CN109759339B - Sorting method, sorting device and sorting terminal for logistics packages - Google Patents
Sorting method, sorting device and sorting terminal for logistics packages Download PDFInfo
- Publication number
- CN109759339B CN109759339B CN201910156000.3A CN201910156000A CN109759339B CN 109759339 B CN109759339 B CN 109759339B CN 201910156000 A CN201910156000 A CN 201910156000A CN 109759339 B CN109759339 B CN 109759339B
- Authority
- CN
- China
- Prior art keywords
- coordinate
- dimensional
- information
- target
- target package
- 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.)
- Active
Links
Images
Abstract
The invention is suitable for the technical field of intelligent logistics and provides a method, a device and a terminal for sorting logistics packages. Wherein, the sorting method comprises the following steps: acquiring three-dimensional image information of a target package, and inputting the three-dimensional image information into a preset feature extraction model to obtain three-dimensional geometric features of the target package; acquiring the receiving information of the target package, wherein the receiving information at least comprises receiving address information; determining a target vehicle for carrying the target package based on the recipient address information; determining a loading location of the target package on the target vehicle based on the three-dimensional geometric features of the target package. The invention realizes the distribution of the parcel loading positions through the three-dimensional geometric characteristics extracted objectively, can reduce the subjective influence of manual parcel loading, improves the reasonable utilization degree of the loading space, and is beneficial to the realization of automatic sorting and the improvement of logistics distribution efficiency.
Description
Technical Field
The invention belongs to the technical field of logistics management, and particularly relates to a method for sorting logistics packages, a sorting device, a terminal and a computer readable storage medium.
Background
Currently, in the process of delivering delivered objects (packages) to users by logistics transportation, a logistics company needs to sort the delivered objects (packages), for example, the packages are sorted according to address information, and the objects with the same or similar destinations are loaded, carried and delivered uniformly.
Traditional commodity circulation letter sorting is carried out by artifical mode, when carrying out the parcel loading, is the staff according to the letter sorting order loading in proper order of parcel usually, is difficult to accomplish to the rational utilization in delivery vehicle loading space, can influence the delivery efficiency of commodity circulation when loading unreasonablely.
Disclosure of Invention
In view of the above, the present invention provides a sorting method, a sorting apparatus, a terminal and a computer readable storage medium for logistics packages, so as to solve the problem that it is difficult to reasonably utilize the loading space of a carrier vehicle due to manual sorting and loading in the prior art.
The first aspect of the embodiment of the invention provides a method for sorting logistics packages, which comprises the following steps:
acquiring three-dimensional image information of a target package, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target package in a preset scene;
inputting the three-dimensional image information into a preset feature extraction model to obtain the three-dimensional geometric features of the target package;
acquiring the receiving information of the target package, wherein the receiving information at least comprises receiving address information;
determining a target vehicle for carrying the target package based on the recipient address information;
determining a loading location of the target package on the target vehicle based on the three-dimensional geometric features of the target package.
A second aspect of the embodiments of the present invention provides a sorting apparatus for logistics packages, including:
the three-dimensional image acquisition unit is used for acquiring three-dimensional image information of a target package, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target package in a preset scene;
the three-dimensional feature extraction unit is used for inputting the three-dimensional image information into a preset feature extraction model to obtain the three-dimensional geometric features of the target package;
the receiving information acquiring unit is used for acquiring receiving information of the target package, wherein the receiving information at least comprises receiving address information;
a first determination unit for determining a target vehicle for carrying the target package based on the recipient address information;
a second determination unit for determining a loading position of the target package on the target vehicle based on the three-dimensional geometric features of the target package.
A third aspect of embodiments of the present invention provides a sorting terminal, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method for sorting logistic packages according to any one of the above.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method for sorting logistics packages according to any one of the above.
Compared with the prior art, the invention has the following beneficial effects:
on one hand, three-dimensional geometric characteristics of the target package are extracted by a preset characteristic extraction model through acquiring three-dimensional image information of the target package; on the other hand, by acquiring the recipient address information of the target package, a transport tool is allocated to the target package based on the recipient address information; since the three-dimensional geometric features reflect the size of the space that the object may occupy, after the three-dimensional geometric features of the target package are extracted, the loading position of the target package on the transport assigned to it may be determined based on the three-dimensional geometric features. Therefore, the invention realizes the distribution of the parcel loading positions through the three-dimensional geometric characteristics which are objectively extracted, can reduce the subjective influence of manual parcel loading, improves the reasonable utilization degree of the loading space, and is beneficial to the realization of automatic sorting and the improvement of logistics distribution efficiency.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flow chart of a method for sorting logistics packages according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a sorting device for logistics packages provided by an embodiment of the invention;
fig. 3 is a schematic diagram of a sorting terminal provided by an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following description is made by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, it shows a flow chart of implementation of the sorting method for logistics packages provided by the embodiment of the present invention, and details are as follows:
in step 101, three-dimensional image information of a target parcel is acquired, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target parcel in a predetermined scene.
In an automatic sorting scene of the logistics packages, the logistics packages can be placed on a conveyor belt, the conveyor belt is used for sequentially conveying the packages, a three-dimensional image sensor, such as a three-dimensional laser image sensor or a three-dimensional infrared image sensor, can be arranged at a specified position of the conveyor belt, a monitoring scene of the three-dimensional image sensor is a preset scene, when the conveyed packages pass through the preset scene, three-dimensional image information of the conveyed packages (namely target packages) is collected through the three-dimensional image sensor, and the three-dimensional image information at least comprises a plurality of three-dimensional coordinate information of the target packages in the preset scene. For example, for a package having a three-dimensional shape of a cube, the three-dimensional image information includes at least three-dimensional coordinate information of the positions of a plurality of vertices thereof.
Optionally, the step 101 may include:
acquiring two-dimensional plane image information of the target package overlooked in the preset scene;
acquiring height information of the target parcel in the preset scene;
and performing three-dimensional image reconstruction based on the overlooked two-dimensional plane image information and the height information to obtain the three-dimensional image information of the target package.
In the embodiment of the invention, two-dimensional plane image information of the target package overlooked in a preset scene can be acquired through a two-dimensional image sensor; height information of the target package in the preset scene can be acquired through a ranging sensor; therefore, three-dimensional image reconstruction is carried out based on the obtained overlooked two-dimensional plane image information and the obtained height information, the height information is used as a depth element of each pixel point on the two-dimensional plane image and is fused to the two-dimensional plane image, and the three-dimensional image information of the target parcel is obtained.
Optionally, the step 101 may include:
acquiring a reflection pattern of structured light of a specified pattern on the target package;
and calculating the three-dimensional image information of the target parcel based on the pattern deformation of the reflection pattern and the specified mode pattern.
In the embodiment of the invention, in a preset scene, the structured light of the specified mode pattern can be used for irradiating the target parcel, the reflection pattern of the structured light of the specified mode pattern on the target parcel is obtained, the shape of the target parcel can deform the specified mode pattern, and the three-dimensional image information of the target parcel can be obtained by calculating through the deformation.
For example, when the structured light projector projects structured light of a specified pattern (e.g., a bar pattern), if projected on a plane, the two-dimensional image obtained by the image sensor on the plane is still a bar pattern, and if an object (e.g., a parcel) exists on the projected plane, the two-dimensional image obtained by the image sensor on the plane will be a bar pattern with deformation. Then, by using various structured light principles and algorithms (e.g., triangulation principles), accurate three-dimensional surface information of an object on a plane can be calculated. That is, three-dimensional image information of the object can be obtained.
In step 102, the three-dimensional image information is input into a preset feature extraction model to obtain the three-dimensional geometric features of the target package.
In an embodiment of the present invention, the extracted three-dimensional geometric features at least include a length, a width, and a height of the object parcel in the predetermined scene, where the length, the width, and the height may respectively correspond to distances in three-dimensional coordinate directions in the predetermined scene.
In the embodiment of the invention, the key point information in the three-dimensional image information can be rapidly extracted by using the preset feature extraction model, so that the three-dimensional geometric feature of the target package is obtained.
Optionally, the feature extraction model is a convolutional neural network, and the convolutional neural network includes a first convolutional layer, a second convolutional layer, and an output layer;
the first convolution layer is used for extracting side information from the three-dimensional image information; the side information refers to the information of the side where the intersection line of the intersection planes in the three-dimensional image information of the target package is located.
The second convolutional layer is used for extracting end point information from the side information; the endpoint information refers to information of endpoints of each edge corresponding to the edge information.
The output layer is used for extracting a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate and a sixth endpoint coordinate from the endpoint information, wherein the first endpoint coordinate and the second endpoint coordinate respectively represent endpoints with the maximum height coordinate and the minimum height coordinate, the third endpoint coordinate and the fourth endpoint coordinate respectively represent endpoints with the maximum width coordinate and the minimum width coordinate, and the fifth endpoint coordinate and the sixth endpoint coordinate respectively represent endpoints with the maximum length coordinate and the minimum length coordinate;
wherein the height coordinate, the width coordinate, and the length coordinate correspond to three spatial directions in the three-dimensional coordinate, respectively, for example, in the three-dimensional coordinate (x, y, z), z may be used to represent the coordinate in the height direction, x may represent the coordinate in the length direction, and y may represent the coordinate in the width direction.
In the embodiment of the invention, the convolutional neural network is utilized to extract six endpoint information in the three-dimensional image information, and the six endpoint information can represent the three-dimensional geometric shape of the target parcel. For example, the coordinate difference in the height direction of the first endpoint coordinate and the second endpoint coordinate reflects the maximum height of the target package, the coordinate difference in the width direction of the third endpoint coordinate and the fourth endpoint coordinate reflects the maximum width of the target package, and the coordinate difference in the length direction of the fifth endpoint coordinate and the sixth endpoint coordinate reflects the maximum length of the target package. And the maximum height, width and length of the target package reflects the maximum geometry of the target package. Thereby facilitating selection of a loading location for the target package that can accommodate the target package.
It should be noted that, in the present invention, by obtaining three-dimensional image information of a target parcel, extracting three-dimensional geometric features (a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate, and a sixth endpoint coordinate) of the three-dimensional image information by using a convolutional neural network, representing a three-dimensional size of the target parcel by using the six three-dimensional coordinates, and further matching a suitable loading position for the target parcel, the present invention is applicable to parcels of different shapes, for example, parcels of non-standard cubic shapes can still be loaded by using an accommodating space matched by the six three-dimensional coordinates, and the problem in the prior art that the size of the parcel of non-standard cubic shapes is difficult to objectively describe is solved.
Optionally, before the inputting the three-dimensional image information into a preset feature extraction model to obtain the three-dimensional geometric feature of the target package, the method further includes:
obtaining a certain number of three-dimensional image samples to form a training set;
training the convolutional neural network by using the training set in a supervised learning mode;
and utilizing a gradient descent method to minimize a loss function to reversely adjust the weight parameters in the convolutional neural network layer by layer so as to improve the precision of the convolutional neural network.
In the embodiment of the invention, the convolutional neural network is trained in a supervised learning mode, and the parameters (convolutional kernels) of each convolutional layer of the convolutional neural network are determined. The method is favorable for improving the output precision of the convolutional neural network.
In step 103, receiving information of the target package is obtained, where the receiving information at least includes receiving address information.
In the embodiment of the invention, the delivery direction of the target package can be obtained by obtaining the receiving information of the target package and determining the receiving address, and further vehicles and other transportation tools driving to the delivery direction can be selected according to the delivery direction.
Optionally, the receiving information further includes a contact number of the recipient, and after the step 102, the method further includes:
calculating volume information of the target parcel based on the three-dimensional geometric features;
and sending the volume information to the contact number of the recipient.
In the embodiment of the invention, the volume information of the target package can be calculated by utilizing the extracted three-dimensional geometric characteristics, and the volume information of the target package is sent to the receiver of the target package, so that the receiver can timely know the volume of the package to be received, and the problem that the receiver is inconvenient to take and carry due to overlarge package volume is solved.
In step 104, a target vehicle for carrying the target package is determined based on the recipient address information.
In the embodiment of the invention, a plurality of transport means are respectively sent to different regions, the region to which the package is sent can be determined through the address receiving information, and then the target transport means capable of carrying the target package is determined.
In step 105, a loading location of the target package on the target vehicle is determined based on the three-dimensional geometric characteristics of the target package.
In the embodiment of the invention, the maximum volume of the target parcel is determined by extracting the three-dimensional geometric characteristics of the target parcel, and then the spatial position suitable for loading the target parcel can be selected on the transport tool.
Optionally, the step 105 may include:
acquiring three-dimensional geometrical characteristics of loading spaces of each wrapped loading pane arranged on the target transport tool;
selecting a target parcel loading pane matched with the three-dimensional geometric characteristics of the target parcel from the three-dimensional geometric characteristics of the loading space of each parcel loading pane;
determining the target package loading pane as a loading location of the target package on the target transport.
In the embodiment of the invention, a plurality of parcel loading panes for loading parcels are arranged on each logistics transport tool, and the size and the three-dimensional geometrical characteristics of each parcel loading pane on each logistics transport tool can be acquired in advance. Here, the three-dimensional geometrical feature of the parcel loading pane refers to the three-dimensional geometrical feature of its accommodation space, and may include a maximum height, a maximum length, and a maximum width that can be accommodated. By matching the three-dimensional geometry of the target package with the three-dimensional geometry of each package loading pane, a target package loading pane matching the three-dimensional geometry of the target package may be selected and determined as the loading location of the target package on the target transport.
The invention can reasonably distribute the loading positions matched with the sizes and the shapes of the packages with different sizes and shapes, and is beneficial to realizing the automatic loading of the logistics package sorting and the reasonable utilization of the loading space.
In the invention, on one hand, the three-dimensional geometric characteristics of the target package are extracted by acquiring the three-dimensional image information of the target package and utilizing a preset characteristic extraction model; on the other hand, by acquiring the recipient address information of the target package, a transport tool is allocated to the target package based on the recipient address information; since the three-dimensional geometric features reflect the size of the space that the object may occupy, after the three-dimensional geometric features of the target package are extracted, the loading position of the target package on the transport assigned to it may be determined based on the three-dimensional geometric features. Therefore, the invention realizes the distribution of the parcel loading positions through the three-dimensional geometric characteristics which are objectively extracted, can reduce the subjective influence of manual parcel loading, improves the reasonable utilization degree of the loading space, and is beneficial to the realization of automatic sorting and the improvement of logistics distribution efficiency.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The following are embodiments of the apparatus of the invention, reference being made to the corresponding method embodiments described above for details which are not described in detail therein.
Fig. 2 shows a schematic structural diagram of a sorting apparatus for logistics packages provided by an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
as shown in fig. 2, the sorting apparatus 2 for logistic package includes: a three-dimensional image acquisition unit 21, a three-dimensional feature extraction unit 22, an addressee information acquisition unit 23, a first determination unit 24, and a second determination unit 25.
A three-dimensional image obtaining unit 21 configured to obtain three-dimensional image information of a target parcel, wherein the three-dimensional image information at least includes a plurality of three-dimensional coordinates of the target parcel in a predetermined scene;
the three-dimensional feature extraction unit 22 is configured to input the three-dimensional image information into a preset feature extraction model to obtain a three-dimensional geometric feature of the target package;
an addressee information obtaining unit 23, configured to obtain addressee information of the target package, where the addressee information at least includes addressee information;
a first determination unit 24, configured to determine a target transportation vehicle for carrying the target package based on the recipient address information;
a second determining unit 25, configured to determine a loading position of the target package on the target transportation vehicle based on the three-dimensional geometric characteristics of the target package.
Optionally, the sorting device 2 for logistic packages further includes:
a three-dimensional feature acquisition unit, configured to acquire three-dimensional geometric features of loading spaces each of which wraps a loading pane, provided on the target transport;
a loading pane selecting unit, configured to select a target package loading pane matching the three-dimensional geometric features of the target package from the three-dimensional geometric features of the loading space of each package loading pane;
the second determination unit 25 is specifically configured to determine the target package loading pane as a loading position of the target package on the target transportation vehicle.
Optionally, the sorting device 2 for logistic packages further includes:
the two-dimensional image acquisition unit is used for acquiring two-dimensional plane image information overlooked in the preset scene by the target package;
the height information acquisition unit is used for acquiring the height information of the target parcel in the preset scene;
the three-dimensional image obtaining unit 21 is specifically configured to perform three-dimensional image reconstruction based on the two-dimensional planar image information of the top view and the height information to obtain three-dimensional image information of the target package.
Optionally, the sorting device 2 for logistic packages further includes:
a reflection pattern acquisition unit for acquiring a reflection pattern of the structured light of the specified mode pattern on the target package;
the three-dimensional image obtaining unit 21 is specifically configured to calculate three-dimensional image information of the target package based on the pattern deformation of the reflection pattern and the specified mode pattern.
Optionally, the feature extraction model is a convolutional neural network, and the convolutional neural network includes a first convolutional layer, a second convolutional layer, and an output layer;
the first convolution layer is used for extracting side information from the three-dimensional image information;
the second convolutional layer is used for extracting end point information from the side information;
the output layer is used for extracting a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate and a sixth endpoint coordinate from the endpoint information, wherein the first endpoint coordinate and the second endpoint coordinate respectively represent endpoints with the maximum height coordinate and the minimum height coordinate, the third endpoint coordinate and the fourth endpoint coordinate respectively represent endpoints with the maximum width coordinate and the minimum width coordinate, and the fifth endpoint coordinate and the sixth endpoint coordinate respectively represent endpoints with the maximum length coordinate and the minimum length coordinate;
wherein the height coordinate, the width coordinate, and the length coordinate correspond to three spatial directions in a three-dimensional coordinate, respectively.
Optionally, the sorting device 2 for logistic packages further includes:
a training set obtaining unit, configured to obtain a certain number of three-dimensional image samples to form a training set before inputting the three-dimensional image information into a preset feature extraction model to obtain a three-dimensional geometric feature of the target package;
and the supervision training unit is used for training the convolutional neural network by utilizing the training set in a supervision learning mode and reversely adjusting the weight parameters in the convolutional neural network layer by utilizing a gradient descent method minimum loss function so as to improve the precision of the convolutional neural network.
Optionally, the receiving information further includes a contact number of a recipient, and the sorting device 2 for the logistics packages further includes:
the volume calculation unit is used for calculating the volume information of the target parcel based on the three-dimensional geometric characteristics after the three-dimensional image information is input into a preset characteristic extraction model to obtain the three-dimensional geometric characteristics of the target parcel;
and the volume information sending unit is used for sending the volume information to the contact number of the recipient.
In the invention, on one hand, the three-dimensional geometric characteristics of the target package are extracted by acquiring the three-dimensional image information of the target package and utilizing a preset characteristic extraction model; on the other hand, by acquiring the recipient address information of the target package, a transport tool is allocated to the target package based on the recipient address information; since the three-dimensional geometric features reflect the size of the space that the object may occupy, after the three-dimensional geometric features of the target package are extracted, the loading position of the target package on the transport assigned to it may be determined based on the three-dimensional geometric features. Therefore, the invention realizes the distribution of the parcel loading positions through the three-dimensional geometric characteristics which are objectively extracted, can reduce the subjective influence of manual parcel loading, improves the reasonable utilization degree of the loading space, and is beneficial to the realization of automatic sorting and the improvement of logistics distribution efficiency.
Fig. 3 is a schematic diagram of a sorting terminal according to an embodiment of the present invention. As shown in fig. 3, the sorting terminal 3 of this embodiment includes: a processor 30, a memory 31 and a computer program 32 stored in said memory 31 and executable on said processor 30. The processor 30, when executing the computer program 32, implements the steps in the above-described embodiments of the method for sorting logistics packages, such as the steps 101 to 105 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 32, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the units 21 to 25 shown in fig. 2.
Illustratively, the computer program 32 may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 32 in the terminal 3. For example, the computer program 32 may be divided into a three-dimensional image acquisition unit, a three-dimensional feature extraction unit, an addressee information acquisition unit, a first determination unit and a second determination unit, and the specific functions of each unit are as follows:
the three-dimensional image acquisition unit is used for acquiring three-dimensional image information of a target package, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target package in a preset scene;
the three-dimensional feature extraction unit is used for inputting the three-dimensional image information into a preset feature extraction model to obtain the three-dimensional geometric features of the target package;
the receiving information acquiring unit is used for acquiring receiving information of the target package, wherein the receiving information at least comprises receiving address information;
a first determination unit for determining a target vehicle for carrying the target package based on the recipient address information;
a second determination unit for determining a loading position of the target package on the target vehicle based on the three-dimensional geometric features of the target package.
The sorting terminal 3 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The sorting terminal may include, but is not limited to, a processor 30, a memory 31. It will be appreciated by those skilled in the art that fig. 3 is merely an example of a sorting terminal 3 and does not constitute a limitation of the sorting terminal 3 and may comprise more or less components than those shown, or some components may be combined, or different components, e.g. the terminal may further comprise input output devices, network access devices, buses, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 31 may be an internal storage unit of the sorting terminal 3, such as a hard disk or a memory of the sorting terminal 3. The memory 31 may also be an external storage device of the sorting terminal 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like provided on the terminal 3. Further, the memory 31 may also comprise both an internal storage unit and an external storage device of the sorting terminal 3. The memory 31 is used for storing the computer program and other programs and data required by the terminal. The memory 31 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (7)
1. A sorting method of logistics packages is characterized by comprising the following steps:
acquiring three-dimensional image information of a target package, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target package in a preset scene;
inputting the three-dimensional image information into a preset feature extraction model to obtain three-dimensional geometric features of the target package, wherein the three-dimensional geometric features at least comprise six endpoint coordinate information, the six endpoint coordinate information is used for representing the three-dimensional size of the target package, the six endpoint coordinate information comprises a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate and a sixth endpoint coordinate, the first endpoint coordinate and the second endpoint coordinate respectively represent endpoints with the largest height coordinate and the smallest height coordinate, the third endpoint coordinate and the fourth endpoint coordinate respectively represent endpoints with the largest width coordinate and the smallest width coordinate, and the fifth endpoint coordinate and the sixth endpoint coordinate respectively represent endpoints with the largest length coordinate and the smallest length coordinate, wherein the height coordinate, the width coordinate and the length coordinate respectively correspond to three spatial directions in a three-dimensional coordinate;
acquiring the receiving information of the target package, wherein the receiving information at least comprises receiving address information;
determining a target vehicle for carrying the target package based on the recipient address information;
determining a loading location of the target package on the target vehicle based on the three-dimensional geometric features of the target package;
wherein the acquiring the three-dimensional image information of the target package comprises:
acquiring two-dimensional plane image information of the target package overlooked in the preset scene; the two-dimensional plane image information is obtained by shooting based on an image sensor positioned above the packages in a package sorting scene;
acquiring height information of the target parcel in the preset scene; the height information is obtained based on the measurement of a distance measuring sensor arranged in a parcel sorting scene;
performing three-dimensional image reconstruction based on the overlooked two-dimensional plane image information and the height information to obtain three-dimensional image information of the target package;
wherein said determining a loading location of said target package on said target conveyance based on three-dimensional geometric characteristics of said target package comprises:
acquiring three-dimensional geometrical characteristics of loading spaces of each wrapped loading pane arranged on the target transport tool;
selecting a target parcel loading pane matched with the three-dimensional geometric characteristics of the target parcel from the three-dimensional geometric characteristics of the loading space of each parcel loading pane;
determining the target package loading pane as a loading location of the target package on the target transport.
2. The method for sorting logistics packages according to claim 1, wherein the feature extraction model is a convolutional neural network, and the convolutional neural network comprises a first convolutional layer, a second convolutional layer and an output layer;
the first convolution layer is used for extracting side information from the three-dimensional image information;
the second convolutional layer is used for extracting end point information from the side information;
the output layer is used for extracting a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate and a sixth endpoint coordinate from the endpoint information.
3. The method for sorting logistics packages according to claim 2, further comprising, before the inputting the three-dimensional image information into a preset feature extraction model to obtain the three-dimensional geometric features of the target package:
obtaining a certain number of three-dimensional image samples to form a training set;
training the convolutional neural network by using the training set in a supervised learning mode;
and utilizing a gradient descent method to minimize a loss function to reversely adjust the weight parameters in the convolutional neural network layer by layer so as to improve the precision of the convolutional neural network.
4. The method for sorting logistics packages of claim 1, wherein the recipient information further comprises a recipient contact number;
after the three-dimensional image information is input into a preset feature extraction model to obtain the three-dimensional geometric features of the target parcel, the method further comprises the following steps:
calculating volume information of the target parcel based on the three-dimensional geometric features;
and sending the volume information to the contact number of the recipient.
5. A sorting device for logistic parcels, characterized in that the sorting device comprises:
the three-dimensional image acquisition unit is used for acquiring three-dimensional image information of a target package, wherein the three-dimensional image information at least comprises a plurality of three-dimensional coordinates of the target package in a preset scene;
a three-dimensional feature extraction unit, configured to input the three-dimensional image information into a preset feature extraction model to obtain a three-dimensional geometric feature of the target package, where the three-dimensional geometric feature at least includes six endpoint coordinate information, the six endpoint coordinate information is used to represent a three-dimensional size of the target package, the six endpoint coordinate information includes a first endpoint coordinate, a second endpoint coordinate, a third endpoint coordinate, a fourth endpoint coordinate, a fifth endpoint coordinate and a sixth endpoint coordinate, where the first endpoint coordinate and the second endpoint coordinate respectively represent endpoints with a maximum height coordinate and a minimum height coordinate, the third endpoint coordinate and the fourth endpoint coordinate respectively represent endpoints with a maximum width coordinate and a minimum width coordinate, and the fifth endpoint coordinate and the sixth endpoint coordinate respectively represent endpoints with a maximum length coordinate and a minimum length coordinate, wherein the height coordinate, the width coordinate and the length coordinate respectively correspond to three spatial directions in a three-dimensional coordinate;
the receiving information acquiring unit is used for acquiring receiving information of the target package, wherein the receiving information at least comprises receiving address information;
a first determination unit for determining a target vehicle for carrying the target package based on the recipient address information;
a second determination unit for determining a loading position of the target package on the target transport means based on the three-dimensional geometric characteristics of the target package;
wherein, the sorting device still includes:
the two-dimensional image acquisition unit is used for acquiring two-dimensional plane image information overlooked in the preset scene by the target package; the two-dimensional plane image information is obtained by shooting based on an image sensor positioned above the packages in a package sorting scene;
the height information acquisition unit is used for acquiring the height information of the target parcel in the preset scene; the height information is obtained based on the measurement of a distance measuring sensor arranged in a parcel sorting scene;
correspondingly, the three-dimensional image obtaining unit is specifically configured to perform three-dimensional image reconstruction based on the two-dimensional planar image information of the overlooking and the height information to obtain three-dimensional image information of the target package;
wherein, the sorting device still includes:
a three-dimensional feature acquisition unit, configured to acquire three-dimensional geometric features of loading spaces each of which wraps a loading pane, provided on the target transport;
a loading pane selecting unit, configured to select a target package loading pane matching the three-dimensional geometric features of the target package from the three-dimensional geometric features of the loading space of each package loading pane;
correspondingly, the second determining unit is specifically configured to determine the target package loading pane as a loading position of the target package on the target transport vehicle.
6. A sorting terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor when executing the computer program implements the steps of the method for sorting logistic packages according to any of the above claims 1 to 4.
7. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for sorting logistics packages according to any one of the preceding claims 1 to 4.
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 CN109759339A (en) | 2019-05-17 |
| CN109759339B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Citations (8)
| 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 |
| 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 |
| 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 |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1963390A (en) * | 2005-11-08 | 2007-05-16 | 李啸炜 | A precision and high efficiency three-dimensional measuring method |
| CN104077577A (en) * | 2014-07-03 | 2014-10-01 | 浙江大学 | Trademark detection method based on convolutional neural network |
| US9599459B1 (en) * | 2016-02-24 | 2017-03-21 | United Parcel Service Of America, Inc. | Conveyor belt, conveyor belt assembly including an imaging system, and methods of using the same |
| CN108108781A (en) * | 2017-12-07 | 2018-06-01 | 曾学 | A kind of digitized airdrome luggage loading method and its system |
-
2019
- 2019-03-01 CN CN201910156000.3A patent/CN109759339B/en active Active
Patent Citations (8)
| 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 |
| 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 |
| 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 |
| 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 |
|---|
| "多特征组合和用户反馈的图像检索算法";丁万宁等;《吉林大学学报（理学版）》;20171130;第55卷(第6期);第1511-1517页 * |
| "瑞丰快递的具体业务流程是什么https://wenda.so.com/q/1408157589724533";lmfwqyl;《360问答》;20140815;第1页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109759339A (en) | 2019-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180189967A1 (en) | Methods and systems for automatic fullness estimation of containers | |
| DE102019009206B4 (en) | Robot system with dynamic packing mechanism | |
| CN111754515B (en) | Sequential gripping method and device for stacked articles | |
| US9390314B2 (en) | Methods and apparatus for determining dimensions of an item using 3-dimensional triangulation | |
| CN108230321A (en) | Defect inspection method and device | |
| CN111178250A (en) | Object identification positioning method and device and terminal equipment | |
| CN109759339B (en) | Sorting method, sorting device and sorting terminal for logistics packages | |
| CN112802105A (en) | Object grabbing method and device | |
| CN108906637B (en) | Logistics sorting method and terminal equipment | |
| CN110276829A (en) | The three dimensional representation handled by multiple dimensioned voxel Hash | |
| CN113610921B (en) | Hybrid workpiece gripping method, apparatus, and computer readable storage medium | |
| US10282902B1 (en) | Real-time textured 3D models | |
| CN112002015B (en) | Method, device, equipment and medium for generating grid data structure by using disordered point cloud | |
| CN111512115A (en) | Log sizing system and related method | |
| CN114693678B (en) | Intelligent detection method and device for workpiece quality | |
| CN110888345A (en) | Detection device, control device, automatic verification system and method | |
| CN115374885A (en) | Data acquisition method, device and storage medium for real-time tracking of logistics information | |
| CN111160450A (en) | Fruit and vegetable weighing method based on neural network, storage medium and device | |
| CN110793437A (en) | Positioning method and device of manual operator, storage medium and electronic equipment | |
| CN112633187A (en) | Robot automatic handling method and system based on image analysis and storage medium | |
| CN111121640B (en) | Vehicle size detection method and device | |
| US20230305574A1 (en) | Detecting empty workspaces for robotic material handling | |
| WO2019233654A1 (en) | Method for determining a type and a state of an object of interest | |
| CN114638888B (en) | Position determination method and device, electronic equipment and readable storage medium | |
| CN113978987B (en) | Pallet object packaging and picking method, device, equipment and medium |
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 |