CN117077083B - Automatic identification and statistics method for packaged articles - Google Patents
Automatic identification and statistics method for packaged articles Download PDFInfo
- Publication number
- CN117077083B CN117077083B CN202311305978.4A CN202311305978A CN117077083B CN 117077083 B CN117077083 B CN 117077083B CN 202311305978 A CN202311305978 A CN 202311305978A CN 117077083 B CN117077083 B CN 117077083B
- Authority
- CN
- China
- Prior art keywords
- article
- identification
- articles
- boxing
- domain
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 9
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000004806 packaging method and process Methods 0.000 description 10
- 238000012856 packing Methods 0.000 description 3
- 238000012552 review Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an automatic identification and statistics method for boxing articles, which comprises the following steps: acquiring the preset article boxing quantity to be completed from a work item database; the image recognition and statistics device, the bar code/two-dimensional code recognition device and the radio frequency recognition device are utilized to judge, recognize and count the articles, the type and the number of the final articles are judged according to the relative majority result, and the boxing result is sent to operators after the boxing number reaches the requirement. The beneficial effects of the invention are as follows: the packaged articles are identified and counted through different automatic identification technologies, and most decisions are selected as identification results, so that the types and the number of the packaged articles are judged more accurately, and the error rate is reduced.
Description
Technical Field
The invention belongs to the technical field of boxing identification, and particularly relates to an automatic boxing article identification and statistics method.
Background
In various manufacturing and logistics industries, it is essential to accurately identify and record the type and quantity of items in a bin, however, manual inspection and recording systems now being used typically require a significant amount of manpower and may be subject to errors.
The chinese patent application No. 2016109409573 discloses a packaging system relating to the packaging field, in particular to matching packaging with article identification. Before packing and assembling the articles, respectively pasting identification codes, namely two-dimensional codes, on each component and each packing box, and simultaneously inputting information into a software system; when a user opens the package, firstly scanning the two-dimensional code on the outer package, and rapidly acquiring order information, namely the information of articles in the outer package; and then the articles in the package are scanned respectively, and after the user confirms that the scanning is finished, the article information of each article in the outer package box can be obtained. The user client side can be used for comparing the order information with the article information to know whether the order is packaged and sent in error.
According to the scheme, in the packaging stage, the articles contained in the order are collected, the unique product codes are obtained from the intelligent identification article information database, the packaging codes are generated according to all the product codes of the order, then the product two-dimensional codes are generated according to the product codes, the product two-dimensional codes contain the article information of the product, the generated two-dimensional codes are respectively posted to the articles corresponding to the two-dimensional codes before packaging, and then the identification and statistics can be conveniently carried out after packaging. The method can improve the speed of article identification and statistics, but the accuracy of identification and statistics results cannot be ensured by a single identification method.
Disclosure of Invention
In order to solve the problems, the invention provides an automatic identification and statistics method for boxing articles, which comprises the following steps:
s1, acquiring a work item
Acquiring the preset article boxing quantity required to be finished from a work item database, and sequentially boxing articles into boxes;
s2, identifying packaged articles
Respectively identifying the articles which are packaged in sequence by utilizing an image identification statistical device, a bar code/two-dimensional code identification device and a radio frequency identification device, and completing the article identification work if the identification results of the three identification devices are the same; if the identification result of one of the two identification devices is different from the identification result of the other two identification devices and the identification result of the other two identification devices is the same, the identification result of the other two identification devices is used as the article identification result;
s3, counting packaged articles
Counting the objects in sequence by using an image recognition counting device, a bar code/two-dimensional code recognition device and a radio frequency recognition device, counting the total number of the objects recognized in the step S2, and taking a plurality of values in the values as the number of the packaged objects according to the numerical values of the four counting results;
s4, judging whether the boxing is completed
Comparing the number of the boxing articles with the preset number of articles to be completed, if the number of the boxing articles is smaller than the preset number of the articles to be completed, judging that the boxing operation is not completed, and re-executing the step S2; if the number of the boxed articles is the same as the preset number of the articles to be finished, the boxed articles are judged to be finished, the boxed articles are transmitted to corresponding personnel, and the next work item is acquired from the work item database.
Preferably, the image recognition statistical device comprises the following recognition statistical methods:
s11, identifying articles
Acquiring an article picture in case, carrying out article detection and identification on the picture by utilizing an article detection model, executing a step S12 if the article is identified, and executing a step S11 again if the article is not identified;
s12, setting a judging range
Calculating vertex coordinates of a detected article frame by using a byte rack model, generating a unique ID for the article by using self increment, defining a rectangular range by a domain determiner, determining whether the article falls into the rectangular range by the domain determiner through four vertex coordinates of the article frame, and if the article falls into the rectangular range, determining that the article is in the domain; if not, judging that the article is outside the domain;
s13, intra-domain count determination
If the article is judged to be in the domain, searching an article ID set in the domain through a searcher, if the ID of the article is a new ID, proving that a boxing person is putting the article, adding the article ID to the article ID set in the domain, and judging the boxing article quantity +1; if the object ID is in the object ID set in the domain, proving that the boxing personnel only collates the objects in the box, judging the boxing object quantity +0, and not updating the object ID set;
s14, counting and judging outside the domain
If the article is judged to be outside the domain, after the retriever retrieves the article ID set in the domain, if the article ID is in the article ID set in the domain, the person who takes out the article is proved to take out the article due to misplacement of the article, the article ID is removed from the article ID set in the domain, the article quantity-1 is judged to be packaged, if the article ID is not in the article ID set in the domain, the person who takes out the article is proved to move the article outside the box, the article quantity +0 is judged to be packaged, and the article ID set is not updated.
Preferably, the method further comprises step S31, if the identification result of one of the identification devices is different from the identification result of the other two identification devices and the identification result of the other two identification devices is the same, starting the standby identification device corresponding to the identification device to participate in the identification of the next article, and judging the identification result of the next article according to the majority of identification results.
Preferably, in the step S31, when the spare recognition device is used to participate in the next article recognition, the spare recognition device is compared with the corresponding identification result of the original recognition device, if the identification result of the original recognition device is the same as the spare recognition device, it is determined that the original recognition device is not faulty, and if the identification result of the original recognition device is different from the spare recognition device, it is determined that the original recognition device is damaged.
Preferably, when the result of the judgment of one device in the step S31 is different from the other two devices, the early warning information is triggered, and when the recognition result of the standby recognition device is compared with the recognition result of the corresponding original recognition device, if the recognition result is different from the standby recognition device, an alarm is sent.
Preferably, the standby identification devices are all arranged on the side edge of the original identification device in advance, and the standby identification devices are all comprehensively tested and verified in an experimental environment in advance.
Preferably, the image recognition statistical device and the bar code/two-dimensional code recognition device are used for recognizing by acquiring image information in the boxing process through the image acquisition device.
Preferably, in the step S3, if all the four statistics are different or equal to each other, the maximum value in the values is taken as the final article quantity.
Preferably, the method further comprises the step S5 of video monitoring; the whole process of the article boxing process is monitored by monitoring equipment, and one or a plurality of time marks for positioning to key frames are added in a time line of the monitoring video file.
The invention has the advantages that:
three different automatic recognition technologies including image recognition, bar code recognition and radio frequency recognition technologies are adopted to form a group of triple modular redundancy, and the final article type is judged through relative majority results, so that the accuracy of article recognition is improved.
Simultaneously counting the articles by image recognition, bar code recognition and radio frequency recognition technology, introducing statistical parameters of the number of the identified articles, and selecting a majority value of four statistical results to judge the number of the final articles, thereby improving the accuracy of article counting.
By setting up the original counting method of the image device, the objects in the box can be accurately counted, the influence of special conditions on the counting result is avoided, and the accuracy of the counting result of the image recognition counting device is improved.
The standby identification device is introduced, so that the identification and statistics processes of the packaged articles can be ensured not to be influenced by faults of the individual identification device by utilizing the standby identification device, and meanwhile, identification parameters can be added for the identification result, so that the identification accuracy is further improved.
The video monitoring is carried out on the whole boxing process, and the time marks of important events are acquired in real time and encoded in the video, so that the video can be accurately positioned in a review mode, and the retrospective on the boxing process is facilitated.
In summary, the invention can accurately judge the category and the number of the packaged articles by integrating and applying the radio frequency technology, the image recognition technology and the bar code recognition in the article packaging scene.
Drawings
Fig. 1 is a schematic flow chart of embodiment 1 of the present invention.
Fig. 2 is a schematic flow chart of embodiment 2 of the present invention.
Fig. 3 is a schematic flow chart of embodiment 3 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
With reference to fig. 1, there is provided a method for automatically identifying and counting packaged articles, comprising the steps of:
s1, acquiring a work item
And acquiring the preset article boxing quantity required to be finished from the work item database, and sequentially boxing the articles. The structure of a work item comprises: number, date, completion status, mail sending status, responsible email address, list of items, etc. The structure of the object list comprises: the method comprises the steps of article coding, article names, required number and the like, wherein the required number is the preset article boxing number required to be completed, and boxing work can be judged to be completed only when the article boxing number in the packaging box reaches the required number.
S2, identifying packaged articles
The image recognition statistical device, the bar code/two-dimensional code recognition device and the radio frequency recognition device are used for respectively recognizing the objects which are packaged in sequence, the final object category is judged according to a plurality of results, the three recognition devices are used for recognizing four experimental objects, and the recognition results are shown in the table 1;
TABLE 1
As can be seen from table 1, if the three recognition results of the recognition devices are identical, the recognition type of the article is determined with the common recognition result of the three recognition devices, and the article recognition work is completed; if only two identification devices have the same identification result and the identification result of the remaining one identification device is different from the identification results of the two identification devices, the identification results of the two identification devices are used as the article identification results. Since the article 1 and the article 2 in table 1 are each judged as the type a by the three kinds of identifying means, the result of the judgment is the type a article, which is recorded in the storage device corresponding to the computer. The article 3 is judged as an article of type a by the two kinds of recognition devices, and therefore, the article is judged as an article of type a according to a plurality of recognition results, and the article is recorded in a corresponding storage device of the computer. Since the article 4 is judged to be of the type B by the two kinds of recognition devices and of the type a by the one kind of recognition device, the article is judged to be of the type B based on the plurality of recognition results, and the article is recorded in a storage device corresponding to the computer. If the identification results of the three identification means are different, it is indicated that at least two identification means are damaged, the corresponding equipment must be refurbished, which can be ignored because of the lower probability of occurrence.
The image recognition statistical device and the bar code/two-dimensional code recognition device are used for recognizing by acquiring image information in the boxing process through the image acquisition device. The image acquisition device in this embodiment is a camera mounted on top of the boxing line for monitoring the entire boxing process. The image recognition statistical device can capture a boxing video from the camera, and the picture of each frame of the boxing video is detected through an object detection model such as YOLOV5 to recognize the corresponding object. When a packer aligns a bar code or a two-dimensional code on an article with a top camera during packing, the article detection model can also detect the bar code/the two-dimensional code. Then the bar code/two-dimensional code recognition device can analyze the detected bar code/two-dimensional code image into a text and record the text, and recognize the corresponding article. The two radio frequency identification devices are used for reading RFID labels on the articles by using RFID readers and writers to identify the types of the articles.
S3, counting packaged articles
The image recognition and statistics device can count the articles according to the recognized articles, and the bar code/two-dimensional code recognition device records the quantity according to the bar code/two-dimensional code on the scanned articles so as to count the number of the articles. The radio frequency identification device reads RFID tags on the articles by using an RFID reader-writer, and counts the number of the articles according to the number of the read RFID tags. Meanwhile, as shown in the recognition results in table 1, the number of articles can also be counted by calculating the total number of recognized articles in the lateral direction. And taking the value with more occurrence in the four statistics values as the number of the packaged articles according to the statistics result values of the three identification devices and the calculated identified article total quantity value. And the final article quantity is judged by introducing statistical parameters of various article quantities and selecting a plurality of numerical values, so that the accuracy of article statistics is improved.
S4, judging whether the boxing is completed
Comparing the number of the boxing articles with the preset number of articles to be completed, if the number of the boxing articles is smaller than the preset number of the articles to be completed, judging that the boxing operation is not completed, and re-executing the step S2; if the number of the packaged articles is the same as the preset number of the articles to be completed, the completion of the packaging work is judged, the information such as the completion state, the supply number and the like of the work item is updated, the corresponding information is taken as a text, the screenshot is packaged into an accessory, and the accessory is sent to a responsible person through the well-known SMTP server interface service according to the mail address information of the responsible person in the work item. And updating the mail sending condition to the mail sending state in the work item. And then automatically acquiring the next work item to be completed from the work item database, and starting the next boxing task.
It should be noted that if the extreme situation occurs, for example, the four statistics results in step S3 are all different or equal to each other, the maximum value in the values is taken as the final article quantity, in this case, although it cannot be determined whether the maximum value is the actual article quantity, it can be ensured that the quantity in the box is less than or equal to the preset article boxing quantity to be completed after boxing is completed, so that the articles can be loaded by the box, and the boxing quantity of the articles cannot be too large to exceed the volume of the box.
In the embodiment, three different automatic identification technologies including image identification, bar code identification and radio frequency identification technologies form a group of triple modular redundancy, the final article type is judged through relative majority results, the image identification, bar code identification and radio frequency identification technologies also count the articles when the articles are identified, meanwhile, the statistical parameters of the number of the identified articles are introduced, and the majority values of four statistical results are selected to judge the final article number, so that the accuracy of the identification and statistics of the articles is improved.
Example 2
Referring to fig. 2, this embodiment provides a recognition and statistics method of an image recognition and statistics device, which has the same parts as those of embodiment 1, and the recognition and statistics method of the image recognition and statistics device is improved, and the recognition and statistics method of the image recognition and statistics device is as follows:
s11, identifying articles
Acquiring an article picture in case, carrying out article detection and identification on the picture by utilizing an article detection model, executing a step S12 if the article is identified, and executing a step S11 again if the article is not identified;
s12, setting a judging range
Calculating vertex coordinates of a detected article frame by using a byte rack model, generating a unique ID for the article by using self increment, defining a rectangular range by a domain determiner, determining whether the article falls into the rectangular range by the domain determiner through four vertex coordinates of the article frame, and if the article falls into the rectangular range, determining that the article is in the domain; if not, judging that the article is outside the domain;
s13, intra-domain count determination
If the article is judged to be in the domain, searching an article ID set in the domain through a searcher, if the ID of the article is a new ID, proving that a boxing person is putting the article, adding the article ID to the article ID set in the domain, and judging the boxing article quantity +1; if the object ID is in the object ID set in the domain, proving that the boxing personnel only collates the objects in the box, judging the boxing object quantity +0, and not updating the object ID set;
s14, counting and judging outside the domain
If the article is judged to be outside the domain, after the retriever retrieves the article ID set in the domain, if the article ID is in the article ID set in the domain, the person who takes out the article is proved to take out the article due to misplacement of the article, the article ID is removed from the article ID set in the domain, the article quantity-1 is judged to be packaged, if the article ID is not in the article ID set in the domain, the person who takes out the article is proved to move the article outside the box, the article quantity +0 is judged to be packaged, and the article ID set is not updated.
The original image device counting method is established in the embodiment, articles in the box can be accurately counted, the influence of special conditions such as the carrying of operators on the counting result is avoided, and the accuracy of the counting result can be improved.
Example 3
Referring to fig. 3, compared with embodiment 1, the difference is that a corresponding spare identification device is added, and the embodiment further includes step S31, where after step S3, if the identification result of one identification device is different from the identification result of the other two identification devices and the identification result of the other two identification devices is the same, the spare identification device corresponding to the identification device is started to participate in the identification of the next article, and the identification result of the next article is determined according to the majority of identification results. Take table 2 as an example;
TABLE 2
As can be seen from table 2, when the article 1 is identified, the corresponding standby rfid is activated because the rfid is different from the other two. The next article 2 is judged by adding the standby identification device, and then the identification result of the next article 2 is judged according to the majority of identification results.
In this embodiment, each identification device is provided with a standby identification device, the standby identification devices are all arranged on the side of the original identification device in advance, and the standby identification devices are all comprehensively tested and verified in the experimental environment in advance, so that the accuracy of the identification result can be ensured. When the result of the judgment of one device is different from the other two devices in the step S31, the early warning information is triggered, which indicates that the identification device is possibly damaged, and the corresponding standby identification device is started, the computer receives the early warning information, and starts the standby identification device to identify the next article according to the early warning information. By providing the spare recognition device, the article recognition operation can be continued without delaying the overall recognition time. In order to further judge whether the corresponding original identification device is suddenly faulty, when the corresponding standby identification device is used for judging the next article in cooperation with the other two identification devices, the original identification device corresponding to the standby identification device can also judge the next article, if the identification result is the same as that of the standby identification device, the original identification device is judged not to have permanent faults, but sudden conditions, such as the damage of the identified two-dimensional code, are judged. The original identification device can continue to participate in subsequent object judgment, if the identification result is different from the standby identification device, the original identification device is judged to be permanently damaged, and meanwhile, an alarm is sent out to indicate that the identification device needs to be repaired. As shown in table 2, the identification result of the original rfid device on the next article is different from that of the spare rfid device, and it is determined that the original rfid device is damaged, and the original rfid device is not involved in the subsequent article identification, and the original rfid device can be taken out for maintenance. Since the identification device also counts the articles when identifying the articles, when the original identification device judges that the failure occurs, the computer adds the previous statistics result with the statistics result of the subsequent standby identification device to be used as the statistics result of the type identification device on the articles.
Example 4
Step S5, video monitoring is further included on the basis of the embodiment 1; video acquisition, processing and storage are carried out on the whole boxing process; adding one or several time stamps in the timeline of the video file for locating to the key frames; the whole process of the boxing process is shot through the additionally arranged monitoring camera, and the time marks of important events in the boxing process are encoded in the video, so that the video can be accurately positioned in a review mode, and the retrospective of the boxing process is facilitated.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. An automatic identification and statistics method for boxing articles is characterized in that: comprises the following steps of;
s1, acquiring a work item
Acquiring the preset article boxing quantity required to be finished from a work item database, and sequentially boxing articles into boxes;
s2, identifying packaged articles
Respectively identifying the articles which are packaged in sequence by utilizing an image identification statistical device, a bar code/two-dimensional code identification device and a radio frequency identification device, and completing the article identification work if the identification results of the three identification devices are the same; if the identification result of one of the two identification devices is different from the identification result of the other two identification devices and the identification result of the other two identification devices is the same, the identification result of the other two identification devices is used as the article identification result;
s3, counting packaged articles
Counting the objects in sequence by using an image recognition counting device, a bar code/two-dimensional code recognition device and a radio frequency recognition device, counting the total number of the objects recognized in the step S2, and taking a plurality of values in the values as the number of the packaged objects according to the numerical values of the four counting results;
s4, judging whether the boxing is completed
Comparing the number of the boxing articles with the preset number of articles to be completed, if the number of the boxing articles is smaller than the preset number of the articles to be completed, judging that the boxing operation is not completed, and re-executing the step S2; if the number of the boxed articles is the same as the number of the articles to be packaged in the preset manner, judging that the boxing operation is completed, transmitting the boxed work item information to corresponding personnel, and acquiring the next work item from a work item database;
the identification statistical method of the image identification statistical device comprises the following steps:
s11, identifying articles
Acquiring an article picture in case, carrying out article detection and identification on the picture by utilizing an article detection model, executing a step S12 if the article is identified, and executing a step S11 again if the article is not identified;
s12, setting a judging range
Calculating vertex coordinates of a detected article frame by using a byte rack model, generating a unique ID for the article by using self increment, defining a rectangular range by a domain determiner, determining whether the article falls into the rectangular range by the domain determiner through four vertex coordinates of the article frame, and if the article falls into the rectangular range, determining that the article is in the domain; if not, judging that the article is outside the domain;
s13, intra-domain count determination
If the article is judged to be in the domain, searching an article ID set in the domain through a searcher, if the ID of the article is a new ID, proving that a boxing person is putting the article, adding the article ID to the article ID set in the domain, and judging the boxing article quantity +1; if the object ID is in the object ID set in the domain, proving that the boxing personnel only collates the objects in the box, judging the boxing object quantity +0, and not updating the object ID set;
s14, counting and judging outside the domain
If the article is judged to be outside the domain, after the retriever retrieves the article ID set in the domain, if the article ID is in the article ID set in the domain, the person who takes out the article is proved to take out the article due to misplacement of the article, the article ID is removed from the article ID set in the domain, the article quantity-1 is judged to be packaged, if the article ID is not in the article ID set in the domain, the person who takes out the article is proved to move the article outside the box, the article quantity +0 is judged to be packaged, and the article ID set is not updated.
2. The method for automatically identifying and counting packaged articles according to claim 1, wherein: and step S31, wherein after the step S31 is in the step S3, if the identification result of one identification device is different from the identification result of the other two identification devices and the identification result of the other two identification devices is the same, starting the standby identification device corresponding to the identification device to participate in the identification of the next article, and judging the identification result of the next article according to the majority of identification results.
3. The method for automatically identifying and counting packaged articles according to claim 2, wherein: in the step S31, when the spare recognition device is used to participate in the recognition of the next article, the spare recognition device is compared with the corresponding identification result of the original recognition device, if the identification result of the original recognition device is the same as the spare recognition device, the original recognition device is judged to have no fault, and if the identification result of the original recognition device is different from the spare recognition device, the original recognition device is judged to be damaged.
4. A method of automatically identifying and counting packaged articles according to claim 3, wherein: when the result of the judgment of one device is different from the other two devices in the step S31, the early warning information is triggered, and when the recognition result of the standby recognition device is compared with the recognition result of the corresponding original recognition device, if the recognition result is different from the standby recognition device, an alarm is sent.
5. The method for automatically identifying and counting packaged articles according to claim 4, wherein: the standby identification devices are all arranged on the side edges of the original identification devices in advance, and the standby identification devices are all comprehensively tested and verified in an experimental environment in advance.
6. The method for automatically identifying and counting packaged articles according to claim 5, wherein: the image recognition statistical device and the bar code/two-dimensional code recognition device are used for recognizing by acquiring image information in the boxing process through the image acquisition device.
7. The method for automatically identifying and counting packaged articles according to claim 1, wherein: and in the step S3, if all four statistical results are different or are the same in pairs, taking the maximum value in the numerical values as the final article quantity.
8. The method for automatically identifying and counting packaged articles according to claim 1, wherein: step S5, video monitoring is also included; the whole process of the article boxing process is monitored by monitoring equipment, and one or a plurality of time marks for positioning to key frames are added in a time line of the monitoring video file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311305978.4A CN117077083B (en) | 2023-10-10 | 2023-10-10 | Automatic identification and statistics method for packaged articles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311305978.4A CN117077083B (en) | 2023-10-10 | 2023-10-10 | Automatic identification and statistics method for packaged articles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117077083A CN117077083A (en) | 2023-11-17 |
| CN117077083B true CN117077083B (en) | 2024-01-05 |
Family
ID=88719742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311305978.4A Active CN117077083B (en) | 2023-10-10 | 2023-10-10 | Automatic identification and statistics method for packaged articles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077083B (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2617843A1 (en) * | 2005-08-03 | 2007-02-08 | True Product Id Technology (Beijing) Limited | Method of labelling and detectiion of goods and device thereof |
| KR100814456B1 (en) * | 2007-03-20 | 2008-03-17 | 주식회사 나루기술 | A thing collecting management system of a mobile rack according to recognize radio frequency identification tag and method of the same |
| KR20120101917A (en) * | 2011-03-07 | 2012-09-17 | 이상영 | A method and rfid tag using product distribution system for smart mobile users |
| WO2012142882A1 (en) * | 2011-04-19 | 2012-10-26 | 中兴通讯股份有限公司 | Barcode scanning method, system and apparatus for radio frequency identification reader |
| CN103632464A (en) * | 2013-11-14 | 2014-03-12 | 成都博约创信科技有限责任公司 | Image identification and label identification integration settlement method |
| CN104008583A (en) * | 2014-04-29 | 2014-08-27 | 云南电网公司 | Method for implementation of access control on electric power machine room based on two-dimensional code and radio frequency identification technology |
| CN204129757U (en) * | 2014-10-09 | 2015-01-28 | 北京南瑞捷鸿科技有限公司 | The intelligent batch identification radio-frequency unit of integrated image |
| CN105559307A (en) * | 2014-10-14 | 2016-05-11 | 北大方正集团有限公司 | Case inner article identification method and device, case and user terminal |
| CN106372831A (en) * | 2016-08-26 | 2017-02-01 | 无锡卓信信息科技股份有限公司 | Radio-frequency identification technology-based warehouse goods statistics control system |
| CN106778970A (en) * | 2016-12-14 | 2017-05-31 | 北京龙贝世纪科技股份有限公司 | The double mode automatic information identifying system and method for Quick Response Code and RF tag |
| WO2018112930A1 (en) * | 2016-12-23 | 2018-06-28 | 深圳前海达闼云端智能科技有限公司 | Method and device for identifying commodities |
| WO2019019291A1 (en) * | 2017-07-24 | 2019-01-31 | 图灵通诺（北京）科技有限公司 | Settlement method and device of image recognition technology based on convolutional neural network |
| CN109829346A (en) * | 2019-01-11 | 2019-05-31 | 安徽工程大学 | A kind of bar code and two-dimensional code identification method and system based on machine vision |
| CN110110823A (en) * | 2019-04-25 | 2019-08-09 | 浙江工业大学之江学院 | Object based on RFID and image recognition assists in identifying system and method |
| CN110222548A (en) * | 2019-05-30 | 2019-09-10 | 武汉理工大学 | A kind of digital picture detection knowledge method for distinguishing |
| CN110490516A (en) * | 2019-08-01 | 2019-11-22 | 广州织点智能科技有限公司 | A kind of unmanned store shelf article detection method and device |
| CN110852130A (en) * | 2019-11-12 | 2020-02-28 | 上海仪电数字技术股份有限公司 | Identification method and system for identifying bar codes of boxed products in batch |
| WO2022007495A1 (en) * | 2020-07-08 | 2022-01-13 | 北京京东振世信息技术有限公司 | Method and terminal for identifying barcode |
| CN114219408A (en) * | 2021-12-21 | 2022-03-22 | 四川启睿克科技有限公司 | Robot warehouse inventory method based on image recognition and TOF sensor |
| KR102441669B1 (en) * | 2022-04-19 | 2022-09-08 | 이경민 | Port vehicle access control system using rfid and image processing, and method thereof |
| CN116451727A (en) * | 2023-06-16 | 2023-07-18 | 上海英内物联网科技股份有限公司 | Method for continuously coding RFID (radio frequency identification) tag based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10198653B2 (en) * | 2017-04-26 | 2019-02-05 | Sensors Incorporated | System and method for performing production line product identification |
-
2023
- 2023-10-10 CN CN202311305978.4A patent/CN117077083B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2617843A1 (en) * | 2005-08-03 | 2007-02-08 | True Product Id Technology (Beijing) Limited | Method of labelling and detectiion of goods and device thereof |
| KR100814456B1 (en) * | 2007-03-20 | 2008-03-17 | 주식회사 나루기술 | A thing collecting management system of a mobile rack according to recognize radio frequency identification tag and method of the same |
| KR20120101917A (en) * | 2011-03-07 | 2012-09-17 | 이상영 | A method and rfid tag using product distribution system for smart mobile users |
| WO2012142882A1 (en) * | 2011-04-19 | 2012-10-26 | 中兴通讯股份有限公司 | Barcode scanning method, system and apparatus for radio frequency identification reader |
| CN103632464A (en) * | 2013-11-14 | 2014-03-12 | 成都博约创信科技有限责任公司 | Image identification and label identification integration settlement method |
| CN104008583A (en) * | 2014-04-29 | 2014-08-27 | 云南电网公司 | Method for implementation of access control on electric power machine room based on two-dimensional code and radio frequency identification technology |
| CN204129757U (en) * | 2014-10-09 | 2015-01-28 | 北京南瑞捷鸿科技有限公司 | The intelligent batch identification radio-frequency unit of integrated image |
| CN105559307A (en) * | 2014-10-14 | 2016-05-11 | 北大方正集团有限公司 | Case inner article identification method and device, case and user terminal |
| CN106372831A (en) * | 2016-08-26 | 2017-02-01 | 无锡卓信信息科技股份有限公司 | Radio-frequency identification technology-based warehouse goods statistics control system |
| CN106778970A (en) * | 2016-12-14 | 2017-05-31 | 北京龙贝世纪科技股份有限公司 | The double mode automatic information identifying system and method for Quick Response Code and RF tag |
| WO2018112930A1 (en) * | 2016-12-23 | 2018-06-28 | 深圳前海达闼云端智能科技有限公司 | Method and device for identifying commodities |
| WO2019019291A1 (en) * | 2017-07-24 | 2019-01-31 | 图灵通诺（北京）科技有限公司 | Settlement method and device of image recognition technology based on convolutional neural network |
| CN109829346A (en) * | 2019-01-11 | 2019-05-31 | 安徽工程大学 | A kind of bar code and two-dimensional code identification method and system based on machine vision |
| CN110110823A (en) * | 2019-04-25 | 2019-08-09 | 浙江工业大学之江学院 | Object based on RFID and image recognition assists in identifying system and method |
| CN110222548A (en) * | 2019-05-30 | 2019-09-10 | 武汉理工大学 | A kind of digital picture detection knowledge method for distinguishing |
| CN110490516A (en) * | 2019-08-01 | 2019-11-22 | 广州织点智能科技有限公司 | A kind of unmanned store shelf article detection method and device |
| CN110852130A (en) * | 2019-11-12 | 2020-02-28 | 上海仪电数字技术股份有限公司 | Identification method and system for identifying bar codes of boxed products in batch |
| WO2022007495A1 (en) * | 2020-07-08 | 2022-01-13 | 北京京东振世信息技术有限公司 | Method and terminal for identifying barcode |
| CN114219408A (en) * | 2021-12-21 | 2022-03-22 | 四川启睿克科技有限公司 | Robot warehouse inventory method based on image recognition and TOF sensor |
| KR102441669B1 (en) * | 2022-04-19 | 2022-09-08 | 이경민 | Port vehicle access control system using rfid and image processing, and method thereof |
| CN116451727A (en) * | 2023-06-16 | 2023-07-18 | 上海英内物联网科技股份有限公司 | Method for continuously coding RFID (radio frequency identification) tag based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 自动化立体仓库中货物自动识别技术;杨欢;幸芦笙;;江西科学(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117077083A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110709688B (en) | Method for predicting defects in an assembly unit | |
| CN105182935B (en) | A kind of production management system and its control method | |
| US7099728B2 (en) | Quality control system, method, and program | |
| CN110989521A (en) | Intelligent management system for production line | |
| CN110704231A (en) | Fault processing method and device | |
| JP4439340B2 (en) | Manufacturing history management system | |
| CN101689051B (en) | abnormal factor specifying method and system | |
| CN110597196A (en) | Data acquisition system and data acquisition method | |
| US20200204428A1 (en) | System and method of automated fault correction in a network environment | |
| CN107168269A (en) | A kind of MES system that detection is assembled for engine sprocket room housing | |
| CN113688965B (en) | Automatic storage code scanning detection method and cargo management system | |
| US20100175965A1 (en) | Pallet monitoring system and monitoring method | |
| CN117077083B (en) | Automatic identification and statistics method for packaged articles | |
| JP2008502961A (en) | Method for automatic detection of performance data of reading system | |
| US7813974B1 (en) | Method and apparatus for duplicate shipment detection | |
| JP3741628B2 (en) | Production history management system, production history management method, computer program for executing the same, and recording medium | |
| CN111598506A (en) | Inventory management system | |
| US11697558B2 (en) | Automated detection of carton damage | |
| CN116415864A (en) | Intelligent logistics quick inspection machine based on artificial intelligence | |
| US20220375056A1 (en) | Method for predicting defects in assembly units | |
| CN115185792A (en) | Fault hardware processing method, device and system | |
| CN112185058B (en) | Monitoring alarm method, system, equipment and storage medium | |
| CN112288103B (en) | Starting method for equipment detection in petroleum drilling system | |
| CN113239228A (en) | Commodity labeling method based on image recognition | |
| CN109919262B (en) | Intelligent container production line scanning and checking method and checking equipment |
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 |