CN114971443B - A processing method and imaging device for logistics objects - Google Patents
A processing method and imaging device for logistics objects Download PDFInfo
- Publication number
- CN114971443B CN114971443B CN202110193300.6A CN202110193300A CN114971443B CN 114971443 B CN114971443 B CN 114971443B CN 202110193300 A CN202110193300 A CN 202110193300A CN 114971443 B CN114971443 B CN 114971443B
- Authority
- CN
- China
- Prior art keywords
- logistics object
- candidate
- logistics
- description information
- perspective image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The application provides a processing method of a logistics object and imaging equipment. In the application, a first perspective image comprising at least one logistic object is acquired, and descriptive information of at least part of the logistic objects in the at least one logistic object is acquired. Determining the logistics state of the at least one logistics object according to the first perspective image of the at least one logistics object and/or the description information of at least part of the logistics objects in the at least one logistics object. By the method and the device, the accuracy of determining the logistics state of the logistics object can be improved by combining the perspective image of the logistics object and the description information of the logistics object. For example, in a scenario of security inspection of a logistic object, the accuracy of determining whether the logistic object is a forbidden logistic object can be improved.
Description
Technical Field
The present application relates to the field of logistics, and in particular, to a method for processing a logistics object and an imaging device.
Background
At present, the security inspection machine based on the X-ray machine can be used for security inspection of express packages, for example, under the condition that the express packages enter the security inspection machine, the security inspection machine can shoot X-ray images of the express packages in real time, and intelligent identification is carried out according to the X-ray images so as to determine whether the express packages comprise contraband.
However, many personalized features of the objects in the express package are lost in the X-ray image shot by the security inspection machine, so that misjudgment easily occurs when determining whether the express package includes contraband according to the X-ray image, for example, a metal glue gun with a wrench (used for decoration and being non-contraband) is easily misjudged as a real gun (contraband), and the accuracy of determining whether the express package includes contraband is low.
Disclosure of Invention
In order to improve accuracy in determining whether express packages comprise contraband or not, the application discloses a processing method and imaging equipment of a logistics object.
In a first aspect, the present application provides a method for processing a logistic object, the method comprising:
Acquiring a first perspective image comprising at least one logistics object, and acquiring description information of at least part of the logistics objects in the at least one logistics object;
And determining the logistics state of the at least one logistics object according to the first perspective image and/or the description information.
In an optional implementation manner, the determining the logistics state of the at least one logistics object according to the first perspective image and/or the description information includes:
and determining whether the at least one logistics object is damaged according to the first perspective image and the description information.
In an optional implementation manner, the determining the logistics state of the at least one logistics object according to the first perspective image and/or the description information includes:
and determining whether the articles in the at least one logistics object are lost according to the first perspective image and the description information.
In an optional implementation manner, the obtaining the description information of at least part of the at least one logistics object includes:
Determining forbidden candidate logistics objects in the at least one logistics object according to the first perspective image;
acquiring description information of the candidate logistics object;
in an optional implementation manner, the determining the logistics state of the at least one logistics object according to the first perspective image and/or the description information includes:
And checking whether the candidate logistics object is an forbidden logistics object according to the description information.
In an optional implementation manner, the obtaining the description information of the candidate logistics object includes:
intercepting a second perspective image of the candidate logistics object in the first perspective image;
and acquiring the description information of the candidate logistics object according to the second perspective image.
In an optional implementation manner, the obtaining the description information of the candidate logistics object according to the second perspective image includes:
searching the physical image of the candidate logistics object according to the second perspective image in the corresponding relation between the physical image of the logistics object and the description information of the logistics object;
and searching description information corresponding to the physical image of the candidate logistics object in the corresponding relation.
In an alternative implementation, the method further includes:
Before the first perspective image is acquired, acquiring a physical image of the candidate logistics object, wherein the physical image comprises identification information of the candidate logistics object arranged on the surface of the candidate logistics object;
Extracting identification information of the candidate logistics object from the physical image;
Acquiring the description information of the candidate logistics object from the cloud according to the identification information;
and storing the physical image of the candidate logistics object and the description information of the candidate logistics object in the corresponding relation.
In an alternative implementation, the method further includes:
and deleting the physical image of the candidate logistics object and the description information of the candidate logistics object in the corresponding relation under the condition that whether the candidate logistics object is the forbidden logistics object or not is checked according to the description information.
In a second aspect, the present application shows an imaging apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first perspective image comprising at least one logistics object, and the second acquisition module is used for acquiring description information of at least part of the logistics objects in the at least one logistics object;
And the determining module is used for determining the logistics state of the at least one logistics object according to the first perspective image and/or the description information.
In an alternative implementation, the determining module includes:
And the first determining unit is used for determining whether the at least one logistics object is damaged according to the first perspective image and the description information.
In an alternative implementation, the determining module includes:
And the second determining unit is used for determining whether the articles in the at least one logistics object are lost or not according to the first perspective image and the description information.
In an alternative implementation, the second obtaining module includes:
a third determining unit, configured to determine, according to the first perspective image, a forbidden candidate logistics object in the at least one logistics object;
an acquisition unit, configured to acquire description information of the candidate logistics object;
in an alternative implementation, the determining module includes:
and the verification unit is used for verifying whether the candidate logistics object is an forbidden logistics object according to the description information.
In an alternative implementation, the acquiring unit includes:
A clipping subunit, configured to clip, in the first perspective image, a second perspective image of the candidate logistics object;
and the acquisition subunit is used for acquiring the description information of the candidate logistics object according to the second perspective image.
In an optional implementation manner, the obtaining subunit is specifically configured to search, in a correspondence between a physical image of the logistics object and description information of the logistics object, the physical image of the candidate logistics object according to the second perspective image, and search, in the correspondence, description information corresponding to the physical image of the candidate logistics object.
In an alternative implementation manner, the obtaining subunit is further configured to obtain, before obtaining the first perspective image, a physical image of the candidate logistics object, where the physical image includes identification information of the candidate logistics object set on a surface of the candidate logistics object, extract the identification information of the candidate logistics object in the physical image, obtain, according to the identification information, description information of the candidate logistics object from a cloud, and store, in the correspondence, the physical image of the candidate logistics object and the description information of the candidate logistics object.
In an optional implementation manner, the obtaining subunit is further configured to delete, in the correspondence, the physical image of the candidate logistics object and the description information of the candidate logistics object if it has been verified, according to the description information, that the candidate logistics object is an forbidden logistics object.
In a third aspect, the present application shows an electronic device comprising:
A processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method of processing a logistic object according to the first aspect.
In a fourth aspect, the application features a non-transitory computer readable storage medium that, when executed by a processor of an electronic device, enables the electronic device to perform a method of processing a logistic object as described in the first aspect.
In a fifth aspect, the application shows a computer program product which, when executed by a processor of an electronic device, enables the electronic device to perform the method of processing a logistic object according to the first aspect.
Compared with the prior art, the embodiment of the application has the following advantages:
In the application, a first perspective image comprising at least one logistic object is acquired, and descriptive information of at least part of the logistic objects in the at least one logistic object is acquired. Determining the logistics state of the at least one logistics object according to the first perspective image of the at least one logistics object and/or the description information of at least part of the logistics objects in the at least one logistics object. By the method and the device, the accuracy of determining the logistics state of the logistics object can be improved by combining the perspective image of the logistics object and the description information of the logistics object.
For example, in a scenario of security inspection of a logistic object, personalized features of the logistic object may be lost in the first perspective image, so that an error may occur in determining, in at least one logistic object, a forbidden candidate logistic object according to the first perspective image, for example, determining a logistic object that is not actually forbidden as a forbidden logistic object, which may reduce the accuracy of determining whether the logistic object is a forbidden logistic object.
According to the method and the device, after the forbidden candidate logistics objects are determined in at least one logistics object according to the first perspective image, the description information of the candidate logistics objects can be obtained, and the description information of the candidate logistics objects can sometimes show whether the candidate logistics objects are contraband or not, for example, if the candidate logistics objects are contraband, the description information in the logistics objects sometimes has related descriptions about the fact that the candidate logistics objects are contraband or not, and if the candidate logistics objects are not contraband, the description information of the logistics objects often does not have related descriptions about the fact that the candidate logistics objects are contraband or not. Therefore, whether the candidate logistics object is the forbidden logistics object can be checked according to the description information of the candidate logistics object, and as a final result, for example, the forbidden candidate logistics object determined according to the first perspective image can be screened out of misjudged physical non-forbidden logistics objects, so that the accuracy of determining whether the logistics object is the forbidden logistics object can be improved.
Drawings
Fig. 1 is a flow chart illustrating a method for processing a logistics object according to an exemplary embodiment of the present application.
Fig. 2 is a flow chart illustrating a method for processing a logistics object according to an exemplary embodiment of the present application.
Fig. 3 is a flow chart illustrating a method for processing a logistics object according to an exemplary embodiment of the present application.
Fig. 4 is a block diagram showing a configuration of an image forming apparatus according to an exemplary embodiment of the present application.
Fig. 5 is a schematic structural diagram of an apparatus according to an embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description.
Referring to fig. 1, a flow chart of a method for processing a logistic object according to the present application is shown, and the method may include:
In step S101, a first perspective image including at least one logistic object is acquired, and description information of at least a part of the logistic objects among the at least one logistic object is acquired.
In the present application, in the case where it is required to determine the logistics status of at least one logistics object, for example, it is required to perform security check on at least one logistics object (to detect whether the logistics object includes contraband or the like), or determine whether at least one logistics object is broken, or determine whether an article in at least one logistics object is lost or the like, a user may place at least one logistics object in an imaging apparatus (for example, security check machine or the like) so that the imaging apparatus photographs a first perspective image including at least one logistics object.
The first fluoroscopic image may comprise an X-ray image or the like.
The logistics object may include an article or the like that is required to perform a logistics operation, for example, after a buyer purchases a commodity sold by a seller, the seller needs to mail the commodity to the buyer through an express company, in which case the commodity may be regarded as a logistics object. The seller can mail the commodity to the buyer through the express company in the form of an express package, wherein the express package has a unique logistics identifier, such as an express number, and the like, and thus the commodity has the unique logistics identifier.
The subject of execution of this step may be, in one possible case, a security check machine, i.e. the present application improves upon the security check machine such that the security check machine may execute step S102 after capturing a first perspective image comprising at least one logistical object.
In another possible case, the main implementation body of the step may be an electronic device (non-security inspection machine), that is, the security inspection machine is not improved by the present application, the electronic device is in communication connection with the security inspection machine, the security inspection machine may send the first perspective image including at least one logistical object to the electronic device after shooting the first perspective image including at least one logistical object, the electronic device may receive the first perspective image sent by the security inspection machine, and then step S102 may be implemented.
In step S102, a logistics state of the at least one logistics object is determined according to the first perspective image of the at least one logistics object and/or the description information of at least part of the at least one logistics object.
The physical distribution state of the physical distribution object includes, but is not limited to, whether the physical distribution object is prohibited, whether the physical distribution object is broken, whether the articles in the physical distribution object are lost, and the like, and of course, other states can be included, and the application is not limited to one.
How to determine the physical distribution state of the at least one physical distribution object according to the first perspective image of the at least one physical distribution object and/or the description information of at least some physical distribution objects in the at least one physical distribution object can be specifically referred to the embodiments shown later, and will not be described in detail herein.
In the application, a first perspective image comprising at least one logistic object is acquired, and descriptive information of at least part of the logistic objects in the at least one logistic object is acquired. Determining the logistics state of the at least one logistics object according to the first perspective image of the at least one logistics object and/or the description information of at least part of the logistics objects in the at least one logistics object. By the method and the device, the accuracy of determining the logistics state of the logistics object can be improved by combining the perspective image of the logistics object and the description information of the logistics object.
In one embodiment of the present application, when the description information of at least some of the at least one logistic object is acquired in the case where the at least one logistic object needs to be checked (to detect whether the logistic object includes contraband or not), the method may be implemented according to the following flow, with reference to fig. 2:
in step S201, a forbidden candidate logistics object is determined in the at least one logistics object from the first perspective image.
In one embodiment of the present application, where a first perspective image is obtained that includes at least one logistic object, the first perspective image may be subjected to image analysis to determine contraband for the at least one logistic object. Wherein, in the case that one logistic object is contraband, the logistic object can be determined to be the contraband logistic object. Contraband may include firearms, inflammable and explosive articles, articles with strong magnetism, etc., and the contraband may be set according to actual safety requirements, which is not limited by the present application.
In one embodiment of the present application, the first perspective image includes at least a shape contour of the at least one logistic object.
Thus, in one embodiment, perspective images of existing contraband on the market (including the shape profile of the contraband, etc.) can be counted in advance.
In this way, in this step, when determining the forbidden candidate logistics object in the at least one logistics object according to the first perspective image, for the perspective image of any one logistics object included in the first perspective image, the similarity between the second perspective image of the logistics object and the perspective image of the counted contraband existing in the market may be calculated, and in the case that the similarity between the perspective image of the logistics object and the perspective image of any one of the counted contraband existing in the market is greater than the preset threshold, the logistics object may be determined as the forbidden candidate logistics object.
And under the condition that the similarity between the perspective image of the logistic object and the perspective image of any one of the counted contraband articles existing on the market is smaller than or equal to a preset threshold value, determining the logistic object as a non-forbidden logistic object (namely a safe logistic object).
The preset threshold may be determined according to practical situations, and may include 90%, 85%, 80%, or the like, for example, and the present application is not limited to specific numerical values.
In addition, the specific calculation mode for calculating the similarity between the two perspective images can be referred to the existing mode, and the specific calculation mode of the similarity is not limited by the application.
In a further embodiment of the application, the image recognition model may be trained beforehand, so that the image recognition model may be used when determining the forbidden candidate logistics object from the first perspective image among the at least one logistics object.
The training mode of the image recognition model comprises the steps of obtaining at least one training data, wherein the training data comprise a sample perspective image of a sample logistics object and annotation forbidden data of the sample logistics object. And training the model by using at least one training data until parameters in the model are converged, so as to obtain the image recognition model.
The labeling forbidden data is used for indicating that the sample logistics object is a forbidden logistics object or a non-forbidden logistics object.
The model may include xtranse CV, etc.
Thus, when determining the forbidden candidate logistics object in the at least one logistics object according to the first perspective image, the first perspective image can be input into the trained image recognition model to obtain the forbidden candidate logistics object output by the image recognition model.
According to the embodiment of the application, the image recognition model is trained by using at least one training data, so that the image recognition model can learn the image characteristics of the perspective image of the forbidden logistics object and the image characteristics of the perspective image of the non-forbidden logistics object. Thus, the image recognition model can determine the image characteristics of the perspective images of all the logistic objects in the first perspective image, and can determine the logistic object as a forbidden candidate logistic object under the condition that the image characteristics of the perspective image of a certain logistic object accord with the image characteristics of the perspective image of the forbidden logistic object.
In step S202, description information of the candidate physical distribution object is acquired.
In the application, the description information of the logistics object can comprise text-form description information, voice-form description information, picture-form description information, video-form description information and the like.
The description information of the logistics object may include a detailed description of the logistics object, etc.
For example, in the case where the physical distribution object is a commodity that can be sold, the detailed description of the commodity includes a description of the commodity by a seller of the commodity, and the like, and may also include an evaluation of the commodity by a wide range of buyers, and the like.
The seller may introduce functions of the commodity, appearance of the commodity, kind of the commodity, etc.
The manner of acquiring the description information of the candidate logistics object can be specifically referred to the embodiment shown later, and is not described in detail herein.
Accordingly, when determining the logistics state of at least one logistics object according to the first perspective image and the description information, whether the candidate logistics object is an forbidden logistics object can be checked according to the description information of the candidate logistics object.
In one embodiment of the present application, the description information of the candidate physical distribution object may sometimes represent whether the candidate physical distribution object is contraband or not.
For example, if a logistic object is contraband, there are sometimes contraband keywords (keywords for indicating contraband) and the like in descriptive information in the logistic object, such as "gun", "alcohol", and "magnetic", and the like, in one possible case.
In addition, if one logistics object is not prohibited, prohibited keywords and the like often do not exist in the description information of the logistics object.
Therefore, when checking whether the candidate physical distribution object is a forbidden physical distribution object according to the description information of the candidate physical distribution object, in one mode, whether the description information of the candidate physical distribution object has a forbidden keyword can be judged, and when the description information of the candidate physical distribution object has the forbidden keyword, the candidate physical distribution object can be described as being forbidden, and further the candidate physical distribution object can be determined as being forbidden. Under the condition that the forbidden keywords do not exist in the description information of the candidate logistics objects, the candidate logistics objects can be described as non-forbidden articles, and further the candidate logistics objects can be determined as the forbidden logistics objects.
Thus, for any one of the logistic objects, it is assumed that the logistic object is actually a non-forbidden logistic object, and thus, the description information of the logistic object often does not have forbidden keywords and the like.
However, after the perspective image including the logistic object is shot, if the logistic object is determined to be a forbidden logistic object by mistake due to the fact that the shape of the perspective image is similar to the image of the contraband, and the like, the logistic object can be verified to be a non-forbidden logistic object by means of the description information of the logistic object in the mode, so that the situation of misjudgment on the logistic object is avoided as much as possible.
However, sometimes, a misjudgment situation may still occur in the above manner, for example, a physical object candidate that is not actually forbidden is still misjudged as a forbidden candidate.
For example, it is assumed that the candidate physical distribution object is not actually contraband, i.e., the physical distribution object is actually a physical distribution object that is not prohibited, but the description information of the candidate physical distribution object includes a term "prohibited from being placed with the magnetic article (magnetism is prohibited keyword, etc.) to avoid demagnetization", which term does not indicate that the candidate physical distribution object is magnetic, but indicates how to avoid demagnetization of the candidate physical distribution object.
However, in the above manner, it is determined that the forbidden keyword "magnetism" exists in the description information of the candidate logistics object, so that it is verified that the candidate logistics object is the forbidden logistics object, and a misjudgment situation occurs.
Therefore, in order to avoid the occurrence of the erroneous judgment as far as possible, in another embodiment of the present application, the forbidden verification model may be trained in advance, so that when verifying whether the candidate logistics object is the forbidden logistics object according to the description information of the candidate logistics object, the forbidden verification model may be used.
The training mode of the forbidden verification model comprises the steps of obtaining at least one training data, wherein the training data comprise sample description information of a sample logistics object and marked forbidden data of the sample logistics object. And training the model by using at least one training data until the parameters in the model are converged, so as to obtain the forbidden verification model.
The annotation contraband data is used for indicating that the sample logistics object is a contraband logistics object or a non-contraband logistics object. Where the tagging contraband data is used to indicate that the sample logistics object is a contraband logistics object, the tagging contraband data may also include a contraband level, such as electrification, banning, and special goods.
The model may include a master-rcnn, etc.
Therefore, when checking whether the candidate logistics object is the forbidden logistics object according to the description information of the candidate logistics object, the description information can be input into the trained forbidden checking model to obtain the checking result of whether the candidate logistics object output by the forbidden checking model is the forbidden logistics object.
According to the embodiment of the application, the semantics in the description information can be identified based on the forbidden verification model, for example, whether the forbidden keywords in the description information of the candidate logistics object are used for indicating the attribute of the candidate logistics object or not is determined, so that whether the candidate logistics object is the forbidden logistics object or not can be accurately verified according to the description information of the candidate logistics object, and the misjudgment probability is reduced.
The personalized features of the logistic objects may be lost in the first perspective image, so that the situation that an illegal candidate logistic object may occur in at least one logistic object is determined according to the first perspective image, for example, a logistic object which is not illegal in practice is determined to be an illegal logistic object, which reduces the accuracy of determining whether the logistic object is the illegal logistic object.
According to the method and the device, after the forbidden candidate logistics objects are determined in at least one logistics object according to the first perspective image, the description information of the candidate logistics objects can be obtained, and the description information of the candidate logistics objects can sometimes show whether the candidate logistics objects are contraband or not, for example, if the candidate logistics objects are contraband, the description information in the logistics objects sometimes has related descriptions about the fact that the candidate logistics objects are contraband or not, and if the candidate logistics objects are not contraband, the description information of the logistics objects often does not have related descriptions about the fact that the candidate logistics objects are contraband or not. Therefore, whether the candidate logistics object is the forbidden logistics object can be checked according to the description information of the candidate logistics object, and as a final result, for example, the forbidden candidate logistics object determined according to the first perspective image can be screened out of misjudged physical non-forbidden logistics objects, so that the accuracy of determining whether the logistics object is the forbidden logistics object can be improved.
Further, in order to facilitate security personnel to know which logistic objects are forbidden logistic objects, in another embodiment of the present application, a first perspective image may be displayed on a screen, and the forbidden logistic objects that are verified may be selected on the first perspective image.
Thus, the security personnel can see the first perspective image on the screen and see the checked forbidden logistics objects selected by the circle on the first perspective image, and can know which logistics object in the checked at least one logistics object is the forbidden logistics object according to the mark selected by the circle, and then can find out the entity of the forbidden logistics object in the entity of the at least one logistics object according to the outline of the checked forbidden logistics object on the first perspective image.
Under the condition that the marked forbidden data is used for indicating that the sample logistics object is a forbidden logistics object or is a non-forbidden logistics object, the forbidden verification model can output a verification result that the candidate logistics object is the forbidden logistics object or is a verification result of the non-forbidden logistics object.
If the rule-breaking verification model verifies that the candidate logistics object is the rule-breaking logistics object under the condition that rule-breaking data are marked and further comprise rule-breaking grades (such as electrification, banning, magnetism and the like), the rule-breaking verification model can output the rule-breaking grades of the candidate logistics object besides outputting a verification result that the candidate logistics object is the rule-breaking logistics object.
Under the condition that the forbidden verification model also outputs forbidden grades, the verified forbidden grades can be displayed on the screen, so that security check personnel can determine which grade of forbidden articles the verified forbidden logistics object belongs to.
In another embodiment of the present application, referring to fig. 3, in step S202, the method includes:
in step S301, a second perspective image of the candidate logistics object is truncated in the first perspective image.
In the present application, after the candidate logistics object is determined in the first perspective image in step S201, the second perspective image of the candidate logistics object may be truncated in the first perspective image using an image truncation technique, and the specific truncation mode may refer to the existing truncation mode, which is not described in detail herein.
In step S302, description information of the candidate physical distribution object is acquired from the second perspective image of the candidate physical distribution object.
In one embodiment of the present application, before the first perspective image is acquired, a physical image of the candidate logistics object may be acquired, the physical image including identification information of the candidate logistics object set on a surface of the candidate logistics object, and then the identification information of the candidate logistics object may be extracted according to the physical image of the candidate logistics object and cached.
In this way, in one mode, when the description information of the candidate logistics object is obtained according to the second perspective image of the candidate logistics object, the second perspective image of the candidate logistics object may obtain the cached identification information of the candidate logistics object, and the description information of the candidate logistics object may be searched in real time at the cloud according to the identification information of the candidate logistics object.
However, in the above manner, the description information of the candidate logistics object is obtained only after the forbidden candidate logistics object is determined in the at least one logistics object according to the first perspective image (after step S201), and a period of time is required to be spent in the process of searching the description information of the candidate logistics object in real time according to the identification information of the candidate logistics object, so that the efficiency of obtaining the description information of the candidate logistics object is reduced.
Therefore, in order to improve the efficiency of acquiring the description information of the candidate logistics object. In another embodiment of the present application, the steps may be implemented by the following procedures, including:
3021. and searching the physical image of the candidate logistics object according to the second perspective image in the corresponding relation between the physical image of the logistics object and the description information of the logistics object.
In the application, the corresponding relation between the physical image of the logistics object and the description information of the logistics object can be created in advance, and the specific creation flow comprises the following steps:
11 Before the first perspective image is acquired, a physical image of the candidate physical object is acquired, the physical image including identification information of the candidate physical object set on a surface of the candidate physical object.
For example, before the first perspective image is acquired, a camera may be used to capture a physical image of the candidate physical object and buffer the physical image of the candidate physical object.
For example, a camera is arranged above an entrance of the security inspection machine, and the camera can shoot a physical image of the candidate logistics object in the process that the candidate logistics object enters the security inspection machine from the entrance.
12 Extracting identification information of the candidate physical object from the physical image of the candidate physical object.
In the application, the surface of the candidate logistics object is provided with the logistics surface sheet, the logistics surface sheet is provided with the identification information of the candidate logistics object, the identification information of the candidate logistics object comprises the express number, the shopping order number, the commodity name and the like of the candidate logistics object, and the identification information of different logistics objects is different.
The identification information of the candidate physical distribution object can be extracted from the physical image of the candidate physical distribution object by using an image analysis technology, and the application is not limited to a specific image analysis technology.
13 And acquiring the description information of the candidate logistics object from the cloud according to the identification information of the candidate logistics object.
In the application, the cloud end can store the description information and the like of each logistics object.
For example, the electronic device may send an acquisition request to the cloud end, where the acquisition request carries identification information of the candidate logistics object, and the acquisition request is used to request to acquire description information of the candidate logistics object. The cloud receives the acquisition request, extracts the identification information of the candidate logistics object from the acquisition request, acquires the stored description information of the candidate logistics object according to the identification information of the candidate logistics object, and then sends the acquired description information of the candidate logistics object to the electronic equipment. And then the electronic equipment receives the description information of the candidate logistics object sent by the cloud.
14 Storing the acquired physical image of the candidate logistics object and the acquired description information of the candidate logistics object in the corresponding relation between the physical image of the logistics object and the description information of the logistics object.
For example, in one example, the captured physical image of the candidate logistics object and the extracted description information of the candidate logistics object may be formed into a corresponding table entry, and stored in a correspondence between the physical image of the logistics object and the description information of the logistics object.
In this way, in step S3021, the similarity between each of the physical images in the correspondence relationship and the second perspective image may be calculated, and the physical image having the highest similarity with the second perspective image may be used as the physical image of the candidate physical object. The specific calculation method for calculating the similarity between the two images can use the existing calculation method, and the specific calculation method is not limited by the application.
3022. And searching the description information corresponding to the physical image of the candidate logistics object in the corresponding relation between the physical image of the logistics object and the description information of the logistics object.
In the embodiment of the application, the description information of the candidate logistics object can be acquired before the second perspective image of the candidate logistics object is intercepted in the first perspective image (before step S301), and the acquired description information of the candidate logistics object is cached, so that when the description information of the candidate logistics object needs to be acquired, the cached description information of the candidate logistics object can be directly acquired, and the description information of the candidate logistics object does not need to be searched in the cloud in real time according to the identification information of the candidate logistics object, which is equivalent to saving a period of time required in the process of searching the description information of the candidate logistics object in the cloud in real time according to the identification information of the candidate logistics object, thereby improving the efficiency of acquiring the description information of the candidate logistics object.
Further, in the case that whether the candidate physical distribution object is a forbidden physical distribution object has been verified according to the description information of the candidate physical distribution object, so that the security check on the candidate physical distribution object is finished, and then the security check on the candidate physical distribution object may not be continued in the manner of the present application, so that the physical image of the candidate physical distribution object and the description information of the candidate physical distribution object stored in the correspondence between the physical image of the physical distribution object and the description information of the physical distribution object often have no security check-related effect, and therefore, in order to save storage space, in the case that whether the candidate physical distribution object is a forbidden physical distribution object has been verified according to the description information of the candidate physical distribution object, the physical image of the candidate physical distribution object and the description information of the candidate physical distribution object may be deleted in the correspondence between the physical image of the physical distribution object and the description information of the physical distribution object.
In one embodiment of the present application, the logistic object may be damaged during the logistic transportation, for example, if the logistic object includes a fragile product such as glass or ceramic, the fragile product may be damaged due to vibration or collision during the logistic transportation.
If the receiver of the logistic object gets a broken logistic object, the subjective feeling of the receiver of the logistic object is reduced, so that whether the logistic object is broken or not can be detected in advance in order to avoid that the receiver of the logistic object gets a broken logistic object.
For example, whether the at least one logistic object is broken may be determined according to the first perspective image of the at least one logistic object and the description information of the at least one logistic object.
For example, a second perspective image of each logistic object may be truncated in the first perspective image. Then, for any one of the at least one logistic object, the description information of the logistic object may be acquired according to the second perspective image of the logistic object. The specific acquisition manner may refer to step S302, which is not described in detail herein. The description information of the logistics object may include description information in the form of an image, etc., for example, the description information of the logistics object may be an appearance image of the logistics object, etc., and then whether the logistics object is broken may be determined according to the second perspective image of the logistics object and the appearance image of the logistics object. The same is true for each of the other of the at least one logistics object.
Wherein the breakage recognition model may be trained in advance, such that the breakage recognition model may be used when determining whether the logistic object is broken or not based on the second perspective image of the logistic object and the appearance image of the logistic object.
The training mode of the damage identification model comprises the steps of obtaining at least one training data, wherein the training data comprise a sample perspective image of a sample logistics object, a sample appearance image of the sample logistics object and marking damage data of the sample logistics object. And training the model by using at least one training data until parameters in the model are converged to obtain the damage identification model.
The sample perspective image of the sample stream object may comprise a perspective image of a broken sample stream object, and the sample appearance image of the sample stream object comprises an appearance image of an unbroken sample stream object. The sample stream object in the sample perspective image and the sample stream object in the sample appearance image are the same sample stream object.
Wherein the marking damage data is used for indicating the damaged position of the sample flow object in the sample perspective image and the like.
In this way, when determining whether the logistic object is broken or not according to the second perspective image of the logistic object and the appearance image of the logistic object, the second perspective image of the logistic object and the appearance image of the logistic object can be input into the trained broken recognition model, and the result which is output by the broken recognition model and indicates whether the logistic object is broken or not can be obtained.
In one embodiment of the present application, a logistic object may include a plurality of objects, and at least one object may be lost during the logistic transportation of the logistic object, so that the logistic object that has lost the objects needs to be found as early as possible, so as to treat the loss event of the logistic object as early as possible, for example, to reissue a new complete logistic object to the recipient of the logistic object as early as possible, so that the recipient of the ground logistic object can obtain the complete logistic object.
In order to discover whether there is a logistics object with a lost article as early as possible, it may be determined whether the article in the at least one logistics object is lost based on the first perspective image of the at least one logistics object and the description information of the at least one logistics object.
For example, a second perspective image of each logistic object may be truncated in the first perspective image. Then, for any one of the at least one logistic object, the description information of the logistic object may be acquired according to the second perspective image of the logistic object. The specific acquisition manner may refer to step S302, which is not described in detail herein. The description information of the logistics object may include description information in the form of an image, for example, the description information of the logistics object may be an appearance image of the logistics object, where the appearance image of the logistics object includes each item in the logistics object, and then whether the item in the logistics object is lost may be determined according to the second perspective image of the logistics object and the appearance image of the logistics object. The same is true for each of the other of the at least one logistics object.
The loss recognition model can be trained in advance, so that the loss recognition model can be used when determining whether the articles in the logistics object are lost according to the second perspective image of the logistics object and the appearance image of the logistics object.
The training mode of the lost identification model comprises the steps of obtaining at least one training data, wherein the training data comprise a sample perspective image of a sample logistics object, a sample appearance image of the sample logistics object and label lost data of the sample logistics object. And training the model by using at least one training data until parameters in the model are converged, so as to obtain the lost identification model.
The sample perspective image of the sample stream object may comprise a perspective image of the sample stream object missing at least one item, and the sample appearance image of the sample stream object comprises an appearance image of the sample stream object without missing items. The sample stream object in the sample perspective image and the sample stream object in the sample appearance image are the same sample stream object.
The label missing data is used for indicating that a lost article exists in a sample logistics object in the sample perspective image, the position of the lost article in the sample appearance image and the like.
In this way, when determining whether the articles in the logistics object are lost according to the second perspective image of the logistics object and the appearance image of the logistics object, the second perspective image of the logistics object and the appearance image of the logistics object can be input into the trained loss identification model, and a result which is output by the loss identification model and indicates whether the articles in the logistics object are lost is obtained.
It should be noted that, for simplicity of explanation, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the application. Further, those skilled in the art will appreciate that the embodiments described in the specification are all alternative embodiments and that the actions involved are not necessarily required for the present application.
Referring to fig. 4, there is shown a block diagram of an embodiment of an image forming apparatus of the present application, which may include the following modules in particular:
A first obtaining module 11, configured to obtain a first perspective image including at least one logistic object, and a second obtaining module 12, configured to obtain description information of at least some logistic objects in the at least one logistic object;
A determining module 13, configured to determine a logistics state of the at least one logistics object according to the first perspective image and/or the description information.
In an alternative implementation, the determining module includes:
And the first determining unit is used for determining whether the at least one logistics object is damaged according to the first perspective image and the description information.
In an alternative implementation, the determining module includes:
And the second determining unit is used for determining whether the articles in the at least one logistics object are lost or not according to the first perspective image and the description information.
In an alternative implementation, the second obtaining module includes:
a third determining unit, configured to determine, according to the first perspective image, a forbidden candidate logistics object in the at least one logistics object;
an acquisition unit, configured to acquire description information of the candidate logistics object;
in an alternative implementation, the determining module includes:
and the verification unit is used for verifying whether the candidate logistics object is an forbidden logistics object according to the description information.
In an alternative implementation, the acquiring unit includes:
A clipping subunit, configured to clip, in the first perspective image, a second perspective image of the candidate logistics object;
and the acquisition subunit is used for acquiring the description information of the candidate logistics object according to the second perspective image.
In an optional implementation manner, the obtaining subunit is specifically configured to search, in a correspondence between a physical image of the logistics object and description information of the logistics object, the physical image of the candidate logistics object according to the second perspective image, and search, in the correspondence, description information corresponding to the physical image of the candidate logistics object.
In an alternative implementation manner, the obtaining subunit is further configured to obtain, before obtaining the first perspective image, a physical image of the candidate logistics object, where the physical image includes identification information of the candidate logistics object set on a surface of the candidate logistics object, extract the identification information of the candidate logistics object in the physical image, obtain, according to the identification information, description information of the candidate logistics object from a cloud, and store, in the correspondence, the physical image of the candidate logistics object and the description information of the candidate logistics object.
In an optional implementation manner, the obtaining subunit is further configured to delete, in the correspondence, the physical image of the candidate logistics object and the description information of the candidate logistics object if it has been verified, according to the description information, that the candidate logistics object is an forbidden logistics object.
In the application, a first perspective image comprising at least one logistic object is acquired, and descriptive information of at least part of the logistic objects in the at least one logistic object is acquired. Determining the logistics state of the at least one logistics object according to the first perspective image of the at least one logistics object and/or the description information of at least part of the logistics objects in the at least one logistics object. By the method and the device, the accuracy of determining the logistics state of the logistics object can be improved by combining the perspective image of the logistics object and the description information of the logistics object.
For example, in a scenario of security inspection of a logistic object, personalized features of the logistic object may be lost in the first perspective image, so that an error may occur in determining, in at least one logistic object, a forbidden candidate logistic object according to the first perspective image, for example, determining a logistic object that is not actually forbidden as a forbidden logistic object, which may reduce the accuracy of determining whether the logistic object is a forbidden logistic object.
According to the method and the device, after the forbidden candidate logistics objects are determined in at least one logistics object according to the first perspective image, the description information of the candidate logistics objects can be obtained, and the description information of the candidate logistics objects can sometimes show whether the candidate logistics objects are contraband or not, for example, if the candidate logistics objects are contraband, the description information in the logistics objects sometimes has related descriptions about the fact that the candidate logistics objects are contraband or not, and if the candidate logistics objects are not contraband, the description information of the logistics objects often does not have related descriptions about the fact that the candidate logistics objects are contraband or not. Therefore, whether the candidate logistics object is the forbidden logistics object can be checked according to the description information of the candidate logistics object, and as a final result, for example, the forbidden candidate logistics object determined according to the first perspective image can be screened out of misjudged physical non-forbidden logistics objects, so that the accuracy of determining whether the logistics object is the forbidden logistics object can be improved.
The embodiment of the application also provides a non-volatile readable storage medium, where one or more modules (programs) are stored, where the one or more modules are applied to a device, and the instructions (instructions) of each method step in the embodiment of the application may cause the device to execute.
Embodiments of the application provide one or more machine-readable media having instructions stored thereon that, when executed by one or more processors, cause an electronic device to perform a method as described in one or more of the above embodiments. In the embodiment of the application, the electronic equipment comprises a server, a gateway, sub-equipment and the like, wherein the sub-equipment is equipment such as equipment of the internet of things.
Embodiments of the present disclosure may be implemented as an apparatus for performing a desired configuration using any suitable hardware, firmware, software, or any combination thereof, which may include a server (cluster), a terminal device, such as an IoT device, or the like.
Fig. 5 schematically illustrates an exemplary apparatus 1300 that may be used to implement various embodiments described in the present disclosure.
For one embodiment, fig. 5 illustrates an example apparatus 1300 having one or more processors 1302, a control module (chipset) 1304 coupled to at least one of the processor(s) 1302, a memory 1306 coupled to the control module 1304, a non-volatile memory (NVM)/storage 1308 coupled to the control module 1304, one or more input/output devices 1310 coupled to the control module 1304, and a network interface 1312 coupled to the control module 1306.
The processor 1302 may include one or more single-core or multi-core processors, and the processor 1302 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 1300 can be used as a server device such as a gateway in the embodiments of the present application.
In some embodiments, the apparatus 1300 may include one or more computer-readable media (e.g., memory 1306 or NVM/storage 1308) having instructions 1314 and one or more processors 1302 combined with the one or more computer-readable media configured to execute the instructions 1314 to implement the modules to perform actions described in this disclosure.
For one embodiment, the control module 1304 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 1302 and/or any suitable device or component in communication with the control module 1304.
The control module 1304 may include a memory controller module to provide an interface to the memory 1306. The memory controller modules may be hardware modules, software modules, and/or firmware modules.
Memory 1306 may be used to load and store data and/or instructions 1314 for device 1300, for example. For one embodiment, memory 1306 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, memory 1306 may include double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).
For one embodiment, the control module 1304 may include one or more input/output controllers to provide interfaces to the NVM/storage 1308 and the input/output device(s) 1310.
For example, NVM/storage 1308 may be used to store data and/or instructions 1314. NVM/storage 1308 may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage device(s) (e.g., hard disk drive(s) (HDD), compact disk drive(s) (CD) and/or digital versatile disk drive (s)).
NVM/storage 1308 may include storage resources that are physically part of the device on which apparatus 1300 is installed, or may be accessible by the device without necessarily being part of the device. For example, NVM/storage 1308 may be accessed over a network via input/output device(s) 1310.
Input/output device(s) 1310 may provide an interface for apparatus 1300 to communicate with any other suitable device, input/output device 1310 may include a communication component, pinyin component, sensor component, and the like. The network interface 1312 may provide an interface for the device 1300 to communicate over one or more networks, and the device 1300 may communicate wirelessly with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols, such as accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.
For one embodiment, at least one of the processor(s) 1302 may be packaged together with logic of one or more controllers (e.g., memory controller modules) of the control module 1304. For one embodiment, at least one of the processor(s) 1302 may be packaged together with logic of one or more controllers of the control module 1304 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 1302 may be integrated on the same mold as logic of one or more controllers of the control module 1304. For one embodiment, at least one of the processor(s) 1302 may be integrated on the same die with logic of one or more controllers of the control module 1304 to form a system on chip (SoC).
In various embodiments, apparatus 1300 may be, but is not limited to being, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, the apparatus 1300 may have more or fewer components and/or different architectures. For example, in some embodiments, apparatus 1300 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and a speaker.
An embodiment of the application provides an electronic device comprising one or more processors and one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform a method of processing a logistic object as described in one or more of the present applications.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above description of the method and the imaging device for processing a physical distribution object provided by the present application has been provided in detail, and specific examples are used herein to illustrate the principles and embodiments of the present application, and the description of the above examples is only for helping to understand the method and core concept of the present application, and meanwhile, for those skilled in the art, according to the concept of the present application, there are variations in the specific embodiments and application ranges, so the disclosure should not be construed as limiting the present application.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110193300.6A CN114971443B (en) | 2021-02-20 | 2021-02-20 | A processing method and imaging device for logistics objects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110193300.6A CN114971443B (en) | 2021-02-20 | 2021-02-20 | A processing method and imaging device for logistics objects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114971443A CN114971443A (en) | 2022-08-30 |
| CN114971443B true CN114971443B (en) | 2025-01-21 |
Family
ID=82954109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110193300.6A Active CN114971443B (en) | 2021-02-20 | 2021-02-20 | A processing method and imaging device for logistics objects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971443B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119338732A (en) * | 2023-07-20 | 2025-01-21 | 顺丰科技有限公司 | Method, device, electronic device and storage medium for identifying damaged goods in a package |
| CN120235522A (en) * | 2023-12-30 | 2025-07-01 | 顺丰科技有限公司 | Logistics information detection method, system, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503121A (en) * | 2016-10-19 | 2017-03-15 | 公安部第三研究所 | A kind of description method of X-ray safety check image and system |
| CN211149486U (en) * | 2020-03-12 | 2020-07-31 | 东软集团(广州)有限公司 | Collection equipment and logistics express monitoring system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9367770B2 (en) * | 2011-08-30 | 2016-06-14 | Digimarc Corporation | Methods and arrangements for identifying objects |
| CN205333883U (en) * | 2016-02-03 | 2016-06-22 | 龙靖 | A passageway formula X -ray security check machine for safety inspection of express delivery goods |
| CN205404838U (en) * | 2016-03-08 | 2016-07-27 | 龙靖 | A full automated system for coordinating safety inspection of express delivery commodity circulation X -ray security check machine |
| CN107341626A (en) * | 2016-05-03 | 2017-11-10 | 刘露辉 | A kind of method for preventing mail from losing and a kind of equipment for preventing mail from losing |
| EP3579160A1 (en) * | 2017-02-03 | 2019-12-11 | Panasonic Intellectual Property Management Co., Ltd. | Learned model generating method, learned model generating device, and learned model use device |
| CN107679787A (en) * | 2017-09-05 | 2018-02-09 | 中铁华业国际服务外包有限公司 | High ferro logistics system |
| CN109741398A (en) * | 2018-12-28 | 2019-05-10 | 同方威视技术股份有限公司 | Image recognition method, device and computer storage medium |
| CN110554062A (en) * | 2019-10-15 | 2019-12-10 | 实源科技(广州)有限公司 | express mail contraband detection device and detection method |
-
2021
- 2021-02-20 CN CN202110193300.6A patent/CN114971443B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503121A (en) * | 2016-10-19 | 2017-03-15 | 公安部第三研究所 | A kind of description method of X-ray safety check image and system |
| CN211149486U (en) * | 2020-03-12 | 2020-07-31 | 东软集团(广州)有限公司 | Collection equipment and logistics express monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114971443A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI726194B (en) | Image-based vehicle damage assessment method, device and electronic equipment | |
| CN106446816B (en) | Face recognition method and device | |
| US9076195B2 (en) | Methods and apparatus to identify components from images of the components | |
| JP7025354B2 (en) | Automation of image validation | |
| CN111967322B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN104036009B (en) | A kind of method, image searching method and device for searching for matching picture | |
| US20190188729A1 (en) | System and method for detecting counterfeit product based on deep learning | |
| CN106385640B (en) | Video annotation method and device | |
| CN114971443B (en) | A processing method and imaging device for logistics objects | |
| CN110674788A (en) | Vehicle damage assessment method and device | |
| KR20180131621A (en) | Content-based search and retrieval of brand images | |
| WO2021233058A1 (en) | Method for monitoring articles on shop shelf, computer and system | |
| US20190197721A1 (en) | Method, apparatus and system for assisting security inspection | |
| CN113221918B (en) | Target detection method, training method and device of target detection model | |
| CN112308915B (en) | Method and device for locating express parcels | |
| CN111127558B (en) | Method and device for determining assembly detection angle, electronic equipment and storage medium | |
| CN109727058B (en) | User behavior anomaly detection method, device, electronic device, and readable storage medium | |
| CN110019895A (en) | A kind of image search method, device and electronic equipment | |
| CN106682187B (en) | Method and device for establishing image base | |
| CN110619103A (en) | Webpage image-text detection method and device and storage medium | |
| WO2016158438A1 (en) | Inspection processing apparatus, method, and program | |
| CN112819953A (en) | Three-dimensional reconstruction method, network model training method and device and electronic equipment | |
| CN111160410A (en) | Object detection method and device | |
| CN107784507A (en) | Doubtful infringement commodity method for early warning and device, computer-readable storage medium and equipment | |
| CN113297409A (en) | Image searching method and device, electronic equipment and storage 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 |