CN109759339A - Method for sorting, sorting equipment and the sorting terminal of logistics package - Google Patents
Method for sorting, sorting equipment and the sorting terminal of logistics package Download PDFInfo
- Publication number
- CN109759339A CN109759339A CN201910156000.3A CN201910156000A CN109759339A CN 109759339 A CN109759339 A CN 109759339A CN 201910156000 A CN201910156000 A CN 201910156000A CN 109759339 A CN109759339 A CN 109759339A
- Authority
- CN
- China
- Prior art keywords
- target
- package
- dimensional
- sorting
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The present invention is suitable for Intelligent logistics technical field, provides the method for sorting, sorting equipment and sorting terminal of a kind of logistics package.Wherein, the method for sorting includes: the three-dimensional image information for obtaining target package, and the three-dimensional image information is inputted preset Feature Selection Model, obtains the three-dimensional geometry feature of the target package;Obtain the addressee information of the target package, wherein the addressee information includes at least posting address information;Based on the posting address information, the target means of transport for delivering the target package is determined;Based on the three-dimensional geometry feature of target package, the " loaded " position that the target is wrapped on the target means of transport is determined.The present invention realizes the distribution of package " loaded " position by the objective three-dimensional geometry feature extracted, the subjective impact that manual type carries out package loading can be reduced, the reasonable producing level to loading space is improved, and is conducive to the realization of automated sorting and improves logistics distribution efficiency.
Description
Technical field
The invention belongs to method for sorting, sorting equipments, end that logistics management technical field more particularly to a kind of logistics are wrapped up
End and computer readable storage medium.
Background technique
Currently, during sending objects (package) are distributed to user by logistics transportation by logistics company, need into
Row sorting, such as package is classified according to address information, the same or similar article in destination is uniformly subjected to entrucking, fortune
It carries and dispenses.
Traditional logistics sorting is carried out by manual type, and when carrying out package entrucking, usually staff is according to packet
The sorting sequence successively entrucking wrapped up in, it is difficult to accomplish the reasonable utilization to carrier vehicle loading space, will affect when loading unreasonable
The dispatching efficiency of logistics.
Summary of the invention
In view of this, the present invention provides a kind of method for sorting of logistics package, sorting equipment, terminals and computer-readable
Storage medium, to solve to load using manual sorting in the prior art, it is difficult to accomplish the reasonable benefit to carrier vehicle loading space
The problem of using.
The first aspect of the embodiment of the present invention provides a kind of method for sorting of logistics package, comprising:
Obtain the three-dimensional image information of target package, wherein the three-dimensional image information is wrapped up including at least the target
Multiple three-dimensional coordinates in predetermined scene;
The three-dimensional image information is inputted into preset Feature Selection Model, the three-dimensional geometry for obtaining the target package is special
Sign;
Obtain the addressee information of the target package, wherein the addressee information includes at least posting address information;
Based on the posting address information, the target means of transport for delivering the target package is determined;
Based on the three-dimensional geometry feature of target package, determine that the target is wrapped on the target means of transport
" loaded " position.
The second aspect of the embodiment of the present invention provides a kind of sorting equipment of logistics package, comprising:
Acquiring three-dimensional images unit, for obtaining the three-dimensional image information of target package, wherein the three-dimensional image information
The multiple three-dimensional coordinates being wrapped in including at least the target in predetermined scene;
Three-dimensional feature extraction unit obtains institute for the three-dimensional image information to be inputted preset Feature Selection Model
State the three-dimensional geometry feature of target package;
Addressee information acquisition unit, for obtaining the addressee information of the target package, wherein the addressee information is at least
Including posting address information;
First determination unit determines the target for delivering the target package for being based on the posting address information
Means of transport;
Second determination unit, the three-dimensional geometry feature for being wrapped up based on the target, determines that the target is wrapped in institute
State the " loaded " position on target means of transport.
The third aspect of the embodiment of the present invention provides a kind of sorting terminal, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
The step of realizing the method for sorting that the logistics as described in any one is wrapped up.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and point that the logistics as described in any one is wrapped up is realized when the computer program is executed by processor
The step of picking method.
Existing beneficial effect is the present invention compared with prior art:
The three-dimensional image information that one aspect of the present invention is wrapped up by obtaining target, utilizes preset Feature Selection Model to extract
The three-dimensional geometry feature of target package;On the other hand by obtaining the posting address information of target package, it is based on the posting address
Information is the target package distribution means of transport;Since three-dimensional geometry feature reflects the size that object can take up space, mentioning
After the three-dimensional geometry feature for getting target package, it can determine that the target is wrapped in as its distribution according to the three-dimensional geometry feature
" loaded " position on means of transport.Thus, the present invention realizes package " loaded " position by the objective three-dimensional geometry feature extracted
Distribution, it is possible to reduce manual type carries out the subjective impact of package loading, improves to the reasonable producing level of loading space, and
Be conducive to the realization of automated sorting and improve logistics distribution efficiency.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation flow chart of the method for sorting of logistics package provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of the sorting equipment of logistics package provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram of sorting terminal provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
To make the object, technical solutions and advantages of the present invention clearer, pass through specific embodiment below in conjunction with attached drawing
To be illustrated.
Referring to Fig. 1, it illustrates the implementation flow charts of the method for sorting of logistics provided in an embodiment of the present invention package, are described in detail
It is as follows:
In a step 101, the three-dimensional image information of target package is obtained, wherein the three-dimensional image information includes at least
The target is wrapped in multiple three-dimensional coordinates in predetermined scene.
In the automatic sorting scene of logistics package, logistics can be wrapped up and be placed on conveyer belt, successively using conveyer belt
3-dimensional image sensor, such as three-dimensional laser image can be set in a designated position of conveyer belt in the transmission wrapped up
Sensor or three-dimensional infrared image sensor, the monitoring scene of the 3-dimensional image sensor is predetermined scene, when being transmitted
Package pass through the predetermined scene when, by 3-dimensional image sensor acquisition by transmission package (i.e. target package) 3-D image
Information, the three-dimensional image information have included at least multiple three-dimensional coordinate informations that target is wrapped in the predetermined scene.For example, right
In the package that a 3D shape is cube, the three-dimensional coordinate that three-dimensional image information includes at least its multiple vertex position is believed
Breath.
Optionally, above-mentioned steps 101 may include:
It obtains the target and is wrapped in the two-dimensional image information overlooked in the predetermined scene;
Obtain the elevation information that the target is wrapped in the predetermined scene;
Two-dimensional image information and the elevation information based on the vertical view carry out 3-D image reconstruct, obtain institute
State the three-dimensional image information of target package.
In embodiments of the present invention, target can be obtained by two-dimensional image sensor and be wrapped in and overlooked in predetermined scene
Two-dimensional image information;Target can also be obtained by distance measuring sensor be wrapped in the elevation information in the predetermined scene;
The two-dimensional image information of the vertical view based on acquisition and the elevation information of acquisition carry out 3-D image reconstruct as a result, will be high
Information is spent as the depth components of pixel each on two-dimensional image and is fused to two-dimensional image, obtains the target packet
The three-dimensional image information wrapped up in.
Optionally, above-mentioned steps 101 may include:
Obtain the reflection graphic patterns that the structure light of designated mode pattern is superscribed in the target;
Pattern deformation based on the reflection graphic patterns Yu the designated mode pattern calculates the three-dimensional figure of the target package
As information.
In embodiments of the present invention, target can also be wrapped up using the structure light of designated mode pattern in predetermined scene
It is irradiated, obtains the reflection graphic patterns that the structure light of designated mode pattern is superscribed in the target, the shape meeting of target package
So that designated mode pattern is generated deformation, is calculated by the deformation, the three-dimensional image information of available target package.
For example, by the structure light of structured light projector projection designated mode pattern (such as bar paten), if being projeced into
In plane, bar paten is remained as on the two dimensional image in plane that imaging sensor obtains, if there are one in the plane of projection
Object (such as package), the two dimensional image in plane that imaging sensor obtains will be the bar patens for generating deformation.So, lead to
It crosses using various structure light principles and algorithm (such as principle of triangulation), the accurate three-dimensional table of object in plane can be calculated
Face information.Namely the three-dimensional image information of available object.
In a step 102, the three-dimensional image information is inputted into preset Feature Selection Model, obtains the target package
Three-dimensional geometry feature.
In embodiments of the present invention, extracted three-dimensional geometry feature includes at least target and is wrapped in the predetermined scene
Length, width and height, herein, length, width and height can correspond to three three-dimensional coordinates in predetermined scene respectively
Distance on direction.
It in embodiments of the present invention, can be with the pass in rapidly extracting three-dimensional image information using preset Feature Selection Model
Key point information obtains the three-dimensional geometry feature of target package.
Optionally, the Feature Selection Model be convolutional neural networks, the convolutional neural networks include the first convolutional layer,
Second convolutional layer and output layer;
First convolutional layer is for extracting side information from the three-dimensional image information;The side information refers to target packet
The information on side where the intersection of intersecting plane in the three-dimensional image information wrapped up in.
Second convolutional layer is for extracting terminal point information from the side information;The terminal point information refers to side information pair
The information of the endpoint on each side answered.
The output layer is used to extract first end point coordinate, the second extreme coordinates, third endpoint from the terminal point information
Coordinate, the 5th extreme coordinates of the 4th extreme coordinates and the 6th extreme coordinates, wherein the first end point coordinate and the second end
Point coordinate respectively indicates height coordinate maximum and the smallest endpoint of height coordinate, the third extreme coordinates and the 4th endpoint
Coordinate respectively indicates width coordinate maximum and the smallest endpoint of width coordinate, and the 5th extreme coordinates and the 6th endpoint are sat
Mark respectively indicates length coordinate maximum and the smallest endpoint of length coordinate;
Wherein, the height coordinate, width coordinate and length coordinate correspond respectively to three space sides in three-dimensional coordinate
To for example, can indicate that the coordinate in short transverse, x indicate the seat on length direction with z in three-dimensional coordinate (x, y, z)
Mark, y indicate the coordinate in width direction.
In embodiments of the present invention, six terminal point informations in three-dimensional image information are extracted using convolutional neural networks, this six
A terminal point information can indicate the 3 dimensional coil geometry of target package.For example, the height of first end point coordinate and the second extreme coordinates
Coordinate difference on degree direction reflects the maximum height of target package, the width side of third extreme coordinates and the 4th extreme coordinates
Upward coordinate difference reflects the maximum width of target package, on the length direction of the 5th extreme coordinates and the 6th extreme coordinates
Coordinate difference reflect target package maximum length.And maximum height, maximum width and the maximum length that target is wrapped up are anti-
The maximum geometry for having answered the target to wrap up.The loading that can accommodate target package is chosen to be conducive to wrap up for the target
Position.
It should be noted that the three-dimensional image information that the present invention is wrapped up by obtaining target, and utilize convolutional neural networks
Extract three-dimensional geometry feature (first end point coordinate, the second extreme coordinates, third extreme coordinates, the 4th end of three-dimensional image information
Point the 5th extreme coordinates of coordinate and the 6th extreme coordinates), the three-dimensional size of target package is characterized by this six three-dimensional coordinates,
And then suitable " loaded " position is matched for target package, package of different shapes can be applicable in, for example, passing through this six
The matched accommodation space of three-dimensional coordinate institute, for the package of non-standard cubic shaped, remaining on can be loaded, and be solved existing
The problem of its size of objective description is difficult to for the package of non-standard cubic shaped in technology.
Optionally, the three-dimensional image information is inputted into preset Feature Selection Model described, obtains the target packet
Before the three-dimensional geometry feature wrapped up in further include:
Obtain a certain number of 3-D image sample composition training sets;
The convolutional neural networks are trained in the way of supervised learning by the training set;
It is successively anti-to the weight parameter progress in the convolutional neural networks that loss function is minimized using gradient descent method
To adjusting, to improve the precision of the convolutional neural networks.
In embodiments of the present invention, convolutional neural networks are trained in the way of supervised learning, determine convolution
The parameter (convolution kernel) of each convolutional layer of neural network.Be conducive to improve the output accuracy of convolutional neural networks.
In step 103, the addressee information of the target package is obtained, wherein the addressee information includes at least addressee
Address information.
In embodiments of the present invention, by obtaining the addressee information of target package, posting address, the available packet are determined
The outbox whereabouts wrapped up in, and then can be gone always to choose the means of transports such as the vehicle for sailing for the outbox whereabouts according to the outbox.
Optionally, the addressee information further includes addressee's contact number, can also include: after above-mentioned steps 102
Based on the three-dimensional geometry feature, the volume information of the target package is calculated;
The volume information is sent to addressee's contact number.
In embodiments of the present invention, using the three-dimensional geometry feature of extraction, the volume information of target package can be calculated, is led to
The addressee that the volume information of target package is sent to target package is crossed, addressee can be enabled timely to recognize it
The volume for the package to be received solves the problems, such as addressee due to the excessive and inconvenient pickup of package volume and carries.
At step 104, it is based on the posting address information, determines the target haulagman for delivering the target package
Tool.
In embodiments of the present invention, multiple means of transports are sent to different areas respectively, can be with by posting address information
Determine the area that package is sent to, and then determination can deliver the target means of transport of the target package.
In step 105, the three-dimensional geometry feature based on target package, determines that the target is wrapped in the target
" loaded " position on means of transport.
In embodiments of the present invention, by extracting the three-dimensional geometry feature of target package, the largest body of target package is determined
Product, and then the spatial position for being suitble to load target package can be chosen on means of transport.
Optionally, above-mentioned steps 105 may include:
Obtain the three-dimensional geometry feature that each package being arranged on the target means of transport loads the loading space of pane;
Three wrapped up with the target are chosen in the three-dimensional geometry feature for the loading space for loading pane from each package
It ties up the matched target package of geometrical characteristic and loads pane;
The target is wrapped up into loading pane and is determined as the loading position that the target is wrapped on the target means of transport
It sets.
In embodiments of the present invention, it is provided with multiple packages for loading package on each logistics transportation tool and loads window
Lattice can obtain size and three-dimensional geometry feature that each package on each logistics transportation tool loads pane in advance.?
Here, the three-dimensional geometry feature that package loads pane refers to the three-dimensional geometry feature of its accommodation space, may include open ended
Maximum height, maximum length and maximum width.Pane is loaded by the 3 dimensional coil geometry and each package that wrap up target
Three-dimensional geometry feature is matched, and can be chosen and be loaded window with the target package of the three-dimensional geometry characteristic matching of target package
Lattice, and the target is wrapped up into loading pane and is determined as the " loaded " position that the target is wrapped on the target means of transport.
The present invention can be reasonably the package distribution of different size shape and the matched " loaded " position of its size shape, have
Conducive to the automation loading and the reasonable utilization of loading space for realizing logistics packages.
From the foregoing, it will be observed that the three-dimensional image information that one aspect of the present invention is wrapped up by obtaining target, is mentioned using preset feature
The three-dimensional geometry feature for taking model extraction target to wrap up;On the other hand it by obtaining the posting address information of target package, is based on
The posting address information is the target package distribution means of transport;Since three-dimensional geometry feature reflects what object can take up space
Size can determine that the target is wrapped according to the three-dimensional geometry feature after the three-dimensional geometry feature for extracting target package
For the " loaded " position on the means of transport of its distribution.Thus, the present invention realizes packet by the objective three-dimensional geometry feature extracted
Wrap up in the distribution of " loaded " position, it is possible to reduce manual type carries out the subjective impact of package loading, improves to the reasonable of loading space
Producing level, and be conducive to the realization of automated sorting and improve logistics distribution efficiency.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
The following are the device of the invention embodiments can refer to above-mentioned corresponding the details of wherein not detailed description
Embodiment of the method.
Fig. 2 shows the structural schematic diagrams of the sorting equipment of logistics provided in an embodiment of the present invention package, for the ease of saying
Bright, only parts related to embodiments of the present invention are shown, and details are as follows:
As shown in Fig. 2, the sorting equipment 2 of logistics package includes: acquiring three-dimensional images unit 21, three-dimensional feature extraction unit
22, addressee information acquisition unit 23, the first determination unit 24 and the second determination unit 25.
Acquiring three-dimensional images unit 21, for obtaining the three-dimensional image information of target package, wherein the 3-D image letter
Breath includes at least the target and is wrapped in multiple three-dimensional coordinates in predetermined scene;
Three-dimensional feature extraction unit 22 is obtained for the three-dimensional image information to be inputted preset Feature Selection Model
The three-dimensional geometry feature of the target package;
Addressee information acquisition unit 23, for obtaining the addressee information of the target package, wherein the addressee information is extremely
It less include posting address information;
First determination unit 24 determines the mesh for delivering the target package for being based on the posting address information
Mark means of transport;
Second determination unit 25, the three-dimensional geometry feature for being wrapped up based on the target, determines that the target is wrapped in
" loaded " position on the target means of transport.
Optionally, the sorting equipment 2 of logistics package further include:
Three-dimensional feature acquiring unit loads the loading of pane for obtaining each package being arranged on the target means of transport
The three-dimensional geometry feature in space;
Pane selection unit is loaded, for selecting from the three-dimensional geometry feature for the loading space that each package loads pane
It takes and loads pane with the target package of the three-dimensional geometry characteristic matching of target package;
Second determination unit 25 is specifically used for, the target is wrapped up load pane be determined as the target be wrapped in it is described
" loaded " position on target means of transport.
Optionally, the sorting equipment 2 of logistics package further include:
Two dimensional image acquiring unit is wrapped in the 2 d plane picture overlooked in the predetermined scene for obtaining the target
As information;
Elevation information acquiring unit, the elevation information being wrapped in the predetermined scene for obtaining the target;
Acquiring three-dimensional images unit 21 is specifically used for, two-dimensional image information and the height based on the vertical view
Information carries out 3-D image reconstruct, obtains the three-dimensional image information of the target package.
Optionally, the sorting equipment 2 of logistics package further include:
Reflection graphic patterns acquiring unit, the reflectogram that the structure light for obtaining designated mode pattern is superscribed in the target
Case;
Acquiring three-dimensional images unit 21 is specifically used for, the pattern shape based on the reflection graphic patterns Yu the designated mode pattern
Become, calculates the three-dimensional image information of the target package.
Optionally, the Feature Selection Model be convolutional neural networks, the convolutional neural networks include the first convolutional layer,
Second convolutional layer and output layer;
First convolutional layer is for extracting side information from the three-dimensional image information;
Second convolutional layer is for extracting terminal point information from the side information;
The output layer is used to extract first end point coordinate, the second extreme coordinates, third endpoint from the terminal point information
Coordinate, the 5th extreme coordinates of the 4th extreme coordinates and the 6th extreme coordinates, wherein the first end point coordinate and the second end
Point coordinate respectively indicates height coordinate maximum and the smallest endpoint of height coordinate, the third extreme coordinates and the 4th endpoint
Coordinate respectively indicates width coordinate maximum and the smallest endpoint of width coordinate, and the 5th extreme coordinates and the 6th endpoint are sat
Mark respectively indicates length coordinate maximum and the smallest endpoint of length coordinate;
Wherein, the height coordinate, width coordinate and length coordinate correspond respectively to three space sides in three-dimensional coordinate
To.
Optionally, the sorting equipment 2 of logistics package further include:
Training set acquiring unit is obtained for the three-dimensional image information to be inputted preset Feature Selection Model described
Before the three-dimensional geometry feature wrapped up to the target, a certain number of 3-D image sample composition training sets are obtained;
Supervised training unit, for by the training set in the way of supervised learning to the convolutional neural networks
It is trained, and minimizes loss function using gradient descent method and the weight parameter in the convolutional neural networks is carried out successively
It is reversed to adjust, to improve the precision of the convolutional neural networks.
Optionally, the addressee information further includes addressee's contact number, the sorting equipment 2 of logistics package further include:
Volume computing unit is obtained for the three-dimensional image information to be inputted preset Feature Selection Model described
After the three-dimensional geometry feature of the target package, it is based on the three-dimensional geometry feature, calculates the volume letter of the target package
Breath;
Volume information transmission unit, for the volume information to be sent to addressee's contact number.
From the foregoing, it will be observed that the three-dimensional image information that one aspect of the present invention is wrapped up by obtaining target, is mentioned using preset feature
The three-dimensional geometry feature for taking model extraction target to wrap up;On the other hand it by obtaining the posting address information of target package, is based on
The posting address information is the target package distribution means of transport;Since three-dimensional geometry feature reflects what object can take up space
Size can determine that the target is wrapped according to the three-dimensional geometry feature after the three-dimensional geometry feature for extracting target package
For the " loaded " position on the means of transport of its distribution.Thus, the present invention realizes packet by the objective three-dimensional geometry feature extracted
Wrap up in the distribution of " loaded " position, it is possible to reduce manual type carries out the subjective impact of package loading, improves to the reasonable of loading space
Producing level, and be conducive to the realization of automated sorting and improve logistics distribution efficiency.
Fig. 3 is the schematic diagram for the sorting terminal that one embodiment of the invention provides.As shown in figure 3, the sorting of the embodiment is whole
End 3 includes: processor 30, memory 31 and is stored in the meter that can be run in the memory 31 and on the processor 30
Calculation machine program 32.The processor 30 realizes that the method for sorting of above-mentioned each logistics package is real when executing the computer program 32
Apply the step in example, such as step 101 shown in FIG. 1 is to step 105.Alternatively, the processor 30 executes the computer journey
The function of each module/unit in above-mentioned each Installation practice, such as the function of unit 21 to 25 shown in Fig. 2 are realized when sequence 32.
Illustratively, the computer program 32 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 31, and are executed by the processor 30, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 32 in the terminal 3 is described.For example, the computer program 32 can be divided into
Acquiring three-dimensional images unit, three-dimensional feature extraction unit, addressee information acquisition unit, the first determination unit and second determine list
Member, each unit concrete function are as follows:
Acquiring three-dimensional images unit, for obtaining the three-dimensional image information of target package, wherein the three-dimensional image information
The multiple three-dimensional coordinates being wrapped in including at least the target in predetermined scene;
Three-dimensional feature extraction unit obtains institute for the three-dimensional image information to be inputted preset Feature Selection Model
State the three-dimensional geometry feature of target package;
Addressee information acquisition unit, for obtaining the addressee information of the target package, wherein the addressee information is at least
Including posting address information;
First determination unit determines the target for delivering the target package for being based on the posting address information
Means of transport;
Second determination unit, the three-dimensional geometry feature for being wrapped up based on the target, determines that the target is wrapped in institute
State the " loaded " position on target means of transport.
The sorting terminal 3 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The sorting terminal may include, but be not limited only to, processor 30, memory 31.It will be understood by those skilled in the art that Fig. 3
The example for only sorting terminal 3, does not constitute the restriction to sorting terminal 3, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal can also connect including input-output equipment, network
Enter equipment, bus etc..
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 31 can be the internal storage unit of the sorting terminal 3, such as the hard disk or interior of sorting terminal 3
It deposits.The memory 31 is also possible to the External memory equipment of the sorting terminal 3, such as the grafting being equipped in the terminal 3
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Further, the memory 31 can also both include it is described sorting terminal 3 internal storage unit or
Including External memory equipment.The memory 31 is for other programs needed for storing the computer program and the terminal
And data.The memory 31 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal and method can pass through
Other modes are realized.For example, device/terminal embodiment described above is only schematical, for example, the module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, institute
Display or the mutual coupling or direct-coupling or communication connection discussed can be through some interfaces, device or unit
INDIRECT COUPLING or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of method for sorting of logistics package, which is characterized in that the method for sorting includes:
Obtain the three-dimensional image information of target package, wherein the three-dimensional image information is wrapped in pre- including at least the target
Determine multiple three-dimensional coordinates in scene;
The three-dimensional image information is inputted into preset Feature Selection Model, obtains the three-dimensional geometry feature of the target package;
Obtain the addressee information of the target package, wherein the addressee information includes at least posting address information;
Based on the posting address information, the target means of transport for delivering the target package is determined;
Based on the three-dimensional geometry feature of target package, the loading that the target is wrapped on the target means of transport is determined
Position.
2. the method for sorting of logistics according to claim 1 package, which is characterized in that described based on target package
Three-dimensional geometry feature determines the " loaded " position that the target is wrapped on the target means of transport, comprising:
Obtain the three-dimensional geometry feature that each package being arranged on the target means of transport loads the loading space of pane;
It is several that the three-dimensional wrapped up with the target is chosen in the three-dimensional geometry feature for the loading space for loading pane from each package
The target package of what characteristic matching loads pane;
The target is wrapped up into loading pane and is determined as the " loaded " position that the target is wrapped on the target means of transport.
3. the method for sorting of logistics package according to claim 1, which is characterized in that described to obtain what the target was wrapped up
Three-dimensional image information includes:
It obtains the target and is wrapped in the two-dimensional image information overlooked in the predetermined scene;
Obtain the elevation information that the target is wrapped in the predetermined scene;
Two-dimensional image information and the elevation information based on the vertical view carry out 3-D image reconstruct, obtain the mesh
Mark the three-dimensional image information of package.
4. the method for sorting of logistics package according to claim 1, which is characterized in that described to obtain what the target was wrapped up
Three-dimensional image information includes:
Obtain the reflection graphic patterns that the structure light of designated mode pattern is superscribed in the target;
Pattern deformation based on the reflection graphic patterns Yu the designated mode pattern calculates the 3-D image letter of the target package
Breath.
5. the method for sorting of logistics package according to any one of claim 1 to 4, which is characterized in that the feature mentions
Modulus type is convolutional neural networks, and the convolutional neural networks include the first convolutional layer, the second convolutional layer and output layer;
First convolutional layer is for extracting side information from the three-dimensional image information;
Second convolutional layer is for extracting terminal point information from the side information;
The output layer be used for from the terminal point information extract first end point coordinate, the second extreme coordinates, third extreme coordinates,
The 5th extreme coordinates of 4th extreme coordinates and the 6th extreme coordinates, wherein the first end point coordinate and second endpoint are sat
Mark respectively indicates height coordinate maximum and the smallest endpoint of height coordinate, the third extreme coordinates and the 4th extreme coordinates
Respectively indicate width coordinate maximum and the smallest endpoint of width coordinate, the 5th extreme coordinates and the 6th extreme coordinates point
It Biao Shi not length coordinate maximum and the smallest endpoint of length coordinate;
Wherein, the height coordinate, width coordinate and length coordinate correspond respectively to three direction in spaces in three-dimensional coordinate.
6. the method for sorting of logistics package according to claim 5, which is characterized in that believe the 3-D image described
Breath inputs preset Feature Selection Model, before obtaining the three-dimensional geometry feature of the target package further include:
Obtain a certain number of 3-D image sample composition training sets;
The convolutional neural networks are trained in the way of supervised learning by the training set;
Loss function is minimized using gradient descent method, and successively reversed adjust is carried out to the weight parameter in the convolutional neural networks
Section, to improve the precision of the convolutional neural networks.
7. the method for sorting of logistics package according to any one of claim 1 to 4, which is characterized in that the addressee letter
Breath further includes addressee's contact number;
The three-dimensional image information is inputted into preset Feature Selection Model described, obtains the three-dimensional geometry of the target package
After feature further include:
Based on the three-dimensional geometry feature, the volume information of the target package is calculated;
The volume information is sent to addressee's contact number.
8. a kind of sorting equipment of logistics package, which is characterized in that the sorting equipment includes:
Acquiring three-dimensional images unit, for obtaining the three-dimensional image information of target package, wherein the three-dimensional image information is at least
The multiple three-dimensional coordinates being wrapped in including the target in predetermined scene;
Three-dimensional feature extraction unit obtains the mesh for the three-dimensional image information to be inputted preset Feature Selection Model
Mark the three-dimensional geometry feature of package;
Addressee information acquisition unit, for obtaining the addressee information of the target package, wherein the addressee information includes at least
Posting address information;
First determination unit determines the target transport for delivering the target package for being based on the posting address information
Tool;
Second determination unit, the three-dimensional geometry feature for being wrapped up based on the target, determines that the target is wrapped in the mesh
Mark the " loaded " position on means of transport.
9. a kind of sorting terminal, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes claim 1 as above when executing the computer program
To logistics described in any one of 7 wrap up method for sorting the step of.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the computer program realizes point of the package of logistics described in any one of claims 1 to 7 as above when being executed by processor
The step of picking method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910156000.3A CN109759339B (en) | 2019-03-01 | 2019-03-01 | Sorting method, sorting device and sorting terminal for logistics packages |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910156000.3A CN109759339B (en) | 2019-03-01 | 2019-03-01 | Sorting method, sorting device and sorting terminal for logistics packages |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109759339A true CN109759339A (en) | 2019-05-17 |
CN109759339B CN109759339B (en) | 2021-09-17 |
Family
ID=66457556
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910156000.3A Active CN109759339B (en) | 2019-03-01 | 2019-03-01 | Sorting method, sorting device and sorting terminal for logistics packages |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109759339B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112150052A (en) * | 2019-06-28 | 2020-12-29 | 傲基科技股份有限公司 | Method, apparatus, and computer-readable storage medium for delivering objects |
CN112276956A (en) * | 2020-10-30 | 2021-01-29 | 北京市商汤科技开发有限公司 | Article distribution method, device and equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1300348A1 (en) * | 2001-10-08 | 2003-04-09 | Peter E. Kern | Method and device for loading and unloading delivery vehicles |
CN1791475A (en) * | 2003-04-16 | 2006-06-21 | 瑞得包裹邮递股份公司 | Method and device for distributing packages and othres similar dispatched articles |
CN1963390A (en) * | 2005-11-08 | 2007-05-16 | 李啸炜 | A precision and high efficiency three-dimensional measuring method |
CN101140639A (en) * | 2006-09-06 | 2008-03-12 | 张斌 | Method for arranging at most article in finite dimension three dimensions |
CN101815174A (en) * | 2010-01-11 | 2010-08-25 | 北京中星微电子有限公司 | Control method and control device for camera shooting |
CN104077577A (en) * | 2014-07-03 | 2014-10-01 | 浙江大学 | Trademark detection method based on convolutional neural network |
CN204731828U (en) * | 2015-05-14 | 2015-10-28 | 北京速派得物流信息技术有限公司 | A kind of goods for the network shipping of same city-vehicle match system |
CN106296098A (en) * | 2016-08-21 | 2017-01-04 | 吉选 | A kind of intelligence express system and post, send, addressee method |
CN106934581A (en) * | 2017-03-31 | 2017-07-07 | 联想(北京)有限公司 | Information processing method, information processor and electronic equipment |
CN108108781A (en) * | 2017-12-07 | 2018-06-01 | 曾学 | A kind of digitized airdrome luggage loading method and its system |
CN108446628A (en) * | 2018-03-19 | 2018-08-24 | 广东欧珀移动通信有限公司 | Screen control method, device, mobile terminal and computer readable storage medium |
US20180297787A1 (en) * | 2016-02-24 | 2018-10-18 | United Parcel Service Of America, Inc. | Conveyor belt assembly including an imaging system and systems and methods using the same |
-
2019
- 2019-03-01 CN CN201910156000.3A patent/CN109759339B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1300348A1 (en) * | 2001-10-08 | 2003-04-09 | Peter E. Kern | Method and device for loading and unloading delivery vehicles |
CN1791475A (en) * | 2003-04-16 | 2006-06-21 | 瑞得包裹邮递股份公司 | Method and device for distributing packages and othres similar dispatched articles |
CN1963390A (en) * | 2005-11-08 | 2007-05-16 | 李啸炜 | A precision and high efficiency three-dimensional measuring method |
CN101140639A (en) * | 2006-09-06 | 2008-03-12 | 张斌 | Method for arranging at most article in finite dimension three dimensions |
CN101815174A (en) * | 2010-01-11 | 2010-08-25 | 北京中星微电子有限公司 | Control method and control device for camera shooting |
CN104077577A (en) * | 2014-07-03 | 2014-10-01 | 浙江大学 | Trademark detection method based on convolutional neural network |
CN204731828U (en) * | 2015-05-14 | 2015-10-28 | 北京速派得物流信息技术有限公司 | A kind of goods for the network shipping of same city-vehicle match system |
US20180297787A1 (en) * | 2016-02-24 | 2018-10-18 | United Parcel Service Of America, Inc. | Conveyor belt assembly including an imaging system and systems and methods using the same |
CN106296098A (en) * | 2016-08-21 | 2017-01-04 | 吉选 | A kind of intelligence express system and post, send, addressee method |
CN106934581A (en) * | 2017-03-31 | 2017-07-07 | 联想(北京)有限公司 | Information processing method, information processor and electronic equipment |
CN108108781A (en) * | 2017-12-07 | 2018-06-01 | 曾学 | A kind of digitized airdrome luggage loading method and its system |
CN108446628A (en) * | 2018-03-19 | 2018-08-24 | 广东欧珀移动通信有限公司 | Screen control method, device, mobile terminal and computer readable storage medium |
Non-Patent Citations (2)
Title |
---|
LMFWQYL: ""瑞丰快递的具体业务流程是什么https://wenda.so.com/q/1408157589724533"", 《360问答》 * |
丁万宁等: ""多特征组合和用户反馈的图像检索算法"", 《吉林大学学报(理学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112150052A (en) * | 2019-06-28 | 2020-12-29 | 傲基科技股份有限公司 | Method, apparatus, and computer-readable storage medium for delivering objects |
CN112150052B (en) * | 2019-06-28 | 2022-11-18 | 傲基科技股份有限公司 | Method, apparatus, and computer-readable storage medium for delivering objects |
CN112276956A (en) * | 2020-10-30 | 2021-01-29 | 北京市商汤科技开发有限公司 | Article distribution method, device and equipment and storage medium |
CN112276956B (en) * | 2020-10-30 | 2022-05-17 | 北京市商汤科技开发有限公司 | Article distribution method, device and equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109759339B (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhou et al. | Voxelnet: End-to-end learning for point cloud based 3d object detection | |
CN111754515B (en) | Sequential gripping method and device for stacked articles | |
CN106203327B (en) | Lung tumor identification system and method based on convolutional neural networks | |
CN110020620A (en) | Face identification method, device and equipment under a kind of big posture | |
US10452789B2 (en) | Efficient packing of objects | |
CN110276829A (en) | The three dimensional representation handled by multiple dimensioned voxel Hash | |
CN110472534A (en) | 3D object detection method, device, equipment and storage medium based on RGB-D data | |
US20190193956A1 (en) | System for dynamic pallet-build | |
CN109003325A (en) | A kind of method of three-dimensional reconstruction, medium, device and calculate equipment | |
CN1333375C (en) | Three dimensional image processing | |
CN109870983A (en) | Handle the method, apparatus of pallet stacking image and the system for picking of storing in a warehouse | |
CN109015640A (en) | Grasping means, system, computer installation and readable storage medium storing program for executing | |
CN109795830A (en) | It is automatically positioned the method and device of logistics tray | |
US20100061622A1 (en) | Method for aligning objects | |
CN109759339A (en) | Method for sorting, sorting equipment and the sorting terminal of logistics package | |
CN116110041A (en) | System and method for object detection | |
CN109699002A (en) | A kind of interior WiFi localization method, device and terminal device | |
Aleotti et al. | Global registration of mid-range 3D observations and short range next best views | |
CN103871032A (en) | Image enhancement method for Wallis filter based on GPU (Graphics Processing Unit) | |
CN110340901A (en) | A kind of control method, control device and terminal device | |
CN116205561A (en) | Material management method and system based on digital twinning | |
Palla et al. | Fully Convolutional Denoising Autoencoder for 3D Scene Reconstruction from a single depth image | |
CN108399455A (en) | Dispatching method based on genetic algorithm and device | |
CN111401154B (en) | AR-based logistics accurate auxiliary operation device for transparent distribution | |
CN109784593A (en) | Production capacity equalization processing method and device for multistoried storehouse |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |