CN116721407A - Method, device, terminal equipment and storage medium for package data analysis - Google Patents

Method, device, terminal equipment and storage medium for package data analysis Download PDF

Info

Publication number
CN116721407A
CN116721407A CN202310598624.7A CN202310598624A CN116721407A CN 116721407 A CN116721407 A CN 116721407A CN 202310598624 A CN202310598624 A CN 202310598624A CN 116721407 A CN116721407 A CN 116721407A
Authority
CN
China
Prior art keywords
package
data
target
analysis result
combined
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.)
Pending
Application number
CN202310598624.7A
Other languages
Chinese (zh)
Inventor
刘兴昌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Huazhiyuan Information Engineering Co ltd
Guangzhou Huajia Software Co ltd
Guangzhou Jiadu Urban Rail Intelligent Operation And Maintenance Service Co ltd
PCI Technology and Service Co Ltd
Original Assignee
Guangdong Huazhiyuan Information Engineering Co ltd
Guangzhou Huajia Software Co ltd
Guangzhou Jiadu Urban Rail Intelligent Operation And Maintenance Service Co ltd
PCI Technology and Service Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Huazhiyuan Information Engineering Co ltd, Guangzhou Huajia Software Co ltd, Guangzhou Jiadu Urban Rail Intelligent Operation And Maintenance Service Co ltd, PCI Technology and Service Co Ltd filed Critical Guangdong Huazhiyuan Information Engineering Co ltd
Priority to CN202310598624.7A priority Critical patent/CN116721407A/en
Publication of CN116721407A publication Critical patent/CN116721407A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/10Image acquisition
    • G06V10/16Image acquisition using multiple overlapping images; Image stitching
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/255Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00Indexing scheme relating to image or video recognition or understanding
    • G06V2201/05Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Abstract

The application discloses a package data analysis method, a package data analysis device, terminal equipment and a storage medium. According to the method, after the target package is judged to be required to be overlapped on the previous package, the piece-part data of the target package and the piece-part data of the previous package are combined, and the combined piece-part data of the combined package is obtained. And then, executing a data analysis flow on the combined and fragmented data, determining a first security inspection analysis result corresponding to the target package according to the data analysis result, and finally, determining whether to execute a graph judging flow on the combined package according to the first security inspection analysis result and a second security inspection analysis result of the last package. The application combines the wrapped fragment data, can combine the fragment data which is wrongly divided because of the error of a packetizing algorithm or the fact that the continuous package exceeds the maximum package cutting length into the fragment data of the last package, and then analyzes the combined fragment data, thereby reducing the judgment diagram interference to the judgment diagram staff and reducing the omission rate and the misjudgment rate of the package.

Description

Method, device, terminal equipment and storage medium for package data analysis
Technical Field
The embodiment of the application relates to the field of intelligent security inspection, in particular to a parcel data analysis method, a parcel data analysis device, terminal equipment and a storage medium.
Background
At present, in an urban rail transit system, in order to achieve the purpose of reducing the security inspection cost, the security inspection system generally adopts a centralized image judgment mode, packages X-ray pictures of packages are sub-packaged, and sub-packaged data are distributed to different centralized image judgment operators for image judgment in a centralized task scheduling mode. However, due to the influences of the existing sub-packaging algorithm errors, the X-ray machine picture environment and other factors, when sub-packaging is inaccurate or a large number of continuous packages are required to be split for sub-packaging, the same package is divided into two packages and sent to a centralized picture judgment staff for picture judgment, so that the picture judgment accuracy of the centralized picture judgment staff is interfered, and the missed judgment rate and the misjudgment rate of the packages are increased.
In summary, how to reduce the miss rate and the misjudgment rate of packages in the centralized graph judgment in the prior art becomes a technical problem to be solved in the present technology.
Disclosure of Invention
The embodiment of the application provides a package data analysis method, a package data analysis device, terminal equipment and a storage medium, which can reduce the missed judgment rate and the misjudgment rate of packages in the concentrated judgment of graphs in the prior art.
In a first aspect, an embodiment of the present invention provides a method for analyzing package data, including:
receiving the fragment data of a target package sent by an X-ray machine, wherein the target package is a package currently scanned by the X-ray machine;
when the last fragment data of the target package sent by the X-ray machine is received, determining whether the target package needs to be overlapped on the previous package according to an overlapping rule;
if necessary, merging the target wrapped fragment data with the last wrapped fragment data to obtain merged fragment data of merged wrapping;
executing a data analysis flow of the merged fragment data to obtain a data analysis result of the target package;
determining a first security inspection analysis result of the target package according to the data analysis result of the target package;
determining whether to execute a graph judging flow on the combined package according to the first security inspection analysis result and the second security inspection analysis result of the previous package;
and if the combined package is required to be executed, executing the graph judging flow on the combined package.
In a second aspect, an embodiment of the present invention provides a package data analysis apparatus, including:
the data receiving module is used for receiving the fragment data of the target package sent by the X-ray machine, wherein the target package is the package currently scanned by the X-ray machine;
The superposition judging module is used for determining whether the target package needs to be superposed on the previous package according to superposition rules when the last fragment data of the target package sent by the X-ray machine is received;
the data merging module is used for merging the fragment data of the target package with the fragment data of the previous package if the target package needs to be overlapped to the previous package, so as to obtain merged fragment data of the merged package;
the data analysis module is used for executing a data analysis flow of the merged and fragmented data to obtain a data analysis result of the target package;
the security check result determining module is used for determining a first security check analysis result of the target package according to the data analysis result of the target package;
the picture judgment and package opening determining module is used for determining whether to execute a picture judgment flow on the combined package according to the first security inspection analysis result and the second security inspection analysis result of the previous package;
and the graph judging and package opening module is used for executing the graph judging flow on the combined package if the graph judging flow is determined to be executed on the combined package.
In a third aspect, an embodiment of the present invention provides a terminal device, where the terminal device includes a processor and a memory;
The memory is used for storing a computer program and transmitting the computer program to the processor;
the processor is configured to perform a method of package data analysis according to the first aspect according to instructions in the computer program.
In a fourth aspect, embodiments of the present invention provide a storage medium storing computer executable instructions which, when executed by a computer processor, are adapted to carry out a method of parcel data analysis as described in the first aspect.
In the above-mentioned embodiment of the present invention, after determining that the target package needs to be superimposed on the previous package, the slice data of the target package is combined with the slice data of the previous package, so as to obtain the combined slice data of the combined package. And then, executing a data analysis flow on the merged and fragmented data, determining a first security inspection analysis result corresponding to the target package according to the data analysis result, and finally, determining whether to execute a graph judging flow on the merged package according to the first security inspection analysis result and a second security inspection analysis result of the last package. According to the embodiment of the invention, the wrapped fragment data are combined, so that the fragment data which are wrongly divided due to the error of a packetizing algorithm or the fact that the continuous package exceeds the maximum package cutting length can be combined into the fragment data of the previous package, and then the combined fragment data are analyzed, so that the graph judgment interference to a graph judgment staff can be reduced, and the omission rate and the misjudgment rate to the package are reduced.
Drawings
Fig. 1 is a schematic diagram of a complete package according to an embodiment of the present application.
Fig. 2 is a schematic diagram of dividing a complete package into two packages according to an embodiment of the present application.
Fig. 3 is a schematic diagram showing a large number of packets according to an embodiment of the present application.
Fig. 4 is a schematic diagram of another embodiment of the present application for dividing a package into two packages.
Fig. 5 is a flow chart of a package data analysis method according to an embodiment of the present application.
Fig. 6 is a flowchart of another package data analysis method according to an embodiment of the present application.
Fig. 7 is a schematic flow chart of processing fragment data by the judgment server according to the embodiment of the present application.
Fig. 8 is a schematic flow chart of processing a data analysis result by the graph judging server according to the embodiment of the application.
Fig. 9 is a schematic flow chart of processing overlay package data by the data manager according to an embodiment of the present application.
Fig. 10 is a schematic structural diagram of a package data analysis device according to an embodiment of the present application.
Fig. 11 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the application to enable those skilled in the art to practice them. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in, or substituted for, those of others. The scope of embodiments of the application encompasses the full ambit of the claims, as well as all available equivalents of the claims. Embodiments may be referred to herein, individually or collectively, by the term "application" merely for convenience and without intending to voluntarily limit the scope of this application to any single application or inventive concept if more than one is in fact disclosed. Relational terms such as first and second, and the like may be 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, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed. Various embodiments are described herein in a progressive manner, each embodiment focusing on differences from other embodiments, and identical and similar parts between the various embodiments are sufficient to be seen with each other. The structures, products and the like disclosed in the embodiments correspond to the parts disclosed in the embodiments, so that the description is relatively simple, and the relevant parts refer to the description of the method parts.
At present, when a security inspection system performs centralized graph judgment, under the influence of factors such as errors of the existing sub-packaging algorithm and the graph environment of an X-ray machine, sub-packaging inaccuracy possibly occurs, or the situation that a continuous package needs to be split for sub-packaging occurs due to large passenger capacity, and at the moment, the situation that the same package is split into two packages for centralized graph judgment easily occurs. For example, fig. 1 is a package entering an X-ray machine, and the package is in the process of slowly transmitting the package into the X-ray machine, the packaging algorithm cannot quickly obtain the complete scanning data of the package, but needs to identify the package according to the portion of the package transmitted into the X-ray machine in real time, in one case, because the package tail shown in fig. 1 is far from the package body, the time interval of entering the X-ray machine by the package tail and the time interval of entering the X-ray machine by the package body are long, in this case, the packaging algorithm easily identifies the package shown in fig. 1 as two packages shown in fig. 2 for centralized graph judgment. In another case, the connection belt for connecting the tail part and the body of the package in the package shown in fig. 1 may not be scanned by the X-ray machine after entering the X-ray machine or the scanning result of the connection belt is poor, which may also result in the situation that the package shown in fig. 1 is identified as two packages shown in fig. 2 for centralized judgment In addition, the continuous bags appear in the presence of large passenger capacityIn the case of (a), as shown in fig. 3, the packetization algorithm is also prone to splitting one parcel into two parcels when the maximum bale length is exceeded during the transfer of a large number of parcels into X-rays, as shown in fig. 4. After the package is cut, interference is caused when the security inspector makes concentrated graph judgment, and the missed judgment rate and the misjudgment rate of the package are increased.
In summary, in order to solve the technical problem that the missed judgment rate and the misjudgment rate of the package increase after the package is cut, an embodiment of the present invention provides a package data analysis method, as shown in fig. 5, and fig. 5 is a flowchart of the package data analysis method provided by the embodiment of the present invention. The package data analysis method provided by the embodiment of the invention can be executed by the terminal equipment, the terminal equipment can be realized in a software and/or hardware mode, and the terminal equipment can be formed by two or more physical entities or one physical entity. For example, the terminal device may be a computer, a server or a tablet, and in this embodiment, the terminal device is taken as a graph determining server for illustration, where the graph determining server may be deployed in a station in a manner of an entity server, or may be deployed in a cloud platform in a manner of clouding, but when deployed in the cloud platform, it is required to ensure that a network transmission delay from a station security inspection point to the cloud platform is within an allowable range. The parcel data analysis method provided by the embodiment of the invention comprises the following steps:
And step 101, receiving the fragment data of the target package sent by the X-ray machine, wherein the target package is the package currently scanned by the X-ray machine.
In this embodiment, when a passenger performs security inspection, the passenger needs to scan the package in an X-ray machine, and the X-ray machine generates fragment data of the package after scanning the package. The slice data refers to scan data wrapping a certain area. It can be understood that, because the package slowly enters the X-ray machine through the conveyor belt, the X-ray machine cannot directly obtain the complete data of the package, and after the package enters the X-ray machine, the area of the package newly entering the X-ray machine is scanned in a segmented manner to obtain the piece data of the package, and the complete data of the package can be obtained after the piece data of the package is spliced.
After the X-ray machine scans the target package transmitted by the current conveyor belt, the X-ray machine scans the target package to obtain the fragment data of the target package, and sends the fragment data of the target package to the graph judging server. In one embodiment, after receiving the first fragment data of the target package sent by the X-ray machine, the graph determining server generates package data corresponding to the target package, where the package data includes ID information of the target package, fragment data of the target package, and the like, and then adds the package data to the overlay package data, where the form of the overlay package data record data may be a list, a queue, or a set, and in this embodiment, the method is not specifically limited.
And 102, when the last fragment data of the target package sent by the X-ray machine is received, determining whether the target package needs to be overlapped on the previous package according to an overlapping rule.
When the image judging server receives the last fragment data of the target package sent by the X-ray machine, namely the scanning data of the target package is complete. At this time, the graph judging server needs to further judge whether the target package and the previous package belong to the same package according to the stacking rule, so as to determine whether the target package needs to be stacked on the previous package. Wherein the last package refers to the package scanned by the X-ray machine before the target package. In one embodiment, when determining whether the target package needs to be overlapped to the previous package according to the overlapping rule, determining whether the target package is a package of the target type according to the fragment data; if the package is of the target type, further determining whether the interval between the target package and the last package is within a preset range; if the package is within the preset range, further judging whether the previous package is overlapped with other packages or not; if the target package and the previous package are not overlapped, the target package and the previous package can be judged to belong to the same package, and the fact that the target package needs to be overlapped in the previous package is determined. If any of the above conditions is not satisfied, the target package and the previous package are not considered to belong to the same package, and the target package and the previous package do not need to be overlapped.
And 103, if necessary, merging the target wrapped fragment data with the last wrapped fragment data to obtain merged fragment data of the merged package.
If it is determined that the target package needs to be overlapped to the previous package, the graph judging server can combine the fragment data of the target package with the fragment data of the previous package in the overlapped package data to obtain combined fragment data. Meanwhile, the graph judging server can modify the ID information of the target package into the ID information of the last package in the overlapped package data, so that the target package and the last package are combined into the same package, namely, the package is combined, and the package data of the target package and the package data of the last package are package data of the combined package. If the target package and the last package do not need to be combined, the target package is determined to be processed according to the processing flow of the normal package. The normal package treatment process comprises the following steps: and the picture judging server sends the wrapped fragment data to the intelligent picture identifying server for intelligent picture identification, and simultaneously sends the fragment data to the picture judging workstation and the unpacking workstation. And then the graph judging server judges whether contraband is found according to the data analysis result obtained by the intelligent graph recognition, and sends the data analysis result to the unpacking workstation and the graph judging workstation. If the graph judging server finds contraband according to the data analysis result, judging whether to directly unpack, manually judge the graph or directly release the graph; if the package is opened directly, transmitting a package opening instruction to a package opening workstation, and opening and checking the package in the package opening workstation by a worker; if the manual graph judgment is needed, transmitting a graph judgment instruction to a graph judgment workstation, and in the graph judgment workstation, judging the graph of the wrapped segmented data again by a worker according to the wrapped segmented data and the data analysis result, so as to determine whether further package opening inspection is needed, and if the package opening inspection is needed, further transmitting the package opening instruction to the package opening workstation, so as to carry out package opening inspection on the package.
The image judging workstation comprises a slicing data display device, a communication device, a data superposition processing device, a keyboard and a mouse and other input devices. The fragmentation data display equipment displays the fragmentation data and the data analysis result, a diagramming person logs in a diagramming workstation, diagramming is carried out on the diagramming workstation according to the fragmentation data and the data analysis result, and operations such as release, unpacking and rechecking, unpacking and scram are selected according to the judged contraband information. In another embodiment, a scheduling server may be further configured to schedule the graph task to an appropriate graph-determining workstation. The scheduling server is used for receiving the login request, the logout request, the state change and the execution condition of the graph judging task reported by the graph judging workstation, and determining the graph judging task to be distributed to the proper graph judging workstation for processing according to the information reported by the graph judging workstation.
The unpacking workstation comprises a piece of data display device, a communication device, a data superposition processing device, a keyboard and mouse input device, an audible and visual alarm, a video monitoring device, a high-speed camera, an identity card reader-writer and the like. The fragmentation data display device displays the fragmentation data of the package which needs to be unpacked and the data analysis result. The recheck person logs in the unpacking workstation, receives the unpacking task, carries out package interception and inspection according to the information displayed on the unpacking workstation, carries out rechecking result registration according to the rechecking result, can select to release when no contraband exists, can select disposal modes including but not limited to giving up, temporary storage, carrying out recovery, collecting payment, alarming and the like when the contraband exists, registers the type and the name of the contraband, and can register passenger information (including but not limited to name, gender, age, address, contact mode) and the like when necessary.
And 104, executing a data analysis flow for merging the fragmented data to obtain a data analysis result of the target package.
After the merged fragmented data is obtained, the graph judging server can further execute a data analysis flow for the merged fragmented data, wherein the data analysis flow refers to analysis of the fragmented data, and the type of the article, the position of the article, the confidence level of the type of the article and the like in the package are identified, so that a data analysis result of the target package is obtained. Specifically, after the combined fragment data is obtained, the image judging server can send the combined fragment data to the intelligent image identifying server, the intelligent image identifying server analyzes the combined fragment data by adopting an intelligent image identifying algorithm, so that the position of an article in the target package, the type of the article, the confidence level of the type of the article and the like are identified, a data analysis result of the target package is obtained, and the data analysis result of the target package is fed back to the image judging server. The combined fragment data is sent to the intelligent image recognition server for analysis, so that the recognition coverage rate of the articles in the package can be increased, and the false detection rate is reduced.
Step 105, determining a first security inspection analysis result of the target package according to the data analysis result of the target package.
After the graph judging server obtains the data analysis result of the target package, the corresponding first security inspection analysis result of the target package can be determined according to the data analysis result of the target package. For example, the decision server may determine whether there is contraband based on the type of the item in the data analysis result of the target package. If the contraband exists, determining that a first security inspection analysis result of the target package is that the package needs to be opened by judging the graph; and if no contraband exists, determining that the first security inspection analysis result of the target package is release. In one embodiment, the graph judging server may further combine the data analysis result of the target package with the data analysis result of the previous package in the superimposed package data, and send the combined data analysis result to the graph judging workstation and the unpacking workstation for recording and storing.
And step 106, determining whether to execute a graph judging flow on the combined package according to the first security check analysis result and the second security check analysis result of the previous package.
And then, the graph judging server can acquire a second security inspection analysis result of the previous package, and determine whether to execute a graph judging flow on the combined package after the previous package and the target package are combined according to the first security inspection analysis result and the second security inspection analysis result. For example, when any one of the first security inspection analysis result and the second security inspection analysis result is that the package is opened when the graph is required, it is determined that the graph judgment flow is required to be executed on the combined package.
And 107, if the execution is needed, executing a graph judging flow on the combined package.
If the combined package is determined to execute the graph judging process, the graph judging server can send a graph judging instruction to the graph judging workstation or send a package opening instruction to the package opening workstation so as to execute the graph judging process. The graph judging flow is to manually judge the graph of the combined and fragmented data in the graph judging workstation, and determine whether to execute unpacking inspection on the combined package according to the result of the manual graph judgment. If the unpacking inspection needs to be executed, unpacking inspection is carried out on the combined package in the unpacking workstation. After the combined package is processed, the graph judging server can delete the package data of the combined package in the overlapped package data.
In the above-mentioned embodiment of the present invention, after determining that the target package needs to be superimposed on the previous package, the slice data of the target package is combined with the slice data of the previous package, so as to obtain the combined slice data of the combined package. And then, executing a data analysis flow on the combined and fragmented data, determining a first security inspection analysis result corresponding to the target package according to the data analysis result, and finally, determining whether to execute a graph judging flow on the combined package according to the first security inspection analysis result and a second security inspection analysis result of the last package. According to the embodiment of the invention, the wrapped fragment data are combined, so that the fragment data which are wrongly divided due to the error of a packetizing algorithm or the fact that the continuous package exceeds the maximum package cutting length can be combined into the fragment data of the previous package, and then the combined fragment data are analyzed, so that the graph judgment interference to a graph judgment staff can be reduced, and the omission rate and the misjudgment rate to the package are reduced.
As shown in fig. 6, fig. 6 is a flow chart of another package data analysis method according to an embodiment of the present invention, where the package data analysis method shown in fig. 6 is a specific implementation of the package data analysis method, and the method includes:
step 201, receiving the fragment data of the target package sent by the X-ray machine, where the target package is the package currently scanned by the X-ray machine.
And 202, when the last fragment data of the target package sent by the X-ray machine is received, determining whether the target package needs to be overlapped on the previous package according to an overlapping rule.
Based on the above embodiment, determining whether the target package needs to be overlapped with the previous package according to the overlapping rule in step 202 includes:
step 2021, judging whether the target package is a target type package according to all the fragment data of the target package.
When determining whether the target package needs to be overlapped to the previous package according to the overlapping rule, firstly, judging whether the target package is a target type package. Specifically, the width of the target package can be determined according to all the fragment data of the target package, and whether the width of the target package is smaller than a preset width threshold value is judged. If the width is smaller than the preset width threshold, the target package can be considered as a target type package; otherwise, the target package is not the target type package, and the target package can be processed according to the normal package processing flow.
On the basis of the above embodiment, determining whether the target package is a target type package according to all the fragment data of the target package includes:
step 20211, determining the pixel width of the target package according to all the fragment data of the target package.
In one embodiment, the complete data of the target package may be synthesized first from all the fragmented data of the target package. And then determining the pixel width of the target package according to the complete data of the target package.
Step 20212, determining whether the pixel width of the target package is less than a preset pixel column number threshold.
After determining the pixel width of the target package, further judging whether the pixel width of the target package is smaller than a preset pixel column number threshold. The pixel width refers to the width of all pixels forming the target package after the target package is presented in an image mode. The pixel column number threshold refers to a preset number of columns of pixels.
If yes, determining that the target package is a target type package.
If the pixel width of the target package is smaller than the preset pixel column number threshold value, determining that the target package is a target type package.
Step 2022, if the packet is a target type packet, determining whether a time interval between the last fragment data of the target packet and the first fragment data of the previous packet is less than or equal to a preset first duration.
After determining that the width of the target package is smaller than the preset pixel column number threshold, it is necessary to further determine whether the target package and the previous package are adjacent packages. Specifically, whether the time interval between the last piece of data of the target package and the first piece of data of the last package is smaller than or equal to a preset first duration can be judged. If the time length is less than or equal to the first time length, indicating that the target package and the last package are adjacent packages; otherwise, the target package is processed according to the normal package flow.
Based on the above embodiment, if the time interval is greater than the first time period and the time interval between the last piece of data of the target package and the first piece of data of the next package is less than or equal to the first time period, the target package is stacked to the next package.
In another embodiment, after determining that the time interval between the last piece of data of the target package and the first piece of data of the previous package is smaller than or equal to a preset first time length, when further detecting that the time interval between the last piece of data of the target package and the first piece of data of the next package is smaller than or equal to the first time length, it is indicated that the target package and the next package belong to the same package, that is, the piece of data of the next package and the piece of data of the target package need to be overlapped, and the combined piece of data is processed, where the processing is similar to the processing after combining the piece of data of the target package and the piece of data of the previous package in this embodiment, and specifically, the processing after combining the piece of data of the target package and the piece of data of the previous package in this embodiment may be referred to, which will not be repeated in this embodiment.
Step 2023, if the time length is less than or equal to the first time length, determining whether the previous package is already overlapped with other packages.
After determining that the target package and the previous package are adjacent packages, it is further determined whether the previous package has been superimposed with other packages. Specifically, in one embodiment, when merging the fragment data of two packages, the labels are superimposed on the two package labels. For example, when merging the fragment data of two packages, the graph judging server may mark the superposition identifier on the package data of the two packages in the superposition package data, for example, the superposition identifier is "superimposed" or the like. Correspondingly, determining whether the previous package has been superimposed with other packages includes:
step 20231, determining whether the previous package is marked with an overlay mark.
If the overlay mark is not marked, step 20232 determines that the previous package is not overlapped with other packages.
When judging whether the previous package is overlapped with other packages, the graph judging server can judge whether the package data of the previous package is marked with an overlapped mark. Specifically, the map determining server may obtain package data of a previous package from the superimposed package data, and determine whether the package data is marked with the superimposed identifier. If the mark exists, the previous package is indicated to be overlapped with other packages; otherwise, the package is not overlapped with other packages.
Step 2024, if not overlapping with other packages, determining that the target package needs to be overlapped with the previous package.
If the previous package is not superimposed with other packages, it may be determined that the target package needs to be superimposed into the previous package. Otherwise, the target package is processed according to the normal package flow.
Step 203, if necessary, merging the target wrapped fragment data with the last wrapped fragment data to obtain merged fragment data of the merged package.
After determining that the target package is required to be added to the last package, executing a processing flow of overlapping the packages, and combining the piece data of the target package with the piece data of the last package to obtain combined piece data of the combined package. Specifically, when executing the processing flow of stacking packages, the graph judging server can stack the labels on the package data of the target package and the package data label of the previous package in the stacking package data, so as to indicate that the target package and the previous package can not be stacked with other packages. Meanwhile, in the overlapped package data, the ID information of the target package is modified into the package ID information of the last package, so that the target package and the last package are combined into the same package, namely, the combined package. And then checking whether the fragment data of the last package is sent to a graph judging workstation, if so, then reissuing the combined fragment data to the related graph judging workstation. And checking whether the fragment data of the last package is sent to the unpacking workstation or not, if so, then the combined fragment data is reissued to the corresponding unpacking workstation. And checking whether the fragmented data of the previous package is uploaded to the management system or not, if so, retransmitting the combined fragmented data to the management system to replace the original fragmented data of the previous package. Finally, the fragmented data of the last parcel and the target parcel are marked as "processed". The management system has the data storage functions of X-ray package passing record, contraband detection record, package opening record, missed judgment record and the like; meanwhile, the system also provides a historical data retrieval function, and can be used for checking basic information, fragment data, a parcel snap-shot image, image judgment result information, unpacking inspection information and the like of the parcel. As shown in fig. 7, fig. 7 is a specific process of processing the segment data by the decision server.
And 204, executing a data analysis flow for merging the fragmented data to obtain a data analysis result of the target package.
And then, the graph judging server can execute a data analysis flow of the combined and fragmented data, and send the combined and fragmented data to the intelligent graph identifying server for data analysis so as to obtain a data analysis result of the target package. After the data analysis result of the target package is obtained, the graph judging server already confirms that the target package is overlapped with the previous package, so that a processing flow of overlapping the analysis result is needed to be further carried out. In addition, it should be further explained that, before the last fragment data of the target package is not received, the fragment data of the received target package is also sent to the intelligent image recognition server for data analysis by the image judgment server every certain time interval, so as to obtain the data analysis result of the target package with incomplete fragment data. For example, the graph judging server sends the first 2 pieces of segment data and the first 4 pieces of segment data of the target package to the intelligent graph identifying server at intervals to perform data analysis, so that data analysis results of the first 2 pieces of segment data and data analysis results of the first 4 pieces of segment data are obtained respectively. And after the combined fragment data is sent to the intelligent image recognition server for data analysis, if the data analysis result of the target package is not obtained in the second time period, the image judgment server takes the data analysis result of the target package (namely, the incomplete data analysis result of the fragment data) obtained last time as the final data analysis result of the target package.
After the data analysis result of the target package is obtained, the graph judging server can further superimpose the data analysis result of the target package on the data analysis result of the last package in the superimposed package data, namely, the data analysis result of the combined package is obtained, and the data analysis result of the target package is marked as processed. And then, the graph judging server further supplements the combined data analysis results to the corresponding graph judging workstation, the corresponding unpacking workstation and the management system respectively, and marks the data analysis result of the last package as processed.
Step 205, determining a first security inspection analysis result of the target package according to the data analysis result of the target package.
After the data analysis result of the target package is obtained, the graph judging server can determine the first security inspection analysis result of the target package according to the data analysis result of the target package.
And 206, combining the first security inspection analysis result of the target package with the second security inspection analysis result of the previous package to obtain a target security inspection analysis result of the combined package.
After the first security inspection analysis result of the target package is obtained, the graph judging server can obtain the second security inspection analysis result of the previous package, and combine the first security inspection analysis result and the second security inspection analysis result in the superimposed package data to obtain the target security inspection analysis result of the combined package.
Step 207, determining whether a graph judging process is required to be executed on the combined package according to the target security inspection analysis result.
After the target security inspection analysis result is obtained, the graph judging server can judge whether the graph judging process is required to be executed on the combined package according to the target security inspection analysis result. In one embodiment, in step 207, according to the target security inspection analysis result, it is determined whether the graph determining process needs to be performed on the consolidated parcel, including:
step 2071, judging whether the first security inspection analysis result or the second security inspection analysis result is that the graph judgment is needed and unpacking.
Firstly, a graph judging server judges whether a first security inspection analysis result or a second security inspection analysis result in target security inspection analysis results is required to judge the graph and unpack.
Step 2072, if yes, determining that the combined package needs to be executed with the graph judging process.
If any one security inspection analysis result exists as the first security inspection analysis result or the second security inspection analysis result, determining that the combined package needs to execute the graph judging flow. For example, when the second security inspection analysis result is that the image judgment and unpacking are needed and the first security inspection analysis result is that the package is put, since the previous package is going to pass through the X-ray machine before the target package, the package data of the previous package is already transmitted to the image judgment workstation and the unpacking workstation for rechecking, and at this time, it is determined that the image judgment process is needed to be executed for merging the packages, so as to confirm whether the target package has forbidden articles. In addition, when the second security inspection analysis result is release and the first security inspection analysis result is that the package is opened after the package is judged, at this time, because the previous package is inspected, it is also required to determine that the package is combined and the package needs to execute the graph judgment process, so as to recheck the previous package again, and determine whether the forbidden article exists in the previous package. In another embodiment, as shown in fig. 8, after obtaining the data analysis result of the target package and the data analysis result of the previous package, the decision server may take another role in checking and processing whether the merged package needs to be subjected to the processing flow of copying the package. And judging whether the second security inspection analysis result is a release or not, and judging whether the first security inspection analysis result is a graph to be judged and unpacked or not. If both conditions are met, the graph judging server needs to copy the package data of the combined package and then add the package data to the tail of the overlapped package data, and the added combined package is processed according to the graph judging flow. Because the package data of the combined package comprises the package data of the target package, the missed detection of the target package caused by the fact that the last package is released can be avoided.
And step 208, if the combined package needs to be executed, executing a graph judging flow.
Finally, the combined package row judging process is only needed, and the specific process of the judging process can refer to step 107, and the detailed description is omitted in this embodiment. In addition, it should be further noted that, in this embodiment, all the package data added with the superimposed package data are uniformly processed by the data manager in the graph judging server, and the specific processing procedure is as shown in fig. 9, and for each new package data entering the superimposed package data, the data manager may perform the following check: when it is determined that the overlay flag in the package data is "overlaid," the fragment data is "processed," and the analysis result data is "processed," then the package data is considered to be processed and needs to be removed from the list. Otherwise, judging whether the time distance between the last piece of data of the package and the current time exceeds the first duration; if the first time period is exceeded, the package is considered to be unnecessary to wait for the superposition judgment of other packages, and also needs to be removed from superposition package data.
In the above-mentioned embodiment of the present invention, after determining that the target package needs to be superimposed on the previous package, the slice data of the target package is combined with the slice data of the previous package, so as to obtain the combined slice data of the combined package. And then, executing a data analysis flow on the combined and fragmented data, determining a first security inspection analysis result corresponding to the target package according to the data analysis result, and finally, determining whether to execute a graph judging flow on the combined package according to the first security inspection analysis result and a second security inspection analysis result of the last package. According to the embodiment of the invention, the wrapped fragment data are combined, so that the fragment data which are wrongly divided due to the error of a packetizing algorithm or the fact that the continuous package exceeds the maximum package cutting length can be combined into the fragment data of the previous package, and then the combined fragment data are analyzed, so that the graph judgment interference to a graph judgment staff can be reduced, and the omission rate and the misjudgment rate to the package are reduced. In addition, the embodiment of the invention also supports that the small-fragment package is overlapped to the previous package and released due to the overlapped package, and when the small-fragment package is identified as the package needing to be judged and unpacked, the graph judgment process is executed on the previous package and the small-fragment package again, so that the condition that the small-fragment package is missed to be judged due to the overlapped package is avoided, the interference of the small-fragment package is reduced, and meanwhile, the package is ensured to be not missed.
As shown in fig. 10, fig. 10 is a schematic structural diagram of a package data analysis device according to an embodiment of the present invention, where the package data analysis device includes:
the data receiving module 301 is configured to receive fragment data of a target package sent by the X-ray machine, where the target package is a package currently scanned by the X-ray machine;
the superposition judging module 302 is configured to determine, when receiving last fragment data of the target package sent by the X-ray machine, whether the target package needs to be superimposed on a previous package according to a superposition rule;
the data merging module 303 is configured to merge the fragment data of the target package with the fragment data of the previous package to obtain merged fragment data of the merged package if the target package needs to be overlapped with the previous package;
the data analysis module 304 is configured to execute a data analysis flow for merging the fragmented data to obtain a data analysis result of the target package;
the security check result determining module 305 is configured to determine a first security check analysis result of the target package according to the data analysis result of the target package;
the graph judging and package opening determining module 306 is configured to determine whether to execute a graph judging process on the combined package according to the first security check analysis result and the second security check analysis result of the previous package;
And the graph judging and package opening module 307 is configured to execute the graph judging process on the combined package if it is determined that the graph judging process is executed on the combined package.
On the basis of the above embodiment, the superimposition judging module 302 includes:
the target type judging sub-module is used for judging whether the target package is a target type package or not according to all the fragment data of the target package;
the time length judging sub-module is used for judging whether the time interval between the last piece of data of the target package and the first piece of data of the last package is smaller than or equal to the preset first time length if the target package is the target type package;
the superposition judging sub-module is used for judging whether the previous package is superposed with other packages or not if the superposition judging sub-module is smaller than or equal to the first duration;
and the superposition determination submodule is used for determining that the target parcel needs to be superposed on the previous parcel if the target parcel is not superposed with other parcels.
On the basis of the above embodiment, the target type judgment submodule includes:
the pixel width determining unit is used for determining the pixel width of the target package according to all the fragment data of the target package;
the pixel threshold comparison unit is used for judging whether the pixel width of the target package is smaller than a preset pixel column number threshold;
The target type determining unit is used for determining that the target package is a target type package if the target type package is smaller than a preset pixel column number threshold value.
Based on the embodiment, when merging the fragment data of two packages, superposing marks on the two package marks;
the superposition judging submodule comprises:
the mark judging unit is used for judging whether the last package is marked with the superposition mark or not;
and the superposition judging unit is used for determining that the previous parcel is not superposed with other parcels if the superposition mark is not marked.
Based on the foregoing embodiment, the system further includes a next package stacking module, configured to stack the target package to the next package if the time interval is greater than the first time period and the time interval between the last piece of data of the target package and the first piece of data of the next package is less than or equal to the first time period.
Based on the above embodiment, the graph judgment and package opening determining module 306 includes:
the security inspection result merging sub-module is used for merging the first security inspection analysis result of the target package with the second security inspection analysis result of the previous package to obtain a target security inspection analysis result of the merged package;
and the graph judging and package opening judging sub-module is used for determining whether the graph judging process is required to be executed on the combined package according to the target security inspection analysis result.
On the basis of the above embodiment, the graph judging and package opening judging submodule includes:
the picture judgment and unpacking judgment unit is used for judging whether the first security inspection analysis result or the second security inspection analysis result is required to judge whether the picture is unpacked or not;
and the graph judgment and package opening determining unit is used for determining that the graph judgment flow is required to be executed on the combined package if the graph judgment and package opening is required.
The package data analysis device provided by the embodiment of the invention is contained in the terminal equipment, can be used for executing the package data analysis method provided by the embodiment, and has corresponding functions and beneficial effects.
It should be noted that, in the embodiment of the package data analysis device, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
The present embodiment also provides a terminal device, as shown in fig. 11, the terminal device 40 includes a processor 400 and a memory 401;
the memory 401 is used for storing a computer program 402 and transmitting the computer program 402 to the processor 400;
The processor 400 is configured to perform the steps of one of the package data analysis method embodiments described above in accordance with instructions in the computer program 402.
By way of example, computer program 402 may be partitioned into one or more modules/units, which are stored in memory 401 and executed by processor 400 to accomplish the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions to describe the execution of the computer program 402 in the terminal device 40.
The terminal device 40 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. Terminal device 40 may include, but is not limited to, a processor 400, a memory 401. It will be appreciated by those skilled in the art that fig. 11 is merely an example of the terminal device 40 and is not limiting of the terminal device 40, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the terminal device 40 may also include input-output devices, network access devices, buses, etc.
The processor 400 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 401 may be an internal storage unit of the terminal device 40, such as a hard disk or a memory of the terminal device 40. The memory 401 may also be an external storage device of the terminal device 40, such as a plug-in hard disk provided on the terminal device 40, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like. Further, the memory 401 may also include both an internal storage unit and an external storage device of the terminal device 40. The memory 401 is used to store computer programs and other programs and data required for the terminal device 40. The memory 401 may also be used to temporarily store data that has been output or is to be output.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media in which computer programs can be stored.
The embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method of parcel data analysis, the method comprising the steps of:
receiving the fragment data of a target package sent by an X-ray machine, wherein the target package is a package currently scanned by the X-ray machine;
when the last fragment data of the target package sent by the X-ray machine is received, determining whether the target package needs to be overlapped on the previous package according to an overlapping rule;
if necessary, merging the target wrapped piece data with the last wrapped piece data to obtain merged piece data of merged wrapping;
executing a data analysis flow for merging the fragment data to obtain a data analysis result of the target package;
determining a first security inspection analysis result of the target package according to the data analysis result of the target package;
determining whether to execute a graph judging flow on the combined package according to the first security check analysis result and the second security check analysis result of the previous package;
if the combined package is required to be executed, executing a graph judging flow.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the embodiments of the present invention are not limited to the particular embodiments described herein, but are capable of numerous obvious changes, rearrangements and substitutions without departing from the scope of the embodiments of the present invention. Therefore, while the embodiments of the present invention have been described in connection with the above embodiments, the embodiments of the present invention are not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.

Claims (10)

1. A method of package data analysis, comprising:
receiving the fragment data of a target package sent by an X-ray machine, wherein the target package is a package currently scanned by the X-ray machine;
when the last fragment data of the target package sent by the X-ray machine is received, determining whether the target package needs to be overlapped on the previous package according to an overlapping rule;
if necessary, merging the target wrapped fragment data with the last wrapped fragment data to obtain merged fragment data of merged wrapping;
executing a data analysis flow of the merged fragment data to obtain a data analysis result of the target package;
determining a first security inspection analysis result of the target package according to the data analysis result of the target package;
determining whether to execute a graph judging flow on the combined package according to the first security inspection analysis result and the second security inspection analysis result of the previous package;
and if the combined package is required to be executed, executing the graph judging flow on the combined package.
2. The method of claim 1, wherein determining whether the target package needs to be superimposed on a previous package according to a superimposition rule comprises:
Judging whether the target package is a target type package or not according to all the fragment data of the target package;
if the target type package is the target type package, judging whether the time interval between the last piece of data of the target package and the first piece of data of the last package is smaller than or equal to a preset first duration;
if the time length is less than or equal to the first time length, judging whether the last package is overlapped with other packages or not;
and if the target package is not overlapped with other packages, determining that the target package needs to be overlapped with the previous package.
3. The method for analyzing package data according to claim 2, wherein the determining whether the target package is a target type package according to all pieces of data of the target package comprises:
determining the pixel width of the target package according to all the fragment data of the target package;
judging whether the pixel width of the target package is smaller than a preset pixel column number threshold value or not;
and if the target package is smaller than the target type package, determining that the target package is a target type package.
4. The package data analysis method according to claim 2, wherein when combining the fragmented data of two packages, the two package labels are superimposed with a label;
The determining whether the previous package has been superimposed with other packages includes:
judging whether the last package is marked with the superposition identification or not;
and if the superposition identification is not marked, determining that the previous package is not superposed with other packages.
5. The method of claim 2, wherein if the time interval is greater than the first duration and the time interval between the last piece of data of the target package and the first piece of data of the next package is less than or equal to the first duration, the target package is stacked on the next package.
6. The method of claim 1, wherein determining whether to perform a graph-determining process on the consolidated parcel according to the first security analysis result and the second security analysis result of the previous parcel comprises:
combining the first security inspection analysis result of the target package with the second security inspection analysis result of the previous package to obtain a target security inspection analysis result of the combined package;
and determining whether a graph judging flow is required to be executed for the combined package according to the target security inspection analysis result.
7. The method of claim 6, wherein determining whether the merged package needs to be subjected to a graph-determining process according to the target security analysis result, comprises:
judging whether the first security inspection analysis result or the second security inspection analysis result is to be judged and unpacked;
if yes, determining that the graph judging flow needs to be executed on the combined package.
8. A package data analysis device, comprising:
the data receiving module is used for receiving the fragment data of the target package sent by the X-ray machine, wherein the target package is the package currently scanned by the X-ray machine;
the superposition judging module is used for determining whether the target package needs to be superposed on the previous package according to superposition rules when the last fragment data of the target package sent by the X-ray machine is received;
the data merging module is used for merging the fragment data of the target package with the fragment data of the previous package if the target package needs to be overlapped to the previous package, so as to obtain merged fragment data of the merged package;
the data analysis module is used for executing a data analysis flow of the merged and fragmented data to obtain a data analysis result of the target package;
The security check result determining module is used for determining a first security check analysis result of the target package according to the data analysis result of the target package;
the picture judgment and package opening determining module is used for determining whether to execute a picture judgment flow on the combined package according to the first security inspection analysis result and the second security inspection analysis result of the previous package;
and the graph judging and package opening module is used for executing the graph judging flow on the combined package if the graph judging flow is determined to be executed on the combined package.
9. A terminal device, characterized in that the terminal device comprises a processor and a memory;
the memory is used for storing a computer program and transmitting the computer program to the processor;
the processor is configured to perform a method of package data analysis according to any one of claims 1-7 according to instructions in the computer program.
10. A storage medium storing computer executable instructions which, when executed by a computer processor, are adapted to perform a parcel data analysis method according to any of claims 1 to 7.
CN202310598624.7A 2023-05-24 2023-05-24 Method, device, terminal equipment and storage medium for package data analysis Pending CN116721407A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310598624.7A CN116721407A (en) 2023-05-24 2023-05-24 Method, device, terminal equipment and storage medium for package data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310598624.7A CN116721407A (en) 2023-05-24 2023-05-24 Method, device, terminal equipment and storage medium for package data analysis

Publications (1)

Publication Number Publication Date
CN116721407A true CN116721407A (en) 2023-09-08

Family

ID=87872460

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310598624.7A Pending CN116721407A (en) 2023-05-24 2023-05-24 Method, device, terminal equipment and storage medium for package data analysis

Country Status (1)

Country Link
CN (1) CN116721407A (en)

Similar Documents

Publication Publication Date Title
US11768313B2 (en) Multi-scanner networked systems for performing material discrimination processes on scanned objects
Łubkowski et al. Selected issues of reliable identification of object in transport systems using video monitoring services
CN105448103B (en) Vehicle fake-license detection method and system
CN110929066A (en) Method and device for displaying personnel and package information in association manner and security check machine
US7715590B2 (en) Real-time image detection using polarization data
EP2889821A1 (en) Whole-course visualization system and method for logistics articles
EP3005231B1 (en) Method and device for counting objects in image data in frames, computer program product
KR102240806B1 (en) Outgoing packing management method and system using invoice information recognition
CN111382725B (en) Method, device, equipment and storage medium for processing illegal express packages
CN112099104B (en) Security inspection method and device
CN110880028A (en) Method and equipment for distributing packages through conveying line
CN113255651A (en) Package security check method, device and system, node equipment and storage device
EP3770587A1 (en) Inspection device, inspection results management system, inspection results storage method, and inspection results management method
CN114049575A (en) Intelligent detection method and system for contraband of security check machine and electronic equipment
CN116721407A (en) Method, device, terminal equipment and storage medium for package data analysis
CN110619083B (en) Data filtering method and device
EP4038539A1 (en) X-ray detection of meat
CN115660540B (en) Cargo tracking method, cargo tracking device, computer equipment and storage medium
CN116563628A (en) Security check judgment chart identification method, device, equipment and storage medium
CN115512283A (en) Parcel image processing method and device, computer equipment and storage medium
CN111985326A (en) Data processing method and device, electronic equipment and storage medium
KR102649500B1 (en) Image identification apparatus, and product manufacturing apparatus provided with image identification apparatus
CN113978987A (en) Pallet object packaging and picking method, device, equipment and medium
CN113205133A (en) Tunnel water stain intelligent identification method based on multitask learning
CN109388983B (en) Bar code classification method, classification 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