JP5788367B2 - Long object number measuring device, long object number measuring method, and computer program - Google Patents

Description

  The present invention relates to a long object number measuring device, a long object number measuring method, and a computer program, and in particular, for capturing an image of a long object and measuring the number of long objects based on the captured image. It is suitable for use.

  Conventionally, in the steel industry, counting the number of manufactured long objects such as steel bars and steel pipes has been performed. For example, the manufactured steel pipes are stored in a storage place called a stack for each steel pipe having the same specification for the purpose of assembling a shipping lot before shipping. In order to confirm the number of steel pipes to be shipped, etc., it is necessary to measure the number of steel pipes stored in the stack before shipping. Therefore, conventionally, an operator visually counts the steel pipes stored in the stack. When the number of steel pipes included in one lot increases, a large number of steel pipes are stacked in a single stack, so if an operator visually counts steel pipes in this way, a human error occurs and the shipment There is a risk that the required number of steel pipes cannot be shipped. Therefore, there has been a demand for a technique for automatically counting such a long object without manually. As this type of technology, there is a technology described in Patent Document 1.

  In the technique described in Patent Document 1, first, an end surface image obtained by imaging the end surface of the steel bar and a side image obtained by imaging the side surface of the steel bar are obtained, and whether or not the steel bars are stacked based on the end surface image. Determine. When the steel bars are stacked, the larger one of the count values of the steel bars based on the end face images and the count values based on the side images is set as the number of the steel bars.

JP 2003-99755 A

As described above, when the number of long objects included in one lot increases, a large number of long objects are stacked. However, the technique described in Patent Document 1 has a problem that the steel bars cannot be accurately counted when the steel bars are stacked.
In addition, the stacked long objects are usually in contact with at least one of the adjacent long objects. For this reason, with the technique described in Patent Document 1, individual long objects cannot be extracted from the captured images of the end surfaces of the stacked long objects. In particular, for a long object whose end face is not open, the luminance difference at the end face when the end face is illuminated is small, so that the stacked long object is recognized as one large area. . Therefore, when a plurality of long objects whose end faces are not open are stacked, a technique for extracting individual long objects from the captured images of the end faces of the plurality of long objects is desired. Yes.

In addition, a cap colored with a color designated by the customer may be attached to the end surface of the steel pipe in order to prevent foreign matters from entering the steel pipe after shipment. In addition, the end face of the steel bar may be colored for reasons such as identifying a lot. Thus, when the image of the end surface of the long object in which the end surface is colored is captured, according to the technique described in Patent Document 1, the relationship between the color of the end surface of the long object and the color of the background is used. Cannot recognize the long object.
As described above, when a plurality of long objects in a state where the end surfaces are not open and colored are stacked, individual images are taken from the captured images of the end surfaces of the plurality of long objects. A technique for extracting long objects and measuring their number is desired.

  The present invention has been made in view of the above circumstances, even when a plurality of elongated objects in a state where the end face is not open and colored are stacked. It is an object to enable automatic and accurate measurement of the number of a plurality of long objects stacked.

  The long object number measuring device of the present invention is the number of a plurality of long objects in which the end face is not open and is colored in a predetermined color, and is adjacent to each other. A long object number measuring apparatus for measuring the number of a plurality of long objects stacked so that a gap is formed in at least a part of a region, and imaging an end face of the plurality of long objects An original image acquisition unit that acquires an original image that is a color image obtained by the above, and a first color space element that is preset according to the color of the end face from the original image acquired by the original image acquisition unit A first grayscale image creating means for creating a first grayscale image in which each pixel has a pixel value corresponding to the value of the first color space element; The first created by the gray scale image creating means Based on the grayscale binarized image creating means for binarizing the grayscale image to create a grayscale binarized image, and the grayscale binarized image created by the grayscale binarized image creating means, By identifying a group of areas having pixel values corresponding to the color of the end face, and moving the outer edge and the inner edge of the identified group of areas in the direction in which the group of areas exists. A region separating unit that separates the group of regions into a plurality of regions, a counting unit that counts the plurality of long objects based on the number of regions separated by the region separating unit, and the counting unit. Output means for outputting information including the counted number of the plurality of long objects, and the first color space element is a color of the end faces of the plurality of long objects stacked. And wherein the coupling and an element varies accordingly in the case of the color of the background of the end faces of the plurality of elongated article being stacked the stage.

  The method for measuring the number of long objects of the present invention is the number of a plurality of long objects that are in a state where the end face is not open and is colored in a predetermined color, and are adjacent to each other. A method for measuring the number of a plurality of long objects stacked so that a gap is formed in at least a part of a region, wherein the end faces of the plurality of long objects are imaged. An original image acquisition step of acquiring an original image which is a color image obtained by the above, and a first color space element set in advance according to the color of the end face from the original image acquired by the original image acquisition step A first grayscale image creating step of creating a first grayscale image in which each pixel has a pixel value corresponding to the value of the first color space element; The first created by the grayscale image creation process Based on the grayscale binarized image creating step for binarizing the grayscale image to create a grayscale binarized image, and the grayscale binarized image created by the grayscale binarized image creating step, By identifying a group of areas having pixel values corresponding to the color of the end face, and moving the outer edge and the inner edge of the identified group of areas in the direction in which the group of areas exists. A region separation step of separating the group of regions into a plurality of regions, a counting step of counting the plurality of long objects based on the number of regions separated by the region separation step, and the counting step. An output step for outputting information including the counted number of the plurality of long objects, wherein the first color space element is a color of an end face of the plurality of long objects stacked. And wherein the coupling and an element varies accordingly in the case of the color of the background of the end faces of the plurality of elongated article being stacked the stage.

  The computer program according to the present invention causes a computer to function as each means of the long object number measuring apparatus.

  According to the present invention, from the original image, which is a color image obtained by imaging the end faces of a plurality of stacked long objects, the value at the end face color becomes as large as possible. A first grayscale image having a pixel value corresponding to a value of a first color space element that is a smaller element is generated, and the first grayscale image is binarized to generate a grayscale binarized image To do. Then, based on the grayscale binarized image, a group of areas having pixel values corresponding to the color of the end face is identified, and the positions of the outer edge and the inner edge of the identified group of areas are respectively determined. By moving the region in the direction in which the region exists, the group of regions is separated into a plurality of regions, and a plurality of long objects are counted based on the number of separated regions. Therefore, even when a long object having an end face that is not open and colored is stacked, the number of the stacked long objects is automatically and accurately determined. Can be measured.

It is a figure which shows an example of arrangement | positioning of a some steel pipe, an imaging device, and an illuminating device. It is a block diagram which shows an example of a functional structure of a long thing number measuring apparatus. It is a figure which shows an example of a color space element selection table. It is a figure which shows an example of an original image. It is a figure which shows an example of a 1st gray scale image. It is a figure which shows an example of a gray scale binarized image. It is a figure which shows an example of the binarized image after gap complement. It is an example of a 2nd gray scale image. It is a figure which shows an example of a count object area | region extraction image. It is a figure which shows an example of a count object area | region binarized image. It is a figure which shows an example of an area separation binarized image. It is a figure which shows notionally an example of a mode that a count object area | region binarized image is isolate | separated into a some area | region. It is a figure which shows an example of an output image. It is a flowchart explaining an example of operation | movement of a long thing number measuring apparatus.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In each drawing, some components are simplified or omitted for convenience of description.
(Arrangement of long object to be imaged and configuration of apparatus for imaging long object)
FIG. 1 shows a plurality of steel pipes 20a to 20t stored in a stack 10, an imaging device 30 for taking images of end faces of the plurality of steel pipes 20a to 20t, and end faces of the plurality of steel pipes 20a to 20t. It is a figure which shows an example of arrangement | positioning of the illuminating devices 41 and 42 for illuminating. FIG. 1A is a view of the stack 10 as viewed from above, and FIG. 1B and FIG. 1C are directions A (the end face direction of the steel pipe 20) shown in FIG. It is the figure seen from B direction (side surface direction of the steel pipe 20).

In the example shown in FIG. 1, the steel pipes 20a to 20t have the same specifications. Moreover, the caps 50a-50t colored with the same color are attached to each edge part of the steel pipes 20a-20t. Thus, in this embodiment, the end surfaces of the steel pipes 20a to 20t are closed by the caps 50a to 50t. In the present embodiment, it is assumed that the color of the caps 50a to 50t is red.
In the present embodiment, the imaging device 30 is a digital still camera, and the color still images of the end faces of all the steel pipes 20a to 20t stored in a stack in the stack 10 are substantially opposed to the end faces of the steel pipes 20a to 20t. Take an image from the position. As described above, caps 50a to 50t colored with the same color are attached to the respective ends of the steel pipes 20a to 20t. Therefore, capturing images of the end faces of the steel pipes 20a to 20t is equivalent to capturing caps 50a to 50t located on the end faces of the steel pipes 20a to 20t. In the following description, “images of the end faces (caps 50a to 50t) of the steel pipes 20a to 20t” captured by the imaging device 30 are referred to as “original images” as necessary.

  The illuminating devices 41 and 42 are located at positions where the end surfaces (caps 50a to 50t) of all the steel pipes 20a to 20t stored in the stack 10 can be illuminated as uniformly as possible from the left and right of the imaging device 30, respectively. Has been placed.

(Configuration of long object number measuring device)
FIG. 2 is a block diagram illustrating an example of a functional configuration of the long object number measuring apparatus 100.
The long object number measuring apparatus 100 captures images of the end surfaces (caps 50a to 50t) of the plurality of steel pipes 20a to 20t illuminated by the illuminating devices 41 and 42 from the position facing the end surfaces by the imaging device 30. The obtained image (original image) is subjected to image processing, and the plurality of steel pipes 20a to 20t are automatically counted.
2 can be realized by using, for example, a computer (for example, a PC) provided with a CPU, a ROM, a RAM, an HDD, and various interfaces. Below, an example of the function which long object number measuring device 100 has is explained. The long object number measuring device 100 and the imaging device 30 are connected to each other by a USB cable or the like so as to be able to communicate with each other.

(End color information acquisition unit 101)
The end face color information acquisition unit 101 requests the host computer 200 for information indicating the color of the end face of the long object (steel pipe 20) to be counted, and acquires the information from the host computer 200 based on the operation by the operator. In the following description, “information indicating the color of the end face of the long object (steel pipe 20) to be counted” is referred to as “end face color information” as necessary.

Note that the end face color information acquisition unit 101 may acquire end face color information spontaneously transmitted by the host computer 200. In this case, the end face color information acquisition unit 101 acquires a set of information of end face color information and information for identifying the stack 10. Then, the end face color information acquisition unit 101 stores the acquired set of information, and reads end face color information that matches the input stack information based on the operation by the operator.
In addition, the end face color information acquisition unit 101 may directly acquire end face color information based on an operation by the operator (that is, the operator may specify the end face color information).

As described above, in this embodiment, the color of the cap 50 is red. Therefore, the end face color information acquisition unit 101 acquires information indicating red as the end face color information.
The end face color information acquisition unit 101 can be realized by using, for example, a CPU, a ROM, a RAM, a user interface, and a communication interface.

(Color space element selection unit 102)
The color space element selection unit 102 selects a “color space element” corresponding to the color specified by the end face color information acquired by the end face color information acquisition unit 101 from the color space element selection table.
FIG. 3 is a diagram illustrating an example of a color space element selection table.
As shown in FIG. 3, the color, the first color space element, and the second color space element are registered in the color space element selection table 300 in association with each other.

“Color” in the color space element selection table 300 indicates a color specified by the end face color information. Therefore, a color assumed as a color specified by the end face color information is set in advance as “color” in the color space element selection table 300.
Also, “first color space element” and “second color space element” indicate “color space elements” selected from images acquired by the original image acquisition unit 103 as described later.
The “first color space element” is the color of the region of the end face (cap 50) of the steel pipe 20 (the color specified by the end face color information) and the background color of the steel pipe 20 (cap 50). Elements that take different values depending on the case (as large as possible) are preset.
As the “second color space element”, the value when the color is the color of the region of the end face (cap 50) of the steel pipe 20 (the color specified by the end face color information) and the color of the region of the gap between them ( In this case, an element whose difference from the value when it is black) is larger than that in the first color space element is preset. The “second color space element” is preferably an element whose value does not change greatly due to unevenness of the color of the end face (cap 50) of the steel pipe 20.

In the color space element selection table 300 shown in FIG. 3, when the color specified by the end face color information is red, a ^* of the CIE Lab color space is selected as the first color space element, and the second R of the RGB color space is selected as the color space element. When the color specified by the end face color information is green, a ^{* in} the CIE Lab color space is selected as the first color space element, and G in the RGB color space is selected as the second color space element. Is selected. When the color specified by the end face color information is yellow, V (brightness) of the HSV color space is selected as the first color space element, and the RGB color space is selected as the second color space element. R is selected. When the color specified by the end face color information is white, V (brightness) of the HSV color space is selected as the first color space element, and the RGB color space is selected as the second color space element. R is selected.
As described above, in the present embodiment, since the color of the cap 50 is red, the color specified by the end face color information is red. Therefore, the color space element selection unit 102 selects a CIE Lab color space a ^* as a first color space element and an RGB color space R as a second color space element from the color space element selection table 300, respectively. To do.
The color space element selection unit 102 can be realized by using, for example, a CPU, ROM, RAM, and HDD.

(Original image acquisition unit 103)
The original image acquisition unit 103 inputs and stores the original image captured by the imaging device 30. In the present embodiment, it is assumed that when an original image is captured by the imaging device 30, the original image data is automatically input to the original image acquisition unit 103. However, the imaging apparatus 30 may transmit the original image data to the original image acquisition unit 103 in response to a request from the original image acquisition unit 103.
FIG. 4 is a diagram illustrating an example of an original image. As described above, the original image 400 is a color image. In the present embodiment, the original image is an image expressed in the RGB color space.
The original image acquisition unit 103 can be realized by using, for example, a CPU, RAM, ROM, HDD, and communication interface.

(First grayscale image creation unit 104)
The first grayscale image creation unit 104 derives the value of the first color space element selected by the color space element selection unit 102 from the data of each pixel of the original image acquired by the original image acquisition unit 103. Then, each pixel creates a grayscale image having a pixel value corresponding to the value of the first color space element. The gray scale image created by the first gray scale image creation unit 104 is referred to as “first gray scale image” as necessary in the following description.

FIG. 5 is a diagram illustrating an example of the first grayscale image. The first grayscale image 500 shown in FIG. 5 is obtained from the original image 400 shown in FIG.
As described above, the first color space element is the color of the region of the end face (cap 50) of the steel pipe 20 (the color specified by the end face color information) and the background color of the steel pipe 20 (cap 50). It is an element that takes a different value in the case of. Therefore, as shown in FIG. 5, the pixel value of the red cap 50 region (the region where the cap 50 is projected) is different from the pixel values of the other non-red color regions. A grayscale image 500 is obtained.
The first grayscale image creation unit 104 can be realized by using, for example, a CPU, RAM, ROM, and HDD.

(Grayscale binary image creation unit 105)
The grayscale binarized image creation unit 105 binarizes the pixel value of each pixel of the first grayscale image created by the first grayscale image creation unit 104 based on a preset threshold value. . To describe a specific example, the grayscale binarized image creation unit 105 assigns a logic “1” to a pixel having a pixel value equal to or greater than (or less than) a threshold for each pixel of the first grayscale image. The first grayscale image is binarized by assigning logic “0” to pixels whose value is less than (or greater than) the threshold. Further, according to the first color space element selected by the color space element selection unit 102, the grayscale binarized image creation unit 105 has a pixel value within a predetermined range for each pixel of the first grayscale image. The first gray is assigned by assigning a logic “1” to a pixel within (or outside a predetermined range) and assigning a logic “0” to a pixel whose pixel value is outside the predetermined range (or within a predetermined range). The scale image can also be binarized. In this embodiment, logic “1” is assigned to a pixel having a pixel value corresponding to the color (here, red) specified by the end face color information as much as possible, and has a pixel value corresponding to the other color. A threshold value for assigning a logic “0” to a pixel as much as possible is set in advance based on an operation by an operator. In the following description, the binarized image created by the grayscale binarized image creating unit 105 is referred to as a “grayscale binarized image” as necessary.

FIG. 6 is a diagram illustrating an example of a grayscale binarized image. A grayscale binarized image 600 shown in FIG. 6 is obtained from the first grayscale image 500 shown in FIG.
As shown in FIG. 6, in the grayscale binarized image 600, logic “1” is generally assigned to the area of the cap 50 (see the area filled with gray in FIG. 6), and other than that The area is assigned a logic “0” (see white area in FIG. 6).
The grayscale binarized image creating unit 105 can be realized by using, for example, a CPU, RAM, ROM, and user interface. Note that shading correction may be performed before the binarization process.

(Binary image creation unit 106 after gap compensation)
The binarized image creation unit 106 after gap complementation includes a “pixel value” surrounded by an area having a pixel value “1” in the grayscale binarized image created by the grayscale binarized image creation unit 105. The pixel value of “region where is“ 0 ”” is changed to “1”. In the present embodiment, the binarized image creation unit 106 after gap interpolation is adjacent to a pixel having a pixel value of “1” in the grayscale binarized image, either vertically, horizontally, or diagonally. The pixel having the pixel value “1” is set as one region for each pixel of the grayscale binarized image. The binarized image creation unit 106 after gap complementation sets all the pixel values of the pixels inside the region thus obtained to “1”.

  However, this is not always necessary. For example, it may be as follows. That is, in a grayscale binarized image, a pixel having a pixel value “0” and a pixel adjacent to the pixel in any one of vertical, horizontal, and diagonal directions, and having a pixel value “0” For each pixel of the grayscale binarized image, and all the pixels at the outer edge of the region obtained in this way are pixels having a pixel value of “1”. All the pixel values in the contact area may be set to “1”.

In the following description, a grayscale binarized image whose pixel value has been changed by the gap-compensated binarized image creation unit 106 is referred to as a “gap-compensated binarized image” as necessary.
FIG. 7 is a diagram illustrating an example of a binarized image after gap complementation. A binarized image 700 after gap interpolation shown in FIG. 7 is obtained from the grayscale binarized image 600 shown in FIG.
As shown in FIG. 7, in the grayscale binarized image 600 shown in FIG. 6, a white area (pixel value is the pixel value) surrounded by a gray area (area where the pixel value is “1”). “0” area) is painted in gray (the pixel value is changed from “0” to “1”). By doing in this way, the area | region (namely, a group of area | region where the cap 50 exists) in which the color (here red) specified by end surface color information exists can be distinguished clearly from another area | region.
The post-gap complement binarized image creation unit 106 can be realized by using, for example, a CPU, a RAM, and a ROM.

(Second grayscale image creation unit 107)
The second grayscale image creation unit 107 derives the value of the second color space element selected by the color space element selection unit 102 from the data of each pixel of the original image acquired by the original image acquisition unit 103. Then, each pixel creates a grayscale image having a pixel value corresponding to the value of the second color space element. The grayscale image created by the second grayscale image creation unit 107 is referred to as a “second grayscale image” as necessary in the following description.

FIG. 8 shows an example of the second grayscale image. A second grayscale image 800 shown in FIG. 8 is obtained from the original image 400 shown in FIG.
As described above, the value of the second color space element is a color of the region of the end surface (cap 50) of the steel pipe 20 (the color specified by the end surface color information) that does not change greatly due to color unevenness. This is an element in which the difference between the time value and the value when the color is the color of the gap region between them (here, black) is larger than that in the first color space element. Therefore, as shown in FIG. 8, in the second grayscale image 800, the difference in pixel value in the region of the cap 50 that is red is smaller than the original image 400 (color unevenness is reduced), and the cap The difference between the pixel values in the 50 areas and the pixel values in the gap area increases.
The second grayscale image creation unit 107 can be realized by using, for example, a CPU, RAM, ROM, and HDD.

(Counter area extraction image creation unit 108)
The counting target region extraction image creation unit 108 uses the second grayscale image created by the second grayscale image creation unit 107 and the binary after gap interpolation created by the binarized image creation unit 106 after region complementation. A region where the pixel value of the digitized image is “1” is extracted. In the following description, the image obtained by the counting target region extraction image creation unit 108 in this way is referred to as a “counting target region extraction image” as necessary.
FIG. 9 is a diagram illustrating an example of the count target region extraction image 900. The count target region extraction image 900 shown in FIG. 9 is obtained from the gap-compensated binarized image 700 shown in FIG. 7 and the second grayscale image 800 shown in FIG.

As described above, the second grayscale image 800 has a smaller pixel value difference in the cap 50 region that is red than the first grayscale image 500, and the pixel value in the cap 50 region. And the difference between the pixel values in the gap area increases. Therefore, when the area of the cap 50 is extracted from the second grayscale image 800 based on the count target area extraction image 900, the area of the cap 50 can be extracted in a state where the cap 50 stands out.
The count target region extraction image creation unit 108 can be realized by using, for example, a CPU, RAM, ROM, and HDD.

(Counting target region binarized image creation unit 109)
The count target area binarized image creating unit 109 binarizes the pixel value of each pixel of the count target area extracted image created by the count target area extracted image creating unit 108 based on a preset threshold value. More specifically, the count target area binarized image creating unit 109 assigns a logical “1” to a pixel whose pixel value is equal to or greater than (or less than) a threshold for each pixel of the count target area extraction image, By assigning a logic “0” to pixels that are less than (or more than) the threshold value, the count target region extraction image is binarized. In addition, according to the second color space element selected by the color space element selection unit 102, the counting target region binarized image creating unit 109 has a pixel value within a predetermined range for each pixel of the counting target region extraction image. Counting target region extraction by assigning logic “1” to pixels that are inside (or outside a predetermined range) and assigning logic “0” to pixels that have a pixel value outside (or within a predetermined range) The image can also be binarized. In this embodiment, logic “1” is assigned to a pixel having a pixel value corresponding to the color (here, red) specified by the end face color information as much as possible, and has a pixel value corresponding to the other color. A threshold value for assigning a logic “0” to a pixel as much as possible is set in advance based on an operation by an operator. In the following description, the binarized image created by the count target area binarized image creating unit 109 is referred to as “count target area binarized image” as necessary.
FIG. 10 is a diagram illustrating an example of the count target region binarized image. A count target area binarized image 1000 shown in FIG. 10 is obtained from the count target area extracted image 900 shown in FIG. As described above, in the count target region extraction image 900, the difference between the pixel values in the cap 50 region is small, and the difference between the pixel value in the cap 50 region and the pixel value in the gap region is large. . Therefore, when the count target region extraction image 900 is binarized, the region of the cap 50 and the region between them can be clearly distinguished.
The count target area binarized image creation unit 109 can be realized by using, for example, a CPU, a RAM, a ROM, and an HDD.

(Region separation unit 110)
The region separating unit 110 includes a pixel whose pixel value is “1” in the counting target region binarized image created by the counting target region binarized image creating unit 109 and any of vertical, horizontal, and diagonal with respect to the pixel. The region obtained by performing each pixel of the count target region binarized image to set a pixel having a pixel value of “1” as one region. Thus, the count target area binarized image is separated into a plurality of areas (areas of individual caps 50). In the following description, the count target area binarized image that is separated into a plurality of areas is referred to as an “area separated binarized image” as necessary.
FIG. 11 is a diagram illustrating an example of a region separation binarized image. An area separation binarized image 1100 shown in FIG. 11 is obtained from the count target area binarized image 1000 shown in FIG.

FIG. 12 is a diagram conceptually illustrating an example of a state where the count target region binarized image is separated into a plurality of regions.
First, the region separation unit 110 calculates a pixel having a pixel value “1” and a pixel adjacent to the pixel in any one of vertical, horizontal, and diagonal directions and having a pixel value “1”. One pixel is set for each pixel of the binarized image to be counted. As a result, a closed region composed of pixels having a pixel value of “1”, and at least one of the pixels in contact with the outer edge pixel becomes a pixel having a pixel value of “0” (so-called blob). ) Is derived. In the example illustrated in FIG. 10, a region displayed in gray in the count target region binarized image 1000 is derived.

  Next, the region separation unit 110 performs a predetermined process on a pixel at the outer edge of the derived closed region in a direction perpendicular to a tangent line with the pixel on the outer edge as a contact and in the direction in which the closed region exists. Changing the position separated by the number of pixels to the position of the outer edge of the closed region is performed for the pixels of the outer edge of the closed region (attached to the outer edge of the filled region in the top diagram of FIG. 12). See the arrow line). Here, the derived change in the position of the outer edge of the closed region is performed by changing the pixel value of the pixel located between the outer edge pixel of the closed region before the change and the outside of the closed region after the change from “1” to “0”. This can be done by changing to

  Along with such processing, the region separation unit 110 is directed to the inner edge pixel of the derived closed region in a direction perpendicular to a tangent line having the outer edge pixel as a contact, and in the direction in which the closed region exists. Then, changing the position separated by a predetermined number of pixels to the position of the inner edge of the closed area is performed for the pixels of the inner edge of the closed area (the area of the area filled in the top diagram of FIG. 12). (See arrow line on inner edge). Here, the change of the position of the inner edge of the closed region is performed by changing the pixel value of the pixel located between the outer edge pixel of the closed region before the change and the outside of the closed region after the change from “1” to “0”. This can be done. Further, the interval (number of pixels) between the inner edge of the closed region before the change and the inner edge of the closed region after the change, and the interval (number of pixels) between the outer edge of the closed region before the change and the outer edge of the closed region after the change are ( That is, the predetermined number of pixels) has the same value.

  For example, when a certain steel pipe 20 is stacked in a shifted state, the steel pipe 20 is not in contact with another steel pipe 20 on the end face side of the steel pipe 20 imaged by the imaging device 30 ( Or contact only in a small area). Then, in the counting target region binarized image created by the counting target region binarized image creating unit 109, there may be an isolated closed region having no inner edge. In such a case, for the closed region where the inner edge does not exist, for example, only the position of the outer edge of the closed region can be changed as described above.

By performing the above processing step by step as shown in FIG. 12, the region of the cap 50 which is one closed region (see the diagram shown at the top of FIG. 12) It can be divided into 50 regions (see the diagram shown at the bottom of FIG. 12).
As described above, the region separation binary image 1100 shown in FIG. 11 is created. The area separation binarized image 1100 clearly distinguishes the areas of the individual caps 50 (20 areas) from the areas of the other caps 50 (that is, the areas of the individual caps 50 (20 areas)). Will be present alone).
The area separation unit 110 can be realized by using, for example, a CPU, a RAM, and a ROM.

(Blob processing unit 111)
The blob processing unit 111 is a closed region composed of pixels having a pixel value “1” from the region-separated binarized image created by the region separating unit 110, and at least pixels that are in contact with the outer edge pixels. One derives a closed region (so-called blob) that becomes a pixel having a pixel value of “0”. More specifically, the blob processing unit 111 includes a pixel having a pixel value “1” in the region-separated binarized image created by the region separating unit 110 and any of vertical, horizontal, and diagonal with respect to the pixel. The blob is derived by performing, for each pixel of the region-separated binarized image, a pixel adjacent to each other and having a pixel value of “1” as one region.

Next, the blob processing unit 111 performs a labeling process (number allocation) on each derived blob. In the example shown in FIG. 11, 20 numbers are individually assigned to each derived blob.
The blob processing unit 111 can be realized by using, for example, a CPU, a RAM, and a ROM.

(Number deriving unit 112)
The number deriving unit 112 derives the total number of numbers assigned to each blob by the blob processing unit 111 as the number of measurement objects. In the example shown in FIG. 11, “20” is derived as the number of steel pipes 20 (stacked in the stack 10).
The number deriving unit 112 can be realized by using, for example, a CPU, a RAM, and a ROM.

(Output Image Creation Unit 113)
The output image creation unit 113 creates display data for displaying an image including the number of measurement objects (here, the steel pipes 20) derived by the number deriving unit 112.
In the present embodiment, the output image creating unit 113 creates display data for displaying an image including the original image acquired by the original image acquiring unit 103 and the number of steel pipes 20 derived by the number deriving unit 112. To do. Furthermore, in this embodiment, the original image is displayed in a state where the area of the cap 50 in the original image is filled with a predetermined color. For this purpose, the output image creation unit 113 performs the following processing.

  First, the output image creation unit 113 extracts a closed region (so-called blob) in which the pixel value of the region separation binarized image (see FIG. 11) created by the region separation unit 110 is “1”. Next, the output image creation unit 113 determines a predetermined value in a direction perpendicular to a tangent line with the pixel at the outer edge as a contact point and a direction where the closed area does not exist with respect to the outer edge pixel of the extracted closed region. The position separated by the number of pixels is changed to the position of the outer edge of the closed region with respect to the pixels of the outer edge of the closed region. Here, the change in the position of the outer edge of the extracted closed region is performed by changing the pixel value of the pixel located between the outer edge pixel of the closed region before the change and the outside of the closed region after the change from “0” to “1”. This can be done by changing to Further, the predetermined number of pixels is 1 / n times the change in the position of the outer edge / inner edge of the closed region in the region separation unit 110 (n is a number of 1 or more, for example, “1.25”) The predetermined interval (number of pixels) × 1 / n). If the predetermined number of pixels obtained in this way is not an integer, for example, the predetermined number of pixels is made an integer by rounding down or rounding up the value after the decimal point. Thereby, the size of each closed region (so-called blob) created by the region separation unit 110 can be enlarged in a range where the individual closed regions are not adjacent to each other.

Next, the output image creation unit 113 changes the region obtained as described above from the original image data and the original image region acquired by the original image acquisition unit 103 to a predetermined color. Information indicating that the display is to be included is included in the display data. Furthermore, the output image creation unit 113 also includes information indicating that the information indicating the number of steel pipes 20 derived by the number deriving unit 112 is displayed in a predetermined manner in a predetermined area.
The output image creation unit 113 can be realized by using, for example, a CPU, a RAM, and a ROM.

(Output image output unit 114)
The output image output unit 114 outputs the display data created by the output image creation unit 113 to the display device. Thereby, an output image including the number of the steel pipes 20 is displayed on the display device (computer display) connected to the long object number measuring device 100.
FIG. 13 is a diagram illustrating an example of an output image. An output image 1300 shown in FIG. 13 is obtained based on the original image shown in FIG.
As described above, the output image 1300 displays the original image in a state where the area of the cap 50 is changed to a predetermined color and information on the number of the steel pipes 20. In the output image 1300 shown in FIG. 13, the number of the steel pipes 20 is displayed in the upper left area (see the area indicated as “20” in FIG. 13), and the area of the cap 50 is changed to green. An image is displayed. The reason why the area of the cap 50 is changed to a predetermined color is to make it easier for the operator to identify the area of the cap 50.
The output image creation unit 113 can be realized by using, for example, a CPU, RAM, ROM, HDD, and communication interface.

(Operation flowchart)
Next, an example of the operation of the long object number measuring apparatus 100 will be described with reference to the flowchart of FIG.
First, in step S1401, the end face color information acquisition unit 101 acquires end face color information. As described above, the end face color information is information indicating the color of the end face of the long object (steel pipe 20) to be counted.
Next, in step S1402, the color space element selection unit 102 sets “first color space element and second color space element” corresponding to the color specified by the end face color information acquired in step S1401 to the color space. Select from the element selection table 300.

Next, in step S1403, the original image acquisition unit 103 acquires the original image captured by the imaging device 30 (see FIG. 4). As described above, the original image is an image of the end face (cap 50) of the steel pipes 20 stacked.
Next, in step S1404, the first grayscale image creation unit 104 determines that the data of each pixel of the original image acquired in step S1403 corresponds to the value of the first color space element selected in step S1402. The first grayscale image is created by changing each pixel value so that the pixel value becomes the same (see FIG. 5).

Next, in step S1405, the grayscale binarized image creation unit 105 binarizes the pixel value of each pixel of the first grayscale image created in step S1404 based on a preset threshold value. A gray scale binarized image is created (see FIG. 6).
Next, in step S1406, the gap-compensated binarized image creation unit 106 creates a “pixel value” surrounded by an area having a pixel value “1” in the grayscale binarized image created in step S1405. The pixel value of “region where is“ 0 ”” is changed to “1” to create a binarized image after gap interpolation (see FIG. 7).

Next, in step S1407, the second grayscale image creation unit 107 determines that the data of each pixel of the original image acquired in step S1403 corresponds to the value of the second color space element selected in step S1402. Each pixel value is changed so that the pixel value becomes the same, and a second grayscale image is created (see FIG. 8).
Note that the process of step S1407 may be performed at any time from the end of the process of step S1403 to the start of the process of step S1408.
Next, in step S1408, the count target region extraction image creation unit 108 sets the pixel value of the post-gap interpolation binarized image created in step S1406 to “1” from the second grayscale image created in step S1407. ”Is extracted to create a count target region extraction image (see FIG. 9).

Next, in step S1409, the count target region binarized image creating unit 109 binarizes the pixel value of each pixel of the count target region extracted image created in step S1408 based on a preset threshold value. A count target area binarized image is created (see FIG. 10).
Next, in step S1410, the region separation unit 110 selects a pixel whose pixel value is “1” in the count target region binarized image created in step S1409 and any of vertical, horizontal, and diagonal with respect to the pixel. The region obtained by performing each pixel of the count target region binarized image to make a pixel adjacent to each other and having a pixel value “1” as one region is reduced. Thus, a region-separated binary image 1100 is created (see FIGS. 11 and 12).

Next, in step S1411, the blob processing unit 111 is a closed region composed of pixels having a pixel value “1” from the region-separated binarized image created in step S1410, and the outer edge pixel. A closed region (a so-called blob) in which at least one of the pixels in contact with the pixel is a pixel having a pixel value “0” is derived, and a labeling process (number allocation) is performed on each blob.
Next, in step S1412, the number deriving unit 112 derives the total number of numbers assigned to each blob in step S1411 as the number of measurement objects.

Next, in step S1413, the output image creation unit 113, the original image acquired in step S1403, the region separation binarized image created in step S1410, and the number of measurement objects derived in step S1412. Based on the above, display data for displaying an image including the number of measurement objects is created.
Finally, in step S1414, the output image output unit 114 displays the display data created in step S1413 on the display device (see FIG. 13).

(Summary)
As described above, in the present embodiment, from the original image, the first grayscale image having a pixel value corresponding to the value of a ^{* in} the CIE Lab color space, and the pixel value corresponding to the R value in the RGB color space. And a second gray scale image. And the gray scale binarized image which binarized the 1st gray scale image is created, The area | region of the end surface (cap 50) of the steel pipe 20 is made into 2nd using the said gray scale binarized image. A binarized image to be counted is created by extracting from the gray scale image. Then, by moving the outer edge and the inner edge of a group of areas in which the pixel value of the count target area binarized image is “1” in the direction in which the area exists, in the count target area binarized image, Separate the cap regions. Thus, by creating a first grayscale image having a pixel value corresponding to the value of a ^* in the CIE Lab color space, the pixel value of the pixel representing the cap 50 and the pixel value of the pixel representing the background And the region where the cap 50 is present can be accurately identified. In addition, there are long objects stacked by moving the outer edge and inner edge of a group of areas whose pixel values of the count target area binarized image are “1” to the inside of the area. Regions can be separated. Therefore, even when a plurality of long objects in a state where the end face is not open and colored are stacked, the number of the plurality of long objects stacked is automatically determined. Can be measured automatically and accurately.

(Modification)
In this embodiment, the case where the long object used as the object which measures a number is the steel pipe with which the cap was attached to the end surface was mentioned as an example, and was demonstrated. However, the long object for which the number is to be measured is a long object in which the end face is not open and is colored in a predetermined color different from the long object (ground color). I just need it. The long object that is the object of measuring the number may be, for example, a steel bar whose end face is colored with a predetermined color different from the ground color.
Moreover, in this embodiment, the case where the shape of the end surface of the elongate object used as the object which measures the number was circular was mentioned as an example, and was demonstrated. However, the shape of the end face of the long object whose number is to be measured is stacked so that a gap is formed in at least a part between the adjacent long objects on the end face side where imaging is performed. What is necessary is just a long thing. The shape of the end face of the long object that is the object of measuring the number may be, for example, an ellipse or a polygon.
Further, the first color space element and the second color space element are not limited to those described above. Depending on the color of the end face of the long object, for example, an element in the CIE 1976 L ^* u ^* v ^* color space or an element in the CIE XYZ color space is adopted as the first color space element or the second color space element. be able to.

  Further, as in this embodiment, in the grayscale binarized image, the pixel value of the “region where the pixel value is“ 0 ”” surrounded by the region where the pixel value is “1” is set to “1”. It is preferable to change and create a binarized image after gap complementation, because the region extracted from the second grayscale image can be more reliably matched with the region of the cap 50. However, it is not always necessary to create a binarized image after gap compensation. For example, when the color unevenness of the end face is small, a group of regions having a pixel value of “1” in the grayscale binarized image 600 is clear. This region can be a region extracted from the second grayscale image.

  In the present embodiment, a first grayscale image and a second grayscale image are created, a grayscale binarized image is created from the first grayscale image, and a gap is compensated from the grayscale binarized image. A binarized image was created, and a region defined based on the binarized image after gap complementation was extracted from the second grayscale image to create a count target region extracted image. However, it is not always necessary to create at least the second gray scale image, the binarized image after gap interpolation, and the count target region extraction image. The color of the region of the end face (cap 50) of the steel pipe 20 (the color specified by the end face color information) differs from the case of the background color of the steel pipe 20 (cap 50) (as large as possible). The difference between the value when the color is in the region of the end face (cap 50) of the steel pipe 20 and the value when the color is in the region of the gap between them is large, and the value is due to color unevenness. When one element can be selected as an element that does not change greatly, the first color space element and the second color space element can be made the same element. That is, when the first color space element and the second color space element are the same element, a binarized image equivalent to the count target region binarized image is obtained at the stage of the grayscale binarized image. Can be obtained. Therefore, in such a case, the second gray scale image, the binarized image after gap interpolation, and the count target region extraction image are not necessary. Further, as apparent from this, when the first grayscale image and the second grayscale image are generated as in the present embodiment, the first color space element and the second color space element are generated. Are preferably different elements.

The embodiment of the present invention described above can be realized by a computer executing a program. Further, a computer-readable recording medium in which the program is recorded and a computer program product such as the program can also be applied as an embodiment of the present invention. As the recording medium, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.
In addition, the embodiments of the present invention described above are merely examples of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. Is. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

DESCRIPTION OF SYMBOLS 10 Stack 20 Steel pipe 30 Imaging device 41, 42 Illumination device 50 Cap 100 Long object number measuring device 200 Host computer 300 Color space element selection table 400 Original image 500 First gray scale image 600 Gray scale binarized image 700 Gap complement Later binarized image 800 Second grayscale image 900 Count target area extraction image 1000 Count target area binarized image 1100 Area separation binarized image 1300 Output image

Claims (11)

The number of a plurality of long objects in which the end face is not open and is colored with a predetermined color, and a gap is formed in at least a partial region of the long objects adjacent to each other. A long object number measuring device for measuring the number of a plurality of long objects stacked in a stack,
Original image acquisition means for acquiring an original image which is a color image obtained by imaging the end faces of the plurality of long objects;
A value of a first color space element set in advance according to the color of the end face is derived from the original image acquired by the original image acquisition unit, and each pixel has a value of the first color space element. First grayscale image creating means for creating a first grayscale image having a pixel value according to
Grayscale binarized image creating means for binarizing the first grayscale image created by the first grayscale image creating means to create a grayscale binarized image;
Based on the grayscale binarized image created by the grayscale binarized image creating means, a group of regions having pixel values corresponding to the color of the end face is identified, and an outer edge of the identified group of regions And a region separating means for separating the group of regions into a plurality of regions by moving the positions of the inner edges in a direction in which the group of regions exists,
Counting means for counting the plurality of long objects based on the number of areas separated by the area separating means;
Output means for outputting information including the number of the plurality of long objects counted by the counting means,
When the first color space element is a color of an end face of the plurality of stacked long objects and a color of a background of the end faces of the plurality of long objects stacked A device for measuring the number of long objects characterized by having different values.   The region separating means is configured to determine the positions of pixels located at the outer edge and inner edge of a group of regions having pixel values corresponding to the color of the end face in a direction perpendicular to a tangent line with the pixel as a contact, The long object number measuring apparatus according to claim 1, wherein the group of areas is separated into a plurality of areas by moving each group in a direction in which the group of areas exists. A value of a second color space element set in advance according to the color of the end face is derived from the original image acquired by the original image acquisition unit, and each pixel has a value of the second color space element. Second grayscale image creating means for creating a second grayscale image having pixel values according to
Based on the grayscale binarized image created by the grayscale binarized image creating means, an area having a pixel value corresponding to the color of the end face is created by the second grayscale image creating means. Counting target area extraction image creating means for creating a counting target area extraction image by extracting from the second grayscale image;
Counting object area binarized image creating means for binarizing the counting object area extraction image created by the counting object area extraction image creating means to create a counting object area binarized image;
The region separation unit identifies and identifies a group of regions having pixel values corresponding to the color of the end face from the count target region binarized image created by the count target region binarized image creation unit. By separating the positions of the outer edge and inner edge of the group of areas in the direction in which the group of areas exists, the group of areas is separated into a plurality of areas,
The second color space element has a difference between a value when the color is an end face color of the plurality of stacked long objects and a value when the color is a color of a gap between them. The long object number measuring apparatus according to claim 1, wherein the element is larger than that in the first color space element. In the grayscale binarized image created by the grayscale binarized image creating means, the color of the end face among the pixel values of a group of pixels having pixel values not corresponding to the color of the end face. After gap complementation 2 for creating a binarized image after gap complementation by changing pixel values of a region surrounded by a group of pixels having corresponding pixel values to pixel values corresponding to the color of the end face It further has a value image creating means,
The counting target region extraction image creation unit is configured to extract a region having a pixel value corresponding to the color of the end face in the binarized image after gap complementation created by the gap complemented binary image creation unit. The long object count measuring apparatus according to claim 3, wherein a count target region extraction image is created by extracting from the second grayscale image created by the grayscale image creation means.   The long object number measuring device according to any one of claims 1 to 4, wherein the long object is a steel pipe having a cap colored with a predetermined color attached to an end surface thereof. The number of a plurality of long objects in which the end face is not open and is colored with a predetermined color, and a gap is formed in at least a partial region of the long objects adjacent to each other. A long object number measuring method for measuring the number of a plurality of long objects stacked in such a manner,
An original image acquisition step of acquiring an original image that is a color image obtained by imaging the end surfaces of the plurality of long objects;
A value of a first color space element set in advance according to the color of the end face is derived from the original image acquired by the original image acquisition step, and each pixel has a value of the first color space element. A first grayscale image creating step of creating a first grayscale image having a pixel value according to
A grayscale binarized image creating step of binarizing the first grayscale image created by the first grayscale image creating step to create a grayscale binarized image;
Based on the grayscale binarized image created by the grayscale binarized image creating step, a group of regions having pixel values corresponding to the color of the end face is identified, and an outer edge of the identified group of regions And a region separation step of separating the group of regions into a plurality of regions by moving the positions of the inner edges in the direction in which the group of regions exists,
A counting step of counting the plurality of long objects based on the number of regions separated by the region separation step;
An output step of outputting information including the number of the plurality of long objects counted in the counting step,
When the first color space element is a color of an end face of the plurality of stacked long objects and a color of a background of the end faces of the plurality of long objects stacked A method for measuring the number of long objects, which is an element having different values.   In the region separation step, the positions of pixels located on the outer edge and the inner edge of a group of regions having pixel values corresponding to the color of the end face are in a direction perpendicular to a tangent line with the pixel as a contact, The long object count measuring method according to claim 6, wherein the group of areas is separated into a plurality of areas by moving each group in a direction in which the group of areas exists. A value of a second color space element set in advance according to the color of the end face is derived from the original image acquired by the original image acquisition step, and each pixel has a value of the second color space element. A second grayscale image creating step of creating a second grayscale image having a pixel value according to
Based on the grayscale binarized image created by the grayscale binarized image creating step, an area having a pixel value corresponding to the color of the end face was created by the second grayscale image creating step. A counting target region extraction image creating step of creating a counting target region extraction image by extracting from the second grayscale image;
A counting target region binarized image creating step of binarizing the counting target region extracting image created by the counting target region extracting image creating step to create a counting target region binarized image;
The region separation step identifies and identifies a group of regions having pixel values corresponding to the color of the end face from the count target region binarized image created by the count target region binarized image creation step. By separating the positions of the outer edge and inner edge of the group of areas in the direction in which the group of areas exists, the group of areas is separated into a plurality of areas,
The second color space element has a difference between a value when the color is an end face color of the plurality of stacked long objects and a value when the color is a color of a gap between them. The method for measuring the number of long objects according to claim 6 or 7, wherein the element is larger than that in the first color space element. In the grayscale binarized image created by the grayscale binarized image creating step, the color of the end face among the pixel values of a group of pixels having pixel values not corresponding to the color of the end face. After gap complementation 2 for creating a binarized image after gap complementation by changing pixel values of a region surrounded by a group of pixels having corresponding pixel values to pixel values corresponding to the color of the end face It further has a value image creation process,
In the counting target region extraction image creation step, a region having a pixel value corresponding to the color of the end face in the binarized image after gap complementation created by the gap complemented binary image creation step 9. The method for measuring the number of long objects according to claim 8, wherein a count target region extraction image is created by extracting from the second gray scale image created by the gray scale image creation step.   The method for measuring the number of long objects according to any one of claims 6 to 9, wherein the long object is a steel pipe having a cap colored with a predetermined color attached to an end surface thereof.   A computer program for causing a computer to function as each means of the long object number measuring apparatus according to any one of claims 1 to 5.

Images