detection unit 222, an upper end edge detection unit 223, a lower end edge detection unit 224, an inclination angle detection unit 225, and an outer dimension detection unit 226. The function and operation of each component will be described below.

  The left end edge detection unit 221 detects the left end edge of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, when receiving the monochrome binary image data from the image generation unit 210, the left edge detection unit 221 detects the left edge of the postal matter M in the monochrome binary image. For example, the left edge detection unit 221 detects the left edge of the postal matter M in the image by scanning a stripe pattern in the right direction from the left edge of the monochrome binary image. Then, the left end edge detection unit 221 sends data indicating the detected left end edge of the postal matter M to the external dimension calculation unit 226.

  The right end edge detection unit 222 detects the right end edge of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, when the right edge detection unit 222 receives monochrome binary image data from the image generation unit 210, the right edge detection unit 222 detects the right edge of the postal matter M in the monochrome binary image. For example, the right edge detection unit 221 detects the right edge of the postal matter M in the image by scanning a striped pattern from the right edge of the monochrome binary image to the left. Then, the right end edge detection unit 221 sends data indicating the detected right end edge of the postal matter M to the external dimension calculation unit 226.

  The upper edge detection unit 223 detects the upper edge of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, upon receiving monochrome binary image data from the image generation unit 210, the upper edge detection unit 223 detects the upper edge of the postal matter M in the monochrome binary image. For example, the upper edge detection unit 223 detects the upper edge of the postal matter M in the image by scanning a stripe pattern downward from the upper edge of the monochrome binary image. Then, the upper edge detection unit 223 sends data indicating the detected upper edge of the mail M to the outer dimension calculation unit 226.

  The lower edge detection unit 224 detects the lower edge of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, when receiving the monochrome binary image data from the image generation unit 210, the lower edge detecting unit 224 detects the lower edge of the postal matter M in the monochrome binary image. For example, the lower edge detection unit 224 detects the lower edge of the postal matter M in the image by scanning a stripe pattern upward from the lower edge of the monochrome binary image. Then, the lower edge detection unit 224 sends data indicating the lower edge of the detected postal matter M to the outer dimension calculation unit 226.

  The inclination angle detection unit 225 detects the inclination angle of the postal matter M in the monochrome binary image generated by the image generation unit 210. Specifically, when receiving the monochrome binary image data from the image generation unit 210, the inclination angle detection unit 225 detects the inclination angle of the postal matter M in the monochrome binary image. Then, the tilt angle detection unit 225 sends data indicating the detected tilt angle of the postal matter M to the outer dimension calculation unit 226.

  The outer dimension calculation unit 226 detects the position of the left end edge of the postal matter M detected by the left end edge detection unit 221, the position of the right end edge of the postal matter M detected by the right end edge detection unit 222, and the upper end edge detection unit 223 detects it. Based on the position of the upper end edge of the postal matter M and the position of the lower end edge of the postal matter M detected by the lower end edge detecting unit 224, the dimensions of the outer shape of the postal matter M are calculated. Specifically, the outer dimension calculation unit 226 receives data indicating the left edge from the left edge detection unit 221, receives data indicating the right edge from the right edge detection unit 222, and detects data indicating the upper edge as upper edge. When the data indicating the lower edge is received from the lower edge detection unit 224, the outer shape of the postal matter M is determined based on the positions of the left edge, right edge, upper edge, and lower edge indicated by the data. calculate. Then, the outer dimension calculation unit 226 outputs data indicating the calculated outer shape of the postal matter M.

  Further, the outer dimension calculation unit 226 calculates the outer dimension of the postal matter M based further on the tilt angle of the postal matter M detected by the tilt angle detection unit 225. Specifically, when the outer dimension calculation unit 226 receives data indicating the tilt angle of the postal matter M from the tilt angle detection unit 225, the outer dimension of the postal matter M is further based on the tilt angle of the postal matter M. Is calculated.

  FIG. 3 shows an example of a monochrome binary image generated by the image generation unit 210. FIG. 3A shows a case where the density of the postal matter M is different from the density of the belts 111 and 121. FIG. 3B shows a case where the density of the postal matter M is the same as the density of the belts 111 and 121. FIG. 3C shows a case where the shade of part of the postal matter M is the same as that of the belts 111 and 121.

  4 to 7 show an example of an operation flow of the outer shape detection apparatus 200. FIG. First, the wide area image generation unit 211 of the outer shape detection apparatus 200 synthesizes the image data captured by the line imaging apparatus 140 and generates an image of an imaging area wider than the imaging area of each image data (S101). Then, the binarization processing unit 212 of the outer shape detection apparatus 200 binarizes the image generated by the wide area image generation unit 211 to generate a monochrome binary image (S102).

  Then, the left edge detection unit 221 of the outer shape detection apparatus 200 scans the white stripe in the right direction from the left edge of the monochrome binary image generated by the binarization processing unit 212 (S103). The white stripe tracking method is performed using a general image processing method such as boundary line tracking. As a result of the tracking, if the end point of the stripe is found before reaching the center of the image (S104: Yes), the left end edge detecting unit 221 uses the coordinates of the found end point as the left end coordinates of the postal matter M, and the outer dimension calculating unit 226. (S107). If the end point of the white stripe is not found before reaching the center of the image (S104: No), the left edge detection unit 221 similarly searches for the end point in the black stripe (S105). If found (S106: Yes), the left end edge detection unit 221 sends the coordinates of the found end point as the left end coordinates of the postal matter M to the external dimension calculation unit 226 (S107). If not found (S106: No), the left edge detection unit 221 determines that there is no mail M (S108) and ends the process.

  The processing shown in FIG. 5 is a flowchart in which the processing from S103 to S108 shown in FIG. 4 is applied to the right end of the image, and is the same processing as the processing from S103 to S108 shown in FIG. To do.

  Next, the process for obtaining the upper edge will be described with reference to the flowchart of FIG. Since the postal matter M is smaller than the stripe pattern as the image background, a stripe also exists as a background at the upper end of the image. The upper edge detection unit 223 detects and counts white and black stripes from the upper edge of the image (S115). Since the stripe width is known and is a horizontal parallel line with respect to the entire image, it is easy in image processing to detect the stripe using this feature. When the stripe is detected downward from the upper end and an object that is not regarded as a stripe is detected (S116: Yes), the upper edge detection unit 223 determines that the upper edge has been detected (S117). If only the stripe continues to be detected before reaching the middle of the image (S116: No), the upper edge detection unit 223 determines that there is no mail M (S118). If it is determined that the upper edge is detected (S116: Yes), the upper edge detection unit 223 obtains the upper edge coordinate by calculating “the number of detected stripes × the stripe width” (S119) and sends it to the outer dimension calculation unit 226 (S120). ). The same processing is performed from the lower end of the image to obtain the lower end coordinates of the postal matter M, but the processing is the same as in FIG.

  Through the above processing, the top, bottom, left and right end points of the outer shape of the mail piece M can be measured. If the postal matter M is tilted, processing for detecting the end points of a plurality of stripes is added to the above-described process, and the tilt angle detecting unit 225 determines the angle of the postal matter M from the end point sequence. It can be detected (S127). The outer dimension calculation unit 226 then detects the position of the left end edge of the postal matter M detected by the left end edge detection unit 221, the position of the right end edge of the postal matter M detected by the right end edge detection unit 222, and the upper end edge detection unit 223. Based on the position of the upper edge of the postal matter M detected by S. and the position of the lower end edge of the postal matter M detected by the lower end edge detecting unit 224, the dimensions of the outer shape of the postal matter M are calculated (S128). In addition, when the inclination angle detection unit 225 detects the inclination angle of the postal matter M, the external dimension calculation unit 226 further determines the external shape of the postal matter M based on the inclination angle of the postal matter M detected by the inclination angle detection unit 225. Calculate the dimensions.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

100 Outline Detection System 110 Belt Conveyor 111 Belt 112 Roller 120 Belt Conveyor 121 Belt 122 Roller 130 Plate 140 Line Imaging Device 200 Outline Detection Device 210 Image Generation Unit 211 Wide Area Image Generation Unit 212 Binarization Processing Unit 220 Outline Detection Unit 221 Left End Edge detection unit 222 Right end edge detection unit 223 Upper end edge detection unit 224 Lower end edge detection unit 225 Inclination angle detection unit 226 External dimension calculation unit D Conveying direction M Mail

Claims (10)

An outer shape detection system for detecting an outer shape of an object conveyed in a predetermined direction by a conveying device,
A first transport device for transporting the object in a predetermined direction;
A second transport device that is arranged at an interval in the predetermined direction from the installation position of the first transport device, and that delivers the object transported by the first transport device and transports it in the predetermined direction. When,
Stripes arranged between the first transfer device and the second transfer device at positions lower than the transfer surfaces of the first transfer device and the second transfer device and arranged in a direction orthogonal to the predetermined direction. A plate body provided with a pattern on the upper surface;
An imaging device that images an imaging region that is arranged at a position higher than the respective conveyance surfaces of the first conveyance device and the second conveyance device and extends in a direction orthogonal to the predetermined direction above the plate body;
An outer shape detection system comprising: an outer shape detection device that detects an outer shape of the object based on image data captured by the imaging device. The outer shape detection device
An image generation unit that combines the image data captured by the imaging device to generate a monochrome binary image;
The external shape detection system according to claim 1, further comprising: an external shape detection unit that detects an external shape of the object in the monochrome binary image generated by the image generation unit. The image generation unit
A wide-area image generation unit that synthesizes image data captured by the imaging device and generates an image of an imaging area wider than the imaging area of each image data;
The outer shape detection system according to claim 2, further comprising: a binarization processing unit that binarizes the image generated by the wide area image generation unit. The outer shape detector
A left end edge detection unit for detecting a left end edge of the object in the monochrome binary image generated by the image generation unit;
A right edge detection unit that detects a right edge of the object in the monochrome binary image generated by the image generation unit;
An upper edge detecting unit for detecting an upper edge of the object in the monochrome binary image generated by the image generating unit;
The external shape detection system according to claim 2, further comprising: a lower end edge detection unit that detects a lower end edge of the object in the monochrome binary image generated by the image generation unit. The outer shape detector
The position of the left edge of the object detected by the left edge detection unit, the position of the right edge of the object detected by the right edge detection unit, and the upper edge of the object detected by the upper edge detection unit The external shape detection unit according to claim 4, further comprising: an external dimension calculation unit that calculates an external dimension of the object based on the position of the object and a position of a lower edge of the object detected by the lower edge detection unit. system. The outer shape detector
The outer shape detection system according to claim 4, further comprising an inclination angle detection unit that detects an inclination angle of the object in the monochrome binary image generated by the image generation unit. The outer shape detection system according to claim 6, wherein the outer dimension calculation unit calculates the outer dimension of the object based further on the tilt angle of the object detected by the tilt angle detection unit. The left end edge detection unit detects the left end edge of the object in the image by scanning the striped pattern in the right direction from the left end of the monochrome binary image generated by the image generation unit. The outer shape detection system according to any one of claims 7 to 9. The right edge detection unit detects the right edge of the object in the image by scanning the striped pattern from the right edge of the monochrome binary image generated by the image generator to the left. The outer shape detection system according to claim 8. The upper edge detection unit detects the upper edge of the object in the image by scanning the striped pattern downward from the upper end of the monochrome binary image generated by the image generation unit. The external shape detection system according to any one of 9.

Images