WO2019003686A1 - 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 - Google Patents
荷物認識装置、荷物仕分けシステムおよび荷物認識方法 Download PDFInfo
- Publication number
- WO2019003686A1 WO2019003686A1 PCT/JP2018/018943 JP2018018943W WO2019003686A1 WO 2019003686 A1 WO2019003686 A1 WO 2019003686A1 JP 2018018943 W JP2018018943 W JP 2018018943W WO 2019003686 A1 WO2019003686 A1 WO 2019003686A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- package
- color
- image
- processor
- luggage
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C3/00—Sorting according to destination
- B07C3/10—Apparatus characterised by the means used for detection ofthe destination
- B07C3/14—Apparatus characterised by the means used for detection ofthe destination using light-responsive detecting means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C7/00—Sorting by hand only e.g. of mail
- B07C7/005—Computer assisted manual sorting, e.g. for mail
-
- 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
- B65G1/137—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B21/00—Projectors or projection-type viewers; Accessories therefor
- G03B21/14—Details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1413—1D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Definitions
- the present disclosure relates to a package recognition device, a package sorting system, and a package recognition method useful for sorting packages.
- the sorting operation for sorting the packages according to the destination is a time-consuming process, and has relied on manual operations from before, but a technique for automating at least a part of the sorting operation has also been proposed.
- Patent Document 1 tracks moving packages, determines an image to be displayed based on information on a package read from the package and information on the location of the package, projects an image on the package from the projector, and places the image on the package Disclosed is a system for displaying.
- the present disclosure relates to techniques for more efficiently and accurately sorting packages.
- the present disclosure is a package recognition apparatus for recognizing the package based on a color image including one or more packages, comprising: a processor and a memory, the processor cooperating with the memory to convert the color
- the area of the one or more luggage in the image is estimated, the color of the background which is the area excluding the area of the one or more luggage in the color image is switched, and the color of the background of the color switched is used. Recognize each of the one or more packages based on it.
- the present disclosure includes a projection instruction device including the above-described package recognition device, a label reader for reading package specific information from a label attached to a package, a distance image sensor for acquiring a distance image including the package, and the package It is a package sorting system provided with a color image sensor which acquires a color image, and an image projector which projects a projection image which shows a classification place on the package.
- the present disclosure is a method of package recognition that recognizes the package based on a color image including one or more packages, wherein a processor cooperates with a memory to estimate a region of the one or more packages in the color image. And switching a color of a background which is an area excluding the area of the one or more packages in the color image, and recognizing each of the one or more packages based on the background of which the color is switched and the color of the area of the package. .
- sorting of packages can be performed more efficiently and accurately, and further increase in the circulation volume of packages can be coped with.
- the package color can be recognized even when the color of the package is close to or the same as the color of the belt of the transfer conveyor, and degradation of the package tracking accuracy can be prevented.
- FIG. 1 is a block diagram showing the configuration of a package sorting system according to the embodiment.
- FIG. 2 is a block diagram showing the configuration of the projection instruction apparatus according to the embodiment.
- FIG. 3A is a conceptual view showing a state in which the package sorting system is installed in the distribution center and in operation.
- FIG. 3B is a view showing a projected image including numbers on a top surface of the luggage.
- FIG. 4 is a view showing an example of a projection image generated by the projection instruction apparatus according to the embodiment.
- FIG. 5 is a flowchart showing an outline procedure of an operation mainly performed by the projection instruction apparatus.
- FIG. 6 is a flowchart showing the package recognition and tracking process.
- FIG. 7 is a diagram showing an example of switching the background color on a frame-by-frame basis.
- the embodiment which specifically discloses a package recognition device, a package sorting system, and a package recognition method according to the present disclosure will be described in detail with reference to the drawings as appropriate.
- the detailed description may be omitted if necessary.
- detailed description of already well-known matters and redundant description of substantially the same configuration may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art.
- the attached drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and they are not intended to limit the claimed subject matter.
- FIG. 1 is a block diagram showing the configuration of a package sorting system according to the embodiment.
- the package sorting system 100 shown in FIG. 1 is installed, for example, at a distribution center.
- the package sorting system 100 includes a label reader 10, an image sensor 20, a projection instruction device 30, and a projector 40.
- the package sorting system 100 is a system that supports the work of a worker who sorts the packages transported by the transport conveyor.
- the package sorting system 100 is installed at a distribution center owned by, for example, a retailer, a wholesaler, an internet distributor, and the like.
- the luggage to be sorted generally has a substantially rectangular parallelepiped shape, its outer shape is not particularly limited, and the type of luggage is also not particularly limited.
- the configuration of the package sorting system is not limited to that described in FIG.
- the quantity of each component can be appropriately changed according to the purpose, such as connecting a plurality of image sensors 20, the projection instruction device 30, and the projector 40 to one label reader 10.
- the label reader 10 as a reading device is a device including various elements such as a lens, an image sensor and the like (not shown). By using the label reader 10, it is possible to read label recording information in which various information related to the package is recorded from a label attached to the package transported by the transport conveyor. The package can be identified by using the read label recording information. Package specific information is defined by the read information.
- the image sensor 20 is an imaging device including various elements such as a lens, an image sensor, and the like (not shown).
- the image sensor 20 is generally configured as an imaging camera.
- the imaging camera is a three-dimensional camera, a plurality of two-dimensional cameras, or the like.
- the image sensor 20 includes a distance image sensor 22 and a color image sensor 24.
- the distance image sensor 22 picks up an item transported by the transfer conveyor and generates a distance image.
- the generated distance image is used as information indicating the position of the package, the distance to the package, the size of the package, and the like.
- the “distance image” refers to an image containing distance information indicating the distance from the imaging position to the position (including the surface of the luggage) indicated by each pixel (that is, in the present disclosure, the word “image” is a distance image). including). Further, the term “distance image” includes those that can not be recognized as an image by human eyes, such as a table listing numerical values indicating distances.
- the “distance image” may be any information as long as it indicates the relationship between the coordinates in the imaged area and the distance, and the data structure does not matter.
- the distance image sensor 22 is used to identify the position of the package. Therefore, the distance image sensor 22 may be replaced by another sensing device (ultrasonic sensor, infrared sensor, stereo camera, monocular video camera).
- the color image sensor 24 captures a package for which a distance image has been generated, and generates a color image.
- Color image refers to an image in which the color of the surface of the package is expressed in a predetermined gradation, and "gradation” includes not only 256 gradations of RGB but also all kinds such as gray scale.
- the color image sensor 24 is used to track each package for the package specified by the distance image sensor 22.
- the color image sensor 24 can also be replaced with another sensing device (ultrasonic sensor, infrared sensor, stereo camera, single-eye video camera).
- the term "image" includes both a distance image and a color image.
- information output from an image sensor as a sensing device including a distance image sensor and a color image sensor is referred to as sensing information.
- the present embodiment will be described using an image sensor 20 (including a distance image sensor 22 and a color image sensor 24) as an example of a sensing device. Further, in the present embodiment, as an example of sensing information, the description will be made using a distance image which is an output of the distance image sensor 22 and a color image which is an output of the color image sensor 24.
- the projection instruction device 30 plays a role as an arithmetic device in the luggage sorting system 100.
- the projection instruction device 30 includes an input unit 32, a processor 34, a memory 36, and an output unit 38 connected via a bus.
- the input unit 32 receives package specification information that can specify the package acquired from the label recording information read by the label reader 10, the distance image generated by the distance image sensor 22, and the color image generated by the color image sensor 24.
- the processor 34 is configured by a general computing device, and generates a projection image to be projected onto a package based on the package specific information, the distance image and the color image.
- the memory 36 as a storage device performs operations such as reading of control programs necessary for various processes by the processor 34 and saving of data.
- processor 34 and the memory 36 cooperate to control various processes by the projection instruction device 30.
- the output unit 38 outputs the projection image generated by the processor 34 to the projector 40.
- processor does not mean only a single processor.
- processor is a term that means an operation subject in the case where a plurality of processors with the same purpose and processors with different purposes (for example, a general-purpose CPU (Central Processing Unit) and a GPU (Graphic Processing Unit)) perform processing jointly. Also used as.
- the projector 40 is constituted by a general projection device, projects the projection light including the projection image received from the projection instructing device 30 onto a package, and displays the projection light on the package.
- the package sorting system 100 can be constructed by connecting the label reader 10, the image sensor 20 (the distance image sensor 22 and the color image sensor 24), the projection instruction device 30, and the projector 40 by wired communication or wireless communication. Further, two or more devices among the label reader 10, the image sensor 20, the projection instruction device 30, and the projector 40 can be constructed as an integrated device. For example, the image sensor 20 and the projector 40 can be combined to construct an integrated imaging and projection apparatus (see FIG. 3A).
- FIG. 3A is a conceptual view showing a state in which the package sorting system 100 is installed in the distribution center and in operation.
- each worker M visually checks the label affixed to each package P transported by the transport conveyor 50 in the direction of arrow X, and the package for which the worker himself is in charge of delivery arrives Then, it was necessary to pick up the package (pickup) and place it in the vicinity of the worker's own foot, a car, a truck bed and the like.
- sorting by visual inspection of the workers since there is a limit to the work efficiency of the workers, it was necessary to suppress the transport speed to a predetermined value or less.
- positioned above the conveyance conveyor 50 reads the label stuck on each package P conveyed by the conveyance conveyor 50.
- the label describes label recording information including various information on the package.
- the label record information includes information similar to the package identification number individually assigned to the package, the sender's name, address, telephone number, recipient's name, address, telephone number, package type, and the like. The reading of the label may be performed by the worker in charge corresponding to the barcode in the label with the barcode reader as the label reader 10 by hand.
- the image sensor 20 picks up an image (distance image and color image) of the package P transported by the transport conveyor 50, and the position of the package P, the distance to the package P, the size of the package P (the package P is a rectangular parallelepiped) In the case of three side lengths), the color of the package P, the pattern of the package P, etc. are acquired.
- positioning position of the label reader 10 and the image sensor 20, the kind of sensing device, and the order of a process in particular are not limited to the form shown in figure.
- the image sensor 20 and the projector 40 are constructed as an integrated imaging and projecting device 60 and disposed above the transport conveyor 50.
- the projection instruction device 30 which is not shown in FIGS. 3A and 3B, is constituted by a computer disposed, for example, in the vicinity of the transport conveyor 50 or in another room, and information for identifying the package acquired by the label reader 10, and an image. Based on the distance image and the color image generated by the sensor 20, a projection image to be displayed on the package P (for example, the upper surface when the package P is a rectangular parallelepiped) is generated.
- the projection instructing device 30 sends to the projector 40 a projection instruction to project the projection image onto the package P.
- the projector 40 as an image projection apparatus projects the projection light including the projection image generated by the projection instructing device 30 onto the package P, and displays the projection image on the package P.
- the projection image displayed on the package P is, for example, a circled number image having a color indicating the sorting place corresponding to the delivery address of the package P (see FIG. 3B).
- the circled numbers correspond to, for example, the number of the truck carrying the sorted luggage P (the number of the truck itself, the parking lot number, etc.), the number of the shelf or box to be carried into the truck, etc. ing.
- a zip code corresponding to the delivery address, or a number of a worker who should pick up the package P may be used.
- arrows indicating the sorting direction such as right or left with respect to the transport direction of the transport conveyor 50
- characters such as "left” or "right”
- the form of the display is not limited to the circled numbers, and various numbers may be considered such as the numbers enclosed by squares ("3", “359", "24735") as shown in FIG.
- the projected image is not limited to one enclosing a number or letter by a frame, and may be an open number or letter with a background.
- the shapes of numbers or characters to be displayed may be switched.
- the projection image is not limited to a still image, and may be animation.
- the animation it is conceivable to blink, scale, or change the color of each example described above.
- an animation reflecting the sorting direction may be projected.
- Examples of animation reflecting the sorting direction include, for example, moving a light beam or a light spot in the sorting direction, forming all or part of a projected image in the sorting direction, or changing the color, Various things can be considered, such as moving and displaying an arrow in the sorting direction.
- moving and displaying an arrow in the sorting direction When only part of the projected image is targeted for animation, the part that has a large influence on the judgment of the sorting destination by the operator, such as numbers and arrows, is not changed, and the part that has little influence on the sorting destination such as a frame It is conceivable to change it. However, in situations where it is more efficient to intuitively convey the sorting direction than the meaning of numbers etc.
- the “image projection device” is not limited to one that directly projects a light beam onto a package.
- the "image projection apparatus” also includes glasses capable of displaying an image. That is, in the present disclosure, when expressing projection light on a package, displaying an image on a package, projecting an image on a package, etc., the expression is simulated through glasses capable of displaying an image. Also, including making the worker recognize as if the projection light is projected on the package. That is, when the operator wears special glasses capable of displaying an image, the projection image may be superimposed on the image of the luggage P visually recognized through the glasses.
- FIG. 3A at the side of the transfer conveyor 50, there is a worker M who is in charge of picking up a package (other workers are omitted), and the package that has reached their respective area is circled number 1, circled number. 2. Pick up from the transfer conveyor 50 as shown by circle 3 and so on.
- the package P1 has package specification information of “AAA 111” in the label, and that the package specification information of “AAA 111” is to be a target of sorting in the area A. Therefore, when the package P1 arrives at the specific area, the processor 34 transmits the projection image generated as shown in FIG. 3B to the projector 40. Then, the projector 40 projects the projection image onto the package P1. Therefore, it is possible for the worker in the relevant area to easily pay attention to the package P1 to be picked up which has arrived in the specific area for which he is in charge, and as a result, it is possible to sort the packages more efficiently and accurately. It becomes possible.
- the presence or absence of the projection of a plurality of specific areas may be switched to one projector 40, and the plurality of projectors 40 may be switched in their respective specific areas.
- the presence or absence of projection may be switched.
- FIG. 5 is a flowchart showing an outline of an operation procedure mainly performed by the projection instruction device 30 of the present embodiment, in particular the processor 34 of the projection instruction device 30.
- the input unit 32 of the projection instruction device 30 acquires package specification information corresponding to the label recording information from the label reader 10 (step S1).
- the package identification information is at least one of information similar to the package identification number individually assigned to the package, the sender's name, address, phone number, recipient's name, address, phone number, package type, etc.
- the processor 34 assigns an ID as a package identification number for identifying the package to the package identifying information, and records the ID together with time information corresponding to the time when the ID is assigned (step S2).
- the ID recorded in the memory 36 may be a package identification number originally recorded in the package identification information, or the projection instructing device 30 may generate and assign a new ID.
- step S1 after capturing of the distance image of the luggage by the distance image sensor 22 of the image sensor 20, the input unit 32 of the projection instructing device 30 receives the distance image as sensing information from the distance image sensor 22 It acquires (step S20).
- the processor 34 determines whether an ID corresponding to a package present in the distance image is present in the memory 36.
- the processor 34 moves the package between the label reader 10 and the distance image sensor 22 from the distance (known) between the label reader 10 and the distance image sensor 22 and the speed of the transfer conveyor 50. Calculate the time required. Then, by subtracting the time from the time when the distance image is acquired, it is possible to estimate the time when the package present in the distance image is given an ID by the label reader 10 (and the processor 34). Then, it can be estimated that the ID given close to the estimated time is the ID corresponding to the package present in the distance image.
- the method of installing another distance image sensor in the label reader 10 vicinity is mentioned. That is, from when the label reader 10 assigns an ID (and the processor 34), the other distance image sensor installed in the vicinity of the label reader 10 is used to track the package to which the ID is assigned, for each time The distance between the package (and the ID) and the label reader 10 is measured.
- the processor 34 determines a predetermined distance from the distance between the measured package (and the ID) and the label reader 10, the distance of the package in the distance image acquired in step S20, and the distance (known) between the two distance image sensors. It is possible to estimate the ID of the package in the distance image acquired in step S20.
- the processor 34 determines whether or not the ID corresponding to the package included in the distance image is present in the memory 36 (step S30). That is, as described in step S2, in the memory 36, time information corresponding to the time when the package identification information, the ID, and the ID are given is recorded in advance. On the other hand, the processor 34 subtracts the time required for the package to move between the label reader 10 and the range image sensor 22 from the time when the range image is acquired, for example, as described above, so that the package exists in the range image. The time when the ID is given by the label reader 10 (and the processor 34) can be estimated.
- the processor 34 compares the time information recorded in advance in the memory 36 with the estimated time, and if these values are close (for example, when the time difference is less than or equal to a predetermined threshold time), It can be determined that the corresponding ID exists in the memory 36. If it is determined that the ID corresponding to the package exists in the memory 36 (step S30; Yes), the process proceeds to the process of step S60 and subsequent steps.
- step S30 If it is determined that the ID corresponding to the package does not exist in the memory 36 (step S30; No), the processor 34 specifies again the position of the package on the premise that the ID is not assigned to the package (step S30) S40), to give an ID to the package (step S50).
- the color image sensor 24 In parallel with the above-described steps, the color image sensor 24 generates a color image of each package for which the distance image has been acquired. Then, based on the color image from the color image sensor 24 acquired by the input unit 32, the processor 34 tracks the luggage with an ID which is transported and moved by the transport conveyor 50 (step S60). Then, the processor 34 determines, based on the color image, whether or not the package being tracked is picked up by the operator (step S70). If it is determined that the package is not picked up by the worker (Step S70; No), the processor 34 determines whether the package exists in a specific area (a predetermined sorting area where the package is to be picked up) described later. judge.
- a specific area a predetermined sorting area where the package is to be picked up
- step S80 When it is determined that the package is in the specific area (reached) (step S80; Yes), the processor 34 generates a projection image and transmits it to the projector 40 (step S90). If it is not determined that the package exists in the specific area (reached) (step S80; No), the process returns to step S60, and the processor 34 continues tracking the package.
- step S70 If it is determined in step S70 that the package has been picked up by the worker (step S70; Yes), the processor 34 reads the detailed information of the package from the memory 36 (step S100), and generates a projection image including the detailed information
- the projection image generated by the output unit 38 is output to the projector 40 (step S90).
- the projector 40 that has acquired the projection image from the projection instructing device 30 projects the projection image onto the corresponding luggage.
- step S70 is not limited to that described above.
- the determination in step S70 may be omitted.
- contact determination with a worker's hand and a package, and a color image, a distance image, etc. is also possible to use contact determination with a worker's hand and a package, and a color image, a distance image, etc. for implementation of determination of step S70.
- the detailed procedure of each process is further described.
- the color of the background is mainly the color of the belt of the transfer conveyor 50. If the color of the package is close to or the same as this color, it will be difficult to recognize the package, and furthermore, There is a possibility that tracking will not be possible.
- the package can be reliably identified by tracking the package.
- the processor 34 performs mask processing of the image to detect the package from the distance image of the package included in the sensing information, and thereafter obtains a background area excluding the package in the color image of the package included in the sensing information, Switch the background color.
- the processor 34 performs mask processing of the image to detect the package from the distance image of the package included in the sensing information, and thereafter obtains a background area excluding the package in the color image of the package included in the sensing information, Switch the background color.
- the color of the background which is an area excluding the package in the color image
- the package can be recognized even if the color of the package is close to or the same as the color of the belt of the transfer conveyor 50.
- recognition of the package becomes difficult. Therefore, by preparing a plurality of types of background color and switching them, it becomes possible to recognize the package.
- the switching of the plurality of background colors is performed, for example, at predetermined intervals including each frame.
- the background color to a plurality of colors different from the color of the package and switching the colors, the package can be reliably recognized, and the tracking accuracy can be kept high.
- FIG. 6 is an example of a flow corresponding to the above-described processing.
- the flow shown here shows the detailed processing in step S60 in the flowchart of the outline procedure in FIG. That is, the processor 34 detects the package from the distance image of the package included in the sensing information, and cuts out the region of the package detected from the distance image (step S101).
- the processor 34 detects the package from the distance image of the package included in the sensing information, and cuts out the region of the package detected from the distance image (step S101).
- the positional relationship between the distance image and the color image needs to be known in advance.
- the positional relationship between the distance image and the color image can be recognized, for example, by extracting a parameter indicating the correspondence between the distance image and the coordinate system of the color image by image processing and generating a transformation matrix.
- the processor 34 detects a package from the distance image, generates a mask image Imm obtained by cutting out the detected package area, and uses this mask image Imm to load the package in the package color image Imc included in the sensing information. Ask for backgrounds to exclude. Then, the obtained background color is switched at predetermined intervals (step S102). The switching of the background color is performed, for example, for each frame described above. Also, the background color to be switched selects a color different from the currently recognized color of the package. For example, among the background color candidates, one having a large difference in pixel value between the package color and the background color candidate is selected.
- FIG. 7 is a diagram showing an example of switching the background color on a frame-by-frame basis.
- three colors of pink, yellow and blue are prepared as background colors, and these colors are switched for each frame.
- the difference between pink, yellow and blue is represented by the density of dots. That is, pink is the coarsest, blue is the finest, and yellow is the middle of them.
- the color of the background is switched to pink at frame t1, to yellow at frame t2, and to blue at frame t3. Thereafter, the switching is repeated in the same manner.
- a color different from the color of the luggage is selected. For example, when the color of the luggage is yellow, yellow is excluded from the background color candidates, and pink and blue are switched.
- the processor 34 recognizes the package by switching the background color for each frame (step S103). In this case, if there is a plurality of packages, recognition is performed for all of them.
- the processor 34 starts tracking the recognized packages (step S104). Note that, as described above, the processor 34 generates a projection image for the recognized package, and the output unit 38 outputs the generated projection image to the projector 40. For example, a red circle 1, a green circle 2, or a blue circle 3 is projected onto each package.
- the tracking accuracy of the package is improved by estimating the region of the package in the color image using the distance image and tracking each package by the color image.
- recognition may be missed if the background color and the package color are similar, so in the present disclosure, the background color is switched. It reduces the possibility of such mistakes.
- the background color is switched between the three colors of pink, yellow and blue for each frame, but the present invention is not limited to this.
- the background color may be another color prepared in advance, or may be generated as needed for each frame. For example, if the color of the package is different from the color of the belt of the transfer conveyor 50, the color of the belt of the transfer conveyor 50 may be added as a candidate for the background color.
- RGB values that define the background color with a function using a frame number. For example, when each of RGB has 256 tones, a value obtained by adding a remainder obtained by dividing a frame number by 256 to a predetermined initial value may be used.
- the initial value or the value dividing the frame number is randomly set, the background color can be set more variously, and the tracking accuracy can be maintained.
- the background color is switched for each frame, but the present invention is not limited to this.
- the switching may be performed every two or more predetermined frames, or the switching cycle itself may be variable.
- the cycle may be shortened if the frequency of occurrence of tracking errors of packages increases.
- the background color may not be switched. Switching the background color can maintain the tracking accuracy of the package on average, but if the switched background color itself is similar to the color of the package, it is better to keep the tracking accuracy of the package if you do not switch the reverse There are times when you can do it. In such a case, it is desirable to use the background color for which tracking is successful as long as possible.
- the tracking accuracy can be evaluated, for example, by determining whether or not the package detected in the past frame has increased or decreased in the current frame.
- the number of packages also increases or decreases as the worker installs them on the pickup or the transfer conveyor 50, an increase or decrease in one package can occur even without a tracking error. Therefore, in the case where the tracking accuracy is determined by the number of packages, it is desirable to provide a predetermined threshold (increase or decrease of at least two or more).
- the user may be able to set the background color candidate.
- the color itself may be specified, or a color range may be specified. For example, assuming that the package is a general cardboard box, it is very likely that the brown package will be transported, but the red or green package is unlikely to be transported. Therefore, by setting to avoid a color close to brown as a candidate for the background color, or by setting red or green, it is possible to reduce the possibility of setting a color that falls in recognition accuracy as the background color.
- the background color candidate may be set in consideration of the color of the package. For example, by setting the background color candidate so as to avoid the color of the package successfully tracked in the previous frame, the possibility of losing the package already successfully tracked can be reduced. Selection of such background color candidates can be realized, for example, by evaluating the RGB values of the package being tracked. For example, for each RGB value, extract the closest value among packages under tracking, and set the median of the values as the background color, and set the color far from any package color as the background color I can do it.
- the distance image is used to obtain information indicating the position of the load, the distance to the load, the size of the load, etc., but the present invention is not limited to this.
- the above embodiment roughly estimates the position, distance, size, etc. of the package, and then sets the background color for accurate tracking by the color image, so it is used at the rough estimation stage.
- the means For example, if a two-dimensional barcode or the like attached to a package is used, it is possible to recognize the position, distance, size, and the like of the package without using a distance image.
- the present disclosure is useful for providing a package recognition device, a package sorting system, and a package recognition method that can reliably recognize the package even if the package color is close to or the same as the color of the transfer conveyor.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Sorting Of Articles (AREA)
- Warehouses Or Storage Devices (AREA)
Abstract
Description
図1は、実施の形態にかかる荷物仕分けシステムの構成を示すブロック図である。図1に示す荷物仕分けシステム100は、例えば物流センターに設置される。荷物仕分けシステム100は、ラベルリーダ10と、画像センサ20と、投影指示装置30と、プロジェクタ40とを備える。荷物仕分けシステム100は、搬送コンベヤにより搬送されてくる荷物を仕分ける作業員の作業を支援するシステムである。荷物仕分けシステム100は、例えば小売業者、卸売業者、インターネット流通業者などが所有する物流センターに設置される。仕分け対象の荷物は、一般的には略直方体の形状を有するものであるが、その外形は特に限定はされず、荷物の種類も特に限定されない。なお、荷物仕分けシステムの構成は図1に記載したものに限定されない。例えば、一台のラベルリーダ10に複数の画像センサ20と、投影指示装置30と、プロジェクタ40を接続させるなど、各構成要素の数量は目的に応じて適宜変更させることができる。
図3Aは、荷物仕分けシステム100が物流センターに設置され、稼働している状況を示す概念図である。従来の方法によれば、各作業者Mが、搬送コンベヤ50により矢印X方向に搬送されてくる各荷物Pに貼付されたラベルを目視によりチェックし、作業者自身が配送を担当する荷物が到着したら当該荷物を拾い上げて(ピックアップ)、作業者自身の足元、かご、トラックの荷台等の近傍に一旦置く必要があった。しかしながら、作業者の目視による仕分けの場合、作業者の作業効率には限界があるから、搬送速度を所定の値以下に抑える必要があった。結果として、作業者が単位時間内に仕分けることが可能な荷物の量の限界値は低かった。また、作業者がラベルの目視に際して誤認を行うことにより、仕分けに際して誤りを引き起こす可能性があった。近年、荷物の流通量は増大しており、これらの問題はより注目されつつある。
図5は、本実施形態の投影指示装置30、特に投影指示装置30のプロセッサ34が主として行う動作手順の概要を示すフローチャートである。まず、ラベルリーダ10による荷物のラベルのラベル記録情報の読み取り後、投影指示装置30の入力部32がラベルリーダ10から、ラベル記録情報に対応した荷物特定情報を取得する(ステップS1)。荷物特定情報とは、当該荷物に個別に付与される荷物特定番号、発送人の氏名、住所、電話番号、受取人の氏名、住所、電話番号、荷物の種類、等に類似する情報の少なくとも一つ含む情報である。プロセッサ34は、当該荷物特定情報に対して、当該荷物を特定する荷物特定番号としてのIDを付与し、IDを付与した時刻に対応する時刻情報とともにメモリ36に記録する(ステップS2)。メモリ36に記録するIDは、荷物特定情報に元から記録されていた荷物特定番号でもよいし、投影指示装置30が新しいIDを生成して付与してもよい。
距離画像を取得した荷物の色画像を用いて荷物の認識・追従を行う場合において、荷物が搬送される速度を用いて、次のフレームにおける位置を予測することにより、荷物の認識領域を絞ることができ、認識率の向上が図れる。しかしながら、荷物を認識する認識領域を絞ったとしても、背景の色が認識対象である荷物の色に近かったり、同じであったりした場合、認識対象である荷物の形状を誤ってしまったり、もしくは想定外の方向に移動した場合に認識から外れてしまったりする可能性が高い。すなわち、荷物の追跡精度が劣化してしまう可能性が高い。荷物仕分けシステムにおいては、背景の色は主に搬送コンベヤ50のベルトの色であり、この色に荷物の色が近かったり、同じであったりした場合、荷物の認識が困難となり、さらには荷物の追跡ができなくなる可能性が生じ得る。
20 画像センサ
22 距離画像センサ
24 色画像センサ
30 投影指示装置
32 入力部
34 プロセッサ
36 メモリ
38 出力部
40 プロジェクタ
50 搬送コンベヤ
60 撮像投影装置
100 荷物仕分けシステム
P 荷物
Claims (8)
- 1以上の荷物を含む色画像に基づき、前記荷物を認識する荷物認識装置であって、
プロセッサと、
メモリと、を備え、
前記プロセッサは、前記メモリと協働して、
前記色画像における前記1以上の荷物の領域を推定し、
前記色画像における前記1以上の荷物の領域を除く領域である背景の色を切り替え、
前記色を切り替えた背景と前記荷物の領域の色とに基づいて、前記1以上の荷物それぞれを認識する、
荷物認識装置。 - 請求項1に記載の荷物認識装置であって、
前記プロセッサは、前記背景の色を所定周期ごとに切り替える、
荷物認識装置。 - 請求項2に記載の荷物認識装置であって、
前記プロセッサは、前記荷物の認識精度に応じて、前記背景の色を切り替える周期を変更する、
荷物認識装置。 - 請求項1に記載の荷物認識装置であって、
前記プロセッサは、過去のフレームで認識に成功した荷物の色と異なる色を前記背景の色の候補とする、
荷物認識装置。 - 請求項1に記載の荷物認識装置であって、
前記プロセッサは、更に、
背景の色の候補の指定を受け付け、受け付けた候補の範囲内で前記背景の色を切り替える、
荷物認識装置。 - 請求項1から請求項4のいずれか1項に記載の荷物認識装置であって、
前記プロセッサは、距離画像を用いて、前記色画像における前記1以上の荷物の領域を推定する、
荷物認識装置。 - 請求項1に記載の荷物認識装置を含む投影指示装置と、荷物に貼付されたラベルから荷物特定情報を読み取るラベルリーダと、前記荷物を含む距離画像を取得する距離画像センサと、前記荷物を含む色画像を取得する色画像センサと、仕分け先を示す投影画像を前記荷物に投影する画像投影装置と、を備える荷物仕分けシステム。
- 1以上の荷物を含む色画像に基づき、前記荷物を認識する荷物認識方法であって、
プロセッサがメモリと協働して、
前記色画像における前記1以上の荷物の領域を推定し、
前記色画像における前記1以上の荷物の領域を除く領域である背景の色を切り替え、
前記色を切り替えた背景と前記荷物の領域の色とに基づいて、前記1以上の荷物それぞれを認識する、
荷物認識方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/623,667 US11145066B2 (en) | 2017-06-30 | 2018-05-16 | Parcel recognition device, parcel sorting system, and parcel recognition method |
EP18822731.8A EP3647232A4 (en) | 2017-06-30 | 2018-05-16 | BAGGAGE DETECTION DEVICE, BAGGAGE SORTING SYSTEM AND BAGGAGE DETECTION METHOD |
JP2019526669A JP7126065B2 (ja) | 2017-06-30 | 2018-05-16 | 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017-129574 | 2017-06-30 | ||
JP2017129574 | 2017-06-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019003686A1 true WO2019003686A1 (ja) | 2019-01-03 |
Family
ID=64742083
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2018/018943 WO2019003686A1 (ja) | 2017-06-30 | 2018-05-16 | 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US11145066B2 (ja) |
EP (1) | EP3647232A4 (ja) |
JP (1) | JP7126065B2 (ja) |
WO (1) | WO2019003686A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3953067A4 (en) * | 2019-04-10 | 2022-12-21 | Laitram, LLC | PACKAGE DETECTION AND INTELLIGENT SORTING |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7090134B2 (en) | 2003-03-04 | 2006-08-15 | United Parcel Service Of America, Inc. | System for projecting a handling instruction onto a moving item or parcel |
WO2007080834A1 (ja) * | 2006-01-10 | 2007-07-19 | Matsushita Electric Industrial Co., Ltd. | 色補正処理装置および色補正処理方法、ならびに、動的なカメラ色補正装置およびそれを用いた映像検索装置 |
WO2015145982A1 (ja) * | 2014-03-28 | 2015-10-01 | 日本電気株式会社 | 情報処理装置、情報処理システム、物流システム、情報処理方法およびプログラム記憶媒体 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1995024278A1 (en) | 1994-03-07 | 1995-09-14 | International Business Machines Corporation | Improvements in image processing |
US5737438A (en) * | 1994-03-07 | 1998-04-07 | International Business Machine Corp. | Image processing |
US6047889A (en) * | 1995-06-08 | 2000-04-11 | Psc Scanning, Inc. | Fixed commercial and industrial scanning system |
JP2000171215A (ja) * | 1998-12-03 | 2000-06-23 | Techno Wave:Kk | 物流情報読取り装置 |
FR2825817B1 (fr) * | 2001-06-07 | 2003-09-19 | Commissariat Energie Atomique | Procede de traitement d'images pour l'extraction automatique d'elements semantiques |
JP2011100244A (ja) * | 2009-11-05 | 2011-05-19 | Nippon Telegr & Teleph Corp <Ntt> | 文字色提案装置、文字色提案方法およびプログラム |
ES2837552T3 (es) * | 2010-03-13 | 2021-06-30 | Univ Carnegie Mellon | Método para reconocer y clasificar una planta de raíz desnuda |
-
2018
- 2018-05-16 US US16/623,667 patent/US11145066B2/en active Active
- 2018-05-16 EP EP18822731.8A patent/EP3647232A4/en active Pending
- 2018-05-16 WO PCT/JP2018/018943 patent/WO2019003686A1/ja active Application Filing
- 2018-05-16 JP JP2019526669A patent/JP7126065B2/ja active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7090134B2 (en) | 2003-03-04 | 2006-08-15 | United Parcel Service Of America, Inc. | System for projecting a handling instruction onto a moving item or parcel |
WO2007080834A1 (ja) * | 2006-01-10 | 2007-07-19 | Matsushita Electric Industrial Co., Ltd. | 色補正処理装置および色補正処理方法、ならびに、動的なカメラ色補正装置およびそれを用いた映像検索装置 |
WO2015145982A1 (ja) * | 2014-03-28 | 2015-10-01 | 日本電気株式会社 | 情報処理装置、情報処理システム、物流システム、情報処理方法およびプログラム記憶媒体 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3647232A4 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3953067A4 (en) * | 2019-04-10 | 2022-12-21 | Laitram, LLC | PACKAGE DETECTION AND INTELLIGENT SORTING |
Also Published As
Publication number | Publication date |
---|---|
JP7126065B2 (ja) | 2022-08-26 |
EP3647232A1 (en) | 2020-05-06 |
EP3647232A4 (en) | 2020-11-11 |
US11145066B2 (en) | 2021-10-12 |
JPWO2019003686A1 (ja) | 2020-04-23 |
US20200193612A1 (en) | 2020-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200282429A1 (en) | Package sorting system, projected instruction device, and package sorting method | |
JP7126066B2 (ja) | 投影指示装置、荷物仕分けシステムおよび投影指示方法 | |
WO2019064805A1 (ja) | 投影指示装置、荷物仕分けシステムおよび投影指示方法 | |
JP7129617B2 (ja) | 投影指示装置、荷物仕分けシステムおよび投影指示方法 | |
US11369999B2 (en) | Parcel determination device, parcel sorting system, and parcel determination method | |
JP7129616B2 (ja) | 投影指示装置、荷物仕分けシステムおよび投影指示方法 | |
WO2019003686A1 (ja) | 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 | |
JP7129614B2 (ja) | 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 | |
JP7194884B2 (ja) | 荷物仕分けシステム、投影指示装置、投影指示方法 | |
JP7045621B2 (ja) | 荷物認識装置、荷物仕分けシステムおよび荷物認識方法 |
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: 18822731 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2019526669 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2018822731 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2018822731 Country of ref document: EP Effective date: 20200130 |