WO2022254991A1 - Method for determining article type and system for determining article type - Google Patents

Method for determining article type and system for determining article type Download PDF

Info

Publication number
WO2022254991A1
WO2022254991A1 PCT/JP2022/018426 JP2022018426W WO2022254991A1 WO 2022254991 A1 WO2022254991 A1 WO 2022254991A1 JP 2022018426 W JP2022018426 W JP 2022018426W WO 2022254991 A1 WO2022254991 A1 WO 2022254991A1
Authority
WO
WIPO (PCT)
Prior art keywords
article
linear shape
type determination
point cloud
type
Prior art date
Application number
PCT/JP2022/018426
Other languages
French (fr)
Japanese (ja)
Inventor
学 橋本
大祐 福島
Original Assignee
村田機械株式会社
学校法人梅村学園
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 村田機械株式会社, 学校法人梅村学園 filed Critical 村田機械株式会社
Publication of WO2022254991A1 publication Critical patent/WO2022254991A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
    • B65G1/02—Storage devices
    • B65G1/04—Storage devices mechanical
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures

Definitions

  • the present invention relates to an article type determination method and an article type determination system for determining the type of an approximately rectangular parallelepiped article.
  • the present invention has been made in view of the above problems, and an object of the present invention is to provide an article type determination method and an article type determination system for determining the type of an article using point data obtained by three-dimensionally detecting unevenness on the surface of an article.
  • one aspect of the present invention provides an article type determination method using a detector that acquires a plurality of three-dimensional point data of a distance from an article to detect an article having a substantially rectangular parallelepiped shape.
  • An article type determination method for determining the type of an article based on the shape characteristics of a detection surface portion including a surface facing a container comprising: a point group acquisition step of acquiring point data at a plurality of locations on the detection surface portion of the article as a point cloud; , based on the point cloud acquired in the point cloud acquisition step, an edge detection step of detecting a pair of opposing edges of the detection surface portion of the article; and a pair of edges detected by the edge detection step. Based on the point group existing between and a type determination step of determining the type of the article.
  • another article type determination system includes a detector that acquires a distance to an article as three-dimensional multiple point data, and an article facing the detector. and an article type determination device that determines the type of an article based on the shape characteristics of the detection surface portion including the surface to be detected, wherein the article type determination device acquires point data of a plurality of locations on the detection surface portion of the article as a point group.
  • a group acquisition unit an edge detection unit that detects a pair of opposing edges of a detection surface of the article based on the point cloud acquired by the point cloud acquisition unit; a linear shape extracting unit for extracting a linear shape having linearity extending in a direction along the edge based on a point group existing between a pair of edges; and a straight line extracted by the linear shape extracting unit. and a type determination unit that determines the type of the article based on the shape.
  • FIG. 1 is a perspective view showing an article type determination system to which an article type determination method is applied; FIG. It is a perspective view which shows the transfer apparatus vicinity of an goods kind determination system.
  • 1 is a block diagram showing the functional configuration of an article type determination system;
  • FIG. 7 is a flow chart showing the flow of processing by a section detection unit; It is a figure which shows the processing state in each stage of the process of an area detection part.
  • 4 is a flow chart showing the flow of processing in an edge detection unit; It is a figure which shows the processing state in each stage of the process of an edge detection part.
  • 7 is a flow chart showing the flow of processing of a linear shape extraction unit; It is a figure which shows the processing state in each stage of the process of a linear shape extraction part. It is a flow chart which shows a flow of processing of an article kind judgment part.
  • FIG. 1 is a perspective view showing an article type determination system to which the article type determination method is applied.
  • FIG. 2 is a perspective view showing the vicinity of the transfer device 130 of the article type determination system.
  • the product type determination system 100 is a system for determining the type of the product 200 placed on the rack 110, and includes a detector 140 and a product type determination device 160 (not shown in FIGS. 1 and 2). there is In the case of this embodiment, the article type determination system 100 automatically conveys the articles 200 brought in, automatically transfers the articles 200 to the storage position of the articles 200, and automatically transfers the articles 200 from the storage position. It is a device capable of transporting a loaded article 200 and is incorporated in a so-called automated warehouse including a transport device 120 and a transfer device 130 .
  • the article 200 to be determined by the article type determination system 100 is not particularly limited as long as it has a substantially rectangular parallelepiped shape.
  • the term “substantially rectangular parallelepiped shape” includes a shape formed by six flat rectangular parallelepipeds, and also includes a shape having ribs, flange-like protrusions, depressions and holes like a handle.
  • the article 200 includes a first type article having a flat surface without linear unevenness on the surface, such as a cardboard box, a paper box, and a wooden box, and a container, a tray, a foldable container, and the like.
  • the rack 110 stores a plurality of substantially rectangular parallelepiped articles 200 arranged side by side such that the detection surfaces 201 of the articles 200 facing the area where the conveying device 120 moves are along a predetermined arrangement direction (the X-axis direction in the drawing). It is a facility to In the case of this embodiment, the rack 110 includes a shelf board 111 that holds the articles 200 in a placed state, and supports 112 that support the shelf board 111 .
  • the shelf board 111 has a flat plate shape, and the position where the article 200 is stored is not particularly limited.
  • the rack 110 is stored in a state in which the first type of articles 200 and the second type of articles 200 are mixed.
  • the drawing shows the rack 110 on one side as viewed in the moving direction of the conveying device 120, the racks 110 may be arranged on both sides.
  • the transport device 120 is a device that holds and transports the article 200, and is not particularly limited as long as the detector 140 is attached.
  • Examples of the transport device 120 include a trackless automated guided vehicle that holds the article 200 and autonomously travels on the floor, and a track-guided vehicle that holds the article 200 and travels along a predetermined track such as a rail. can do.
  • the conveying device 120 can hold a rail 121, a truck 122 running on the rail 121, a mast 123 attached to the truck 122 in an upright state and moving together with the truck 122, and an article 200. It is a so-called stacker crane provided with an elevator 124 that moves up and down along a mast 123 .
  • the transfer device 130 is a device that transfers the articles 200 between the rack 110 and the lifting platform 124 of the transport device 120, and is arranged in a depth direction perpendicular to the direction in which the articles 200 are arranged (the X-axis direction in the drawing) in the horizontal plane.
  • the article 200 is moved and transferred in the Y-axis direction in the drawing.
  • the type of the transfer device 130 is not particularly limited. For example, the article 200 is transferred while being slid, or the article 200 is scooped up and transferred.
  • the transfer device 130 is attached to the lift table 124 of the transport device 120, and can transfer the article 200 between the rack 110 and the lift table 124. . Note that when the racks 110 are arranged on both sides of the conveying device 120, the transfer device 130 is configured to transfer the article 200 to any of the racks 110 on either side.
  • the detector 140 is a sensor that acquires the distance between the detector 140 and multiple points on the detection surface portion 201 including the surface facing the detector 140 of the article 200 as multiple three-dimensional point data.
  • the type of detector 140 is not particularly limited, but examples thereof include three-dimensional ranging sensors such as LiDAR (Laser Imaging Detection and Ranging) sensors and TOF (Time of Flight) cameras.
  • the place where the detector 140 is installed is not particularly limited, but for example, if it is installed where the article 200 is transferred, it is preferable because the relative positional relationship between the transfer position and the article 200 can be accurately detected.
  • the detector 140 is attached to the lifting platform 124 of the transport device 120 .
  • the number of detectors 140 provided in article type determination system 100 is not particularly limited, in the case of this embodiment, two detectors 140 are provided in line in the arrangement direction of articles 200 .
  • the distance between the two detectors 140 is such that point data with a predetermined density or more can be acquired, and the assumed longest width of the articles 200 stored in the rack 110 in the arrangement direction and the adjacent articles set on both sides thereof 200 is set so as to include a distance range in which the area covering the gap with 200 can be detected at once.
  • the detectors 140 are attached one by one on both sides of the lift table 124 in the width direction (the X-axis direction in the drawing). That is, the detectors 140 are arranged on both sides of the area through which the articles 200 transferred by the transfer device 130 pass. This makes it possible to accurately detect the positional relationship between the area where the article 200 is transferred and the article 200 stored in the rack 110 in the vicinity thereof.
  • FIG. 3 is a block diagram showing the functional configuration of the product type determination system.
  • the product type determination device 160 is a device that determines the type of product based on the shape features of the detection surface portion 201 of the product 200 .
  • the product type determination device 160 includes a point group acquisition unit 151, an edge detection unit 155, a linear shape extraction unit 156, and a type determination unit 157 as processing units realized by causing a processor to execute a program.
  • the article type determination device 160 includes a section detection section 152 .
  • the point cloud acquisition unit 151 acquires point data at a plurality of locations on the detection surface 201 of the article 200 from the detector 140 as a point cloud.
  • the data structure of the point data is not particularly limited, but includes, for example, three-dimensional data indicating the relative positional relationship with respect to the transfer device 130 .
  • the arrangement direction of articles 200 on shelf board 111 of rack 110 (the X-axis direction in the figure)
  • the orthogonal direction the Z-axis direction in the figure) perpendicular to the arrangement direction on detection surface 201
  • the arrangement direction and It contains Cartesian coordinate system data with data in the depth direction (the Y-axis direction in the figure) that is perpendicular to any of the orthogonal directions.
  • the article type determination system 100 includes a plurality of detectors 140 arranged in the array direction, and the point cloud acquisition unit 151 acquires a point cloud from each of the detectors 140 . Since the adjacent detectors 140 partially overlap the imaging field angles, the point cloud acquisition unit 151 statistically processes the point data included in the overlapping regions, and obtains the point clouds of the plurality of detectors 140. are combined to form a single image. This makes it possible to process point data relating to the detection surface portions 201 of a plurality of articles 200 in the arrangement direction as one image. It should be noted that instead of synthesizing the point groups of the plurality of detectors 140 into one image, processing results may be obtained using images corresponding to the point groups of the respective detectors 140, and the results may be synthesized. .
  • the section detection unit 152 detects, from the point cloud acquired by the point cloud acquisition unit 151, an article-free section in which no article 200 exists in the arrangement direction.
  • FIG. 4 is a flow chart showing the processing flow of the section detection unit.
  • FIG. 5 is a diagram showing the processing state at each stage of the process of the section detection unit.
  • the section detection unit 152 executes a trimming process of extracting point data included in a predetermined region from the point cloud acquired from the point cloud acquisition unit 151 (S101, trimming step).
  • the predetermined area is not particularly limited, but includes, for example, the central position of the minimum height (the length in the orthogonal direction) of the article 200 stored in the rack 110, and is a band-shaped area having a predetermined height. I can give an example. Specifically, point data having a value in the orthogonal direction (Z-axis direction in the figure) less than the first threshold is excluded, and the orthogonal direction (Z-axis direction in the figure) greater than the second threshold (> first threshold) is excluded.
  • the point data in the range of the first threshold value or more and the second threshold value or less are extracted. Since the no-item section is detected based on the data of the predetermined height range in the trimming process, the effects of reflection from the shelf plate 111 of the rack 110 and the effects of ribs, flanges, holes, etc. provided on the surface of the article 200 are suppressed. This makes it possible to accurately detect empty sections. In addition, it is possible to suppress the data amount of the point group and promote the processing of the next step.
  • the section detection unit 152 projects the point group trimmed in the trimming process in the depth direction (transfer direction) to generate a two-dimensional first projection image shown in FIG. first projection step). Specifically, a two-dimensional first projection image is generated by excluding data in the depth direction (the Y-axis direction in the figure) from each point data.
  • the section detection unit 152 may generate a two-dimensional first projection image by vertically projecting the point group trimmed by the trimming process.
  • the section detection unit 152 performs morphology processing on the first projected image, interpolates between point data that existed as rough points, and corresponds to the article 200 as shown in FIG. 5(b). The data is changed so that the portion to be processed becomes a mass (white portion in the image of FIG. 5) (S103, first morphology step). In the case of the present embodiment, the section detection unit 152 performs closing processing that repeats expansion and contraction as morphology processing.
  • the section detection unit 152 searches for an existence section indicating a section in which the article 200 exists (S104, existence section rough search step).
  • the section detection unit 152 detects that the part (the white part in (b) of FIG. 5) regarded as a white lump in the first morphology process is interrupted in the vertical direction in the image corresponding to the orthogonal direction. Replaces missing parts and replaces parts that are regarded as a single white mass.
  • the existing interval end searching step is executed, the state becomes as shown in the image of FIG. 5(c), for example.
  • the interval detection unit 152 detects one end in the arrangement direction (horizontal direction in FIG. 5) of the white mass updated in the gap filling process or the white mass updated in the existence interval rough search process. to the other end (inverted triangular marks in (d) and (e) of FIG. 5) as the existence section corresponding to the section in which the article 200 exists (S107, existence section identification step). Also, sections other than existing sections, such as between adjacent existing sections, are specified as non-item sections.
  • the section detection unit 152 determines the middle position in the arrangement direction (horizontal direction in FIG. 5) of the empty section as the reference position (the position of the arrow in (e) of FIG. 5) (S108, reference position determination process).
  • the criteria for determining the reference position are not particularly limited, but for example, the center position between the ends of adjacent existing intervals may be determined as the reference position.
  • the end of the virtual existing section is located at a predetermined distance from the end of the existing section.
  • the reference position may be set between the edge of the existing section and the edge of the virtual existing section.
  • the distance at which the virtual existing section is provided may be equal to the first section threshold.
  • the predetermined second section threshold value the right side of (e) in FIG. 5
  • the edge detection unit 155 detects at least a pair of opposite edges of the detection surface 201 of the article 200 based on the point cloud acquired by the point cloud acquisition unit 151 .
  • the edge detector 155 detects two pairs of edges that intersect (perpendicular to) each other as contours.
  • FIG. 6 is a flow chart showing the processing flow of the edge detector.
  • FIG. 7 is a diagram showing the processing state at each stage of the process of the edge detector. The vertical line shown in the center in the left-right direction of FIG. 7 indicates the boundary of the areas corresponding to the two detectors 140 .
  • the edge detection unit 155 projects the point cloud acquired from the point cloud acquisition unit 151 in the depth direction (transfer direction) along the normal direction of the detection surface unit 201, and divides the data in the depth direction of each point data into two.
  • a projection image with gradation which is the second two-dimensional projection image shown in FIG. 7A, is generated by converting the gradation of each dot in the dimensional plane (S201, second projection step).
  • the projected image with gradation is expressed in grayscale.
  • the edge detection unit 155 performs morphology processing on the projected image with gradation, and supplements portions where point data is missing to correspond to the article 200 shown in FIG. 7B.
  • the data is changed so that the portion to be processed becomes one mass (S202, second morphology step).
  • the edge detection unit 155 performs closing processing that repeats expansion and contraction as morphology processing on the entire image including the existence section detected by the section detection unit 152 .
  • the edge detection unit 155 detects a pair of opposing edges that are edges of the detection surface 201 of the article 200 (S203, edge detection step).
  • the edge detection unit 155 detects each of the portions (three portions aligned in the left-right direction in FIG. 7B) regarded as one mass by the second morphology process for each existing section.
  • a binary image without gradation is obtained. Detected by image analysis.
  • the edge detection unit 155 detects a pair of lines extending in the vertical direction (corresponding to the orthogonal direction) of the detected rectangular contour as edges.
  • contours are detected for each of the point groups acquired from the two detectors 140. Therefore, for the existing section including the boundary, two contours are detected as shown in FIG. 7(c). detected.
  • the linear shape extracting unit 156 Based on the point group existing between the pair of edges detected by the linear shape extracting unit 156, the linear shape extracting unit 156 analyzes the image of the linear shape having linearity extending in the direction along the edge. Extract by FIG. 8 is a flow chart showing the flow of processing of the linear shape extraction unit. FIG. 9 is a diagram showing the processing state at each stage of the process of the linear shape extraction unit.
  • the contour obtained by image analysis is updated by several pixels (corresponding to several millimeters) inside.
  • the linear shape extraction unit 156 extracts the linear shape using the projection image with gradation generated in the second projection step (S201). Further, the linear shape extractor 156 extracts the linear shape using point data included inside the contour determined by the edge detector 155 . As a result, it is possible to search for a linear shape while excluding the edge portion of the article 200, thereby preventing erroneous detection of the type of the article 200 based on the point data corresponding to the edge portion.
  • the straight line shape extractor 156 acquires the gradation projected image from the edge detection unit 155, and extracts the gradation projected image within each contour based on a predetermined straight line detection algorithm as shown in FIG. 9(d). Linear shape candidates included in the gradation-applied projection image are extracted (S301, linear shape candidate extraction step).
  • the linear shape extracting unit 156 removes noise from the extracted linear shape candidates, and extracts a portion corresponding to the rib-like protruding portion on the detection surface 201 of the article 200 as shown in FIG. 9(e).
  • the data is updated so as to form a lump of linear shape (the white portion in the contour on the left side of (e) of FIG. 9) (S302, noise elimination step).
  • the linear shape extraction unit 156 extracts a linear shape from the noise-removed linear shape candidates (S203, linear shape extraction step).
  • the linear shape extractor 156 extracts a linear shape candidate that is parallel or substantially parallel to a pair of edges extending in the vertical direction (corresponding to the orthogonal direction) in the figure as a linear shape. This results in an image as shown in FIG. 9(f).
  • linear shape candidates that are parallel or substantially parallel to a pair of edges extending in the left-right direction (corresponding to the arrangement direction) in the figure are also extracted as linear shapes.
  • the type determination unit 157 determines the type of the article 200 based on the linear shape extracted by the linear shape extraction unit 156. In the case of this embodiment, as in the flowchart of the type determination process shown in FIG. When the linear shape is extracted in the linear shape extraction step (S401: Yes), the detection surface portion of the product 200 is the second type with irregularities. It is determined to be an article. Finally, the type determination unit 157 notifies the transport device 120 of the determination result (S104).
  • the article type determination device 160 executes the edge portion detection process, the linear shape extraction process, and the article type determination process for each article existence section separated by the section detection unit 152, Each result is reported to the transport device 120 .
  • the edge of the article 200 since the edge of the article 200 has a linear shape, the edge is excluded and the linear shape is extracted to determine the type of article. is determined, the first type of article 200 having a flat surface texture of the detection surface portion 201 and the second type of article 200 having an uneven surface such as ribs are arranged in a mixed state on the rack 110. , the type of the article 200 can be determined with high accuracy.
  • the determination accuracy of the type of article 200 can be improved by determining using a linear shape along a pair of opposing edges of the detection surface portion 201 .
  • the type of the article 200 is determined for each existing section.
  • the types of a plurality of articles 200 can be notified to the conveying device 120 or the like at high speed based on the points acquired at one time.
  • the present invention is not limited to the above embodiments.
  • another embodiment realized by arbitrarily combining the constituent elements described in this specification or omitting some of the constituent elements may be an embodiment of the present invention.
  • the present invention also includes modifications obtained by making various modifications to the above-described embodiment within the scope of the gist of the present invention, that is, the meaning of the words described in the claims, which a person skilled in the art can think of. be
  • the case where the pair of edges are parallel has been described. do not have.
  • the type of the article 200 may be determined based on at least one slope of the linear shape.
  • the type of the article 200 may be determined using point data sandwiched between a pair of edges without detecting the contour.
  • the width of the article 200 located in the center of the three articles 200 continuously arranged on the shelf board 111 of the rack 110 is added to the width of the empty sections existing on both sides.
  • a single detector 140 may be provided to detect the entire range at once.
  • the type of the article 200 was determined for each of the point groups obtained from the plurality of detectors 140. After combining the plurality of point groups into one point group, the type of the article 200 was determined. I don't mind.
  • the rack 110 that can two-dimensionally store the articles 200 in the horizontal direction and the vertical direction has been exemplified, the rack 110 may store the articles 200 one-dimensionally along the traveling direction of the carriage. do not have.
  • the present invention can be used in automated warehouses, distribution bases, factory facilities, etc. where it is required to discriminate the type of goods.
  • Article type determination system 110 Rack 111 Shelf board 112 Post 120 Conveying device 121 Rail 122 Cart 123 Mast 124 Lifting table 130 Transfer device 140 Detector 151 Point group acquisition unit 152 Section detection unit 155 Edge detection unit 156 Linear shape extraction unit 157 type determination section 160 article type determination device 200 article 201 detection surface section

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Warehouses Or Storage Devices (AREA)
  • Image Analysis (AREA)

Abstract

This system (100) for determining article type comprises: a detector (140) that acquires, as a plurality of three-dimensional point data, the distance to an article (200); and an article type determination device (160) that determines the type of the article (200) on the basis of a profile characteristic of a detected surface part (201) of the article (200). The article type determination device (160) is provided with: a point cloud acquisition unit (151) that acquires, as a point cloud, the point data pertaining to the detected edge part (201); an edge part detection unit (155) that detects a pair of mutually opposing edge parts of the detected surface part (201) on the basis of the point cloud; a linear profile extraction unit (156) that extracts a linear profile extending in a direction following the edge parts on the basis of a point cloud present between the pair of edge parts; and a type determination unit (157) that determines the type of the article (200) on the basis of the linear profile.

Description

物品種類判定方法、および物品種類判定システムArticle type determination method and article type determination system
　本発明は、略直方体状の物品の種類を判定する、物品種類判定方法、および物品種類判定システムに関する。 The present invention relates to an article type determination method and an article type determination system for determining the type of an approximately rectangular parallelepiped article.
　従来、特許文献１に記載されるように、物品の種類を示す識別情報を含むＲＦＩＤタグを複数の物品に付しておき、そのＲＦＩＤ（Ｒａｄｉｏ　Ｆｒｅｑｕｅｎｃｙ　ｉｄｅｎｔｉｆｉｅｒ）タグを読み取ることにより物品の種類を判定する技術が存在している。 Conventionally, as described in Patent Document 1, RFID tags containing identification information indicating the types of goods are attached to a plurality of goods, and the types of goods are determined by reading the RFID (Radio Frequency Identifier) tags. Technology exists to do so.
特開２０１９－２０２８４１号公報JP 2019-202841 A
　ところが、従来の技術では、予めすべての物品にＲＦＩＤタグを貼り付ける必要があり、ＲＦＩＤタグが貼り付けられていない物品を判定することはできなかった。 However, with conventional technology, it was necessary to affix RFID tags to all items in advance, and it was not possible to determine which items did not have RFID tags affixed.
　本発明は上記課題に鑑みなされたものであり、物品の表面の凹凸を三次元的に検出した点データを用いて物品の種類を判定する物品種類判定方法、および物品種類判定システムの提供を目的とする。 SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide an article type determination method and an article type determination system for determining the type of an article using point data obtained by three-dimensionally detecting unevenness on the surface of an article. and
　上記目的を達成するために、本発明の１つである物品種類判定方法は、物品との距離を三次元的な複数の点データとして取得する検出器を用い、略直方体状の物品の前記検出器と対向する面を含む検出面部の形状的特徴に基づき物品の種類を判定する物品種類判定方法であって、物品の検出面部の複数箇所の点データを点群として取得する点群取得工程と、前記点群取得工程において取得された点群に基づき、前記物品の検出面部の相対向する一対の縁部を検出する縁部検出工程と、前記縁部検出工程により検出された一対の縁部の間に存在する点群に基づいて、当該縁部に沿う方向に延在する直線性を有する直線形状を抽出する直線形状抽出工程と、前記直線形状抽出工程により抽出された直線形状に基づき前記物品の種類を判定する種類判定工程と、を含む。 In order to achieve the above object, one aspect of the present invention provides an article type determination method using a detector that acquires a plurality of three-dimensional point data of a distance from an article to detect an article having a substantially rectangular parallelepiped shape. An article type determination method for determining the type of an article based on the shape characteristics of a detection surface portion including a surface facing a container, the method comprising: a point group acquisition step of acquiring point data at a plurality of locations on the detection surface portion of the article as a point cloud; , based on the point cloud acquired in the point cloud acquisition step, an edge detection step of detecting a pair of opposing edges of the detection surface portion of the article; and a pair of edges detected by the edge detection step. Based on the point group existing between and a type determination step of determining the type of the article.
　上記目的を達成するために、本発明の他の１つである物品種類判定システムは、物品との距離を三次元的な複数の点データとして取得する検出器と、物品の前記検出器と対向する面を含む検出面部の形状的特徴に基づき物品の種類を判定する物品種類判定装置とを備え、前記物品種類判定装置は、物品の検出面部の複数箇所の点データを点群として取得する点群取得部と、前記点群取得部において取得された点群に基づき、前記物品の検出面部の相対向する一対の縁部を検出する縁部検出部と、前記縁部検出部により検出された一対の縁部の間に存在する点群に基づいて、当該縁部に沿う方向に延在する直線性を有する直線形状を抽出する直線形状抽出部と、前記直線形状抽出部により抽出された直線形状に基づき前記物品の種類を判定する種類判定部と、を備える。 In order to achieve the above object, another article type determination system according to the present invention includes a detector that acquires a distance to an article as three-dimensional multiple point data, and an article facing the detector. and an article type determination device that determines the type of an article based on the shape characteristics of the detection surface portion including the surface to be detected, wherein the article type determination device acquires point data of a plurality of locations on the detection surface portion of the article as a point group. a group acquisition unit; an edge detection unit that detects a pair of opposing edges of a detection surface of the article based on the point cloud acquired by the point cloud acquisition unit; a linear shape extracting unit for extracting a linear shape having linearity extending in a direction along the edge based on a point group existing between a pair of edges; and a straight line extracted by the linear shape extracting unit. and a type determination unit that determines the type of the article based on the shape.
　本発明によれば、表面に直線的な凹凸を有する物品とそれ以外の物品とを判別することができる。 According to the present invention, it is possible to distinguish between articles having linear unevenness on the surface and other articles.
物品種類判定方法が適用される物品種類判定システムを示す斜視図である。1 is a perspective view showing an article type determination system to which an article type determination method is applied; FIG. 物品種類判定システムの移載装置近傍を示す斜視図である。It is a perspective view which shows the transfer apparatus vicinity of an goods kind determination system. 物品種類判定システムの機能構成を示すブロック図である。1 is a block diagram showing the functional configuration of an article type determination system; FIG. 区間検出部の処理の流れを示すフローチャートである。7 is a flow chart showing the flow of processing by a section detection unit; 区間検出部の工程の各段階における処理状態を示す図である。It is a figure which shows the processing state in each stage of the process of an area detection part. 縁部検出部の処理の流れを示すフローチャートである。4 is a flow chart showing the flow of processing in an edge detection unit; 縁部検出部の工程の各段階における処理状態を示す図である。It is a figure which shows the processing state in each stage of the process of an edge detection part. 直線形状抽出部の処理の流れを示すフローチャートである。7 is a flow chart showing the flow of processing of a linear shape extraction unit; 直線形状抽出部の工程の各段階における処理状態を示す図である。It is a figure which shows the processing state in each stage of the process of a linear shape extraction part. 物品種類判定部の処理の流れを示すフローチャートである。It is a flow chart which shows a flow of processing of an article kind judgment part.
　以下、本発明に係る物品種類判定方法、および物品種類判定システムの実施の形態について、図面を参照しつつ説明する。なお、以下の実施の形態は、本発明を説明するために一例を挙示するものであり、本発明を限定する主旨ではない。例えば、以下の実施の形態において示される形状、構造、材料、構成要素、相対的位置関係、接続状態、数値、数式、方法における各段階の内容、各段階の順序などは、一例であり、以下に記載されていない内容を含む場合がある。また、平行、直交などの幾何学的な表現を用いる場合があるが、これらの表現は、数学的な厳密さを示すものではなく、実質的に許容される誤差、ずれなどが含まれる。また、同時、同一などの表現も、実質的に許容される範囲を含んでいる。 An embodiment of an article type determination method and an article type determination system according to the present invention will be described below with reference to the drawings. It should be noted that the following embodiments are examples for explaining the present invention, and are not intended to limit the present invention. For example, the shapes, structures, materials, constituent elements, relative positional relationships, connection states, numerical values, formulas, contents of each step in the method, order of each step, etc. shown in the following embodiments are examples, and are described below. may include content not listed in In addition, geometric expressions such as parallel and orthogonal are sometimes used, but these expressions do not indicate mathematical rigor, and substantially allowable errors, deviations, and the like are included. Expressions such as "simultaneous" and "identical" also include substantially permissible ranges.
　また、図面は、本発明を説明するために適宜強調、省略、または比率の調整を行った模式的な図となっており、実際の形状、位置関係、および比率とは異なる。 In addition, the drawings are schematic diagrams that have been appropriately emphasized, omitted, or adjusted in proportion in order to explain the present invention, and differ from the actual shape, positional relationship, and proportion.
　また、以下では複数の発明を一つの実施の形態として包括的に説明する場合がある。また、以下に記載する内容の一部は、本発明に関する任意の構成要素として説明している。 Also, hereinafter, multiple inventions may be comprehensively explained as one embodiment. Also, some of the contents described below are described as optional components related to the present invention.
　図１は、物品種類判定方法が適用される物品種類判定システムを示す斜視図である。図２は、物品種類判定システムの移載装置１３０近傍を示す斜視図である。物品種類判定システム１００は、ラック１１０に配置された物品２００の種類を判別するシステムであって、検出器１４０と、物品種類判定装置１６０（図１、図２において不図示）と、を備えている。本実施の形態の場合、物品種類判定システム１００は、搬入された物品２００を自動的に搬送して物品２００の保管位置へ物品２００を自動的に移載し、また保管位置から自動的に移載した物品２００を搬送することができる装置であり、搬送装置１２０と、移載装置１３０と、を備えたいわゆる自動倉庫に組み込まれている。 FIG. 1 is a perspective view showing an article type determination system to which the article type determination method is applied. FIG. 2 is a perspective view showing the vicinity of the transfer device 130 of the article type determination system. The product type determination system 100 is a system for determining the type of the product 200 placed on the rack 110, and includes a detector 140 and a product type determination device 160 (not shown in FIGS. 1 and 2). there is In the case of this embodiment, the article type determination system 100 automatically conveys the articles 200 brought in, automatically transfers the articles 200 to the storage position of the articles 200, and automatically transfers the articles 200 from the storage position. It is a device capable of transporting a loaded article 200 and is incorporated in a so-called automated warehouse including a transport device 120 and a transfer device 130 .
　物品種類判定システム１００の判定対象である物品２００は、略直方体状であれば特に限定されるものではない。略直方体状とは、平坦な矩形の六面で形成される形状を含み、またリブ状、フランジ状の突出、持ち手のような窪みや孔などを備える形状も含むものとして記載している。具体的に物品２００としては、段ボール箱、紙箱、木箱など表面に直線的な凹凸の形状を有さない平坦な表面性状を有する第一種類の物品と、コンテナ、トレー、折りたたみ可能なコンテナなど表面に直線的な凹凸の形状を有する表面性状の第二種類の物品と、の二種類の物品が存在する。 The article 200 to be determined by the article type determination system 100 is not particularly limited as long as it has a substantially rectangular parallelepiped shape. The term “substantially rectangular parallelepiped shape” includes a shape formed by six flat rectangular parallelepipeds, and also includes a shape having ribs, flange-like protrusions, depressions and holes like a handle. Specifically, the article 200 includes a first type article having a flat surface without linear unevenness on the surface, such as a cardboard box, a paper box, and a wooden box, and a container, a tray, a foldable container, and the like. There are two types of articles: a second type of article having a surface texture having linear unevenness on the surface.
　ラック１１０は、搬送装置１２０が移動する領域に面する物品２００の検出面部２０１が所定の配列方向（図中Ｘ軸方向）に沿うように並べて配置された略直方体状の複数の物品２００を保管する設備である。本実施の形態の場合、ラック１１０は、物品２００を載置状態で保持する棚板１１１と、棚板１１１を支持する支柱１１２とを備えている。棚板１１１は、平板状であり物品２００を保管する位置は特に限定されない。ラック１１０は、第一種類の物品２００と第二種類の物品２００とが混在した状態で保管される。なお、図には搬送装置１２０の移動方向に視て一方の側方にラック１１０を記載しているが、両側方にラック１１０が配置されていてもかまわない。 The rack 110 stores a plurality of substantially rectangular parallelepiped articles 200 arranged side by side such that the detection surfaces 201 of the articles 200 facing the area where the conveying device 120 moves are along a predetermined arrangement direction (the X-axis direction in the drawing). It is a facility to In the case of this embodiment, the rack 110 includes a shelf board 111 that holds the articles 200 in a placed state, and supports 112 that support the shelf board 111 . The shelf board 111 has a flat plate shape, and the position where the article 200 is stored is not particularly limited. The rack 110 is stored in a state in which the first type of articles 200 and the second type of articles 200 are mixed. Although the drawing shows the rack 110 on one side as viewed in the moving direction of the conveying device 120, the racks 110 may be arranged on both sides.
　搬送装置１２０は、物品２００を保持して搬送する装置であって、検出器１４０が取り付けられるものであれば特に限定されるものではない。搬送装置１２０としては、物品２００を保持して床面上を自律的に走行する無軌道の無人搬送車、物品２００を保持してレールなどの所定の軌道に沿って走行する有軌道台車などを例示することができる。本実施の形態の場合、搬送装置１２０は、レール１２１と、レール１２１上を走行する台車１２２と、台車１２２に起立状に取り付けられ台車１２２とともに移動するマスト１２３と、物品２００を保持可能でありマスト１２３に沿って昇降する昇降台１２４とを備えたいわゆるスタッカクレーンである。 The transport device 120 is a device that holds and transports the article 200, and is not particularly limited as long as the detector 140 is attached. Examples of the transport device 120 include a trackless automated guided vehicle that holds the article 200 and autonomously travels on the floor, and a track-guided vehicle that holds the article 200 and travels along a predetermined track such as a rail. can do. In the case of this embodiment, the conveying device 120 can hold a rail 121, a truck 122 running on the rail 121, a mast 123 attached to the truck 122 in an upright state and moving together with the truck 122, and an article 200. It is a so-called stacker crane provided with an elevator 124 that moves up and down along a mast 123 .
　移載装置１３０は、ラック１１０と搬送装置１２０の昇降台１２４との間で物品２００を移載する装置であり、水平面内において物品２００の配列方向（図中Ｘ軸方向）と直交する奥行方向（図中Ｙ軸方向）に物品２００を移動させて移載する。移載装置１３０の種類は、特に限定されるものではなく、例えば物品２００の対向する両側面を挟持して移載するもの、物品２００の奥側の面、手前側の面などに爪を引っ掛けて物品２００を滑らせながら移載するもの、物品２００をすくい上げて移載するもの等を例示することができる。 The transfer device 130 is a device that transfers the articles 200 between the rack 110 and the lifting platform 124 of the transport device 120, and is arranged in a depth direction perpendicular to the direction in which the articles 200 are arranged (the X-axis direction in the drawing) in the horizontal plane. The article 200 is moved and transferred in the Y-axis direction in the drawing. The type of the transfer device 130 is not particularly limited. For example, the article 200 is transferred while being slid, or the article 200 is scooped up and transferred.
　本実施の形態の場合、移載装置１３０は、搬送装置１２０の昇降台１２４に取り付けられており、ラック１１０と昇降台１２４との間で物品２００を移載することができるものとなっている。なお、搬送装置１２０の両側方にラック１１０が配置されている場合、移載装置１３０は、いずれの側のラック１１０のいずれに対しても物品２００を移載できるように構成される。 In the case of this embodiment, the transfer device 130 is attached to the lift table 124 of the transport device 120, and can transfer the article 200 between the rack 110 and the lift table 124. . Note that when the racks 110 are arranged on both sides of the conveying device 120, the transfer device 130 is configured to transfer the article 200 to any of the racks 110 on either side.
　検出器１４０は、物品２００における検出器１４０と対向する面を含む検出面部２０１の複数箇所と検出器１４０との間の距離を三次元的な複数の点データとして取得するセンサである。検出器１４０の種類は、特に限定されるものではないが、例えばＬｉＤＡＲ（Ｌａｓｅｒ　Ｉｍａｇｉｎｇ　Ｄｅｔｅｃｔｉｏｎ　ａｎｄ　Ｒａｎｇｉｎｇ）センサ、ＴＯＦ（Ｔｉｍｅ　ｏｆ　Ｆｌｉｇｈｔ）カメラなどの三次元測距センサを例示することができる。 The detector 140 is a sensor that acquires the distance between the detector 140 and multiple points on the detection surface portion 201 including the surface facing the detector 140 of the article 200 as multiple three-dimensional point data. The type of detector 140 is not particularly limited, but examples thereof include three-dimensional ranging sensors such as LiDAR (Laser Imaging Detection and Ranging) sensors and TOF (Time of Flight) cameras.
　検出器１４０が取り付けられる場所は、特に限定されないが、例えば物品２００が移載される場所に取り付けられると、移載位置と物品２００との相対的な位置関係を正確に検出できるため好ましい。本実施の形態の場合、検出器１４０は、搬送装置１２０の昇降台１２４に取り付けられている。物品種類判定システム１００が備える検出器１４０の個数は、特に限定されるものではないが、本実施の形態の場合、物品２００の配列方向に並ぶ２台の検出器１４０を備えている。２台の検出器１４０の距離は、所定の密度以上の点データを取得でき、配列方向におけるラック１１０に保管される物品２００の想定される最長の幅、およびその両側に設定される隣り合う物品２００との隙間をカバーする領域を一度に検出できる距離の範囲を含むように設定される。本実施の形態の場合、検出器１４０は、昇降台１２４の幅方向（図中Ｘ軸方向）の両側に一台ずつ取り付けられている。つまり、検出器１４０は、移載装置１３０によって移載される物品２００が通過する領域の両側部にそれぞれ配置されている。これにより、物品２００が移載される領域とその近傍のラック１１０に保管される物品２００との位置関係を正確に検出することが可能となる。 The place where the detector 140 is installed is not particularly limited, but for example, if it is installed where the article 200 is transferred, it is preferable because the relative positional relationship between the transfer position and the article 200 can be accurately detected. In the case of this embodiment, the detector 140 is attached to the lifting platform 124 of the transport device 120 . Although the number of detectors 140 provided in article type determination system 100 is not particularly limited, in the case of this embodiment, two detectors 140 are provided in line in the arrangement direction of articles 200 . The distance between the two detectors 140 is such that point data with a predetermined density or more can be acquired, and the assumed longest width of the articles 200 stored in the rack 110 in the arrangement direction and the adjacent articles set on both sides thereof 200 is set so as to include a distance range in which the area covering the gap with 200 can be detected at once. In the case of this embodiment, the detectors 140 are attached one by one on both sides of the lift table 124 in the width direction (the X-axis direction in the drawing). That is, the detectors 140 are arranged on both sides of the area through which the articles 200 transferred by the transfer device 130 pass. This makes it possible to accurately detect the positional relationship between the area where the article 200 is transferred and the article 200 stored in the rack 110 in the vicinity thereof.
　図３は、物品種類判定システムの機能構成を示すブロック図である。物品種類判定装置１６０は、物品２００の検出面部２０１の形状的特徴に基づき物品の種類を判定する装置である。物品種類判定装置１６０は、プログラムをプロセッサーに実行させることにより実現される処理部として、点群取得部１５１と、縁部検出部１５５と、直線形状抽出部１５６と、種類判定部１５７を備えている。本実施の形態の場合、物品種類判定装置１６０は、区間検出部１５２を備えている。 FIG. 3 is a block diagram showing the functional configuration of the product type determination system. The product type determination device 160 is a device that determines the type of product based on the shape features of the detection surface portion 201 of the product 200 . The product type determination device 160 includes a point group acquisition unit 151, an edge detection unit 155, a linear shape extraction unit 156, and a type determination unit 157 as processing units realized by causing a processor to execute a program. there is In the case of this embodiment, the article type determination device 160 includes a section detection section 152 .
　点群取得部１５１は、物品２００の検出面部２０１における複数箇所の点データを検出器１４０から点群として取得する。点データのデータ構造は、特に限定されるものではないが、例えば移載装置１３０に対する相対的な位置関係を示す三次元のデータを含んでいる。本実施の形態の場合、ラック１１０の棚板１１１における物品２００の配列方向（図中Ｘ軸方向）、検出面部２０１において配列方向に直交する直交方向（図中Ｚ軸方向）、および配列方向と直交方向のいずれにも直交する奥行方向（図中Ｙ軸方向）のデータを備えた直交座標系のデータを含んでいる。 The point cloud acquisition unit 151 acquires point data at a plurality of locations on the detection surface 201 of the article 200 from the detector 140 as a point cloud. The data structure of the point data is not particularly limited, but includes, for example, three-dimensional data indicating the relative positional relationship with respect to the transfer device 130 . In the case of this embodiment, the arrangement direction of articles 200 on shelf board 111 of rack 110 (the X-axis direction in the figure), the orthogonal direction (the Z-axis direction in the figure) perpendicular to the arrangement direction on detection surface 201, and the arrangement direction and It contains Cartesian coordinate system data with data in the depth direction (the Y-axis direction in the figure) that is perpendicular to any of the orthogonal directions.
　本実施の形態の場合、物品種類判定システム１００は、配列方向に並ぶ複数の検出器１４０を備えており、点群取得部１５１は、検出器１４０のそれぞれから点群を取得している。隣り合う検出器１４０は、撮像画角の一部が重複しているため、点群取得部１５１は、重複している領域に含まれる点データを統計処理し、複数の検出器１４０の点群を一枚の画像となるように合成している。これにより、配列方向において複数の物品２００の検出面部２０１に関する点データを一枚の画像として処理することが可能となる。なお、複数の検出器１４０の点群を１枚の画像に合成せず、各検出器１４０の点群に対応する画像を用いて処理結果を出し、その結果を合成するものであってもよい。 In the case of this embodiment, the article type determination system 100 includes a plurality of detectors 140 arranged in the array direction, and the point cloud acquisition unit 151 acquires a point cloud from each of the detectors 140 . Since the adjacent detectors 140 partially overlap the imaging field angles, the point cloud acquisition unit 151 statistically processes the point data included in the overlapping regions, and obtains the point clouds of the plurality of detectors 140. are combined to form a single image. This makes it possible to process point data relating to the detection surface portions 201 of a plurality of articles 200 in the arrangement direction as one image. It should be noted that instead of synthesizing the point groups of the plurality of detectors 140 into one image, processing results may be obtained using images corresponding to the point groups of the respective detectors 140, and the results may be synthesized. .
　区間検出部１５２は、点群取得部１５１において取得された点群から配列方向において物品２００が存在しない無物品区間を検出する。図４は、区間検出部の処理の流れを示すフローチャートである。図５は、区間検出部の工程の各段階における処理状態を示す図である。 The section detection unit 152 detects, from the point cloud acquired by the point cloud acquisition unit 151, an article-free section in which no article 200 exists in the arrangement direction. FIG. 4 is a flow chart showing the processing flow of the section detection unit. FIG. 5 is a diagram showing the processing state at each stage of the process of the section detection unit.
　区間検出部１５２の処理の流れの例を説明する。まず、区間検出部１５２は、点群取得部１５１から取得した点群から所定の領域内に含まれる点データを取り出すトリミング処理を実行する（Ｓ１０１、トリミング工程）。所定の領域は、特に限定されるものではないが、例えばラック１１０に保管される物品２００の最小高さ（直交方向の長さ）の中央位置を含み、所定の高さを有する帯状の領域を例示できる。具体的には、第一閾値未満の直交方向（図中Ｚ軸方向）の値を有する点データを除外し、かつ第二閾値（＞第一閾値）より大の直交方向（図中Ｚ軸方向）の値を有する点データを除外する。つまり、第一閾値以上、第二閾値以下の範囲にある点データを抽出する。トリミング工程により所定の高さ範囲のデータにより無物品区間の検出を行うため、ラック１１０の棚板１１１による反射などの影響、物品２００の表面に設けられるリブ、フランジ、孔などの影響を抑制する事ができ、正確に無物品区間を検出することが可能となる。また、点群のデータ量を抑制して次工程の処理の促進を図ることができる。 An example of the processing flow of the section detection unit 152 will be described. First, the section detection unit 152 executes a trimming process of extracting point data included in a predetermined region from the point cloud acquired from the point cloud acquisition unit 151 (S101, trimming step). The predetermined area is not particularly limited, but includes, for example, the central position of the minimum height (the length in the orthogonal direction) of the article 200 stored in the rack 110, and is a band-shaped area having a predetermined height. I can give an example. Specifically, point data having a value in the orthogonal direction (Z-axis direction in the figure) less than the first threshold is excluded, and the orthogonal direction (Z-axis direction in the figure) greater than the second threshold (> first threshold) is excluded. ) are excluded. That is, the point data in the range of the first threshold value or more and the second threshold value or less are extracted. Since the no-item section is detected based on the data of the predetermined height range in the trimming process, the effects of reflection from the shelf plate 111 of the rack 110 and the effects of ribs, flanges, holes, etc. provided on the surface of the article 200 are suppressed. This makes it possible to accurately detect empty sections. In addition, it is possible to suppress the data amount of the point group and promote the processing of the next step.
　次に、区間検出部１５２は、トリミング工程によってトリミングされた点群を奥行方向（移載方向）に投影して図５の（ａ）に示す二次元の第一投影画像を生成する（Ｓ１０２、第一投影工程）。具体的には、各点データから奥行方向（図中Ｙ軸方向）のデータを除外することにより二次元の第一投影画像を生成する。ここで、区間検出部１５２は、トリミング工程によってトリミングされた点群を上下方向に投影して二次元の第一投影画像を生成するものであってもよい。 Next, the section detection unit 152 projects the point group trimmed in the trimming process in the depth direction (transfer direction) to generate a two-dimensional first projection image shown in FIG. first projection step). Specifically, a two-dimensional first projection image is generated by excluding data in the depth direction (the Y-axis direction in the figure) from each point data. Here, the section detection unit 152 may generate a two-dimensional first projection image by vertically projecting the point group trimmed by the trimming process.
　次に、区間検出部１５２は、第一投影画像に対しモフォロジー処理を実行し、荒い点として存在していた点データの間を補完して図５の（ｂ）に示すように物品２００に対応する部分が一塊（図５の画像中における白色部分）となるようにデータを変更する（Ｓ１０３、第一モフォロジー工程）。本実施の形態の場合、区間検出部１５２は、モフォロジー処理として膨張と収縮とを繰り返すクロージング処理を行う。 Next, the section detection unit 152 performs morphology processing on the first projected image, interpolates between point data that existed as rough points, and corresponds to the article 200 as shown in FIG. 5(b). The data is changed so that the portion to be processed becomes a mass (white portion in the image of FIG. 5) (S103, first morphology step). In the case of the present embodiment, the section detection unit 152 performs closing processing that repeats expansion and contraction as morphology processing.
　次に、区間検出部１５２は、物品２００が存在している区間を示す存在区間を探索する（Ｓ１０４、存在区間荒探索工程）。本実施の形態の場合、区間検出部１５２は、第一モフォロジー工程により白色の一塊とみなした部分（図５の（ｂ）中の白色部分）について、直交方向に対応する画像における上下方向において途切れた部分、欠落した部分を補完して白色の一塊とみなす部分を更新する。存在区間端探索工程を実行すると例えば図５の（ｃ）の画像の様な状態になる。 Next, the section detection unit 152 searches for an existence section indicating a section in which the article 200 exists (S104, existence section rough search step). In the case of the present embodiment, the section detection unit 152 detects that the part (the white part in (b) of FIG. 5) regarded as a white lump in the first morphology process is interrupted in the vertical direction in the image corresponding to the orthogonal direction. Replaces missing parts and replaces parts that are regarded as a single white mass. When the existing interval end searching step is executed, the state becomes as shown in the image of FIG. 5(c), for example.
　次に、区間検出部１５２は、隣り合う白色の一塊の部分の間の区間の配列方向に対応する画像における横方向（図面に向かって左右方向）の黒色部分の距離と所定のギャップ閾値とを比較する（Ｓ１０５）。黒色部分の距離がギャップ閾値以下の場合（Ｓ１０５：Ｙｅｓ）、区間検出部１５２は、図５の（ｄ）に示すように、当該ギャップを埋めるように補完して白色の一塊とみなす部分を更新する（Ｓ１０６、ギャップ充填工程）。なお、図４中に記載される「＜＝」は小なりイコールを示している。 Next, the section detection unit 152 calculates the distance of the black section in the horizontal direction (horizontal direction as viewed in the drawing) in the image corresponding to the arrangement direction of the section between adjacent white blocks and a predetermined gap threshold. Compare (S105). When the distance of the black portion is equal to or less than the gap threshold (S105: Yes), the section detection unit 152 updates the portion regarded as a white lump by interpolating to fill the gap, as shown in (d) of FIG. (S106, gap filling step). Note that "<=" shown in FIG. 4 indicates less than equal.
　次に、区間検出部１５２は、ギャップ充填工程において更新された白色の一塊の部分、または存在区間荒探索工程で更新された白色の一塊の部分の配列方向（図５中横方向）における一端部から他端部まで（図５の（ｄ）（ｅ）の逆三角印）を物品２００が存在する区間に対応する存在区間として特定する（Ｓ１０７、存在区間特定工程）。また、隣り合う存在区間の間など存在区間以外の区間を無物品区間として特定する。 Next, the interval detection unit 152 detects one end in the arrangement direction (horizontal direction in FIG. 5) of the white mass updated in the gap filling process or the white mass updated in the existence interval rough search process. to the other end (inverted triangular marks in (d) and (e) of FIG. 5) as the existence section corresponding to the section in which the article 200 exists (S107, existence section identification step). Also, sections other than existing sections, such as between adjacent existing sections, are specified as non-item sections.
　次に、区間検出部１５２は、無物品区間の配列方向（図５の横方向）における中間の位置を基準位置（図５の（ｅ）の矢印の位置）として決定する（Ｓ１０８、基準位置決定工程）。基準位置の決定基準は特に限定されるものではないが、例えば、隣り合う存在区間の端部の間の中央の位置を基準位置として決定してもよい。また、所定の第一区間閾値以上の長さの無物品区間が存在する場合（図５の（ｅ）の左側）、存在区間の端部から所定の距離離れた位置に仮想の存在区間の端部（図５の（ｅ）の三角印）を設定し、存在区間の端部と仮想的な存在区間の端部との間に基準位置を設定してもかまわない。なお、仮想の存在区間を設ける距離は、第一区間閾値と同等であってもかまわない。また、存在区間の端部に挟まれていない無物品区間であって所定の第二区間閾値以下の無物品区間の場合（図５の（ｅ）の右側）、画像の端部を基準位置として設定してもかまわない。 Next, the section detection unit 152 determines the middle position in the arrangement direction (horizontal direction in FIG. 5) of the empty section as the reference position (the position of the arrow in (e) of FIG. 5) (S108, reference position determination process). The criteria for determining the reference position are not particularly limited, but for example, the center position between the ends of adjacent existing intervals may be determined as the reference position. In addition, when there is an empty section with a length equal to or greater than the first section threshold (the left side of (e) in FIG. 5), the end of the virtual existing section is located at a predetermined distance from the end of the existing section. The reference position may be set between the edge of the existing section and the edge of the virtual existing section. Note that the distance at which the virtual existing section is provided may be equal to the first section threshold. In addition, in the case of an empty section that is not sandwiched between the ends of existing sections and is equal to or smaller than the predetermined second section threshold value (the right side of (e) in FIG. 5), the end of the image is used as the reference position. You can set it.
　縁部検出部１５５は、点群取得部１５１において取得された点群に基づき、物品２００の検出面部２０１の相対向する少なくとも一対の縁部を検出する。本実施の形態の場合、縁部検出部１５５は、相互に交差（直交）する二対の縁部を輪郭として検出する。図６は、縁部検出部の処理の流れを示すフローチャートである。図７は、縁部検出部の工程の各段階における処理状態を示す図である。なお、図７の左右方向における中央に示される縦線は、二つの検出器１４０が対応する領域の境界を示している。 The edge detection unit 155 detects at least a pair of opposite edges of the detection surface 201 of the article 200 based on the point cloud acquired by the point cloud acquisition unit 151 . In the case of the present embodiment, the edge detector 155 detects two pairs of edges that intersect (perpendicular to) each other as contours. FIG. 6 is a flow chart showing the processing flow of the edge detector. FIG. 7 is a diagram showing the processing state at each stage of the process of the edge detector. The vertical line shown in the center in the left-right direction of FIG. 7 indicates the boundary of the areas corresponding to the two detectors 140 .
　縁部検出部１５５の処理の流れの例を説明する。まず、縁部検出部１５５は、点群取得部１５１から取得した点群を検出面部２０１の法線方向に沿う奥行方向（移載方向）に投影し、各点データの奥行方向のデータを二次元平面内の各ドットの階調に変換して図７の（ａ）に示す二次元の第二投影画像である階調付き投影画像を生成する（Ｓ２０１、第二投影工程）。本実施の形態の場合、階調付き投影画像は、グレースケールで表されている。 An example of the processing flow of the edge detection unit 155 will be described. First, the edge detection unit 155 projects the point cloud acquired from the point cloud acquisition unit 151 in the depth direction (transfer direction) along the normal direction of the detection surface unit 201, and divides the data in the depth direction of each point data into two. A projection image with gradation, which is the second two-dimensional projection image shown in FIG. 7A, is generated by converting the gradation of each dot in the dimensional plane (S201, second projection step). In the case of this embodiment, the projected image with gradation is expressed in grayscale.
　次に、縁部検出部１５５は、階調付き投影画像に対しモフォロジー処理を実行し、点データが欠落している部分などを補完して図７の（ｂ）に示すような物品２００に対応する部分が一塊となるようにデータを変更する（Ｓ２０２、第二モフォロジー工程）。本実施の形態の場合、縁部検出部１５５は、区間検出部１５２において検出された存在区間を含む画像全体に、モフォロジー処理として膨張と収縮とを繰り返すクロージング処理を行う。 Next, the edge detection unit 155 performs morphology processing on the projected image with gradation, and supplements portions where point data is missing to correspond to the article 200 shown in FIG. 7B. The data is changed so that the portion to be processed becomes one mass (S202, second morphology step). In the case of the present embodiment, the edge detection unit 155 performs closing processing that repeats expansion and contraction as morphology processing on the entire image including the existence section detected by the section detection unit 152 .
　次に、縁部検出部１５５は、物品２００の検出面部２０１の端縁である対向する一対の縁部を検出する（Ｓ２０３、縁部検出工程）。本実施の形態の場合、縁部検出部１５５は、存在区間毎に第二モフォロジー工程により一塊とみなした部分（図７の（ｂ）中の左右方向に並ぶ三つの部分）のそれぞれについて図７の（ｃ）に示すように階調を除いた二値の画像とし、この二値の画像に基づいて検出面部２０１の輪郭（図７の（ｃ）中の矩形で示された部分）をそれぞれ画像解析により検出する。縁部検出部１５５は、検出された矩形の輪郭の図中の上下方向（直交方向に対応）に延在する一対の線をそれぞれ縁部として検出する。本実施の形態の場合、二つの検出器１４０から取得した点群のそれぞれについて輪郭を検出しているため、境界を含む存在区間については図７の（ｃ）に示すように、二つの輪郭が検出される。 Next, the edge detection unit 155 detects a pair of opposing edges that are edges of the detection surface 201 of the article 200 (S203, edge detection step). In the case of the present embodiment, the edge detection unit 155 detects each of the portions (three portions aligned in the left-right direction in FIG. 7B) regarded as one mass by the second morphology process for each existing section. As shown in (c) of (c) of FIG. 7, a binary image without gradation is obtained. Detected by image analysis. The edge detection unit 155 detects a pair of lines extending in the vertical direction (corresponding to the orthogonal direction) of the detected rectangular contour as edges. In the case of the present embodiment, contours are detected for each of the point groups acquired from the two detectors 140. Therefore, for the existing section including the boundary, two contours are detected as shown in FIG. 7(c). detected.
　直線形状抽出部１５６は、直線形状抽出部１５６により検出された一対の縁部の間に存在する点群に基づいて、当該縁部に沿う方向に延在する直線性を有する直線形状を画像解析により抽出する。図８は、直線形状抽出部の処理の流れを示すフローチャートである。図９は、直線形状抽出部の工程の各段階における処理状態を示す図である。 Based on the point group existing between the pair of edges detected by the linear shape extracting unit 156, the linear shape extracting unit 156 analyzes the image of the linear shape having linearity extending in the direction along the edge. Extract by FIG. 8 is a flow chart showing the flow of processing of the linear shape extraction unit. FIG. 9 is a diagram showing the processing state at each stage of the process of the linear shape extraction unit.
　本実施の形態の場合、画像解析により得られた輪郭を数ピクセル（数ミリメートルに対応）分内側になるように輪郭を更新している。 In the case of the present embodiment, the contour obtained by image analysis is updated by several pixels (corresponding to several millimeters) inside.
　本実施の形態の場合、直線形状抽出部１５６は、第二投影工程（Ｓ２０１）により生成された階調付き投影画像を用いて直線形状を抽出している。また、直線形状抽出部１５６は、縁部検出部１５５により決定された輪郭の内側に含まれる点データを用いて直線形状を抽出している。これにより、物品２００のエッジ部分を除外して直線形状を探索することができ、エッジ部分に該当する点データによる物品２００の種類の誤検出を防止している。 In the case of the present embodiment, the linear shape extraction unit 156 extracts the linear shape using the projection image with gradation generated in the second projection step (S201). Further, the linear shape extractor 156 extracts the linear shape using point data included inside the contour determined by the edge detector 155 . As a result, it is possible to search for a linear shape while excluding the edge portion of the article 200, thereby preventing erroneous detection of the type of the article 200 based on the point data corresponding to the edge portion.
　直線形状抽出部１５６の処理の流れを説明する。直線形状抽出部１５６は、縁部検出部１５５から階調付き投影画像を取得し、それぞれの輪郭内の階調付き投影画像に対して所定の直線検出アルゴリズムに基づき図９の（ｄ）に示されるような階調付き投影画像に含まれる直線形状候補を抽出する（Ｓ３０１、直線形状候補抽出工程）。 The processing flow of the linear shape extraction unit 156 will be explained. The straight line shape extractor 156 acquires the gradation projected image from the edge detection unit 155, and extracts the gradation projected image within each contour based on a predetermined straight line detection algorithm as shown in FIG. 9(d). Linear shape candidates included in the gradation-applied projection image are extracted (S301, linear shape candidate extraction step).
　次に、直線形状抽出部１５６は、抽出された直線形状候補に対し、ノイズを除去して図９の（ｅ）に示すような物品２００の検出面部２０１にリブ状に突出する部分に対応する一塊の線状（図９の（ｅ）の左側の輪郭内における白色部分）となるようにデータを更新する（Ｓ３０２、ノイズ除去工程）。 Next, the linear shape extracting unit 156 removes noise from the extracted linear shape candidates, and extracts a portion corresponding to the rib-like protruding portion on the detection surface 201 of the article 200 as shown in FIG. 9(e). The data is updated so as to form a lump of linear shape (the white portion in the contour on the left side of (e) of FIG. 9) (S302, noise elimination step).
　次に、直線形状抽出部１５６は、ノイズが除去された直線形状候補から直線形状を抽出する（Ｓ２０３、直線形状抽出工程）。本実施の形態の場合、直線形状抽出部１５６は、図中の上下方向（直交方向に対応）に延在する一対の縁部と平行、または略平行の直線形状候補を直線形状として抽出する。これにより図９の（ｆ）に示すような画像となる。なお、本実施の形態の場合、図中の左右方向（配列方向に対応）に延在する一対の縁部と平行、または略平行の直線形状候補も直線形状として抽出している。 Next, the linear shape extraction unit 156 extracts a linear shape from the noise-removed linear shape candidates (S203, linear shape extraction step). In the case of this embodiment, the linear shape extractor 156 extracts a linear shape candidate that is parallel or substantially parallel to a pair of edges extending in the vertical direction (corresponding to the orthogonal direction) in the figure as a linear shape. This results in an image as shown in FIG. 9(f). In the case of this embodiment, linear shape candidates that are parallel or substantially parallel to a pair of edges extending in the left-right direction (corresponding to the arrangement direction) in the figure are also extracted as linear shapes.
　種類判定部１５７は、直線形状抽出部１５６により抽出された直線形状に基づき物品２００の種類を判定する。本実施の形態の場合、図１０に示す種類判定工程のフローチャートのように、種類判定部１５７は、直線形状抽出工程において直線形状が抽出されない場合（Ｓ４０１：Ｎｏ）、物品２００の検出面部が平坦な表面性状を有する第一種類の物品であると判定し（Ｓ４０３）、直線形状抽出工程において直線形状が抽出された場合（Ｓ４０１：Ｙｅｓ）、物品２００の検出面部が凹凸を有する第二種類の物品であると判定する。最後に種類判定部１５７は、判定結果を搬送装置１２０に報知する（Ｓ１０４）。 The type determination unit 157 determines the type of the article 200 based on the linear shape extracted by the linear shape extraction unit 156. In the case of this embodiment, as in the flowchart of the type determination process shown in FIG. When the linear shape is extracted in the linear shape extraction step (S401: Yes), the detection surface portion of the product 200 is the second type with irregularities. It is determined to be an article. Finally, the type determination unit 157 notifies the transport device 120 of the determination result (S104).
　本実施の形態の場合、物品種類判定装置１６０は、以上の縁部検出工程、直線形状抽出工程、物品種類判定工程を、区間検出部１５２により分離された各物品存在区間に対して実行し、それぞれの結果を搬送装置１２０に報知している。 In the case of the present embodiment, the article type determination device 160 executes the edge portion detection process, the linear shape extraction process, and the article type determination process for each article existence section separated by the section detection unit 152, Each result is reported to the transport device 120 .
　以上の実施の形態に係る物品種類判定システム１００によれば、物品２００の縁部は直線性のある形状を有しているため、当該縁部を除外した上で直線形状を抽出し物品の種類を判定することで、検出面部２０１が平坦な表面性状を有する第一種類の物品２００と、表面にリブなどの凹凸を有する第二種類の物品２００とがラック１１０に混在状態で配列される環境においても物品２００の種類を高精度で判定することができる。 According to the article type determination system 100 according to the above embodiment, since the edge of the article 200 has a linear shape, the edge is excluded and the linear shape is extracted to determine the type of article. is determined, the first type of article 200 having a flat surface texture of the detection surface portion 201 and the second type of article 200 having an uneven surface such as ribs are arranged in a mixed state on the rack 110. , the type of the article 200 can be determined with high accuracy.
　特に、検出面部２０１の対向する一対のエッジに沿った直線形状を用いて判定することにより、物品２００の種類の判定精度を向上させることができる。 In particular, the determination accuracy of the type of article 200 can be improved by determining using a linear shape along a pair of opposing edges of the detection surface portion 201 .
　また、隣り合う物品２００の間における物品２００が存在しない区間である無物品区間を検出して点群に対し物品２００相互の分離を行った後、各存在区間に対して物品２００の種類の判定を行うため、一度に取得した点群に基づき複数の物品２００の種類を高速に搬送装置１２０などに報知することができる。 In addition, after detecting non-item sections, which are sections in which no article 200 exists between adjacent articles 200, and separating the articles 200 from each other in the point cloud, the type of the article 200 is determined for each existing section. , the types of a plurality of articles 200 can be notified to the conveying device 120 or the like at high speed based on the points acquired at one time.
　また、二値の投影画像に基づき輪郭を決定し、決定された輪郭内の階調付き投影画像に基づき直線形状を抽出することにより、物品２００の縁部を効果的に除外することが可能となる。 It is also possible to effectively exclude the edges of the article 200 by determining the contour based on the binary projection image and extracting the linear shape based on the grayscale projection image within the determined contour. Become.
　また、抽出した直線形状候補に対しノイズ処理等を実行したのち直線形状を抽出することにより、点群に多くのノイズが含まれている場合でも物品２００の種類の判定に有効な直線形状を抽出することが可能となる。 In addition, by extracting the linear shape after executing noise processing etc. on the extracted linear shape candidate, even if the point cloud contains a lot of noise, the linear shape that is effective for determining the type of the article 200 is extracted. It becomes possible to
　なお、本発明は、上記実施の形態に限定されるものではない。例えば、本明細書において記載した構成要素を任意に組み合わせて、また、構成要素のいくつかを除外して実現される別の実施の形態を本発明の実施の形態としてもよい。また、上記実施の形態に対して本発明の主旨、すなわち、請求の範囲に記載される文言が示す意味を逸脱しない範囲で当業者が思いつく各種変形を施して得られる変形例も本発明に含まれる。 It should be noted that the present invention is not limited to the above embodiments. For example, another embodiment realized by arbitrarily combining the constituent elements described in this specification or omitting some of the constituent elements may be an embodiment of the present invention. The present invention also includes modifications obtained by making various modifications to the above-described embodiment within the scope of the gist of the present invention, that is, the meaning of the words described in the claims, which a person skilled in the art can think of. be
　例えば、上記実施の形態では一対の縁部が平行である場合を説明したが、例えば検出面部２０１が台形状であって一対の縁部が平行でない場合に物品種類判定方法を適用してもかまわない。この場合、一対の縁部にそう直線形状の傾きは二種類存在する。この場合少なくとも一方の傾きの直線形状に基づき物品２００の種類を判定してもかまわない。 For example, in the above-described embodiment, the case where the pair of edges are parallel has been described. do not have. In this case, there are two types of slopes of the linear shape at the pair of edges. In this case, the type of the article 200 may be determined based on at least one slope of the linear shape.
　また、検出面部２０１の輪郭を検出する場合を説明したが、輪郭を検出することなく一対の縁部に挟まれる点データを用いて物品２００の種類を判定してもかまわない。 Also, the case of detecting the contour of the detection surface portion 201 has been described, but the type of the article 200 may be determined using point data sandwiched between a pair of edges without detecting the contour.
　また、検出器１４０を複数備える場合を例示したが、ラック１１０の棚板１１１に連続して三つ並ぶ物品２００の中央に位置する物品２００の幅に両側に存在する無物品区間の幅を加えた範囲を一度に検出できる１台の検出器１４０を備えてもかまわない。 In addition, although the case where a plurality of detectors 140 are provided has been illustrated, the width of the article 200 located in the center of the three articles 200 continuously arranged on the shelf board 111 of the rack 110 is added to the width of the empty sections existing on both sides. A single detector 140 may be provided to detect the entire range at once.
　また、複数の検出器１４０から得られる点群のそれぞれについて物品２００の種類の判定を行ったが、複数の点群を合成して一つの点群とした後、物品２００の種類を判定してもかまわない。 Also, the type of the article 200 was determined for each of the point groups obtained from the plurality of detectors 140. After combining the plurality of point groups into one point group, the type of the article 200 was determined. I don't mind.
　また、水平方向、および鉛直方向に物品２００を二次元的に保管できるラック１１０を例示したが、ラック１１０は、搬送台車の走行する方向に沿って一次元的に物品２００を保管するものでもかまわない。 Moreover, although the rack 110 that can two-dimensionally store the articles 200 in the horizontal direction and the vertical direction has been exemplified, the rack 110 may store the articles 200 one-dimensionally along the traveling direction of the carriage. do not have.
　また、モフォロジー工程や、ノイズの除去処理工程などは省略することが可能である。 Also, it is possible to omit the morphology process and the noise removal process.
　また、上記実施例では画像全体に対するモフォロジー処理を施す例を示したが、存在区間のそれぞれについてモフォロジー処理をおこなっても同様の効果を奏する。 Also, in the above embodiment, an example of performing morphology processing on the entire image was shown, but the same effect can be obtained by performing morphology processing on each of the existence intervals.
　本発明は、物品の種類を判別することが要求される自動倉庫、物流拠点、工場設備などに利用可能である。 The present invention can be used in automated warehouses, distribution bases, factory facilities, etc. where it is required to discriminate the type of goods.
１００　物品種類判定システム
１１０　ラック
１１１　棚板
１１２　支柱
１２０　搬送装置
１２１　レール
１２２　台車
１２３　マスト
１２４　昇降台
１３０　移載装置
１４０　検出器
１５１　点群取得部
１５２　区間検出部
１５５　縁部検出部
１５６　直線形状抽出部
１５７　種類判定部
１６０　物品種類判定装置
２００　物品
２０１　検出面部 100 Article type determination system 110 Rack 111 Shelf board 112 Post 120 Conveying device 121 Rail 122 Cart 123 Mast 124 Lifting table 130 Transfer device 140 Detector 151 Point group acquisition unit 152 Section detection unit 155 Edge detection unit 156 Linear shape extraction unit 157 type determination section 160 article type determination device 200 article 201 detection surface section

Claims (6)

  1. 　物品との距離を三次元的な複数の点データとして取得する検出器を用い、略直方体状の物品における前記検出器と対向する面を含む検出面部の形状的特徴に基づき物品の種類を判定する物品種類判定方法であって、
    　物品の検出面部の複数箇所の点データを点群として取得する点群取得工程と、
    　前記点群取得工程において取得された点群に基づき、前記物品の検出面部における相対向する一対の縁部を検出する縁部検出工程と、
    　前記縁部検出工程により検出された一対の縁部の間に存在する点群に基づいて、当該縁部に沿う方向に延在する直線性を有する直線形状を抽出する直線形状抽出工程と、
    　前記直線形状抽出工程により抽出された直線形状に基づき前記物品の種類を判定する種類判定工程と、
    を含む物品種類判定方法。     Using a detector that acquires the distance from an article as three-dimensional multiple point data, the type of the article is determined based on the shape features of the detection surface portion including the surface facing the detector in the substantially rectangular parallelepiped article. An article type determination method comprising:
    a point cloud acquisition step of acquiring point data at a plurality of locations on the detection surface of the article as a point cloud;
    an edge detection step of detecting a pair of opposing edges on the detection surface portion of the article based on the point cloud acquired in the point cloud acquisition step;
    A linear shape extraction step of extracting a linear shape having linearity extending in a direction along the edge based on the point group existing between the pair of edges detected by the edge detection step;
    a type determination step of determining the type of the article based on the linear shape extracted by the linear shape extraction step;
    Article type determination method including
  2. 　前記縁部検出工程において、
    　前記点群取得工程において取得された点群に基づき、物品の検出面部の輪郭を検出し、
    　前記直線形状抽出工程において、
    　前記縁部検出工程により検出された前記輪郭の内側に存在する点群に基づいて、直線形状を抽出する、 
    請求項１に記載の物品種類判定方法。     In the edge detection step,
    detecting the contour of the detection surface portion of the article based on the point cloud acquired in the point cloud acquisition step;
    In the linear shape extraction step,
    extracting a linear shape based on a group of points existing inside the contour detected by the edge detection step;
    The article type determination method according to claim 1.
  3. 　前記縁部検出工程において、
    　前記点群取得工程において取得された前記点群を前記検出面部の法線方向に沿う奥行方向に投影し前記奥行方向のデータを階調に変換して示す階調付き投影画像を生成し、生成された前記階調付き投影画像に基づき物品の縁部を検出し、
    　前記直線形状抽出工程において、
    　前記階調付き投影画像に基づいて直線形状を抽出する、
    請求項１または２に記載の物品種類判定方法。     In the edge detection step,
    projecting the point cloud acquired in the point cloud acquiring step in the depth direction along the normal direction of the detection surface portion, and generating a projected image with gradation showing the data in the depth direction converted into gradation; detecting the edge of the article based on the projected image with gradation;
    In the linear shape extraction step,
    extracting a linear shape based on the projected image with gradation;
    The article type determination method according to claim 1 or 2.
  4. 　前記直線形状抽出工程において、
    　前記階調付き投影画像に基づいて直線性を有する形状に対応する部分の候補である直線形状候補を抽出し、前記直線形状候補からノイズを除去した後、直線形状を抽出する、
    請求項３に記載の物品種類判定方法。     In the linear shape extraction step,
    extracting a linear shape candidate, which is a candidate for a portion corresponding to a shape having linearity based on the projected image with gradation, removing noise from the linear shape candidate, and then extracting the linear shape;
    The article type determination method according to claim 3.
  5. 　前記直線形状抽出工程において直線形状が抽出されない場合、前記種類判定工程において、前記物品の検出面部が平坦な表面性状を有する第一種類の物品であると判定し、前記直線形状抽出工程において直線形状が抽出された場合、前記種類判定工程において、前記物品の検出面部が凹凸を有する第二種類の物品であると判定する
    請求項１から４のいずれか一項に記載の物品種類判定方法。     When the linear shape is not extracted in the linear shape extraction step, the type determination step determines that the detection surface portion of the article is the first type of product having a flat surface texture, 5. The article type determination method according to any one of claims 1 to 4, wherein, in the type determination step, the article is determined to be a second type article having unevenness on the detection surface portion when is extracted.
  6. 　物品との距離を三次元的な複数の点データとして取得する検出器と、
    　物品の前記検出器と対向する面を含む検出面部の形状的特徴に基づき物品の種類を判定する物品種類判定装置とを備え、
    　前記物品種類判定装置は、
    　物品の検出面部の複数箇所の点データを点群として取得する点群取得部と、
    　前記点群取得部において取得された点群に基づき、前記物品の検出面部の相対向する一対の縁部を検出する縁部検出部と、
    　前記縁部検出部により検出された一対の縁部の間に存在する点群に基づいて、当該縁部に沿う方向に延在する直線性を有する直線形状を抽出する直線形状抽出部と、
    　前記直線形状抽出部により抽出された直線形状に基づき前記物品の種類を判定する種類判定部と、
    を備える物品種類判定システム。     a detector that acquires the distance to the article as three-dimensional multiple point data;
    an article type determination device that determines the type of the article based on the shape characteristics of the detection surface portion including the surface of the article facing the detector,
    The article type determination device is
    a point cloud acquisition unit that acquires point data at a plurality of locations on the detection surface of the article as a point cloud;
    an edge detection unit that detects a pair of opposing edges of the detection surface of the article based on the point cloud acquired by the point cloud acquisition unit;
    a linear shape extraction unit that extracts a linear shape having linearity extending in a direction along the edge based on a point group existing between the pair of edges detected by the edge detection unit;
    a type determination unit that determines the type of the article based on the linear shape extracted by the linear shape extraction unit;
    An article type determination system comprising:
PCT/JP2022/018426 2021-06-01 2022-04-21 Method for determining article type and system for determining article type WO2022254991A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-092274 2021-06-01
JP2021092274A JP2022184429A (en) 2021-06-01 2021-06-01 Article type determination method and article type determination system

Publications (1)

Publication Number Publication Date
WO2022254991A1 true WO2022254991A1 (en) 2022-12-08

Family

ID=84323131

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/018426 WO2022254991A1 (en) 2021-06-01 2022-04-21 Method for determining article type and system for determining article type

Country Status (2)

Country Link
JP (1) JP2022184429A (en)
WO (1) WO2022254991A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010247959A (en) * 2009-04-16 2010-11-04 Ihi Corp Box-shaped work recognizing device and method
JP2011209116A (en) * 2010-03-30 2011-10-20 Dainippon Screen Mfg Co Ltd Three-dimensional position/attitude recognition apparatus and system using the same, method, program
JP2012126532A (en) * 2010-12-16 2012-07-05 Japan Tobacco Inc Article management device, article management method and program
JP2012153470A (en) * 2011-01-25 2012-08-16 Murata Machinery Ltd Automatic warehouse
JP2013053915A (en) * 2011-09-02 2013-03-21 Pasuko:Kk Data analysis device, data analysis method and program

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010247959A (en) * 2009-04-16 2010-11-04 Ihi Corp Box-shaped work recognizing device and method
JP2011209116A (en) * 2010-03-30 2011-10-20 Dainippon Screen Mfg Co Ltd Three-dimensional position/attitude recognition apparatus and system using the same, method, program
JP2012126532A (en) * 2010-12-16 2012-07-05 Japan Tobacco Inc Article management device, article management method and program
JP2012153470A (en) * 2011-01-25 2012-08-16 Murata Machinery Ltd Automatic warehouse
JP2013053915A (en) * 2011-09-02 2013-03-21 Pasuko:Kk Data analysis device, data analysis method and program

Also Published As

Publication number Publication date
JP2022184429A (en) 2022-12-13

Similar Documents

Publication Publication Date Title
CN108692681B (en) Recess detection device, conveyance device, and recess detection method
CN110322457B (en) 2D and 3D vision combined unstacking method
US10290115B2 (en) Device and method for determining the volume of an object moved by an industrial truck
CN111328408B (en) Shape information generating device, control device, loading/unloading device, distribution system, program, and control method
JP6649796B2 (en) Object state specifying method, object state specifying apparatus, and carrier
US7864302B2 (en) Method for detecting objects with a pivotable sensor device
CN105431370A (en) Method and system for automatically landing containers on a landing target using a container crane
EP3347672B1 (en) An apparatus for the determination of the features of at least a moving load
US12055943B2 (en) Pallet detection device, forklift, pallet detection method, and program
WO2022254990A1 (en) Edge position detection method, transfer position determination method, and article transfer system
JP2006300929A (en) Device for recognizing three-dimensional position of object, and depalettizing system
CN105067418B (en) A kind of plastic pallet physical features detection device based on laser scanning
WO2022254991A1 (en) Method for determining article type and system for determining article type
WO2022254992A1 (en) Angle detection method and angle detection system
JP5601332B2 (en) Transport vehicle
JP2024002525A (en) Bar code detection system, method for detecting bar code, and bar code detection program
WO2022162134A1 (en) System and method for using a camera to detect robot position on grid.
US20220097969A1 (en) Flexible, robotic automated storage and retrieval system
US20210347617A1 (en) Engaging an element
CN213301104U (en) Size detection system
CN116342695B (en) Unmanned forklift truck goods placing detection method and device, unmanned forklift truck and storage medium
TWI843363B (en) Shelf positioning method of a transporting device and transporting device capable of positioning a shelf
JP2017201493A (en) Columnar object recognition method, columnar object recognition apparatus, and unmanned traveling vehicle
CN118255087A (en) Goods shelf positioning method of conveying device and conveying device capable of positioning goods shelf
WO2024107684A1 (en) Logistics autonomous vehicle with robust object detection, localization and monitoring

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22815747

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22815747

Country of ref document: EP

Kind code of ref document: A1