KR102488693B1 - Manless parcel management system - Google Patents

Abstract

The present invention obtains vision information on at least one person entering and exiting a parcel storage area and at least one parcel, and among at least one person, a delivery barcode tagged by a delivery driver and a character tagged by a recipient among at least one person Recognition unit that recognizes barcodes and generates barcode information, extracts size information, movement route information, location information, number information, stacking information, and labeling information of at least one parcel based on vision information, and based on vision information and barcode information Provided is an unmanned delivery management system comprising a server unit for determining whether or not the package is stolen and an output unit for outputting a result according to whether or not the package is stolen.

Description

Unmanned parcel management system {Manless parcel management system}

The present invention relates to an unmanned courier management system, and more particularly, image processing based on vision information recognized by a recognition unit to analyze a three-dimensional image of a parcel and to prevent theft of a parcel through barcode information and a facial image of a person entering and leaving the parcel It is about unmanned delivery management system.

BACKGROUND OF THE INVENTION [0002] In recent years, online product sales such as e-commerce, TV home shopping, and mail order over the Internet are rapidly increasing, and mail or goods are frequently delivered when the recipient is absent.

In the case of multi-unit dwellings such as apartments or officetels, mail or items delivered while the recipient is absent are received and stored in the security office. There is a problem in that a delivery man or courier driver has to move to the guard room and ask for the storage of mail or articles, which is inconvenient, and when the guard room is empty, mail or articles cannot be delivered at all.

From the security guard's point of view, there was a burden associated with the storage of entrusted mail or articles, as well as the inconvenience of notifying the recipient to pick up the mail or articles by phone or intercom.

In addition, if the mail or items entrusted to the security guard are damaged or lost, a dispute over legal responsibility may also occur.

In addition, some people are reluctant to face the courier driver even during the time the recipient stays at home. In particular, women living alone often avoid direct confrontation with the courier driver in consideration of the risk of crime.

In addition, in reality, delivery of parcels is carried out by keeping a delivery book in the management office of an apartment or shopping mall, and after the delivery driver places the parcel, the delivery date and recipient's name are recorded by hand on the delivery book. Record receipt by hand in the courier ledger.

Accordingly, the process and procedure for delivering and receiving parcels to both the courier driver and the recipient are complicated, requiring unnecessary time and inefficient, and therefore, technology development is required to solve these problems.

(Patent Document 1) Patent Publication No. 10-2016-0048601 (2016.05.04.)

(Patent Document 2) Patent Publication No. 10-2016-0144052 (2016.12.16.)

An object of the present invention to solve the above problems is to implement a three-dimensional image of a parcel based on at least one parcel image taken in real time, and size information of the parcel extracted from at least one parcel image. , moving route information, location information, number information, stacking information, labeling information, and three-dimensional images are comprehensively analyzed to prevent theft of parcels and to provide an unmanned delivery management system that can respond quickly in case of theft.

In addition, an object of the present invention to solve the above problem is an unmanned delivery management system that determines whether or not a parcel is stolen based on at least one facial image and barcode information, generates a warning sound in case of theft, and informs the police station of the fact that the parcel has been stolen. is to provide

The technical problem to be achieved by the present invention is not limited to the above-mentioned technical problem, and other technical problems not mentioned can be clearly understood by those skilled in the art from the description below. There will be.

The configuration of the present invention for achieving the above object is to obtain vision information on at least one person entering and leaving the parcel storage area and at least one parcel, and to obtain a parcel barcode tagged by a courier driver among the at least one person and a recognition unit for generating barcode information by recognizing a character barcode tagged by a recipient among the at least one visitor; Based on the vision information, size information, movement route information, location information, number information, stacking information, and labeling information of the at least one package are extracted, and based on the vision information and the barcode information, it is determined whether or not the package is stolen. server unit to do; and an output unit for outputting a result according to whether or not the package is stolen.

In an embodiment of the present invention, the recognition unit is arranged to face the parcel storage area and captures the at least one person entering and exiting the parcel storage area and the at least one parcel in real time, thereby capturing the at least one person and A vision sensor unit including at least one camera that obtains vision information about the at least one parcel, wherein the vision information includes a facial image of the at least one visitor and the image of the at least one parcel, The server unit may include: an information storage unit for storing the at least one person's face image and the at least one parcel image transmitted from the vision sensor unit; and comparing the face image of the at least one visitor transmitted from the information storage unit to distinguish the same person and non-identical person, and comparing the at least one parcel image to create access information that distinguishes the same courier and non-identical courier. and a recognition unit, wherein the access recognition unit transmits the access information to the control unit.

In an embodiment of the present invention, the server unit includes: a size recognition unit for extracting the size information by recognizing the size of the at least one parcel based on the at least one parcel image transmitted from the information storage unit; a quantity determination unit for acquiring the number information obtained by counting the quantity of the package based on the size information transmitted from the size recognition unit; and a location recognition unit generating a 3D map based on the at least one parcel image transmitted from the information storage unit and generating the location information on the location of the at least one parcel, wherein the size recognition unit further includes the size recognition unit. , The quantity determination unit and the location recognition unit may transmit the size information, the number information, and the location information to the control unit.

In an embodiment of the present invention, the server unit tracks the at least one parcel and the movement path of the at least one visitor based on the facial image of the at least one visitor and the image of the at least one parcel, and the movement route information. It may further include a path estimation unit that generates a path estimation unit, and the path estimation unit transmits the movement path information to the control unit.

In an embodiment of the present invention, the recognition unit generates delivery barcode information and text barcode information based on the delivery barcode tagged by the delivery driver and the text barcode tagged by the recipient, and transmits them to the information storage unit and a barcode recognition unit, wherein the server unit matches the delivery barcode information transmitted from the information storage unit with the text barcode information and transmits matching information determined to match to the control unit. It can be characterized by doing.

In an embodiment of the present invention, the server unit receives and analyzes the vision information, the access information, the size information, the number information, the location information, the movement route information, and the matching information to determine whether or not the package has been stolen. and a theft confirmation unit that determines, when the theft confirmation unit determines that the parcel has been stolen, it generates warning information indicating that the parcel has been stolen so that the output unit, the police station, the recipient, and the courier driver work It may be characterized in that the facial image of the courier thief among the entrants is transmitted to the police station at the same time as transmitting to at least one of the courier companies.

In an embodiment of the present invention, the output unit may include a display unit outputting the matching information transmitted from the control unit; and a sound unit receiving the warning information transmitted from the control unit and sounding a warning sound.

The effect of the present invention according to the configuration as described above is to realize a three-dimensional image of a parcel based on at least one parcel image taken in real time, and size information of the parcel extracted from at least one parcel image, By comprehensively analyzing movement route information, location information, number information, stacking information, labeling information, and 3D images, it is possible to prevent theft of parcels and respond promptly in case of theft.

In addition, the effect of the present invention according to the configuration as described above is to determine whether or not the parcel is stolen based on at least one facial image and barcode information, generate a warning sound in case of theft, and promptly respond according to a notification to the police station of the stolen fact. can

The effects of the present invention are not limited to the above effects, and should be understood to include all effects that can be inferred from the detailed description of the present invention or the configuration of the invention described in the claims.

1 is a block diagram showing an unmanned parcel delivery management system according to an embodiment of the present invention.
Figure 2 is a perspective view showing a recognition unit of the unmanned parcel delivery management system according to an embodiment of the present invention.
Figure 3 is a perspective view showing that the recognition unit of the unmanned delivery management system according to an embodiment of the present invention is provided with three cameras.
Figure 4 is a perspective view showing that the recognition unit of the unmanned delivery management system according to an embodiment of the present invention is provided with two cameras.
Figure 5 is a flow chart showing a three-dimensional image analysis method of parcel delivery according to an embodiment of the present invention.
6 is a flow chart showing a method for preventing theft of parcels delivered using a three-dimensional image analysis method for parcels according to an embodiment of the present invention.
7 is an operation flow chart showing the operation flow of FIG. 1 according to an embodiment of the present invention.

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and, therefore, is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected (connected, contacted, combined)" with another part, this is not only "directly connected", but also "indirectly connected" with another member in between. "Including cases where In addition, when a part "includes" a certain component, it means that it may further include other components without excluding other components unless otherwise stated.

Terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

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

1. Unmanned delivery management system (400)

Hereinafter, an unmanned parcel delivery management system according to an embodiment of the present invention will be described with reference to FIGS. 1 to 4.

1 is a block diagram showing an unmanned parcel delivery management system according to an embodiment of the present invention.

Referring to FIG. 1 , an unmanned parcel delivery management system 400 according to an embodiment of the present invention includes a recognition unit 100, a server unit 200, and an output unit 300.

Figure 2 is a perspective view showing a recognition unit of the unmanned parcel delivery management system according to an embodiment of the present invention.

Referring to FIG. 2, the recognition unit 100 acquires vision information for at least one person entering and leaving the parcel storage area S and at least one parcel, and a delivery barcode tagged by a courier driver among at least one person. and barcode information is generated by recognizing a character barcode tagged by a recipient among at least one visitor.

The recognition unit 100 for this includes a vision sensor unit 110 and a barcode recognition unit 120 .

Figure 3 is a perspective view showing that the recognition unit of the unmanned delivery management system according to an embodiment of the present invention is provided with three cameras. Figure 4 is a perspective view showing that the recognition unit of the unmanned delivery management system according to an embodiment of the present invention is provided with two cameras.

The vision sensor unit 110 is arranged to face the delivery storage area S and captures at least one person entering and exiting the delivery storage area S and at least one delivery parcel in real time, thereby capturing at least one visitor and at least one parcel. Acquires vision information about parcel delivery. At this time, the vision information includes at least one facial image of the visitor and at least one parcel image.

The vision sensor unit 110 for acquiring the vision information includes a first camera 111, a second camera 112, and a third camera 113 as shown in FIG.

The first camera 111, the second camera 112, and the third camera 113 are arranged to face the delivery storage area S, and the first camera ( 111), it is preferable that the areas photographed by the second camera 112 and the third camera 113 overlap.

However, the present invention is a modified example, and as shown in FIG. 4, the first camera 111 and the second camera 112 may be formed to take a picture of the parcel storage area (S).

The barcode recognition unit 120 generates delivery barcode information and text barcode information based on a delivery barcode tagged by a delivery driver among visitors and a text barcode tagged by a recipient among visitors and transmits them to the information storage unit.

The barcode recognition unit 120 for this may include a barcode sensor capable of recognizing a delivery barcode and a character barcode.

Here, the delivery barcode and the text barcode are barcodes containing unique information given to each parcel.

Specifically, the courier barcode is a barcode transmitted to the mobile terminal of the courier when the courier is entrusted to the courier, and the text barcode is a barcode containing unique information about the courier consigned to the courier, and is transmitted to the mobile terminal of the recipient.

That is, the parcel delivery barcode and the text barcode are different only in the transmission location and transmission form, but the unique information is the same barcode.

Therefore, after the courier driver places the parcel in the parcel storage area (S) and recognizes the parcel barcode in the barcode recognition unit 120, the recipient recognizes the text barcode in the barcode recognition section 120, so that the parcel barcode and the text barcode are If it matches, you can receive the parcel. A detailed description related to this will be described later in detail.

The server unit 200 extracts size information, movement route information, location information, number information, stacking information, and labeling information of at least one parcel based on the vision information, and determines whether or not the parcel is stolen based on the vision information and barcode information. judge

The server unit 200 for this purpose includes an information storage unit 210, an access recognition unit 220, a size recognition unit 230, a quantity determination unit 240, a location recognition unit 250, a path estimation unit 260, It includes a barcode matching unit 270, a theft confirmation unit 280 and a control unit 290.

The information storage unit 210 stores at least one face image of the visitor and at least one parcel image transmitted from the vision sensor unit 110 .

At this time, the at least one visitor's facial image and at least one parcel image are images taken by the first camera 111, the second camera 112, and the third camera 113, and the first camera 111, the first Since the positions of the second camera 112 and the third camera 113 are different, the images are captured at different angles.

The access recognition unit 220 compares at least one visitor's facial image transmitted from the information storage unit 210 to distinguish between the same person and a non-identical person, and compares at least one parcel image to distinguish between the same courier and non-identical courier. Create access information.

Specifically, the access recognition unit 220 compares the facial image of one of at least one person. At this time, the facial images are three facial images captured by the first to third cameras 111, 112, and 113. The access recognition unit 220 recognizes objects in the face image and extracts contour lines and features.

In the same manner as described above, the access recognition unit 220 recognizes an object of at least one visitor's face image, extracts contours and features, and compares them to distinguish between the same person and non-identical person.

Next, the access recognition unit 220 generates access information by matching information recording the entry and exit times of the same person and non-identical person with the facial image, and transmits the information to the control unit 290.

The size recognition unit 230 extracts size information by recognizing the size of at least one parcel based on at least one parcel image transmitted from the information storage unit 210 .

Specifically, the size recognition unit 230 matches the images of the delivery parcel photographed by the first to third cameras 111, 112, and 113 to determine whether the parcel is identical or non-identical. For this purpose, the size recognition unit 230 recognizes the object of the parcel image, extracts outlines and features, and recognizes the size of the parcel through a process of comparing and matching the parcel image with surrounding images.

The quantity determination unit 240 obtains number information obtained by counting the quantity of parcels based on the size information transmitted from the size recognition unit 230 .

The location recognition unit 250 creates a 3D map based on at least one parcel image transmitted from the information storage unit 210 to generate location information on the location of at least one parcel.

Specifically, the location recognition unit 250, similar to the access recognition unit 220, recognizes an object of at least one parcel image of the parcel, extracts the outline and features, and compares the parcel image with the surrounding images to determine the location of the parcel. Recognize.

The aforementioned size recognition unit 230, quantity determination unit 240, and location recognition unit 250 transmit size information, number information, and location information to the control unit 290.

The route estimating unit 260 generates movement route information by tracking the movement path of at least one parcel and at least one person based on the face image of at least one person and at least one image of parcel delivery.

Specifically, the path estimation unit 260 tracks the moving path of the package based on the location information generated by the location recognition unit 250 . To this end, the path estimating unit 260 can estimate the moving path of the package by tracking it in real time after generating labeling information for labeling the 3D package for sale.

The path estimation unit 260 transmits movement path information to the control unit 290 .

The barcode matching unit 270 matches the courier barcode information and the text barcode information transmitted from the information storage unit 210 to determine whether or not they match, and transmits the matching information to the control unit 290 .

If the barcode matching unit 270 matches the parcel delivery barcode information and the text barcode information, the barcode recognition unit 120 determines that the recipient tagged with the text barcode is the person to receive the parcel, and converts the matching information among the matching information to the control unit. 290, and at this time, the sound unit 320 to be described later does not generate a warning sound.

On the other hand, if the barcode matching unit 270 does not match the delivery barcode information and the text barcode information, it is determined that the recipient tagged with the text barcode to the barcode recognition unit 120 is not the person to receive the parcel, and the information inconsistent among the matching information. is transmitted to the control unit 290, and at this time, a warning sound is generated from the sound unit 320 to be described later.

The theft confirmation unit 280 determines whether the parcel is stolen by receiving and analyzing vision information, access information, size information, number information and location information, movement route information, and matching information.

Specifically, the theft confirmation unit 280 generates a three-dimensional image of the parcel based on vision information, access information, size information, number information and location information, movement route information, and matching information, and performs real-time tracking for the three-dimensional image, Comprehensively analyzes whether or not the three-dimensional image of the parcel is in or out, whether the quantity is added or subtracted, and whether the location is changed.

For example, the theft confirmation unit 280 determines whether or not it has been stolen by comprehensively grasping matters such as a change in the location of the initially placed parcel, a change in the quantity of the parcel, or a change in the quantity of the parcel. do.

If the theft confirmation unit 280 determines that the parcel has been stolen, it generates warning information indicating that the parcel has been stolen and sends it to at least one of the output unit 300, the police station, the recipient, and the courier company where the courier driver works. At the same time as the transmission, the facial image of the courier thief among the entrants can be transmitted to the police station.

The control unit 290 includes vision information transmitted from the information storage unit 210, access information transmitted from the access recognition unit 220, size information transmitted from the size recognition unit 230, and quantity information transmitted from the quantity determination unit 240. The number information, location information transmitted from the location recognition unit 250, movement route information transmitted from the path estimation unit 260, and matching information transmitted from the barcode matching unit 270 are transmitted to the theft confirmation unit 280.

At this time, the theft confirmation unit 280 comprehensively analyzes the received information based on the stolen or not, generates warning information and transmits it to the control unit 290.

Thereafter, the controller 290 may transmit warning information to the sound unit 320 and control the sound unit 320 to generate a warning sound. In addition, the control unit 290 transmits matching information to the display unit 310 and controls the display unit 310 to output matching results.

The output unit 300 outputs a result depending on whether or not the package is stolen. The output unit 300 for this includes a display unit 310 and a sound unit 320 .

The display unit 310 outputs matching information transmitted from the control unit 290 .

The sound unit 320 receives the warning information transmitted from the theft confirmation unit 280 and sounds a warning sound.

2. Three-dimensional image analysis method of parcel delivery

Hereinafter, a three-dimensional image analysis method for parcel delivery according to an embodiment of the present invention will be described with reference to FIGS. 1 to 5. The three-dimensional image analysis method of parcel delivery according to an embodiment of the present invention shares all components and technical characteristics of the unmanned parcel delivery management system 400 described above.

Figure 5 is a flow chart showing a three-dimensional image analysis method of parcel delivery according to an embodiment of the present invention.

The three-dimensional image analysis method of parcel delivery according to an embodiment of the present invention includes (a) the recognizing unit 100 acquiring vision information for at least one parcel and recognizing a barcode (S10), (b) a server unit ( 200) analyzing the vision information for at least one parcel and extracting size information, movement route information, location information, number information, stacking information and labeling information for at least one parcel (S20), (c) server unit (200) implementing at least one parcel into a 3D image based on size information, movement route information, location information, number information, stacking information and labeling information of at least one parcel (S30) and (d) server unit (200) includes a step (S40) of tracking the three-dimensional image of at least one parcel.

In the step (a), (a1) the vision sensor unit 110 provided in the recognition unit 10 photographs at least one parcel in real time to obtain at least one parcel image included in the vision information, ( a2) the barcode recognition unit 120 provided in the recognition unit 100 recognizing at least one delivery barcode for at least one delivery item tagged by a delivery driver among at least one visitor to generate delivery barcode information; and (a3) The vision sensor unit 110 and the barcode recognition unit 120 transmit at least one parcel image and delivery barcode information to the server unit 200.

In the step (a1), as described above, at least one camera 111, 112, 113 provided by the vision sensor unit 110 shoots in real time toward the parcel storage area S, and returns to the parcel storage area S. At least one parcel entering and exiting is photographed, and at least one image of the parcel is obtained.

Next, in the step (a2), after recognizing the delivery barcode tagged by the delivery driver, delivery barcode information including unique information included in the delivery barcode is generated. At this time, the courier barcode information may include a waybill number, product order number, orderer name (=recipient name), product name, product price, top and bottom difference history, and the like.

Next, in the step (a3), the vision sensor unit 110 transmits at least one parcel image to the server unit 200, and the barcode recognition unit 120 transmits delivery barcode information to the server unit 200. .

In the step (b), (b1) the information storage unit 210 provided in the server unit 200 stores at least one parcel image and delivery barcode information transmitted from the vision sensor unit 110; (b2 ) The access recognition unit 220 provided in the server unit 200 compares at least one package image to generate access information by classifying the same delivery service and non-identical delivery service, (b3) Provided in the server unit 200 The size recognition unit 230 extracts size information by recognizing the size of at least one package based on at least one package image transmitted from the information storage unit 210, (b4) to the server unit 200 Acquiring number information by counting the quantity of parcels based on the size information transmitted from the size recognition unit 230 by the provided quantity determination unit 240, (b5) location recognition unit provided in the server unit 200 250 creates a three-dimensional image of at least one parcel based on the image of at least one parcel transmitted from the information storage unit 210, thereby providing location information on the location of at least one parcel and the location where at least one parcel is stacked. It includes the step of generating stacking information and labeling information for labeling at least one courier parcel, and the access recognition unit 220, the size recognition unit 230, the quantity detection unit 240, and the location recognition unit 250 Access information, size information, number information, location information, stacking information, and labeling information are transmitted to the control unit 290.

In the step (b2), the entry/exit recognition unit 220 compares at least one surrounding image in at least one parcel image photographed from different angles, and compares at least one parcel image with at least one surrounding image. It is determined whether at least one courier parcel is the same courier or non-identical courier. For this purpose, the entry/exit recognition unit 220 recognizes an object from at least one parcel image, extracts an outline and features, distinguishes whether or not at least one parcel is identical, and then counts the entry/exit of at least one parcel.

In the step (b3), the size recognition unit 230 compares at least one parcel image with each other to estimate the size. In detail, at least one parcel image may include an image of the parcel and images surrounding the parcel.

The size recognition unit 230 compares at least one peripheral image in at least one parcel image taken from different angles, compares at least one parcel image with at least one peripheral image, and extracts the relative size of the parcel. to generate size information.

Next, in step (b4), the quantity determination unit 240 counts the quantity of parcels based on the size information. However, the quantity determination unit 240 may determine the quantity by receiving access information from the access recognition unit 220 as needed.

Next, in the step (b5), a three-dimensional image of at least one parcel is generated based on the image of the at least one parcel. At this time, a method of generating a three-dimensional image of at least one parcel is similar to the above steps (b2) to (b4).

Specifically, the location recognition unit 250 recognizes an object by image processing after extracting contours and features from at least one delivery image.

In addition, the location recognition unit 250 generates stacking information indicating an image in a state in which delivery images, which are recognized objects, are stacked. For example, assuming that 10 parcels are sequentially placed in the parcel storage area S, the location recognition unit 250 recognizes an object based on at least one parcel image for sequentially arranged parcels, and then 10 Stacking information about the state in which the parcels are stacked is created.

At the same time, the location recognition unit 250 generates labeling information for labeling at least one parcel, performs marking on each parcel, and generates location information so that each location can be recognized as coordinates.

Next, in step (b), (b6) the path estimation unit 260 provided in the server unit 200 selects at least one parcel and at least one parcel based on the face image of at least one visitor and at least one parcel image. The method further includes generating movement route information by tracking the movement route of the visitor.

At this time, the path estimating unit 260 may receive the labeling information performed in step (b5) or track the moving path of the package based on the labeling information generated by the path estimating unit 260.

The route estimation unit 260 transmits movement route information to the control unit 290 .

According to the present invention, the server unit 200 analyzes through information processing and image processing based on the vision information recognized by the recognition unit 100, and analyzes the size information of at least one parcel, movement route information, It creates location information, number information, stacking information and labeling information.

3. A method for preventing theft of parcels using a three-dimensional image analysis method of parcels

Hereinafter, with reference to FIGS. 1 to 7, a method for preventing theft of parcels using a three-dimensional image analysis method for parcels according to an embodiment of the present invention will be described. The method for preventing theft of parcels using the three-dimensional image analysis method of parcels according to an embodiment of the present invention shares all components and technical features of the unmanned parcel delivery management system 400 and the three-dimensional image analysis method for parcels.

6 is a flow chart showing a method for preventing theft of parcels delivered using a three-dimensional image analysis method for parcels according to an embodiment of the present invention. 7 is an operation flow chart showing the operation flow of FIG. 1 according to an embodiment of the present invention.

In the method for preventing theft of parcels using the three-dimensional image analysis method of parcels according to an embodiment of the present invention, (A) the recognition unit 100 acquires vision information for at least one parcel and at least one person entering the parcel, and recognizes a barcode. Step (S100), (B) the server unit 200 analyzes the vision information and extracts size information, movement route information, location information, number information, stacking information, and labeling information of at least one parcel, and converts the parcel into a three-dimensional image. (S200), (C) the server unit 200 determining whether or not at least one package is stolen based on the three-dimensional image and the barcode (S300), and (D) the output unit 300 at least one It includes a step (S400) of outputting a result according to whether or not the parcel is stolen.

Here, the steps (A) and (B) include all steps of the three-dimensional image analysis method of the parcel delivery product described above, and in addition to the method of analyzing the three-dimensional image of the parcel delivery object, barcode information and vision information for at least one visitor contains more content

In the step (A), (A1) the vision sensor unit 110 provided in the recognition unit 100 photographs at least one parcel and at least one visitor in real time, and at least one parcel image included in the vision information and Acquiring at least one facial image, (A2) the barcode recognition unit 120 provided in the recognition unit 100 detects at least one delivery barcode for at least one delivery package tagged by a delivery driver among at least one visitor Recognizing and generating parcel barcode information, (A3) barcode recognition unit 120 recognizing a character barcode tagged by a recipient among at least one visitor and generating parcel barcode information, and (A4) vision sensor unit (110) and the barcode recognition unit 120 transmitting at least one parcel image, at least one face image, delivery barcode information, and text barcode information to the server unit 200.

In the step (A1), at least one facial image of at least one visitor not included in the step (a) (S10) of the three-dimensional image analysis method for parcel delivery according to the present invention is acquired in real time.

Next, in step (A2), the barcode recognition unit 120 recognizes at least one delivery barcode to generate a delivery barcode. Ewha Womans University, the delivery barcode is a barcode containing unique information about the delivery parcel to be delivered to the recipient by the delivery driver among the entrants, and the delivery driver tags the barcode to the barcode recognition unit 120 using a mobile terminal.

Next, the barcode recognition unit 120 generates delivery barcode information according to the step (A3), and the vision sensor unit 110 and the barcode recognition unit 120 generate at least one parcel image, At least one facial image, courier barcode information, and text barcode information are transmitted to the server unit 200.

Next, in step (B), (B1) the information storage unit 210 provided in the server unit 200 transmits from the vision sensor unit 110 at least one parcel image, at least one facial image, and a delivery barcode. Step of storing information, (B2) the size recognition unit 230 provided in the server unit 200 recognizes the size of at least one package based on the image of at least one package delivered from the information storage unit 210 Step of extracting size information, (B3) obtaining number information by counting the quantity of parcels based on the size information transmitted from the size recognition unit 230 by the quantity determination unit 240 provided in the server unit 200 Step, (B4) the location recognition unit 250 provided in the server unit 200 generates a three-dimensional image of at least one package based on the image of at least one package delivered from the information storage unit 210, It includes generating location information about the location of the parcel, stacking information about the location where at least one parcel is stacked, and labeling information for labeling the at least one parcel, and a size recognition unit 230, a quantity determination unit ( 240) and the location recognition unit 250 transmit size information, number information, location information, stacking information, and labeling information to the control unit 290.

The above steps (B1) to (B4) are the same as the (b2) steps (S20) to (b4) steps (S40) described in the three-dimensional image analysis method for parcel delivery of the present invention, so a detailed description thereof Please refer to the foregoing.

In addition, in step (B), (B5) the path estimation unit 260 provided in the server unit 200 selects at least one parcel and at least one parcel based on the facial image of at least one visitor and at least one parcel image. The method further includes generating movement route information by tracking the movement route of the visitor, and the route estimation unit 260 transmits the movement route information to the control unit 290 .

In the step (B5), the labeling information performed in the step (B4) may be received or generated by the path estimation unit 260, and the delivery route and the moving route of the visitor may be tracked based on the labeling information.

Specifically, in the case of parcel delivery, the moving path is tracked by labeling the object image of the parcel for sale in the same manner as described above.

On the other hand, in the case of a visitor, in the same way as tracking parcels, the outline and features of at least one facial image are extracted to create an object image recognizing the object, and after labeling the generated facial object image, it is tracked to determine the identity of the visitor path can be estimated.

In addition, in the step (B), (B6) the access recognition unit 220 provided in the server unit 200 compares at least one facial image, divides it into the same person and non-identical person, and compares at least one parcel image. The step of generating access information by classifying the same delivery service and non-identical delivery service is further included, and the access recognition unit 220 transmits the access information to the control unit 290.

At this time, the access recognition unit 220 processes at least one face image and at least one parcel image to extract outlines and features, distinguishes between the same person and non-identical person, and the same courier and non-identical courier, and generates access information for them. do.

In addition, in step (B), (B7) the barcode matching unit 270 provided in the server unit 200 matches the delivery barcode information and the text barcode information transmitted from the information storage unit 210 to determine whether they match. A step of transmitting matching information to the control unit 290 is further included.

Next, in the step (C), (C1) the theft confirmation unit 280 provided in the server unit 200 provides vision information, access information, size information, number information and location information, movement route information and matching information, and parcel delivery. Step of receiving the three-dimensional image of (C2) as the theft confirmation unit 280 analyzes the vision information, access information, size information, number information and location information, movement route information and matching information, and the three-dimensional image of the parcel, Further comprising the step of determining whether or not theft is stolen, the theft confirmation unit 280 generates warning information indicating that the parcel has been stolen when it is determined that the parcel has been stolen, so that the output unit 300, the police station, the recipient, and the courier driver work It is transmitted to at least one of the delivery service providers that are sent to the police station, and at the same time, the facial image of the delivery thief is transmitted to the police station.

For example, in the case of frequent access to the parcel storage area (S) by persons other than the courier driver in the access information, it is determined that there is a possibility of theft of the parcel, and the frequently accessed persons are separately classified and listed, and the subsequent access status is determined. can manage

In addition, if there is a change in the number of parcels in the number information, if the location of the parcel is changed in the location information, or if the parcel barcode information and text barcode information in the matching information are inconsistent, it is determined that there is a possibility of theft of the parcel and that there is a possibility of theft. You can continuously manage the labeling of delivered packages.

Specifically, the theft confirmation unit 280 determines that the parcel has been stolen when the parcel disappears in a state where the text barcode information is not received or the parcel barcode information and the text barcode information do not match, and provides warning information indicating that the parcel has been stolen. After generation, it is transmitted to at least one of the output unit 300, the police station, the recipient, and the courier company where the courier driver works, and at the same time, the facial image of the courier thief among the entrants is transmitted to the police station.

Next, the step (D) includes (D1) outputting the matching information transmitted from the control unit 290 by the display unit 310 provided in the output unit 300 and (D2) provided in the output unit 300. The sound unit 320 receives the warning information transmitted from the control unit 290 and sounds a warning sound.

According to the above, the present invention generates information related to the size, movement path, location, quantity, stacking state, and labeling of the parcel based on at least one image of the parcel, implements a three-dimensional image of the parcel, and implements at least one facial image. Based on, it is determined whether the same person is the same, and theft of the parcel can be prevented and prevented through whether the courier barcode information and the text barcode information match.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included in the scope of the present invention.

100: recognition unit
110: vision sensor unit
111: first camera
112: second camera
113; 3rd camera
120: barcode recognition unit
200: server unit
210: information storage unit
220: access recognition unit
230: size recognition unit
240: quantity determination unit
250: location recognition unit
260: path estimation unit
270: barcode matching unit
280: theft confirmation unit
290: control unit
300: output unit
310: display unit
320: sound unit
400: unmanned delivery management system

Claims (7)

Acquire vision information including facial images of the plurality of visitors and images of the parcels of the plurality of parcels as a plurality of visitors and parcels entering and exiting the parcel storage area are photographed in real time by being arranged to face the parcel storage area. Based on the vision sensor unit including a plurality of cameras to perform and the delivery barcode tagged by the delivery driver among the plurality of visitors and the text barcode tagged by the recipient among the plurality of visitors, delivery barcode information and text barcode information are generated. A recognition unit including a barcode recognition unit;
an information storage unit for storing the facial images of the plurality of visitors and the delivery image of the plurality of parcels transmitted from the vision sensor unit;
The plurality of facial images of the plurality of visitors transmitted from the information storage unit are compared with each other to distinguish the same person and non-identical person, and the plurality of parcel images of the plurality of parcels are compared with each other to distinguish the same courier and non-identical courier. An access recognition unit for generating one access information, a size recognition unit for extracting size information by recognizing the size of the plurality of parcels based on the plurality of parcel images transmitted from the information storage unit, and a size recognition unit for extracting size information. A quantity grasping unit that obtains number information on the quantity of the plurality of parcels obtained by counting the size information, and contours and features are extracted from the plurality of parcels images transmitted from the information storage unit, and image processing is performed to process the plurality of parcels. Recognizes, generates stacking information representing an image of a state in which the plurality of recognized parcel images are stacked, and marks and labels the multiple parcel images so that the locations of the multiple parcel parcels can be recognized as coordinates. A location recognition unit for generating labeling information and generating location information on the locations of the plurality of parcels by generating a 3D map for the plurality of parcel images placed in the parcel storage area based on the plurality of parcel images; A path estimation unit for generating movement route information by tracking the movement routes of the plurality of parcels and the plurality of visitors based on the plurality of facial images and the labeling information of the plurality of parcel images, and the information transmitted from the information storage unit. A barcode matching unit that transmits matching information determined by matching the courier barcode information and the text barcode information to the control unit, and the vision information, the access information, the size information, the number information and the location information, and the movement route information and a server unit including a theft confirmation unit that determines whether or not the package is stolen by receiving and analyzing the matching information; and
An unmanned parcel delivery management system comprising: an output unit for outputting a result according to whether the parcel is stolen or not.
According to claim 1,
The access recognition unit transmits the access information to the control unit.
According to claim 2,
The size recognition unit, the quantity detection unit and the location recognition unit transmit the size information, the number information and the location information to the control unit.
According to claim 2,
The route estimation unit transmits the movement route information to the control unit.
delete According to claim 2,
When the theft confirmation unit determines that the parcel has been stolen, it generates warning information indicating that the parcel has been stolen and transmits it to at least one of the output unit, the police station, the recipient, and the courier company where the courier driver works; At the same time, the unmanned courier management system characterized in that for transmitting the facial image of the courier thief among the entrants to the police station.
According to claim 6,
the output unit,
a display unit outputting the matching information transmitted from the control unit; and
The unmanned delivery management system comprising a; acoustic unit for receiving the warning information transmitted from the control unit and sounding a warning sound.

Images