CN115294370B - Warehouse-in and warehouse-out detection device and detection method based on twin model - Google Patents
Warehouse-in and warehouse-out detection device and detection method based on twin model Download PDFInfo
- Publication number
- CN115294370B CN115294370B CN202211219027.0A CN202211219027A CN115294370B CN 115294370 B CN115294370 B CN 115294370B CN 202211219027 A CN202211219027 A CN 202211219027A CN 115294370 B CN115294370 B CN 115294370B
- Authority
- CN
- China
- Prior art keywords
- warehouse
- vehicle
- image
- similarity
- weight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention provides a warehouse-in and warehouse-out detection device based on a twin model, which comprises a server and a warehouse-in and warehouse-out monitoring alarm device connected with the server, wherein the warehouse-in and warehouse-out monitoring alarm device images detected vehicles entering and exiting a warehouse and cargos in the vehicles through an X-ray imaging device, and obtains the weights of the detected vehicles and cargos in the vehicles through a bearing type weighing sensor; and obtaining the similarity between the current image and the previous image by utilizing the twin model in the server, and judging whether the object is packaged or not by combining the weight comparison result. The intelligent scanning contrast of goods entering and exiting warehouse is realized through the twin model-based warehouse entering and exiting detection device to judge whether the goods are packaged, and the twin model-based warehouse entering and exiting detection device has the advantages of saving human resources and improving the safety and reliability of the goods transportation process.
Description
Technical Field
The invention relates to the technical field of warehouse conveying management devices, in particular to a warehouse entering and exiting detection device and method based on a twin model.
Background
Along with the surge of internet surge, network electronic commerce is continuously rising, distribution and delivery of freight tasks through networks are becoming popular, and as one or more warehouses are set in each place to temporarily park and store cargoes and vehicles for loading cargoes, the current warehouse in-out treatment is basically carried out manually, so that not only is much labor consumed, but also the speed of checking cannot be ensured, and meanwhile, the freight transportation with large weight and more stacked objects is very troublesome to check, and the probability of omission is very high.
Disclosure of Invention
The invention aims to provide a detection device and a detection method for entering and exiting a warehouse based on a twin model, which solve one or more of the problems in the prior art.
In a first aspect, the invention provides a warehouse-in and warehouse-out detection device based on a twin model, which comprises a server and a warehouse-in and warehouse-out monitoring alarm device connected with the server,
the warehouse-in and warehouse-out monitoring alarm device is used for monitoring vehicles entering and exiting a warehouse and cargoes in the vehicles and acquiring images and weights of the vehicles and the cargoes in the vehicles;
the server is internally provided with a main control module, a data comparison module applying the digital twin model, a storage module and a communication module, wherein the data comparison module applying the digital twin model, the storage module and the communication module are all connected with the main control module,
the communication module is used for being connected with the detection device and transmitting data;
the storage module is used for establishing a database, storing historical data of detected articles, a value range of similarity, a value range of errors of weight, a vehicle number, an image of the vehicle and the weight of the vehicle through the database, wherein the image of the vehicle, the weight of the vehicle and the vehicle number are correspondingly stored, and the historical data comprises the image and the weight of the articles detected before;
the data comparison module is used for comparing images and weights, feeding back comparison results to the main control module, correspondingly storing the results in the database by the main control module, and generating display instructions according to the results and transmitting the display instructions to the communication module in combination with the results.
In some embodiments, the warehouse-in and warehouse-out monitoring alarm device comprises a display component connected with the communication module, wherein the display component comprises a display device and/or a monitoring terminal, and the display component is used for displaying results according to display instructions;
the display device is arranged on one side of the detection device and is used for timely obtaining results of workers at the position of the detection device;
the monitoring terminal is used for monitoring results of workers who are not located at the position of the detection device.
In some embodiments, the warehouse-in and warehouse-out monitoring alarm device comprises a base and a shell arranged on the base, wherein a channel for vehicles to pass through is arranged in the shell, the left side, the right side and the upper side of the channel are provided with mounting seats, the mounting seats are embedded with X-ray imaging equipment, the bottom of the channel is provided with a bearing type weighing sensor,
the X-ray imaging equipment is used for imaging the vehicle and cargoes in the vehicle to form corresponding 3D images;
the support type load cell is used for weighing the weight of the vehicle and the goods in the vehicle when the goods are detected.
In some embodiments, the base is formed by concrete casting, the base is internally provided with a reinforcing steel bar, the top of the reinforcing steel bar penetrates out of the base and is inserted into a shell formed by concrete casting, the bottom of the shell is embedded in the base, the lower part of the base is embedded in rammed filling soil, and a triangular reinforcing plate is arranged between the upper surface of the base and the outer side surface of the shell.
In some embodiments, the bottom of the channel is provided with a support plate, the support type weighing sensor is arranged below the support plate, the vehicle runs onto the support plate, and the total weight of the vehicle, the goods in the vehicle and the support plate is weighed by the support type weighing sensor.
In some embodiments, the database further stores the object type and the weight of the supporting plate, the historical data comprises the corresponding stored vehicle number, the type of goods in the vehicle, the goods number and the detection time, the images of the vehicle are 3D images formed by the X-ray imaging equipment of the vehicle which is not loaded and acquired, and the information stored in the historical data is ordered according to the sequence of the detected time; when the current detection is performed, the current detection time is acquired, and the current image, the weight, the vehicle number, the type of goods in the vehicle and the goods number are combined and stored in the historical data to form the latest historical record.
In some embodiments of the present invention, in some embodiments,
be equipped with two protective sleeves between mount pad and the casing, two protective sleeves are including laminating and with the fixed first protective sheath of casing, set up in the inboard second protective sheath of being connected with the mount pad of first protective sheath, set up by a plurality of springs between the lateral wall of the left and right of second protective sheath and the last three direction and the first protective sheath, the bottom of second protective sheath, the bottom of first protective sheath and casing laminating in proper order are fixed, bearing formula weighing sensor sets up in the second protective sheath inboard, bearing formula weighing sensor is equipped with concrete cushion all around, make level the bottom of passageway through concrete cushion, the bottom of mount pad is connected with concrete cushion, the upper surface of filling flushes with the bottom of second protective sheath.
In some embodiments, the outer side surface of the shell is provided with an alarm connected with the server, and the warehouse-in and warehouse-out monitoring alarm device further comprises two automatic rolling doors connected with the server, wherein the two automatic rolling doors are respectively arranged at the front end and the rear end of the shell and used for closing the channel.
In a second aspect, the present invention provides a detection method of a detection device for entering and exiting a warehouse based on a twin model, comprising the following steps:
acquiring a current image and weight corresponding to a vehicle and goods in the vehicle;
acquiring images and weights corresponding to the goods in the historical data;
comparing images, namely analyzing and comparing the acquired images in the historical data with the current images by adopting a twin model, acquiring a similarity value between the two images, and judging whether the similarity value is in a similarity value range or not;
comparing the weights, calculating the difference between the weight in the obtained historical data and the current weight, and judging whether the difference is in the error value range;
judging whether the article is packaged according to the image comparison result and the weight comparison result.
In some embodiments of the present invention, in some embodiments,
the article comprises a shell and a main body, wherein the database stores images and weights of the independent shells, and the historical data stores main body types and numbers;
the process of obtaining the image and the weight corresponding to the object in the historical data comprises the following steps: acquiring information with the same main body type and serial number in the historical data according to the main body type and serial number, and then forming a required original image and original weight for the acquired information according to the image and weight with the detected time closest to the current detection time;
the process of image contrast and weight contrast comprises the following steps:
s1, comparing images, adopting a twin model to analyze and compare an original image and a current image, obtaining a similarity value between the two images, judging whether the similarity value is in a similarity value range,
s1.1, if the value of the similarity is not in the value range of the similarity, respectively acquiring images of vehicles corresponding to a current image and an original image by utilizing a twin model, acquiring the weights of the two vehicles, and entering S2;
s1.2, if the value of the similarity is in the value range of the similarity, entering S5;
s2, acquiring a current cargo image, and erasing a shell part on the current image according to the image of the vehicle corresponding to the current image to form the current cargo image;
s3, acquiring an original cargo image, and erasing a vehicle part on the original image according to the image of the vehicle corresponding to the original image to form the original cargo image;
s4, comparing the secondary images, analyzing and comparing the original cargo image and the current cargo image by adopting a twin model, obtaining the value of the similarity between the two cargo images, judging whether the value of the similarity is in the value range of the similarity,
s4.1, if the value of the similarity is not in the value range of the similarity, directly judging that the cargoes are inconsistent, and packing the cargoes;
s4.2, if the value of the similarity is in the value range of the similarity, entering S6;
s5, calculating the difference value between the original weight and the current weight, judging whether the difference value is within the error value range,
s5.1, if the difference value is not in the error value range, directly judging that the cargoes are inconsistent, and packing the cargoes;
s5.2, if the difference value is in the error value range, the goods are consistent, and the goods are not packaged;
s6, calculating the obtained difference value between the original weight and the weight of the vehicle closest to the original image and the weight of the supporting plate, judging whether the difference value is in the error value range,
s6.1, if the difference value is not in the error value range, directly judging that the cargoes are inconsistent, and packing the cargoes;
and S6.2, if the difference value is in the error value range, the goods are consistent, and the goods are not packaged.
The device for detecting the entering and exiting of the warehouse based on the twin model has the advantages that:
the X-ray imaging equipment can be directly used for imaging articles, vehicles and cargoes in the vehicles;
and the combination of the image and the weight confirms the articles, the vehicle and the goods in the vehicle, and judges whether the articles are packaged or not, so that the safety and the reliability in the transportation process are effectively improved.
Drawings
FIG. 1 is a schematic diagram of a library entry and exit detection device using a twin model in some embodiments of the present invention;
FIG. 2 is a flow chart of a comparison method of object detection based on a twinning model in some embodiments of the invention.
Detailed Description
Example 1
With reference to fig. 2, the embodiment proposes an article detection comparison method based on a twin model, which includes the following steps:
s1, establishing a database for storing historical data of detected articles, images and weights of independent shells, a value range of similarity, a value range of errors of weights and article type numbers, wherein the historical data comprises images, weights and main body types and numbers when the articles are detected before, the articles can only comprise a main body, the shells and the main bodies, the article type numbers of the articles only comprise the main body are set to be 01, and the article type numbers of the articles comprising the shells and the main body are set to be 02;
s2, inputting the article type of the article, and if the input article type number is 01, entering a step S3; if the input article type number is 02, the step S4 is entered;
s3, respectively comparing the images with the weights, and outputting a comparison result, wherein the specific process comprises the following steps:
s3.1, acquiring the current image and weight of the article;
s3.2, acquiring images and weights corresponding to the articles in the historical data;
s3.3, comparing the images, analyzing and comparing the images in the acquired historical data with the current images by adopting a twin model, acquiring a similarity value between the two images, and judging whether the similarity value is in a similarity value range or not;
s3.4, comparing the weights, calculating a difference value between the weight in the obtained historical data and the current weight, and judging whether the difference value is in the error value range;
s3.5, the value of the similarity in S3.3 is in the value range of the similarity, and the difference value in S3.4 is in the value range of the error, outputting a comparison result that the articles are consistent, not being unpacked, otherwise outputting a comparison result that the articles are inconsistent, and packing the articles;
s4, performing image comparison, adopting a twin model to analyze and compare an original image and a current image, obtaining a similarity value between the two images, judging whether the similarity value is in a similarity value range,
s4.1, if the similarity value is not in the similarity value range, respectively acquiring images of the shells corresponding to the current image and the original image by utilizing the twin model, acquiring the weights of the two shells, and entering S5;
s4.2, if the value of the similarity is in the value range of the similarity, entering S8;
s5, acquiring a current main body image, and erasing a shell part on the current image according to the image of the shell corresponding to the current image to form the current main body image;
s6, acquiring an original main body image, and erasing a shell part on the original image according to an image of a shell corresponding to the original image to form the original main body image;
s7, comparing the secondary images, analyzing and comparing the original main body image and the current main body image by adopting a twin model, obtaining the value of the similarity between the two main body images, judging whether the value of the similarity is in the value range of the similarity or not, outputting a comparison result to be inconsistent with the articles, and regulating the articles; otherwise, S9 is entered;
s8, calculating a difference value between the original weight and the current weight, judging whether the difference value is in an error value range, outputting a comparison result that the objects are inconsistent if the difference value is not in the error value range, and packaging the objects; otherwise, outputting a comparison result that the articles are consistent and are not packaged;
s9, calculating the obtained difference value between the original weight and the weight of the shell closest to the original image, judging whether the difference value is in the error value range or not, and outputting a comparison result that the objects are inconsistent and the objects are packaged; and otherwise, outputting a comparison result to be consistent with the objects, and not being unpacked.
It should be noted that, the image is a 3D image formed by imaging with an X-ray imaging device, and for an article including a housing and a main body, the 3D image includes not only the image of the housing but also the image of the main body displayed through the housing image, where the related X-ray imaging device may directly use an existing device on the market, so that a detailed description is omitted herein;
the shell image is also a 3D image acquired by the X-ray imaging equipment;
the historical data also comprises the time of the detected object, the image and the weight are correspondingly stored, and the time of the detected object is sequenced according to the sequence of the detected time; when the current detection is performed, the current detection time is acquired, and the current image and the weight are combined and stored in the historical data to form the latest historical record.
The object type of the object to be compared can be directly set before the object is executed by the object-entering and exiting warehouse detection device based on the twin model.
In some embodiments of the present invention, in some embodiments,
the process of obtaining the image and the weight corresponding to the object in the historical data comprises the following steps: and acquiring a list containing images, weights and detected times, wherein the types and the numbers of the main bodies are consistent, in the historical data according to the types and the numbers of the main bodies, and then acquiring the images and the weights, the detected times of which are closest to the current detected time, in the list, so as to form the required original images and the required original weights.
The above-mentioned determination of the similarity between two images by the twin model can be directly implemented by using the prior art, so that details are not described here.
The process of acquiring the subject image involved in S5 and S6 is:
respectively acquiring a corresponding six view according to a current 3D image, acquiring a corresponding six view according to a 3D image of a shell corresponding to the current image, acquiring a corresponding six view according to an original 3D image, and acquiring a corresponding six view according to a 3D image of a shell corresponding to the original image, wherein the six views refer to images of six visual angles including up, down, left, right, front and back;
performing image processing on the four obtained six views, wherein the image processing comprises image filtering, threshold segmentation, morphological particle filtering and sub-pixel extraction;
removing the outline of the shell on the six views corresponding to the current 3D image by applying the processed six views of the shell corresponding to the current image, obtaining the six views corresponding to the current main body, and then reconstructing the 3D image according to the six views corresponding to the current main body to obtain the current main body image;
and removing the outline of the shell on the six views corresponding to the original 3D image by applying the processed six views of the shell corresponding to the original 3D image, obtaining the six views corresponding to the current main body, and then reconstructing the 3D image according to the six views corresponding to the current main body to obtain the original main body image.
The process of acquiring the subject image in S5 and S6 may also be directly implemented by using the prior art, so that a detailed description is omitted herein.
Example 2
In combination with the content shown in fig. 1, the device for applying the device for detecting whether the warehouse enters or exits based on the twin model is provided in the embodiment, which comprises a server and a warehouse entering and exiting monitoring alarm device connected with the server,
the warehouse-in monitoring alarm device is used for monitoring vehicles entering and exiting a warehouse and cargoes in the vehicles and acquiring images and weights of the vehicles and the cargoes in the vehicles;
the server is used for storing and executing an application program of the database entering and exiting detection device based on the twin model to realize the database entering and exiting detection device based on the twin model, a main control module, a data comparison module applying the digital twin model, a storage module and a communication module are arranged in the server, the data comparison module applying the digital twin model, the storage module and the communication module are all connected with the main control module,
the communication module is used for being connected with the detection device and transmitting data;
the storage module is used for establishing a database, wherein the database stores detected historical data which are sequenced according to detection time, 3D images of vehicles, weight of the vehicles, vehicle numbers, value ranges of similarity and errors of weight, cargo types and weight of the supporting plate 42, the historical data comprises 3D images, vehicle numbers, weight, cargo types in the vehicles, cargo numbers and detection time which are correspondingly stored when the vehicles and cargoes in the vehicles are detected before, and the 3D images of the vehicles, the weights of the vehicles and the vehicle numbers which are acquired through the X-ray imaging equipment are correspondingly stored;
the data comparison module is used for comparing images and weights, feeding back comparison results to the main control module, correspondingly storing the results in the database by the main control module, and generating display instructions according to the results and transmitting the display instructions to the communication module in combination with the results.
The warehouse-in and warehouse-out monitoring alarm device is used for monitoring vehicles 7 entering and exiting the warehouse and cargoes in the vehicles 7, and comprises a base 2 and a shell 31 arranged on the base 2, wherein a channel 6 which penetrates through the front side and the rear side of the shell 31 and is used for the passing of the vehicles 7 is arranged in the shell 31, mounting seats 50 are arranged on the left side, the right side and the upper side walls of the channel 6 in three directions, X-ray imaging equipment 51 is embedded on the mounting seats 50, and a bearing weighing sensor 41 is arranged at the bottom of the channel 6.
The base 2 is formed by concrete pouring, the base 2 is internally provided with reinforcing steel bars, the tops of the reinforcing steel bars penetrate through the base 2 and are inserted into the shell 31 formed by the concrete pouring, the bottoms of the shell 31 are embedded into the base 2, and the arrangement can effectively ensure the connection tightness between the base 2 and the shell 31;
the lower part of the base 2 is buried in the tamped filling 1, and a triangular reinforcing plate 20 is arranged between the upper surface of the base 2 and the outer side surface of the shell 31.
The bottom of passageway 6 is equipped with bearing board 42, and bearing formula weighing sensor 41 sets up in the below of bearing board 42, and the vehicle is on going to bearing board 42, weighs the total weight of vehicle 7, the interior goods of vehicle 7 and bearing board 42 through bearing formula weighing sensor 41, wherein can avoid vehicle 7 and its interior goods to directly act on bearing formula weighing sensor 41 through the setting of bearing board 42, plays the effect of protection to bearing formula weighing sensor 41, strengthens bearing formula weighing sensor 41's life.
The mounting seat 50 and the shell 31 are provided with double protection sleeves, the double protection sleeves comprise a first protection sleeve 32 which is attached to the first protection sleeve 32 and fixed to the shell 31, a second protection sleeve 34 which is arranged on the inner side of the first protection sleeve 32 and connected with the mounting seat 50 is arranged between the side walls of the left and right directions and the upper three directions of the second protection sleeve 34 and the first protection sleeve 32, a buffer effect between the double protection sleeves can be enhanced, the springs are not arranged between the second protection sleeve 34 and the first protection sleeve 32 at the bottom, the bottom of the second protection sleeve 34, the bottom of the first protection sleeve 32 and the shell 31 are directly attached to each other and fixed in sequence, a bearing type weighing sensor 41 is arranged on the inner side of the second protection sleeve 34, a concrete cushion layer 40 is arranged around the bearing type weighing sensor 41, the bottom of the mounting seat 50 is leveled with the bottom of a channel 6 through the concrete cushion layer 40, and the upper surface of the filling soil 1 is leveled with the bottom of the second protection sleeve 34.
The fixing may be performed by directly using a conventional method such as a bolt.
The outer side surface of the shell 31 is also provided with an alarm connected with a server, and the warehouse-in and warehouse-out monitoring alarm device comprises two automatic rolling doors connected with the server, wherein the two automatic rolling doors are respectively installed at the front end and the rear end of the shell 31 and used for sealing the channel 6.
In some embodiments, the device further comprises a display component connected with the communication module, the display component comprises a display device and/or a monitoring terminal, and the display component is used for displaying results according to the display instruction;
the display device is arranged on one side of the detection device and is used for timely obtaining results of workers at the position of the detection device;
the monitoring terminal is used for monitoring results of workers who are not located at the position of the detection device. The safety and reliability of the article in the flowing process are further enhanced through the dual monitoring arrangement.
In a specific implementation, an alarm touch button connected to a server is mounted on the outer side surface of the housing 31, or an alarm releasing module for releasing an alarm is mounted in the display device, and a trigger is provided on the display interface of the display device and connected to the alarm releasing module.
The thickness of the housing 31 may be set directly according to the thickness of the concrete building layer currently achieving the explosion-proof effect.
The working principle of the warehouse-in and warehouse-out monitoring alarm device is as follows:
s2.1, the vehicle 17 is opened into the channel 6, the vehicle 17 is completely placed on the supporting plate 42, the X-ray imaging equipment 51 arranged on the inner wall of the channel 6 images the vehicle 17 and the goods in the vehicle 17 to acquire the current 3D images of the vehicle 17 and the goods in the vehicle 17, meanwhile, the supporting type weighing sensor 41 below the supporting plate 42 measures the supporting plate 42, the vehicle 17 and the goods in the vehicle 17 to acquire the current total weight, and meanwhile, the current detection time is acquired;
s2.2, inputting a cargo number in the current vehicle 17, and acquiring a 3D image, weight and vehicle number corresponding to the detection time closest to the current time in the same cargo number in the historical data as a sample image, sample weight and sample number;
s2.3, inputting the vehicle number of the current vehicle 17, comparing the vehicle number with the sample number, entering S2.4 if the comparison is consistent, and entering S2.5 if the comparison is inconsistent;
s2.4, respectively comparing the images with the weight, and outputting a comparison result, wherein the specific process comprises the following steps:
s2.4.1, comparing the images, namely analyzing and comparing the acquired current 3D image with the sample image by adopting a twin model, acquiring a similarity value between the two images, and judging whether the similarity value is in a similarity value range or not;
s2.4.2, comparing the weights, calculating the difference between the weight of the obtained sample and the current total weight, and judging whether the difference is within the error value range;
s2.4.3 and S2.4.1, outputting a comparison result that the articles are consistent when the value of the similarity is within the value range of the similarity and the difference value in S2.4.2 is within the value range of the error, and outputting a comparison result that the articles are inconsistent when the comparison result is not unpacked, unpacking the articles, and entering S2.10;
s2.5, acquiring the corresponding weight of the current vehicle and the 3D model of the current vehicle according to the vehicle number of the current vehicle 17, and acquiring the corresponding weight of the sample vehicle and the 3D model of the sample vehicle according to the sample number;
s2.6, acquiring a current cargo image, and erasing a shell part on the current 3D image according to a 3D model of the current vehicle to form the current cargo image;
s2.7, acquiring a cargo image of the sample, and erasing a shell part on the sample image according to a 3D model of a vehicle of the sample to form the cargo image of the sample;
s2.8, comparing the secondary images, analyzing and comparing the cargo images of the sample with the current cargo images by adopting a twin model, obtaining the value of the similarity between the two cargo images, judging whether the value of the similarity is in the value range of the similarity or not, outputting a comparison result to be inconsistent with the articles if the value of the similarity is not in the value range of the similarity, and packing the articles to enter S2.10; otherwise, S2.9 is entered;
s2.9, calculating the obtained difference value (the weight of the sample, the weight of the supporting plate 42 and the weight of the sample) and the obtained difference value (the current total weight, the weight of the supporting plate 42 and the current weight of the vehicle), judging whether the difference value is in the error value range or not, outputting a comparison result that the objects are inconsistent, and packing the objects to enter S2.10; otherwise, outputting a comparison result that the articles are consistent and are not packaged;
s2.10, the server sends out an alarm instruction, the alarm works, and sends out an alarm signal of light and/or sound, the two automatic rolling doors lower the closed channel 6, and meanwhile, the alarm signal that goods are exchanged is displayed on a display device connected with the server.
When the alarm needs to be released, the alarm is released by clicking an alarm contact button or a trigger piece on a display interface of the display device, the alarm stops working, and the rolling shutter door is lifted and reset.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that several similar modifications and improvements can be made without departing from the inventive concept, and these should also be considered as protecting the scope of the present invention.
Claims (7)
1. The warehouse-in and warehouse-out detection device based on the twin model is characterized by comprising a server and a warehouse-in and warehouse-out monitoring alarm device connected with the server,
the warehouse-in and warehouse-out monitoring alarm device comprises a base (2) and a shell (31) arranged on the base (2), wherein a channel (6) penetrating through the front side and the rear side of the shell (31) and used for passing a vehicle (7) is arranged in the shell (31), mounting seats (50) are arranged on the left side, the right side and the upper side of the channel (6), X-ray imaging equipment (51) is embedded on the mounting seats (50), a bearing weighing sensor (41) is arranged at the bottom of the channel (6), an alarm connected with a server is arranged on the outer side surface of the shell (31), the warehouse-in and warehouse-out monitoring alarm device further comprises two automatic rolling doors connected with the server, the two automatic rolling doors are respectively arranged at the front end and the rear end of the shell (31) and used for sealing the channel (6),
the X-ray imaging device (51) is used for imaging the vehicle (7) and cargoes in the vehicle (7) to form corresponding 3D images;
the supporting type weighing sensor (41) is used for weighing the weight of the vehicle (7) and the detected goods in the vehicle (7);
the server is internally provided with a main control module, a data comparison module applying the digital twin model, a storage module and a communication module, wherein the data comparison module applying the digital twin model, the storage module and the communication module are all connected with the main control module,
the communication module is used for being connected with the detection device and transmitting data;
the storage module is used for establishing a database, storing historical data of detected articles, a value range of similarity, a value range of errors of weight, a vehicle number, an image of the vehicle and the weight of the vehicle through the database, wherein the image of the vehicle, the weight of the vehicle and the vehicle number are correspondingly stored, the historical data comprises images and weights of the articles detected before, and the image of the vehicle is a 3D image formed by an X-ray imaging device without loading the acquired vehicle;
the data comparison module is used for comparing images and weights, feeding back comparison results to the main control module, correspondingly storing the results in the database by the main control module, and generating display instructions according to the results and transmitting the display instructions to the communication module in combination with the results.
2. The device for detecting the entering and exiting of the warehouse based on the twin model according to claim 1, wherein the device for detecting the entering and exiting of the warehouse comprises a display component connected with the communication module, the display component comprises a display device and/or a monitoring terminal, and the display component is used for displaying results according to display instructions;
the display device is arranged on one side of the detection device and is used for timely obtaining results of workers at the position of the detection device;
the monitoring terminal is used for monitoring results of workers who are not located at the position of the detection device.
3. The warehouse-in and warehouse-out detection device based on the twin model according to claim 1, wherein the base (2) is formed by concrete pouring, a reinforcing steel bar is arranged in the base (2), the top of the reinforcing steel bar penetrates out of the base (2) and is inserted into a shell (31) formed by concrete pouring, the bottom of the shell (31) is embedded in the base (2), the lower part of the base (2) is embedded in the tamped filling soil (1), and a triangular reinforcing plate (20) is arranged between the upper surface of the base (2) and the outer side face of the shell (31).
4. A twin model based in-out garage inspection apparatus according to claim 3, wherein the bottom of the tunnel (6) is provided with a support plate (42), the support type weighing sensor (41) is provided under the support plate (42), the vehicle runs onto the support plate (42), and the vehicle (7), the goods in the vehicle (7) and the total weight of the support plate (42) are weighed by the support type weighing sensor (41).
5. The device for detecting the entering and exiting of the warehouse based on the twin model according to claim 4, wherein the database is also stored with the object type and the weight of the supporting plate, the historical data comprises the corresponding stored vehicle number, the type of goods in the vehicle, the number of goods and the detection time, and the information stored in the historical data is sequenced according to the sequence of the detected time; when the current detection is performed, the current detection time is acquired, and the current image, the weight, the vehicle number, the type of goods in the vehicle and the goods number are combined and stored in the historical data to form the latest historical record.
6. The twin model-based in-out library inspection device according to claim 4, wherein,
be equipped with two protective sleeves between mount pad (50) and casing (31), two protective sleeves are including laminating and with the fixed first protective sheath (32) of casing (31), set up in first protective sheath (32) inboard and with second protective sheath (34) that mount pad (50) are connected, set up between the lateral wall of the left and right of second protective sheath (34) and the last three direction and first protective sheath (32) by a plurality of springs (33), the bottom of second protective sheath (34), the bottom of first protective sheath (32) and casing (31) laminating in proper order are fixed, bearing formula weighing sensor (41) set up in second protective sheath (34) inboard, bearing formula weighing sensor (41) are equipped with concrete cushion (40) all around, make level to the bottom of passageway (6) through concrete cushion (40), the bottom of mount pad (50) is connected with concrete cushion (40), the upper surface of filling out soil (1) flushes with the bottom of second protective sheath (34).
7. The detection method of the warehouse-in and warehouse-out detection device based on the twin model is characterized by comprising the following steps of:
s1, acquiring a vehicle and current images and weights corresponding to articles in the vehicle, wherein the articles comprise a shell and a main body, and the images and weights of the independent shells are stored in a database;
s2, acquiring images and weights corresponding to the articles in historical data, wherein the types, the numbers and the images and weights corresponding to the articles of the main body are stored in the historical data, and the specific process is as follows:
acquiring information with the same main body type and serial number in the historical data according to the main body type and serial number, and then forming a required original image and original weight for the acquired information according to the image and weight with the detected time closest to the current detection time;
s3, comparing the images, analyzing and comparing the original image and the current image by adopting a twin model, obtaining the value of the similarity between the two images, judging whether the value of the similarity is in the value range of the similarity,
s3.1, if the value of the similarity is not in the value range of the similarity, respectively acquiring images of the vehicles corresponding to the current image and the original image by utilizing the twin model, acquiring the weights of the two vehicles, and entering S4;
s3.2, if the value of the similarity is in the value range of the similarity, entering S7;
s4, acquiring a current cargo image, and erasing a shell part on the current image according to the image of the vehicle corresponding to the current image to form the current cargo image;
s5, acquiring an original cargo image, and erasing a vehicle part on the original image according to the image of the vehicle corresponding to the original image to form the original cargo image;
s6, comparing the secondary images, analyzing and comparing the original cargo image and the current cargo image by adopting a twin model, obtaining the value of the similarity between the two cargo images, judging whether the value of the similarity is in the value range of the similarity,
s6.1, if the value of the similarity is not in the value range of the similarity, directly judging that the cargoes are inconsistent, and packing the cargoes;
s6.2, if the value of the similarity is in the value range of the similarity, entering S8;
s7, calculating the difference value between the original weight and the current weight, judging whether the difference value is within the error value range,
s7.1, if the difference value is not in the error value range, directly judging that the cargoes are inconsistent, and packing the cargoes;
s7.2, if the difference value is in the error value range, the goods are consistent, and the goods are not packaged;
s8, calculating the obtained difference value between the original weight and the weight of the vehicle closest to the original image and the weight of the supporting plate, judging whether the difference value is within the error value range,
s8.1, if the difference value is not in the error value range, directly judging that the cargoes are inconsistent, and packing the cargoes;
and S8.2, if the difference value is in the error value range, the goods are consistent, and the goods are not packaged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219027.0A CN115294370B (en) | 2022-10-08 | 2022-10-08 | Warehouse-in and warehouse-out detection device and detection method based on twin model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219027.0A CN115294370B (en) | 2022-10-08 | 2022-10-08 | Warehouse-in and warehouse-out detection device and detection method based on twin model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115294370A CN115294370A (en) | 2022-11-04 |
| CN115294370B true CN115294370B (en) | 2023-05-09 |
Family
ID=83833763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211219027.0A Active CN115294370B (en) | 2022-10-08 | 2022-10-08 | Warehouse-in and warehouse-out detection device and detection method based on twin model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115294370B (en) |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001228A (en) * | 2020-07-08 | 2020-11-27 | 上海品览数据科技有限公司 | Video monitoring warehouse in-out counting system and method based on deep learning |
| CN112539816B (en) * | 2020-12-03 | 2022-03-01 | 西安科技大学 | Dynamic weighing correction method based on deep neural network in digital twin environment |
-
2022
- 2022-10-08 CN CN202211219027.0A patent/CN115294370B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115294370A (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11099294B2 (en) | Distributed analysis x-ray inspection methods and systems | |
| TWI267762B (en) | Apparatus and method for detecting radiation or radiation shielding in shipping containers | |
| CN110648470B (en) | Posting method and device, express cabinet and medium | |
| CN1774731B (en) | Apparatus and method for detecting radiation or radiation shielding in containers | |
| CN101532968A (en) | Vehicle check system for green channel | |
| CN113469871A (en) | Carriage loadable space detection method and device based on three-dimensional laser | |
| CN115294370B (en) | Warehouse-in and warehouse-out detection device and detection method based on twin model | |
| CN117329971B (en) | Compartment balance detection method and system based on three-dimensional laser radar | |
| CN107144332A (en) | A kind of True k Scale Weighing System and method based on instrument long-distance automatic clear | |
| JP3711839B2 (en) | Vehicle luggage state detection device | |
| JP6435572B2 (en) | Container weight calculation system and container weight calculation method | |
| KR20140001241U (en) | System for unguarded automobiles gauge control using ERP and preventing cheating | |
| JP2016102662A (en) | Container weight measuring system and container weight measuring method | |
| CN108460542B (en) | Grain depot warehouse-in and warehouse-out management method and device and computer readable storage medium | |
| EP4198463A1 (en) | Method and system for measuring weight of cargo of an articulated vehicle | |
| CN212340394U (en) | Vehicle-mounted real-time weighing data monitoring and managing platform for transport vehicle | |
| CN201438180U (en) | Green-channel vehicle checking system | |
| JPH07206118A (en) | Warehousing and discharging work control system | |
| Fomenko et al. | ORGANIZATIONAL-TACTICAL AND INFORMATION-TECHNICAL SUPPORT OF PREVENTION, DETECTION AND INVESTIGATION OF CRIMES | |
| CN116643008A (en) | Method and system for detecting hiding of human body in vehicle based on dynamic threshold | |
| Ries et al. | X-ray cargo inspection | |
| CN117094628A (en) | Intelligent transport vehicle control method, device, equipment and medium | |
| CN116977414A (en) | Cargo compartment storage state detection system, cargo compartment storage state detection program, and cargo compartment storage state detection method | |
| CN117629361A (en) | Measuring system and method provided with weighing sensor |
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 |