CN112926617A - Packaging change detection method and device, cloud computer equipment and storage medium - Google Patents
Packaging change detection method and device, cloud computer equipment and storage medium Download PDFInfo
- Publication number
- CN112926617A CN112926617A CN201911245150.8A CN201911245150A CN112926617A CN 112926617 A CN112926617 A CN 112926617A CN 201911245150 A CN201911245150 A CN 201911245150A CN 112926617 A CN112926617 A CN 112926617A
- Authority
- CN
- China
- Prior art keywords
- image
- parcel
- package
- detected
- transit point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 230000008859 change Effects 0.000 title claims abstract description 33
- 238000004806 packaging method and process Methods 0.000 title claims description 6
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012546 transfer Methods 0.000 claims abstract description 11
- 238000004590 computer program Methods 0.000 claims description 23
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 19
- 230000000875 corresponding effect Effects 0.000 description 33
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Abstract
The application relates to a package change detection method and device, cloud computer equipment and a storage medium. The method comprises the following steps: receiving a parcel image and a parcel order number sent by computer equipment at a current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point; acquiring image characteristics corresponding to the package image; determining the corresponding comparison characteristic of the package to be detected according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the transit point of the last express; and comparing the image characteristic with the comparison characteristic to determine whether the package of the to-be-detected package is changed. The method can improve the detection accuracy.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for detecting a package change, a cloud computing device, and a storage medium.
Background
In the logistics industry, often because of the irregular transportation operation of business personnel, the parcel that leads to being transported is damaged. Transportation personnel often evade liability by privately replacing damaged overpacks. Therefore, to restrict the business personnel from operating according to the work specification, the outer packaging of the package is typically inspected at each site of transport. However, most of the conventional detection methods manually check and compare the monitoring data of each site in real time to determine whether the package outer package is replaced. The manual detection mode is time-consuming and labor-consuming, and the detection precision is reduced.
Disclosure of Invention
In view of the above, it is necessary to provide a package change detection method, a package change detection apparatus, a cloud computer device, and a storage medium, which can improve detection accuracy.
A method of package change detection, the method comprising:
receiving a parcel image and a parcel order number sent by computer equipment at a current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
acquiring image characteristics corresponding to the parcel images;
determining the corresponding comparison characteristic of the parcel to be detected according to the parcel single number; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point;
and comparing the image characteristics with the comparison characteristics to determine whether the package of the package to be detected is changed.
In one embodiment, the method further comprises:
when the package of the package to be detected is determined not to be changed, storing the image characteristics of the package to be detected at the current express transit point according to the package single number;
and when the image characteristics of the to-be-detected package at the next express transit point are received, acquiring the image characteristics of the to-be-detected package at the current express transit point as the comparison characteristics of the image characteristics of the next express transit point.
In one embodiment, the acquiring image features corresponding to the package image includes:
calling a pre-trained neural network;
and embedding the package image into an array with preset dimensionality by using the neural network, wherein the obtained array is the image characteristic corresponding to the package image.
In one embodiment, before invoking the pre-trained neural network, the method further includes:
carrying out target detection on the parcel image to obtain the coordinate position of a parcel in the parcel image;
and cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
In one embodiment, the comparing the image feature with the comparison feature to determine whether the package of the parcel to be detected is altered includes:
calculating the space distance between the image characteristic and the comparison characteristic to obtain the similarity between the current express transit point and the previous express transit point of the parcel to be detected;
and when the similarity is smaller than a threshold value, determining that the package of the package to be detected is changed.
In one embodiment, the method further comprises:
and when the package of the package to be detected is determined to be changed, generating early warning information and feeding the early warning information back to the computer equipment.
A package change detection device, the device comprising:
the receiving module is used for receiving the parcel image and the parcel order number sent by the computer equipment of the current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
the acquisition module is used for acquiring the image characteristics corresponding to the parcel images;
the determining module is used for determining the corresponding comparison characteristic of the package to be detected according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point;
and the comparison module is used for comparing the image characteristics with the comparison characteristics to determine whether the package of the to-be-detected package is changed.
In one embodiment, the apparatus further comprises a save module;
the storage module is used for storing the image characteristics of the to-be-detected package at the current express transit point according to the package single number when the package of the to-be-detected package is determined not to be changed;
the obtaining module is further used for obtaining the image characteristic of the parcel to be detected at the current express transit point as the comparison characteristic of the image characteristic of the next express transit point when the image characteristic of the parcel to be detected at the next express transit point is received.
A cloud computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor is characterized in that the processor implements any one of the steps of the package change detection method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of detecting a change in a package according to any one of the preceding claims.
According to the package change detection method and device, the cloud computer equipment and the storage medium, after the parcel single number and the parcel image of the to-be-detected parcel, which are acquired by the industrial camera located at the current express transit point and sent by the computer equipment, are received, the image feature of the parcel image is obtained, the image feature of the to-be-detected parcel at the previous express transit point is determined as the comparison feature according to the parcel single number, and then the comparison feature is compared with the image feature to determine whether the package of the to-be-detected parcel is changed. The method realizes automatic detection of package change, does not need to check monitoring data by a large amount of manpower, and can improve detection accuracy.
Drawings
FIG. 1 is a diagram of an exemplary environment in which a method for detecting a change in a package may be implemented;
FIG. 2 is a schematic flow chart diagram illustrating a method for detecting a package change in one embodiment;
FIG. 3A is a schematic flow chart diagram illustrating the steps for cropping a parcel image in one embodiment;
FIG. 3B is a diagram of a package image in one embodiment;
FIG. 4 is a schematic flow chart of a package change detection method according to another embodiment;
FIG. 5 is a block diagram showing the structure of a package change detection device according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The package change detection method provided by the application can be applied to the application environment shown in fig. 1. The application environment involves an industrial camera 102, a computer device 104, and a cloud computing device 106. The industrial camera 102 and the computer device 104 communicate with each other through a network, and the computer device 104 and the cloud server 106 communicate with each other through the network. The industrial camera 102 is located at each express transit point, and the computer device 104 is a local server of each express transit point. It should be understood that each courier transit point has a corresponding industrial camera 102 and computing and device 104.
Specifically, the industrial camera 102 is configured to collect a parcel image and a parcel order number of a parcel to be detected passing through a corresponding express transit point, and then the industrial camera 102 sends the collected parcel image and parcel image to the cloud computer device 106 via the computer device 104. It should be appreciated that where the industrial camera 102 and the cloud computer device 106 are communicable, the industrial camera 102 can directly send the captured package images and the package images to the cloud computer device 106. After receiving the parcel image and the parcel order number of any transit point, the cloud computer device 106 acquires image characteristics corresponding to the parcel image; the cloud server 106 determines a comparison characteristic corresponding to the parcel to be detected according to the parcel single number; the comparison characteristic is the image characteristic of the parcel to be detected at the transit point of the last express; cloud computing device 106 compares the image characteristics to the comparison characteristics to determine whether the packaging of the package to be detected has changed. The computer device 104 and the cloud computer device 106 may be terminals or servers, the terminals may be but are not limited to various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the servers may be implemented by independent servers or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a package change detection method is provided, which is described by taking the method as an example applied to the cloud computing device in fig. 1, and includes the following steps:
step S202, receiving a parcel image and a parcel order number sent by computer equipment at a current express transit point; the parcel image and the parcel single number are acquired by an industrial camera located at the current express transit point.
The express transfer point is a place where the express passes in the transportation process, and comprises an express sending place, a transfer place, an arrival place and the like. The parcel image is obtained by image acquisition of the parcel to be detected, and the parcel single number is the unique identifier of the parcel. The packages to be detected are packages currently subjected to change inspection.
Specifically, after the express reaches the current express transit point from the last express transit point, the industrial camera arranged at the current express transit point performs image acquisition and single number scanning on the express, and a parcel image and a parcel single number of a parcel to be detected are obtained. Then, the industrial camera sends the parcel image and the parcel single number to the computer equipment of the current express transit point, and the computer equipment sends the parcel image and the parcel single number to the cloud computer equipment.
And step S204, acquiring image characteristics corresponding to the package image.
The image features refer to image information extracted from an image, and the common image features include color features, texture features, shape features, spatial relationship features and the like.
Specifically, after a parcel image of a parcel to be detected is received, digital image processing is performed on the parcel image, and image features of the parcel image are extracted and obtained by using a corresponding image feature extraction algorithm. The feature extraction algorithm may employ any one of a number of methods including, but not limited to, one or more combinations of color histograms, signal processing methods, modeling methods, geometric parameter methods, image segmentation extraction methods, key point-based feature descriptors, and edge extraction methods.
In one embodiment, in step S204, the acquiring image features corresponding to the package image specifically includes: calling a pre-trained neural network; and embedding the package image into an array with preset dimensionality by using a neural network, wherein the obtained array is the image characteristic corresponding to the package image.
Specifically, the neural network is a convolutional neural network trained in advance according to training samples and a loss function and used for extracting image features of the package image. The training sample is a training set made of the same image wrapped in different fields. In this embodiment, the loss function is preferably cross entropy loss and triplet loss, and the final result of the loss function is a weighted sum of the cross entropy loss and the triplet loss. The weight ratio of cross entry loss (the weight ratio of the cross and triple loss) can be set according to the actual situation.
When the image characteristics are obtained, the pre-trained neural network can be called, and the package image is input into the neural network. And carrying out operations such as convolution pooling on the parcel image by a neural network so as to embed the parcel image into a space with preset dimensionality. And the obtained array of the preset dimensionality is the image characteristic of the package image. The preset dimension can also be set according to the actual situation, and the preset dimension is preferably 1024 in the embodiment. Then, the image feature in this embodiment is a 1024-dimensional array.
Step S206, determining the corresponding contrast characteristics of the to-be-detected package according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point.
The cloud computer equipment stores image characteristics corresponding to express at each express transfer point, and the parcel single number is unique. Therefore, the image characteristics of the same express at different transit points are stored in a correlated manner through the parcel single number. The comparison feature is an image feature compared with an image feature of the parcel to be detected, and should be an image feature corresponding to the express transit points before the current express transit point, preferably an image feature corresponding to the last express transit point.
Specifically, since the image features of the express at each express transit point are stored in association with the parcel list number, after the image features of the parcel image are extracted, the comparison features can be obtained from the database storing the image features through the parcel list number corresponding to the parcel image.
And S208, comparing the image characteristics with the comparison characteristics to determine whether the package of the to-be-detected package is changed.
Specifically, after the image feature of the package image and the contrast feature corresponding to the image feature are acquired, similarity comparison is performed on the image feature and the contrast feature. The comparison of the similarity may be performed by any method, including but not limited to histogram matching, matrix decomposition, feature point-based image similarity calculation, and the like. When the similarity of the two is higher than a preset threshold value, it can be determined that the model of the to-be-detected package at the current express transit point is not different from the template corresponding to the previous express transit point, and the package of the to-be-detected package is not changed. And when the similarity of the two is higher than a preset threshold value, the fact that the pattern of the to-be-detected package at the current express transit point is different from the template corresponding to the last express transit point is shown, and the package of the to-be-detected package may have a change condition.
In one embodiment, the step S208 of comparing the image characteristic with the comparison characteristic and determining whether the package of the parcel to be detected is altered specifically includes: calculating the space distance between the image characteristic and the comparison characteristic to obtain the similarity between the current express transit point and the previous express transit point of the parcel to be detected; and when the similarity is smaller than the threshold value, determining that the package of the package to be detected is changed.
Specifically, the spatial distance between the image feature and the comparison feature is calculated through a spatial distance algorithm, and the obtained spatial distance is the similarity between the image feature and the comparison feature, namely the similarity between the current express transit point and the previous express transit point of the parcel to be detected. The calculation of spatial distance includes, but is not limited to, Euclidean distance, Manhattan distance, Chebyshev distance, cosine distance, etc. In the present embodiment, the euclidean distance is prioritized.
And calculating by using a calculation formula of the Euclidean distance to obtain the Euclidean distance between the 1024-dimensional image feature and the 1024-dimensional contrast feature. In general, smaller values of the obtained distance indicate more similarity. In the embodiment, the Euclidean distance value of the image characteristic and the comparison characteristic is compared with the preset threshold, when the Euclidean distance value is smaller than the preset threshold, the similarity between the image characteristic and the comparison characteristic is represented, the parcel to be detected is similar to the previous express transit point in the current express, and the parcel to be detected is not subjected to external package change.
In the package change detection method, after a parcel single number and a parcel image of a parcel to be detected, which are acquired by an industrial camera located at a current express transit point and sent by a computer device, are received, the image characteristics of the parcel image are acquired, the image characteristics of the parcel to be detected at the last express transit point are determined as comparison characteristics according to the parcel single number, and then the comparison characteristics and the image characteristics are compared to determine whether the package of the parcel to be detected is changed. The method realizes automatic detection of package change, does not need to check monitoring data by a large amount of manpower, and can improve detection accuracy.
In one embodiment, after step S208, when it is determined that the package of the package to be detected is not changed, storing the image feature of the package to be detected at the current express transit point according to the package order number; when the image characteristics of the package to be detected at the next express transit point are received, the image characteristics of the package to be detected at the current express transit point are obtained and used as the comparison characteristics of the image characteristics of the next express transit point.
Specifically, when the external package of the to-be-detected package reaching the current express transit point is determined not to be changed according to the comparison, the image characteristics of the to-be-detected package at the current express transit point are associated and mapped with the package single number, and then the image characteristics and the package single number are stored in the database. When the express is transported to the next express transit point, the image characteristics can be obtained from the database according to the parcel order number and used as the comparison characteristics. So as to compare with the image characteristics of the next express transit point to determine whether the package is changed during the transportation process.
In one embodiment, when it is determined that the external package of the to-be-detected package reaching the current express transit point is changed, early warning information can be generated, wherein the early warning information comprises the package order number of the changed package. And then, returning the early warning information comprising the parcel order number to the computer equipment corresponding to the express transit point for informing the staff of the express transit point to check.
In one embodiment, as shown in FIG. 3A, before acquiring the image feature of the parcel image, the method further comprises the following steps:
step S302, carrying out target detection on the parcel image to obtain the coordinate position of the parcel in the parcel image;
and step S304, cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
Specifically, the object detection algorithm, for example, SSD (Single Shot multi box Detector) object detection algorithm, performs object detection on the parcel image collected by the industrial camera, and obtains the coordinate position of the parcel in the collected parcel image. And then, positioning the parcel from the acquired parcel image according to the coordinate position, and cutting an image area where the parcel is located from the acquired parcel image to obtain a parcel area image. The parcel region image may be understood as an image cut from the captured parcel image that includes only parcels. Referring to fig. 3B, the left image is a parcel image captured by an industrial camera, including parcels and background. The right image is the parcel area image that includes only parcels. And taking the parcel area image only including the parcel as a final parcel image, and acquiring the image characteristics of the final parcel image. Additionally, in order for the package image size input to the neural network to satisfy the image size received by the neural network, the package image whose image size does not satisfy 224 × 224 size may be scaled to 224 × 224. In this embodiment, because the original parcel image collected by the industrial camera usually includes a large number of background areas in addition to the parcels, the parcel image including only the parcels is obtained by cutting the collected original parcel image through target detection in this embodiment, so that the influence of the background areas on the detection is removed, and the accuracy of the detection is improved.
In one embodiment, as shown in fig. 4, another package change detection method is provided, which is described by taking the method as an example applied to fig. 1, and includes the following steps:
s1, the industrial camera 102 collects the parcel image and the parcel single number of the parcel to be detected,
s2, the industrial camera 102 sends the package image and the package order number to the computer device 104.
S3, the computer device 104 receives the parcel image and the parcel form number and obtains the image characteristics of the parcel image.
Specifically, the SSD destination detection algorithm is used to detect the coordinate location of the package on the package image from the package image. And cutting the image area including the package from the package image according to the coordinate position to obtain a final package image. And calling a preset neural network to embed the package image into a 1024-dimensional array to obtain image characteristics.
S4, computer device 104 sends the image feature and the parcel ticket number to cloud computer device 106.
And S5, the cloud computer device 106 acquires the contrast characteristics of the image characteristics according to the received parcel single number, and compares the image characteristics with the contrast characteristics to determine whether the package of the parcel to be detected is changed.
Specifically, the cloud computer device 106 compares the obtained euclidean distance value with the threshold value by calculating the euclidean distance between the image feature and the comparison feature. And when the Euclidean distance value is larger than or equal to the threshold value, determining that the image characteristics are not similar to the comparison characteristics, and indicating that the package of the package to be detected is changed after the package is transported from the last express transit point to the current express transit point. And when the Euclidean distance value is smaller than the threshold value, determining that the image characteristics are similar to the comparison characteristics, and indicating that the package is not changed when the package to be detected is transported from the last express transit point to the current express transit point.
S6, when the remote computer device 106 determines that the packaging has changed, generating early warning information to feed back to the computer device 104.
In this embodiment, package detection work is completed through cooperation of local computer equipment of express delivery transfer point and cloud computer equipment, so that burden of the cloud computer equipment is reduced, and processing efficiency is improved.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a package change detecting device including: a receiving module 502, an obtaining module 504, a determining module 506, and a comparing module 508, wherein:
a receiving module 502, configured to receive a parcel image and a parcel order number sent by a computer device at a current express transit point; the parcel image and the parcel single number are acquired by an industrial camera located at the current express transit point.
The obtaining module 504 is configured to obtain an image feature corresponding to the package image.
A determining module 506, configured to determine, according to the parcel single number, a comparison characteristic corresponding to the parcel to be detected; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point.
A comparing module 508, configured to compare the image characteristic with the comparison characteristic, and determine whether the package of the package to be detected is changed.
In one embodiment, the package change detection device further includes a storage module, configured to store, according to the parcel single number, an image feature that the package to be detected is located at the current express transit point when it is determined that the package of the package to be detected is not changed.
The acquisition module is further used for acquiring the image characteristics of the parcel to be detected at the current express transit point as the comparison characteristics of the image characteristics of the next express transit point when the image characteristics of the parcel to be detected at the next express transit point are received.
In one embodiment, the obtaining module is further configured to call a pre-trained neural network; and embedding the package image into an array with preset dimensionality by using a neural network, wherein the obtained array is the image characteristic corresponding to the package image.
In one embodiment, the obtaining module is further configured to perform target detection on the parcel image to obtain a coordinate position of a parcel in the parcel image; and cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
In one embodiment, the comparison module is further configured to calculate a spatial distance between the image feature and the comparison feature, and obtain a similarity between the current express transit point and the previous express transit point of the package to be detected; and when the similarity is smaller than the threshold value, determining that the package of the package to be detected is changed.
In one embodiment, the package change detection apparatus further includes a feedback module, configured to generate and feed back the warning information to the computer device when it is determined that the package of the package to be detected is changed.
For the specific limitation of the package change detection device, reference may be made to the above limitation of the package change detection method, which is not described herein again. The modules in the package change detection apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device or a cloud computer device is provided, and both the computer device and the cloud computer device may be servers, and the internal structure diagram of each of the computer device and the cloud computer device may be as shown in fig. 6. The computer equipment and the cloud computer equipment respectively comprise a processor, a memory, a network interface and a database which are connected through a system bus. Wherein the computer device and the processor of the cloud computing device are configured to provide computing and control capabilities. The memories of the computer device and the cloud computer device comprise nonvolatile storage media and internal memories. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing the parcel images and the parcel list numbers, and the database of the cloud computer equipment is used for storing data such as image characteristics. The network interface of the cloud computer device is used for being connected and communicated with external computer devices through a network. The computer program is executed by a processor to implement a method of package change detection.
Those skilled in the art will appreciate that the structure shown in fig. 6 is a block diagram of only a portion of the structure related to the present application, and does not constitute a limitation on the computer device or the cloud computing device to which the present application is applied, and a specific computer device or cloud computing device may include more or less components than those shown in the figure, or combine some components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
receiving a parcel image and a parcel order number sent by computer equipment at a current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
acquiring image characteristics corresponding to the package image;
determining the corresponding comparison characteristic of the package to be detected according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the transit point of the last express;
and comparing the image characteristic with the comparison characteristic to determine whether the package of the to-be-detected package is changed.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the package of the package to be detected is determined not to be changed, storing the image characteristics of the package to be detected at the current express transit point according to the package single number.
The acquisition module is further used for acquiring the image characteristics of the parcel to be detected at the current express transit point as the comparison characteristics of the image characteristics of the next express transit point when the image characteristics of the parcel to be detected at the next express transit point are received.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
calling a pre-trained neural network; and embedding the package image into an array with preset dimensionality by using a neural network, wherein the obtained array is the image characteristic corresponding to the package image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out target detection on the parcel image to obtain the coordinate position of a parcel in the parcel image; and cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
calculating the space distance between the image characteristic and the comparison characteristic to obtain the similarity between the current express transit point and the previous express transit point of the parcel to be detected; and when the similarity is smaller than the threshold value, determining that the package of the package to be detected is changed.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the package of the package to be detected is determined to be changed, generating early warning information and feeding the early warning information back to the computer equipment.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving a parcel image and a parcel order number sent by computer equipment at a current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
acquiring image characteristics corresponding to the package image;
determining the corresponding comparison characteristic of the package to be detected according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the transit point of the last express;
and comparing the image characteristic with the comparison characteristic to determine whether the package of the to-be-detected package is changed.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and when the package of the package to be detected is determined not to be changed, storing the image characteristics of the package to be detected at the current express transit point according to the package single number.
The acquisition module is further used for acquiring the image characteristics of the parcel to be detected at the current express transit point as the comparison characteristics of the image characteristics of the next express transit point when the image characteristics of the parcel to be detected at the next express transit point are received.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calling a pre-trained neural network; and embedding the package image into an array with preset dimensionality by using a neural network, wherein the obtained array is the image characteristic corresponding to the package image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out target detection on the parcel image to obtain the coordinate position of a parcel in the parcel image; and cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating the space distance between the image characteristic and the comparison characteristic to obtain the similarity between the current express transit point and the previous express transit point of the parcel to be detected; and when the similarity is smaller than the threshold value, determining that the package of the package to be detected is changed.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and when the package of the package to be detected is determined to be changed, generating early warning information and feeding the early warning information back to the computer equipment.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of package change detection, the method comprising:
receiving a parcel image and a parcel order number sent by computer equipment at a current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
acquiring image characteristics corresponding to the parcel images;
determining the corresponding comparison characteristic of the parcel to be detected according to the parcel single number; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point;
and comparing the image characteristics with the comparison characteristics to determine whether the package of the package to be detected is changed.
2. The method of claim 1, further comprising:
when the package of the package to be detected is determined not to be changed, storing the image characteristics of the package to be detected at the current express transit point according to the package single number;
and when the image characteristics of the to-be-detected package at the next express transit point are received, acquiring the image characteristics of the to-be-detected package at the current express transit point as the comparison characteristics of the image characteristics of the next express transit point.
3. The method of claim 1, wherein the obtaining image features corresponding to the package images comprises:
calling a pre-trained neural network;
and embedding the package image into an array with preset dimensionality by using the neural network, wherein the obtained array is the image characteristic corresponding to the package image.
4. The method of claim 3, wherein before invoking the pre-trained neural network, further comprising:
carrying out target detection on the parcel image to obtain the coordinate position of a parcel in the parcel image;
and cutting the parcel image according to the coordinate position of the parcel to obtain a parcel area image, and taking the parcel area image as the parcel image.
5. The method of claim 1, wherein comparing the image characteristic to the comparison characteristic to determine whether the packaging of the package to be detected is altered comprises:
calculating the space distance between the image characteristic and the comparison characteristic to obtain the similarity between the current express transit point and the previous express transit point of the parcel to be detected;
and when the similarity is smaller than a threshold value, determining that the package of the package to be detected is changed.
6. The method of claim 1, further comprising:
and when the package of the package to be detected is determined to be changed, generating early warning information and feeding the early warning information back to the computer equipment.
7. A package change detection device, the device comprising:
the receiving module is used for receiving the parcel image and the parcel order number sent by the computer equipment of the current express transfer point; the parcel image and the parcel single number are acquired by an industrial camera positioned at the current express transit point;
the acquisition module is used for acquiring the image characteristics corresponding to the parcel images;
the determining module is used for determining the corresponding comparison characteristic of the package to be detected according to the package single number; the comparison characteristic is the image characteristic of the parcel to be detected at the last express transit point;
and the comparison module is used for comparing the image characteristics with the comparison characteristics to determine whether the package of the to-be-detected package is changed.
8. The apparatus of claim 6, further comprising a save module;
the storage module is used for storing the image characteristics of the to-be-detected package at the current express transit point according to the package single number when the package of the to-be-detected package is determined not to be changed;
the obtaining module is further used for obtaining the image characteristic of the parcel to be detected at the current express transit point as the comparison characteristic of the image characteristic of the next express transit point when the image characteristic of the parcel to be detected at the next express transit point is received.
9. Cloud computing device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911245150.8A CN112926617A (en) | 2019-12-06 | 2019-12-06 | Packaging change detection method and device, cloud computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911245150.8A CN112926617A (en) | 2019-12-06 | 2019-12-06 | Packaging change detection method and device, cloud computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112926617A true CN112926617A (en) | 2021-06-08 |
Family
ID=76162017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911245150.8A Pending CN112926617A (en) | 2019-12-06 | 2019-12-06 | Packaging change detection method and device, cloud computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112926617A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005067586A2 (en) * | 2004-01-06 | 2005-07-28 | Thomson Licensing | Improved techniques for detecting, analyzing, and using visible authentication patterns |
| CN102722729A (en) * | 2011-03-22 | 2012-10-10 | 柯尼卡美能达美国研究所有限公司 | Method of detection document alteration by comparing characters using shape features of characters |
| US20140279596A1 (en) * | 2013-03-14 | 2014-09-18 | Coreorient Oy | System and method for managing transportation and storage of goods |
| CN104616297A (en) * | 2015-01-26 | 2015-05-13 | 山东省计算中心（国家超级计算济南中心） | Improved SIFI algorithm for image tampering forensics |
| CN107016516A (en) * | 2015-09-25 | 2017-08-04 | 手持产品公司 | System for wrapping up situation through transport monitoring |
| CN107025424A (en) * | 2010-03-10 | 2017-08-08 | 智能连接科技私人有限公司 | The method that label, the method distorted in detection packaging and article confirm |
| CN107818322A (en) * | 2017-10-13 | 2018-03-20 | 上海眼控科技股份有限公司 | A kind of vehicle VIN code tampering detection system and methods for vehicle annual test |
| CN108780596A (en) * | 2016-02-29 | 2018-11-09 | 路标株式会社 | Information processing system |
| CN109063694A (en) * | 2018-09-12 | 2018-12-21 | 北京科技大学 | A kind of video object detection recognition method |
| CN109923570A (en) * | 2016-10-19 | 2019-06-21 | Pa·科特公司 | System for dispensing object by the individual in community, wherein monitoring content by imaging when transfer is wrapped up between individual |
| CN110033018A (en) * | 2019-03-06 | 2019-07-19 | 平安科技（深圳）有限公司 | Shape similarity judgment method, device and computer readable storage medium |
| WO2019218774A1 (en) * | 2018-05-14 | 2019-11-21 | 腾讯科技（深圳）有限公司 | Object recognition method and device, and storage medium |
| CN110516100A (en) * | 2019-08-29 | 2019-11-29 | 武汉纺织大学 | A kind of calculation method of image similarity, system, storage medium and electronic equipment |
-
2019
- 2019-12-06 CN CN201911245150.8A patent/CN112926617A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005067586A2 (en) * | 2004-01-06 | 2005-07-28 | Thomson Licensing | Improved techniques for detecting, analyzing, and using visible authentication patterns |
| CN107025424A (en) * | 2010-03-10 | 2017-08-08 | 智能连接科技私人有限公司 | The method that label, the method distorted in detection packaging and article confirm |
| CN102722729A (en) * | 2011-03-22 | 2012-10-10 | 柯尼卡美能达美国研究所有限公司 | Method of detection document alteration by comparing characters using shape features of characters |
| US20140279596A1 (en) * | 2013-03-14 | 2014-09-18 | Coreorient Oy | System and method for managing transportation and storage of goods |
| CN104616297A (en) * | 2015-01-26 | 2015-05-13 | 山东省计算中心（国家超级计算济南中心） | Improved SIFI algorithm for image tampering forensics |
| CN107016516A (en) * | 2015-09-25 | 2017-08-04 | 手持产品公司 | System for wrapping up situation through transport monitoring |
| CN108780596A (en) * | 2016-02-29 | 2018-11-09 | 路标株式会社 | Information processing system |
| CN109923570A (en) * | 2016-10-19 | 2019-06-21 | Pa·科特公司 | System for dispensing object by the individual in community, wherein monitoring content by imaging when transfer is wrapped up between individual |
| CN107818322A (en) * | 2017-10-13 | 2018-03-20 | 上海眼控科技股份有限公司 | A kind of vehicle VIN code tampering detection system and methods for vehicle annual test |
| WO2019218774A1 (en) * | 2018-05-14 | 2019-11-21 | 腾讯科技（深圳）有限公司 | Object recognition method and device, and storage medium |
| CN109063694A (en) * | 2018-09-12 | 2018-12-21 | 北京科技大学 | A kind of video object detection recognition method |
| CN110033018A (en) * | 2019-03-06 | 2019-07-19 | 平安科技（深圳）有限公司 | Shape similarity judgment method, device and computer readable storage medium |
| CN110516100A (en) * | 2019-08-29 | 2019-11-29 | 武汉纺织大学 | A kind of calculation method of image similarity, system, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035299B (en) | Target tracking method and device, computer equipment and storage medium | |
| CN106446816B (en) | Face recognition method and device | |
| CN110738236B (en) | Image matching method and device, computer equipment and storage medium | |
| CN110569341B (en) | Method and device for configuring chat robot, computer equipment and storage medium | |
| WO2020062702A1 (en) | Method and device for sending text messages, computer device and storage medium | |
| CN110706261A (en) | Vehicle violation detection method and device, computer equipment and storage medium | |
| CN111353540B (en) | Commodity category identification method and device, electronic equipment and storage medium | |
| CN110660078B (en) | Object tracking method, device, computer equipment and storage medium | |
| CN111858977B (en) | Bill information acquisition method, device, computer equipment and storage medium | |
| CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
| CN113255651A (en) | Package security check method, device and system, node equipment and storage device | |
| CN111372042A (en) | Fault detection method and device, computer equipment and storage medium | |
| CN110889341A (en) | Form image recognition method and device based on AI (Artificial Intelligence), computer equipment and storage medium | |
| CN110163183B (en) | Target detection algorithm evaluation method and device, computer equipment and storage medium | |
| CN111191706A (en) | Picture identification method, device, equipment and storage medium | |
| CN112926617A (en) | Packaging change detection method and device, cloud computer equipment and storage medium | |
| CN112579810A (en) | Printed circuit board classification method and device, computer equipment and storage medium | |
| CN112308836B (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN112785595B (en) | Target attribute detection, neural network training and intelligent driving method and device | |
| CN114359918A (en) | Bill information extraction method and device and computer equipment | |
| CN110781056A (en) | Screen detection method and device, computer equipment and storage medium | |
| CN111079575A (en) | Material identification method and system based on packaging image characteristics | |
| CN113780131B (en) | Text image orientation recognition method, text content recognition method, device and equipment | |
| CN113837287B (en) | Certificate abnormal information identification method, device, equipment and medium | |
| CN115995060A (en) | Personnel scheduling method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |