CN111626981A - Method and device for identifying category of goods to be detected - Google Patents
Method and device for identifying category of goods to be detected Download PDFInfo
- Publication number
- CN111626981A CN111626981A CN202010285781.9A CN202010285781A CN111626981A CN 111626981 A CN111626981 A CN 111626981A CN 202010285781 A CN202010285781 A CN 202010285781A CN 111626981 A CN111626981 A CN 111626981A
- Authority
- CN
- China
- Prior art keywords
- category
- detected
- container
- goods
- cargo
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 240000004282 Grewia occidentalis Species 0.000 claims abstract description 11
- 238000012795 verification Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 abstract description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method and a device for identifying the category of goods to be detected, wherein the method comprises the following steps: acquiring a front image of the whole cargo to be detected, and inputting the front image into a segmentation model to obtain a segmented image of the cargo box to be detected; the segmentation model is obtained after training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance; selecting any one of the segmented images of the container to be detected, and inputting the selected image into the identification model to obtain a first cargo category corresponding to the image of the container to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label. The method and the device provided by the embodiment of the invention avoid the problems of large and complex calculation amount in the process of identifying the goods category and improve the accuracy and efficiency of identification.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for identifying the category of goods to be detected.
Background
With the integration of the world economy, more foreign rapid consumer goods companies enter China, and meanwhile, domestic manufacturers grow up step by step, so that the market competition is intensified day by day. Since fast-moving consumer products are impulse purchases, consumers make an impromptu purchasing decision, and thus, the appearance and packaging of the product plays a crucial role in sales. In order to distinguish various products and promote product sales, the packaging of the products needs to be different, and as the fast-moving products belong to visual products, the packaging has more patterns and smaller difference of character information, and the difference of the product types and the difference of characters is difficult.
In traditional logistics storage, the article information of the goods is acquired and registered, workers are required to use the handheld code scanning machine to scan and register bar codes of goods box body representation article specification information in real time, the manual operation work efficiency is relatively low, the cost is high, and the requirements for characteristics of short circulation period of fast-moving goods, high consumption speed and the like are difficult to meet. At present, the goods are generally classified by recognizing the description difference of characters on the surface of the box body, scanning a bar code or a two-dimensional code containing goods information of the goods box body, a traditional image comparison method and the like. The bar code identification technology is that a coded bar code or a two-dimensional code is attached to the surface of a box body, and a special scanning reader-writer is used for transmitting information to the scanning reader-writer from bar codes through optical signals; the image of the image contrast method generally adopts a spectral line image, which is also called an analysis image, and the image is obtained by scientifically detecting and analyzing the internal and external properties and characteristics of an object by using instruments and equipment. And a unique observation and identification method is adopted to analyze the difference and the identity of the spectral line characteristics. The method specifically comprises a feature comparison method, a feature combination method, a geometric construction method, an overlap comparison (feature overlap method) and a comprehensive comparison.
For fast-moving products which take patterns as main expression forms, effective information which can be output by characters is few, and the method can not be suitable for products which have different patterns and the same characters; the field of view recognizable by the bar code recognition technology is small, and the position of the bar code needs to be determined in advance, so that the detection and recognition are generally carried out in a manual handheld mode, and the efficiency is low; the traditional image comparison method needs to process the acquired cargo image by using an image analysis instrument, and has the disadvantages of complex process and high cost.
Therefore, how to avoid the problems of complex process, large calculation amount and high cost of identifying the goods category based on the visual information, and improve the accuracy and efficiency of identification still remains a problem to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying a goods category to be detected, which are used for solving the problems of complex identification process, large calculated amount, high cost and low accuracy of the goods category based on image processing in the prior art.
In a first aspect, an embodiment of the present invention provides a method for identifying a category of goods to be detected, including:
acquiring a front image of the whole cargo to be detected, and inputting the front image into a segmentation model to obtain a segmented image of the cargo box to be detected;
the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance;
selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain a first cargo category corresponding to the image of the container to be detected;
the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
Preferably, the method further comprises:
and acquiring a category identifier corresponding to the first goods category according to a pre-stored corresponding relationship between the goods category and the category identifier.
Preferably, the method further comprises:
acquiring the height of the whole-support cargo by adopting a laser range finder, obtaining the layer number of the whole-support cargo based on the height and the segmented image of the container to be detected, and calculating the height of a single container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category; alternatively, the first and second electrodes may be,
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
Preferably, in the method, the selecting any one of the segmented container images to be detected, and inputting an identification model to obtain a first cargo category corresponding to the container image to be detected specifically includes:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected.
In a second aspect, an embodiment of the present invention provides an apparatus for identifying a category of goods to be detected, including:
the first input unit is used for acquiring a front image of the whole to-be-detected cargo and inputting the front image into the segmentation model to obtain a segmented to-be-detected cargo box image; the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance;
the second input unit is used for selecting any one of the segmented container images to be detected and inputting the identification model to obtain a first cargo category corresponding to the container image to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
Preferably, the apparatus further comprises: the identification unit is used for identifying the unit,
and the category identifier corresponding to the first goods category is obtained according to the pre-stored correspondence between the goods category and the category identifier.
Preferably, the apparatus further comprises: the unit of verification is a unit of verification,
the height measuring device is used for acquiring the height of the whole-tray goods by adopting a laser range finder, obtaining the layer number of the whole-tray goods based on the height and the segmented images of the containers to be detected, and calculating the height of each container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category;
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
Preferably, in the device, the selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain the first cargo category corresponding to the image of the container to be detected specifically includes:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method for identifying the category of goods to be detected according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for identifying a category of goods to be detected as provided in the first aspect.
According to the method and the device provided by the embodiment of the invention, the front image of the entire-support cargo is input into the segmentation model to obtain the segmented cargo box image, any one of the cargo box images is input into the recognition model to obtain the category of the cargo to be detected, wherein the segmentation model and the recognition model are obtained by training on the basis of a large number of samples and labels by using the machine learning principle, the problem that the calculation amount of a traditional image comparison method is large and complicated can be avoided by recognizing the category of the cargo through the pre-trained model, and meanwhile, the model trained through a large number of samples and labels can also ensure the accuracy and the efficiency of recognition. Therefore, the method and the device provided by the embodiment of the invention can avoid the problems of large and complex calculation amount in the process of identifying the goods category, and simultaneously improve the accuracy and efficiency of identification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying categories of goods to be detected according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for identifying categories of goods to be detected according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
The existing identification method for goods categories based on image processing generally has the problems of large calculated amount, high complexity, low identification accuracy and low efficiency of image identification. Accordingly, the embodiment of the invention provides a method for identifying the category of goods to be detected. Fig. 1 is a schematic flowchart of a method for identifying a category of goods to be detected according to an embodiment of the present invention, as shown in fig. 1, the method includes:
Specifically, the goods are carried in or out in the form of a whole pallet when entering or exiting the warehouse, and meanwhile, the goods in the whole pallet belong to the same category by default. The surface of the whole-support goods, which is parallel to the dragging moving direction of the goods and is vertical to the ground, is the front surface of the whole-support goods, namely the surface of the whole-support goods, which is vertical to the warehouse door when the whole-support goods are moved into the warehouse. Generally, when goods enter and exit a warehouse, front images of the whole trusteeship are collected to identify the type of the goods. Therefore, after the front images of the entire pallets are captured, each container image in the front images is firstly divided, that is, all containers and the background are firstly distinguished, and then the containers are distinguished. And inputting the collected front image of the whole support to-be-detected goods into the segmentation model, so as to obtain the segmented image of the container to be detected. The segmentation model is obtained by training based on a sample front image of the entire truer goods and four-corner coordinates of each container marked on the sample front image in advance. The method comprises the steps of carrying out segmentation model training in advance, wherein a training sample is a front image of a large number of collected whole-pallet cargos, coordinates of four corners of each container are marked on the front image of the sample as training labels, the segmentation model obtained after training can segment the input front image of the whole-pallet cargos to obtain four-corner coordinates of each container on the front image, and outputting an image of the container to be detected after segmentation.
Specifically, any one of the segmented images of the container to be detected is input into the recognition model to obtain a first cargo category corresponding to the image of the container to be detected, that is, the image of the container to be detected is input into the recognition model to obtain the first cargo category corresponding to the image of the container. The recognition model is obtained after training based on sample container images and predetermined cargo category labels, namely when the recognition model is trained, a large number of container images are used as samples, and cargo categories are labeled for the sample container images to form training labels, so that the categories of cargos corresponding to the container images can be accurately recognized through the trained recognition model. And finally, taking the first goods category as the category of the goods to be detected.
According to the method provided by the embodiment of the invention, the front image of the whole goods is input into the segmentation model to obtain the segmented container image, and any one of the container images is input into the recognition model to obtain the category of the goods to be detected, wherein the segmentation model and the recognition model are obtained by training on the basis of a large number of samples and labels by using the machine learning principle, the problem that the traditional image comparison method is large in calculation amount and complex can be avoided by recognizing the category of the goods through the pre-trained model, and meanwhile, the model trained through a large number of samples and labels can also ensure the accuracy and efficiency of recognition. Therefore, the method provided by the embodiment of the invention can avoid the problems of large and complex calculation amount in the process of identifying the goods category, and simultaneously improve the accuracy and efficiency of identification.
Based on the above embodiment, the method further includes:
and acquiring a category identifier corresponding to the first goods category according to a pre-stored corresponding relationship between the goods category and the category identifier.
In particular, when performing the category identification, it is also necessary to output the category identification of the goods, and the category identification of the goods is usually described by using an 8-bit "14" code, for example, two different categories of category identifications can be distinguished as "14220011" and "14852212". Because the corresponding relation between the goods category and the category identification is stored in advance, after the goods category is identified, the corresponding relation table between the goods category and the category identification is searched, and the category identification corresponding to the goods can be obtained. The goods are assigned with the category identification corresponding to the goods category, so that the categories of the goods can be conveniently recorded.
Based on any one of the above embodiments, the method further includes:
acquiring the height of the whole-support cargo by adopting a laser range finder, obtaining the layer number of the whole-support cargo based on the height and the segmented image of the container to be detected, and calculating the height of a single container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category;
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
Specifically, the category of the goods to be detected is identified and then verified, if the verification is passed, the category of the goods to be detected is maintained as the first goods category, and if the verification is not passed, the category of the goods is identified again. The specific checking process is that the height of the whole-support goods to be detected is measured through the laser range finder, when the front image of the goods to be detected is divided through the dividing model, the obtained coordinates of the four corners of each container can distinguish all containers from the background, and different containers are distinguished at the same time, so that the number of layers of the containers in the vertical direction can be obtained, and the height of the whole-support goods to be detected, which is measured through the laser range finder, is divided by the number of layers of the containers in the vertical direction to obtain the height of a single container to be detected; and then, according to the corresponding relation between the pre-stored goods category and the height of the container, the height of the container corresponding to the first goods category is searched, if the height of a single container to be detected is equal to the height of the container corresponding to the first goods category, the verification is passed, and if the height of the single container to be detected is different from the height of the container corresponding to the first goods category, the verification is not passed.
Based on any of the above embodiments, in the method, selecting any one of the segmented images of the container to be detected, inputting an identification model, and obtaining a first cargo category corresponding to the image of the container to be detected specifically includes:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected.
Specifically, any one of the segmented container images to be detected is input into the recognition model, the probability values of the input image corresponding to the various cargo categories are output, and then the cargo category with the maximum probability value is selected as the first cargo category corresponding to the container image to be detected. For example, when the recognition model is trained, the training labels only have a category a, a category B, a category C and a category D, and then for the recognition model after training, when a segmented image of the container to be detected is input, the output is the probability value a that the goods in the input image are of the category a, the probability value B that the goods in the input image are of the category B, the probability value C that the goods in the input image are of the category C, and the probability value D that the goods in the input image are of the category D; and if the probability value B > a > d > c, selecting the category B as a first cargo category corresponding to the container image to be detected.
Based on any one of the above embodiments, an embodiment of the present invention provides a device for identifying a category of goods to be detected, and fig. 2 is a schematic structural diagram of the device for identifying a category of goods to be detected according to the embodiment of the present invention. As shown in fig. 2, the apparatus includes a first input unit 210, a second input unit 220, and a determination unit 230, wherein,
the first input unit 210 is configured to collect a front image of a whole container to be detected, input the front image into a segmentation model, and obtain a segmented container image to be detected; the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance;
the second input unit 220 is configured to select any one of the segmented container images to be detected, input an identification model, and obtain a first cargo category corresponding to the container image to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
According to the device provided by the embodiment of the invention, the front image of the whole goods is input into the segmentation model to obtain the segmented container image, and any one of the container images is input into the recognition model to obtain the category of the goods to be detected, wherein the segmentation model and the recognition model are obtained by training on the basis of a large number of samples and labels by using the machine learning principle, the problem that the traditional image comparison method is large in calculation amount and complex can be avoided by recognizing the category of the goods through the pre-trained model, and meanwhile, the model trained through a large number of samples and labels can also ensure the accuracy and efficiency of recognition. Therefore, the device provided by the embodiment of the invention can avoid the problems of large and complex calculation amount in the process of identifying the goods category, and simultaneously improve the accuracy and efficiency of identification.
Based on any one of the above embodiments, the apparatus further includes: the identification unit is used for identifying the unit,
and the category identifier corresponding to the first goods category is obtained according to the pre-stored correspondence between the goods category and the category identifier.
Based on any one of the above embodiments, the apparatus further includes: the unit of verification is a unit of verification,
the height measuring device is used for acquiring the height of the whole-tray goods by adopting a laser range finder, obtaining the layer number of the whole-tray goods based on the height and the segmented images of the containers to be detected, and calculating the height of each container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category;
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
Based on any one of the above embodiments, in the apparatus, selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain the first cargo category corresponding to the image of the container to be detected specifically includes:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected. Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a communication bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the communication bus 304. The processor 301 may invoke a computer program stored on the memory 303 and operable on the processor 301 to perform the methods for identifying the category of goods to be detected provided by the above embodiments, including for example: acquiring a front image of the whole cargo to be detected, and inputting the front image into a segmentation model to obtain a segmented image of the cargo box to be detected; the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance; selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain a first cargo category corresponding to the image of the container to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method for identifying the category of the goods to be detected provided in the foregoing embodiments when executed by a processor, for example, the method includes: acquiring a front image of the whole cargo to be detected, and inputting the front image into a segmentation model to obtain a segmented image of the cargo box to be detected; the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance; selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain a first cargo category corresponding to the image of the container to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of identifying a category of goods to be detected, comprising:
acquiring a front image of the whole cargo to be detected, and inputting the front image into a segmentation model to obtain a segmented image of the cargo box to be detected;
the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance;
selecting any one of the segmented images of the container to be detected, and inputting an identification model to obtain a first cargo category corresponding to the image of the container to be detected;
the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
2. The method for identifying a category of goods to be detected according to claim 1, further comprising:
and acquiring a category identifier corresponding to the first goods category according to a pre-stored corresponding relationship between the goods category and the category identifier.
3. The method for identifying a category of goods to be detected according to claim 1, further comprising:
acquiring the height of the whole-support cargo by adopting a laser range finder, obtaining the layer number of the whole-support cargo based on the height and the segmented image of the container to be detected, and calculating the height of a single container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category;
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
4. The method for identifying the category of goods to be detected according to any one of claims 1 to 3, wherein the selecting any one of the segmented images of the container to be detected and inputting an identification model to obtain the first category of goods corresponding to the image of the container to be detected specifically comprises:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected.
5. A device for identifying a category of goods to be detected, comprising:
the first input unit is used for acquiring a front image of the whole to-be-detected cargo and inputting the front image into the segmentation model to obtain a segmented to-be-detected cargo box image; the segmentation model is obtained by training based on a sample front image of the whole-support cargo and four-corner coordinates of each container marked on the sample front image in advance;
the second input unit is used for selecting any one of the segmented container images to be detected and inputting the identification model to obtain a first cargo category corresponding to the container image to be detected; the identification model is obtained after training based on the sample container image and a predetermined cargo class label.
6. The device for identifying the category of goods to be detected according to claim 5, further comprising: the identification unit is used for identifying the unit,
and the category identifier corresponding to the first goods category is obtained according to the pre-stored correspondence between the goods category and the category identifier.
7. The device for identifying the category of goods to be detected according to claim 5, further comprising: the unit of verification is a unit of verification,
the height measuring device is used for acquiring the height of the whole-tray goods by adopting a laser range finder, obtaining the layer number of the whole-tray goods based on the height and the segmented images of the containers to be detected, and calculating the height of each container to be detected;
acquiring the height of the container corresponding to the first cargo category according to the height corresponding relation between the pre-stored cargo categories and the containers;
if the height of the single container to be detected is equal to that of the container corresponding to the first cargo category, maintaining the category of the cargo to be detected as the first cargo category;
and if the height of the single container to be detected is different from the height of the container corresponding to the first cargo category, identifying the cargo category again.
8. The device for identifying the category of goods to be detected according to any one of claims 5 to 7, wherein the selecting any one of the segmented images of the container to be detected and inputting an identification model to obtain the first category of goods corresponding to the image of the container to be detected specifically comprises:
selecting any one of the segmented images of the container to be detected, inputting the selected image into an identification model, and outputting probability values of the input image corresponding to the categories of the goods;
and selecting the goods category with the maximum probability value as a first goods category corresponding to the container image to be detected.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, carries out the steps of the method of identifying a category of goods to be detected according to any one of claims 1 to 4.
10. A non-transitory 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 identifying a category of goods to be detected according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285781.9A CN111626981A (en) | 2020-04-13 | 2020-04-13 | Method and device for identifying category of goods to be detected |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285781.9A CN111626981A (en) | 2020-04-13 | 2020-04-13 | Method and device for identifying category of goods to be detected |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111626981A true CN111626981A (en) | 2020-09-04 |
Family
ID=72258835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010285781.9A Pending CN111626981A (en) | 2020-04-13 | 2020-04-13 | Method and device for identifying category of goods to be detected |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111626981A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392747A (en) * | 2021-06-07 | 2021-09-14 | 北京优创新港科技股份有限公司 | Goods packing box identification method and system for stereoscopic warehouse |
| CN115376242A (en) * | 2022-08-22 | 2022-11-22 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180157932A1 (en) * | 2016-12-05 | 2018-06-07 | Sap Se | Systems and methods for integrated cargo inspection |
| CN109522933A (en) * | 2018-10-19 | 2019-03-26 | 北京陌上花科技有限公司 | Commodity detection method and device for shelf |
| CN109919040A (en) * | 2019-02-15 | 2019-06-21 | 北京清瞳时代科技有限公司 | The product rule information identifying method and device of cargo |
-
2020
- 2020-04-13 CN CN202010285781.9A patent/CN111626981A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180157932A1 (en) * | 2016-12-05 | 2018-06-07 | Sap Se | Systems and methods for integrated cargo inspection |
| CN109522933A (en) * | 2018-10-19 | 2019-03-26 | 北京陌上花科技有限公司 | Commodity detection method and device for shelf |
| CN109919040A (en) * | 2019-02-15 | 2019-06-21 | 北京清瞳时代科技有限公司 | The product rule information identifying method and device of cargo |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392747A (en) * | 2021-06-07 | 2021-09-14 | 北京优创新港科技股份有限公司 | Goods packing box identification method and system for stereoscopic warehouse |
| CN115376242A (en) * | 2022-08-22 | 2022-11-22 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
| CN115376242B (en) * | 2022-08-22 | 2023-08-08 | 广东便捷神科技股份有限公司 | Automatic goods distribution method for intelligent storage rack of vending machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108154168B (en) | Comprehensive cargo inspection system and method | |
| CN108549870B (en) | Method and device for identifying article display | |
| CN108345912A (en) | Commodity rapid settlement system based on RGBD information and deep learning | |
| CN107767590A (en) | Automatic identification commercialization bar code electronic scale and Automatic identification method | |
| WO2020089896A1 (en) | Automatically tagging images to create labeled dataset for training supervised machine learning models | |
| Kang et al. | A universal defect detection approach for various types of fabrics based on the Elo-rating algorithm of the integral image | |
| CN109598249B (en) | Clothing detection method and device, electronic equipment and storage medium | |
| CN111582359B (en) | Image identification method and device, electronic equipment and medium | |
| CN111626981A (en) | Method and device for identifying category of goods to be detected | |
| CN108955901B (en) | Infrared temperature measurement method and system and terminal equipment | |
| AU2020101729A4 (en) | Continuous labelling assessment of products to improve efficiency of reverse logistics by deep learning model | |
| CN114266514A (en) | Informationized intelligent warehousing management method and system | |
| CN106022379A (en) | Method and device for detecting depreciation degree of screen | |
| CN110909698A (en) | Electronic scale recognition result output method, system, device and readable storage medium | |
| CN109840503A (en) | A kind of method and device of determining information | |
| CN114419038A (en) | Method and device for identifying surface defects of hub, storage medium and electronic equipment | |
| Kuo et al. | Improving defect inspection quality of deep-learning network in dense beans by using hough circle transform for coffee industry | |
| CN110378952A (en) | A kind of image processing method and device | |
| CN114902297A (en) | Bootstrapped image processing-based object classification using region-level annotations | |
| CN115187800A (en) | Artificial intelligence commodity inspection method, device and medium based on deep learning | |
| CN111046883B (en) | Intelligent assessment method and system based on ancient coin image | |
| WO2021081688A1 (en) | Price tag-based out-of-stock detection method and device | |
| CN110956761B (en) | Object processing method and system, computer system and computer readable medium | |
| Candra et al. | Computer Vision Implementation in Scratch Inspection and Color Detection on The Car Roof Surface | |
| CN112800804A (en) | Price tag-based out-of-stock detection method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |