WO2020151530A1

WO2020151530A1 - Method, apparatus and device for counting clothing by number of pieces

Info

Publication number: WO2020151530A1
Application number: PCT/CN2020/071926
Authority: WO
Inventors: 赵永飞; 龙一民; 徐博文; 吴剑; 胡露露; 张民英; 神克乐; 陈新; 尹宁
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-01-23
Filing date: 2020-01-14
Publication date: 2020-07-30
Also published as: CN111476336A; CN111476336B; TW202030641A

Abstract

Provided are a method, apparatus and device for counting clothing by number of pieces. The method comprises: acquiring at least one frame of image data for a quality inspection operation performed on clothing; identifying a moving object in the image data and a working area where the moving object is located; and performing, according to the moving object and the working area, a piece counting operation on the clothing subjected to quality inspection. By means of acquiring at least one frame of image data for a quality inspection operation performed on clothing, identifying a moving object in the image data and a working area where the moving object is located, and performing, according to the moving object and the working area, a piece counting operation on the clothing subjected to quality inspection, the method effectively ensures the piece counting of the clothing subjected to the quality inspection operation, reduces the production management cost of clothing piece counting, ensures the efficiency and accuracy of clothing piece counting, and also facilitates the production management of a factory and improves the management efficiency of the factory; furthermore, the method can enable a user to acquire production process data at any time and understand the progress of order production, thereby finally achieving efficient sales and operation planning.

Description

Piece counting method, device and equipment for clothing

This application claims the priority of the Chinese patent application with the application number 201910063798.7 filed on January 23, 2019, and the invention title of "Piece Counting Method, Apparatus and Equipment for Clothing", the entire content of which is incorporated into this application by reference.

Technical field

The present invention relates to the field of computer technology, in particular to a method, device and equipment for piece counting of clothing.

Background technique

In the production and processing of garments, the processing process of the factory mainly includes three processes: cloth cutting, assembly line/complete, and later. At present, in the subsequent links, garment piece counting operations can be performed. The specific methods for achieving piece counting operations include: using traditional intrusive bar code guns, radio frequency identification RFID technology or directly assigning specialized piece counting personnel to perform manual data entry operations .

However, the use of barcode guns and radio frequency identification RFID technology to perform piece-counting operations on clothing requires increased operation and learning time costs for workers, which greatly increases the cost of processing clothes in the factory; while manual statistics are used to perform piece-counting operations on clothing. , Not only low efficiency, but also increased labor costs, thereby reducing the efficiency of the factory's clothing management.

Summary of the invention

The embodiment of the present invention provides a garment piece counting method, device and equipment, which are used to reduce the cost of garment piece counting, ensure the efficiency of garment piece counting, and thereby improve the management efficiency of garments in factories.

In the first aspect, an embodiment of the present invention provides a garment piece counting method, including:

Acquiring at least one frame of image data for performing quality inspection operations on clothing;

Identifying a moving object in the image data and a working area where the moving object is located;

Perform a piece counting operation on the clothing after quality inspection according to the moving object and the working area.

In a second aspect, an embodiment of the present invention provides a piece counting device for clothing, which includes:

The acquisition module is used to acquire at least one frame of image data for quality inspection of clothing;

Recognition module for recognizing the moving object in the image data and the working area where the moving object is located;

The piece-counting module is used to perform piece-counting operations on the clothing after quality inspection according to the moving object and the working area.

In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are processed by the The garment piece counting method in the first aspect mentioned above is realized when the device is executed.

In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program that enables the computer to implement the garment piece counting method in the first aspect when executed by a computer.

By acquiring at least one frame of image data for performing quality inspection operations on clothing, the moving object in the image data and the working area where the moving object is located are identified, and the quality-inspected image data is compared according to the moving object and the working area. The garment piece counting operation effectively ensures the piece counting statistics of the garments undergoing quality inspection operations, and reduces the production management cost of the garment piece counting, ensures the efficiency and accuracy of the garment piece counting, and facilitates the production management of the factory. The management efficiency of the factory; at the same time, users can obtain production process data and understand the order production progress at any time, and finally realize efficient production and sales collaboration.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a flowchart of a method for counting pieces of clothing provided by an embodiment of the present invention;

FIG. 2 is a flowchart of identifying moving objects in the image data provided by an embodiment of the present invention;

3 is a flowchart of identifying a moving object in each frame of the image data according to at least one frame of the image data and the background model image according to an embodiment of the present invention;

4 is a flowchart of determining a moving object in the image data according to the first pixel value and the second pixel value according to an embodiment of the present invention;

FIG. 5 is a flowchart of identifying a working area where a moving object in the image data is located according to an embodiment of the present invention;

6 is a flowchart of establishing a statistical matrix for reflecting the frequency of movement changes of the moving object provided by an embodiment of the present invention;

FIG. 7 is a flowchart of determining the working area where the moving object is located according to the statistical matrix according to an embodiment of the present invention;

FIG. 8 is a flowchart of updating the statistical matrix according to an embodiment of the present invention;

9 is a flowchart of a piece counting operation performed on the garment after quality inspection according to the moving object and the work area provided by an embodiment of the present invention;

10 is a schematic structural diagram of a piece counting device for clothing provided by an embodiment of the present invention;

Fig. 11 is a schematic structural diagram of an electronic device corresponding to the piece counting device for clothing provided by the embodiment shown in Fig. 10.

detailed description

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms of "a", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, "multiple" Generally, at least two are included, but the inclusion of at least one is not excluded.

It should be understood that the term "and/or" used in this text is only an association relationship describing associated objects, indicating that there can be three types of relationships. For example, A and/or B can mean that there is A alone, and both A and B, there are three cases of B alone. In addition, the character "/" in this text generally indicates that the associated objects before and after are in an "or" relationship.

Depending on the context, the words "if" and "if" as used herein can be interpreted as "when" or "when" or "in response to determination" or "in response to detection". Similarly, depending on the context, the phrase "if determined" or "if detected (statement or event)" can be interpreted as "when determined" or "in response to determination" or "when detected (statement or event) )" or "in response to detection (statement or event)".

It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a commodity or system including a series of elements not only includes those elements, but also includes those elements that are not explicitly listed Other elements of, or also include elements inherent to this commodity or system. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the commodity or system that includes the element.

In addition, the sequence of steps in the following method embodiments is only an example, and is not strictly limited.

Fig. 1 is a flowchart of a method for counting pieces of clothing provided by an embodiment of the present invention; referring to Fig. 1, this embodiment provides a method for counting pieces of clothing. The main body of the method is a piece counting device. When the device executes the piece counting method, it can realize the piece counting statistics of the garments undergoing quality inspection operations in the subsequent process of producing and processing garments. Specifically, the piece counting method may include:

S101: Acquire at least one frame of image data for performing quality inspection operations on clothing.

Among them, the image data in this embodiment can be acquired in real time. For example, when performing quality inspection operations on clothing, an image acquisition device can be installed at a preset position. The image acquisition device can be a camera. The acquisition device can acquire real-time image data for quality inspection operations on clothing. Alternatively, the image data in this embodiment may also be acquired in non-real time. In this case, the image data may be acquired by a preset image acquisition device and stored in a preset storage area, and the image data can be obtained by accessing the storage area; Alternatively, the image data may also be actively or passively sent by the image acquisition device. In this case, the image data may be stored in a preset area of the image acquisition device. Of course, those skilled in the art can also choose other ways to obtain image data for quality inspection operations on clothing according to specific design requirements and application scenarios, as long as the accuracy and reliability of image data acquisition can be guaranteed. Repeat.

Optionally, after acquiring at least one frame of image data for quality inspection of clothing, in order to ensure the quality and efficiency of processing the image data, the method in this embodiment may further include: adjusting the resolution of at least one frame of image data , So that the resolution of the image data meets the preset standard.

Among them, the preset standard is preset, and those skilled in the art can set different resolution standards according to specific application requirements. For example, the preset standard may mean that the resolution of the image data is 320*240dpi; or, the preset The standard may mean that the resolution of the image data is 640*480dpi and so on. It should be noted that if the resolution of the image data meets the preset standard, the accuracy and reliability of the analysis and recognition of the image data can be guaranteed. Therefore, after the image data is obtained, the resolution of the image data can be obtained first. When the rate is greater than the preset standard, it means that the image data at this time is a large-resolution image. When the image data is processed, the amount of calculated data is relatively large. Therefore, in order to ensure the quality and efficiency of image data processing, the image can be reduced The resolution of the data can reduce the amount of calculation for processing the image data, thereby ensuring the real-time and reliability of the image data processing. When the resolution of the image data is less than the preset standard, it means that the image data at this time is a small resolution image. During processing, in order to ensure the accuracy of identifying the moving objects and working areas in the image data, the image data can be improved Resolution.

For example: 320*240dpi is used as the preset standard resolution. When the resolution of the acquired image data is 1280*720dpi, the resolution is greater than the preset standard. Therefore, the current image data can be downsampled. The resolution of image data is adjusted from 1280*720dpi to 320*240dpi, thereby reducing the amount of calculation for processing image data, ensuring the real-time and reliability of image data processing, and obtaining accurate processing results . When the resolution of the acquired image data is 160*120dpi, the resolution is less than the preset standard. Therefore, the current image data can be adjusted so that the resolution of the image data is adjusted from 160*120dpi to 320*240dpi, so It can effectively ensure the accuracy of image data recognition, so that accurate processing results can be obtained.

Optionally, before identifying the moving object in the image data and the working area where the moving object is located, the method in this embodiment may further include: filtering and denoising processing on at least one frame of image data.

When acquiring image data, due to the influence of the working environment of the moving object and other factors, the acquired image data may have a lot of noise. In order to improve the accuracy of image data processing, a Gaussian model can be used for at least one frame of image The data undergoes filtering and denoising processing to eliminate the noise mixed in the image and obtain clearer image data.

S102: Identify a moving object in the image data and a working area where the moving object is located.

After the image data is acquired, the image data can be analyzed and processed to identify the moving object in the image data and the working area where the moving object is located. Among them, the moving object refers to the staff who performs the quality inspection operation on the clothing, and the working area where the moving object is located refers to the area where the staff performs the quality inspection operation on the clothing.

Among them, this embodiment does not limit the specific implementation process of recognizing moving objects and working areas. Those skilled in the art can choose different implementation methods according to specific design requirements and application scenarios, for example: recognizing moving objects in image data When using the working area where the moving object is located, the contour information of all objects in the image data can be obtained first, and the contour information of all objects can be analyzed and compared with the pre-set standard contour information. The standard contour information is pre-stored with the staff Corresponding contour information, it can be understood that the standard contour information can be one or more; the object corresponding to the contour information matching at least one standard contour information is determined as a moving object; then, the moving object is acquired in the image data For the time information of all areas in the, the area whose time information is greater than or equal to the preset time threshold is determined as the working area where the moving object is located. Of course, those skilled in the art can also use other methods to identify the moving object and the working area, as long as the accuracy of acquiring the moving object and the working area can be ensured, which will not be repeated here.

S103: Perform a piece counting operation on the clothing after quality inspection according to the moving object and the work area.

After acquiring the moving object and the working area, the moving object and the working area can be analyzed and processed, and whether to perform piece counting operations on the clothing can be realized according to the analysis and processing results; specifically, refer to FIG. 9 as shown in FIG. According to the moving object and work area, the piece counting operation of the clothing after quality inspection can include:

S1031: Detect whether the moving object is located in the work area.

Regarding whether the moving object is located in the working area, one achievable way is: whether the moving object is located in the working area can refer to whether the position of the moving object is located in the working area. In the area, the current position information of the moving object can be obtained first to determine whether the current position information is in the working area. If the current position information is in the working area, it can be determined that the moving object is located in the working area; if the current position information is not working In the area, it can be determined that the moving object is not in the work area.

As to whether the moving object is located in the working area, another achievable way is: whether the moving object is located in the working area can refer to whether the motion change range of the moving object is located in the working area. When it is in the working area, you can first obtain the motion change range of the moving object to determine whether the motion change range exceeds the work area. If the motion change range does not exceed the work area, you can determine that the moving object is located in the work area; if the motion change range exceeds the work area Area, you can determine that the moving object is not in the work area.

Of course, those skilled in the art can also use other methods to detect whether the moving object is located in the working area according to specific application scenarios and design requirements, as long as the accuracy and reliability of the detection can be ensured, which will not be repeated here.

S1032: If the moving object is not in the work area, perform a piece counting operation on the clothing after quality inspection.

Among them, since the frequency of the behavior of moving objects to place clothes after quality inspection is significantly lower than the frequency of behaviors of moving objects to repeatedly check clothes during quality inspection of clothes, based on this regular feature, the placement behavior of clothes after quality inspection can be identified and tested. When the moving object exceeds the working area, it means that the moving object at this time is placing the clothing after the quality inspection is completed, and then the piece-counting operation can be performed on the clothing after the quality inspection, so that the clothing after the quality inspection operation can be obtained Number of pieces.

It is understandable that the method in this embodiment may further include: if the moving object is in the working area, no piece counting operation is performed.

Further, after the moving object is not in the working area, the method in this embodiment may further include:

S1033: If the moving object is located in the preset first area, perform a piece counting operation on qualified clothing after quality inspection.

Wherein, the preset first area is used to place the clothing whose quality inspection results are qualified, and the first area may be located at a preset position of the work area, for example, the first area may be located on the left or right side of the work area; When the moving object is no longer in the working area and is located in the first area, it means that the moving object has completed the quality inspection operation of the clothing, and the quality inspection result of the clothing is qualified. Therefore, the moving object is executing the placement of qualified clothing in the first area. For the operation in one area, at this time, the qualified garment can be counted.

S1034: If the moving object is located in the preset second area, perform a piece counting operation on the unqualified clothing after quality inspection.

Among them, the preset second area is used to place the clothes whose quality inspection results are unqualified. The second area can be located at the preset position of the working area. It should be noted that the second area and the first area have different settings. ; For example, when the first area is located on the left side of the working area, the second area can be located on the right side of the working area; when the first area is located on the right side of the working area, the second area can be located on the left side of the working area; When the object is no longer in the working area and is located in the second area, it means that the moving object has completed the quality inspection operation of the clothing, and the quality inspection result of the clothing is unqualified. Therefore, the moving object is executing the unqualified clothing placement The operation in the second area, at this time, can perform piece counting operations on unqualified garments.

It should be noted that the piece-counting operation in this embodiment can include three piece-counting operations: (1) Perform piece-counting P for garments that have completed the quality inspection operation; (2) Perform piece-counting P1 for garments that have passed the quality inspection; (3) Pair The unqualified clothing shall be subjected to piece counting P2; it is understandable that, in general, P=P1+P2.

When the detection result is that the moving object is located in the work area, it means that the moving object at this time is performing quality inspection operations on the clothing, and therefore, the piece counting operation on the clothing is not performed.

Optionally, the method in this embodiment may further include:

S104: Store at least one frame of image data of the moving object performing quality inspection operations on the clothing.

When performing piece counting statistics on clothing for quality inspection operations, a corresponding image data can be stored for each piece of clothing, so that users can view or retrieve relevant piece counting records at any time.

It is understandable that the method in this embodiment may further include:

S105: Store image data of at least one frame of qualified clothing placed on the moving object.

S106: Store at least one frame of image data of unqualified clothing placed on the moving object.

Similarly, when placing clothes after quality inspection operations, statistics can be performed on the clothes placed with different quality inspection results and quality inspection results, and the corresponding image data for each garment when statistics are stored can be stored. So that users can view or retrieve relevant records of piece counting at any time.

The clothing piece counting method provided in this embodiment uses at least one frame of image data for performing quality inspection operations on clothing to identify the moving object in the image data and the working area where the moving object is located, and perform quality inspection based on the moving object and the working area. The piece-counting operation of the later garments effectively guarantees the piece-counting statistics of the garments undergoing quality inspection operations, and reduces the production and management cost of the garment piece-counting, ensuring the efficiency and accuracy of the garment piece-counting, and also facilitates the production management of the factory. The management efficiency of the factory is improved; at the same time, users can obtain production process data and understand the order production progress at any time, and finally realize efficient production and sales collaboration.

Fig. 2 is a flow chart of identifying moving objects in image data provided by an embodiment of the present invention; Fig. 3 is a process of identifying moving objects in each frame of image data according to at least one frame of image data and a background model image provided by an embodiment of the present invention Figure 4 is a flowchart of determining a moving object in image data according to the first pixel value and the second pixel value provided by an embodiment of the present invention; on the basis of the above embodiment, continue to refer to Figures 2 to 4, This embodiment does not limit the specific implementation process of recognizing moving objects in image data. Those skilled in the art can set according to specific design requirements. Preferably, recognizing moving objects in image data in this embodiment may include :

S1021: Create a background model image based on at least one frame of image data.

Wherein, a Gaussian mixture background modeling method may be used to establish a background model image of the acquired at least one frame of image data, and the background model image includes a working environment of a moving object. Specifically, a background model image can be established based on all image data; alternatively, at least one background model image can be established based on at least one frame of image data, that is, a background model can be established based on part of the image data in at least one frame of image data For the image, another background model image is established based on other image data in at least one frame of image data. Preferably, a background model image can be established based on all the image data.

In addition, the size of the established background model image is the same as the size of the image data. For example, in the existing 1000 frames of image data, a corresponding background model image can be created based on 1000 frames of image data, and the size of the created background model image is the same as the size of the image data; alternatively, it can also be based on 1000 frames of image data Corresponding first background model image and second background model image, wherein the size of the first background model image is the same as the size of the corresponding image data; the size of the second background model image is the same as the size of the corresponding image data the same.

S1022: Identify a moving object in each frame of image data according to at least one frame of image data and a background model image.

After the background model image is established, each frame of image data can be analyzed and compared with the background model image, so as to identify the moving object in each frame of image data. Specifically, identifying a moving object in each frame of image data according to at least one frame of image data and a background model image may include:

S10221: Obtain the first pixel value of each pixel in at least one frame of image data and the second pixel value of the same pixel in the background model image.

Since the background model image and the image data have the same size, for each pixel in the image data, there is a corresponding pixel in the background model image. In order to identify the moving object, the first pixel value of each pixel in the image data can be obtained, and the second pixel value of the corresponding pixel in the background model image can be obtained. Specifically, the method in the prior art can be used to obtain The pixel value will not be explained here.

S10222: Determine a moving object in the image data according to the first pixel value and the second pixel value.

After acquiring the first pixel value and the second pixel value, the first pixel value and the second pixel value may be analyzed and processed, so as to determine the moving object in the image data according to the analysis and processing result. Specifically, determining the moving object in the image data according to the first pixel value and the second pixel value may include:

S102221: Obtain a difference value between the first pixel value and the second pixel value.

Wherein, the difference value is the degree of difference between the first pixel value and the second pixel value. Specifically, the difference value may be the difference between the first pixel value and the second pixel value, or the difference value may also be the difference between the first pixel value and the second pixel value. The ratio of the second pixel value; of course, those skilled in the art can also adopt other ways to reflect the difference value between the first pixel value and the second pixel value, which will not be repeated here.

S102222: Search for all pixels with a difference value greater than or equal to a preset pixel threshold in the image data, where all the pixels constitute a moving object in the image data.

For each image data, the image data includes a dynamic area and a static area. The dynamic area is the area where the pixels in the image data can change, that is: the dynamic area is composed of dynamic pixels; the static area is the image data The area in which the pixels basically do not change, that is, the static area is composed of static pixels. It can be seen from the above that the area where the moving object is located is the dynamic area in the image data. Furthermore, when the difference between the first pixel value and the second pixel value is greater than or equal to the pixel threshold, it indicates that the pixels in the image data and the background The corresponding pixels in the model image have a large difference. The pixel can be determined to be a dynamic pixel, so that all the dynamic pixels in the image data can be obtained. At this time, all the dynamic pixels constitute the image data. Moving objects.

In addition, the pixel threshold value in this embodiment is preset. Those skilled in the art can determine the specific value range of the pixel threshold value according to specific design requirements and application scenarios. It is understood that different difference values may correspond to different values. Pixel threshold; Example 1: When the difference value is the difference between the first pixel value and the second pixel value, the corresponding pixel threshold can be TH1, and then the moving object in the image data can be determined according to the following formula:

Among them, Currentground (i, j) is the first pixel value of a pixel in a certain frame of image data, Background (i, j) is the second pixel value of the corresponding pixel in the background model image, Foreground (i, j) is The difference area of the image data relative to the background model image, and the difference area is the moving object in the image data.

Example 2: When the difference value is the ratio of the first pixel value to the second pixel value, the corresponding pixel threshold can be TH2, and the moving object in the image data can be determined according to the following formula:

Recognizing the moving objects in the image data in the above manner effectively ensures the accuracy and reliability of the recognition of the moving objects in each frame of image data, thereby ensuring the accuracy of the piece-counting operation of the clothing.

FIG. 5 is a flowchart of identifying the working area of a moving object in image data provided by an embodiment of the present invention; FIG. 6 is a flowchart of establishing a statistical matrix used to reflect the frequency of motion changes of moving objects provided by an embodiment of the present invention; 7 is a flow chart of determining the working area of the moving object based on the statistical matrix provided by the embodiment of the present invention; on the basis of the above embodiment, continuing to refer to Figures 5 to 7, it can be seen that this embodiment is useful for identifying moving objects in image data. The specific implementation process of the working area is not limited, and those skilled in the art can set according to specific design requirements. Preferably, the working area where the moving object in the recognition image data is located in this embodiment may include:

S1023: Establish a statistical matrix for reflecting the motion change frequency of the moving object, and the size of the statistical matrix is the same as the size of the image data.

Wherein, referring to FIG. 6, the establishment of a statistical matrix used to reflect the motion change frequency of a moving object may include:

S10231: Obtain a statistical value corresponding to each pixel in at least one frame of image data.

S10232: Establish a statistical matrix based on statistical values.

Among them, the statistical value can be determined based on the motion characteristics of each pixel in each frame of image data. Since each image data includes a dynamic area and a static area, the pixels in the dynamic area can be dynamic pixels. The pixel in the static area can be a static pixel, and the motion characteristic of the pixel is whether the pixel is a dynamic pixel or a static pixel; when the pixel is a dynamic pixel, it can correspond to a preset statistical value; When the pixel is a static pixel, it can correspond to another preset statistical value. After obtaining multiple statistical values, a statistical matrix can be established based on the statistical values, and the size of the established statistical matrix is the same as the size of the image data.

For example, in the existing 500 frames of image data, the size of each image data is 320X240dpi. Therefore, an initial statistical matrix with a size of 320*240 can be established first, assuming that each element in the initial statistical matrix is 0, that is, : The default initial statistical value of each element is 0. When identifying the motion characteristics of pixel A in the first frame of image data, determine that pixel A is a dynamic pixel. At this time, you can add 1 to the element corresponding to pixel A in the initial statistical matrix to obtain The statistical value corresponding to pixel A is 1. When identifying the motion characteristics of pixel A in the second frame of image data, it is found that the pixel A is a static pixel. At this time, the initial statistical matrix can be made to correspond to pixel A The element of is kept unchanged. Based on the first stitch image data, the statistical value corresponding to the pixel A in the initial statistical matrix can be determined as 1. When identifying the motion characteristics of the pixel B in the first frame of image data, it is found that the pixel B is a dynamic pixel. At this time, you can add 1 to the element corresponding to the pixel B in the initial statistical matrix to obtain The statistical value corresponding to pixel B is 1. When identifying the motion characteristics of pixel B in the second frame of image data, it is found that the pixel B is a dynamic pixel. At this time, the pixel B in the statistical matrix can be The corresponding statistical value is determined 2; specifically, the statistical value in the statistical matrix satisfies the following relationship:

Among them, Motionground (i, j) is the preset statistical value in the statistical matrix, Foreground (i, j) is the motion characteristic of each pixel in the image data, when Foreground (i, j) = 0, it means this The pixels at time are static pixels. When Foreground(i,j)=255, it means that the pixels at this time are dynamic pixels.

After analyzing and processing the pixels in all the image data according to the above relational expressions, the statistical values corresponding to the pixels in all the image data can be obtained, and the statistical matrix can be established based on the statistical values.

S1024: Determine the working area where the moving object is located according to the statistical matrix.

After the statistical matrix is obtained, the statistical matrix can be used to determine the working area. Specifically, determining the working area of the moving object according to the statistical matrix can include:

S10241: Perform normalization processing on the statistical matrix to obtain a pixel gray value corresponding to each statistical value in the statistical matrix.

S10242: When the pixel grayscale value is greater than or equal to the preset grayscale threshold, determine the pixel area corresponding to the pixel grayscale value as the working area where the moving object is located.

Among them, the gray threshold is a preset limit. This embodiment does not limit its specific numerical range. Those skilled in the art can set it arbitrarily according to specific design requirements. For example, the gray threshold can be 20, 30 Or 40 and so on. After normalizing the statistical matrix, the statistical matrix can be displayed as an image. The gray value of each pixel in the image is 0-255. When the pixel gray value is greater than or equal to the gray threshold , It means that the pixel area corresponding to the gray value of the pixel changes frequently, and the pixel area corresponding to the gray value of the pixel can be determined as the working area where the moving object is located.

The statistical matrix is used to identify the working area where the moving object is located. Specifically, the statistical matrix is used to analyze which pixel areas in the image data change frequently and which pixel areas basically do not change. Based on the above-mentioned frequency of movement changes, it is estimated that the moving object is performing normally. The scope of the work area of quality inspection; specifically, the area where the movement frequency is relatively high is identified, and this area is the work area for the moving object to perform the quality inspection operation, thus effectively ensuring the accuracy and reliability of the work area recognition, and further improving The precision used by this piece counting method.

In specific applications, the numerical value of the statistical matrix cannot be increased indefinitely. If the numerical elements of the statistical matrix increase to a certain degree, it will affect the accuracy of processing the image data; and the quality of clothing is inspected on the moving objects. During operation, the working area where the moving object is located is not static. It can be changed at any time according to the change of the moving object. Therefore, in order to ensure the accuracy of identifying the working area, the statistical matrix can be updated periodically . Specifically, the method in this embodiment may further include:

S201: Update the statistical matrix.

Wherein, referring to FIG. 8, updating the statistical matrix may include:

S2011: Obtain a preset update coefficient, where the update coefficient is a positive number less than 1.

Among them, the update coefficient is preset, and this embodiment does not limit its specific numerical range. Those skilled in the art can set it arbitrarily according to specific application requirements, as long as it can ensure that the update coefficient meets the above requirements. That is, the update coefficient can be any value that satisfies the above conditions, for example: 0.1, 0.2, 0.3, 0.5, 0.8, etc. For ease of description, the following content is described with an update coefficient of 0.5 as an example.

S2012: Multiply all the statistical values included in the statistical matrix with the update coefficients to obtain the updated values.

S2013: Obtain the updated statistical matrix based on the updated values.

After the update coefficient is obtained, the statistical values in the statistical matrix can be adjusted according to the obtained update coefficients to reduce the numerical elements in the statistical values, namely Motionground(A)=0.5*Motionground(B); where, Motionground( A) is all the statistical values after adjustment, Motionground(B) is all the statistical values before adjustment, and 0.5 is the update coefficient.

When updating the statistical matrix, the statistical matrix can be updated according to the preset period or the preset fixed number of frames, so that the overall value of the statistical matrix is updated according to the preset update coefficient, so that the update can be used The latter statistical matrix recognizes the work area, realizes the adaptive estimation of the work area of the moving object, and effectively ensures the accuracy and reliability of the work area determination.

For specific applications, a camera can be installed at a preset position in the factory. The camera can collect real-time image data of a moving object performing quality inspection operations on clothing. After the image data is obtained, the obtained image data can be obtained by Gaussian filtering. Perform filtering and denoising processing; then, use Gaussian mixture background modeling method to perform background modeling image based on the working environment of the moving object, and determine the moving object in the image data according to the established background model image. Then, according to the movement change frequency of the moving object, the area with a relatively high movement change frequency is identified, that is, the normal working area for quality inspection of clothing. Since the frequency of the behavior of placing clothes after the quality inspection on the clothing is significantly lower than the behavior frequency of the sports object repeatedly checking the clothing during the quality inspection, based on this regular characteristic, the quality inspection status of the sports object can be judged, and the quality of the clothing can be judged. After the inspection is completed, the garment can be counted, and the image data for the quality inspection operation can be saved.

The method provided by this application embodiment can effectively reduce the cost and difficulty of digital transformation of the factory, and has the characteristics of lightweight deployment and strong reproducibility. The factory can be obtained in real time without changing the original working methods of workers. The real-time progress of clothing processing is synchronized to producers, platforms, and consumers, so as to achieve efficient production and sales synergy, and it is conducive to accurate matching, optimization and improvement of workers' working conditions.

FIG. 10 is a schematic structural diagram of a piece counting device for clothing provided by an embodiment of the present invention; referring to FIG. 10, this embodiment provides a piece counting device for clothing, which can perform the above-mentioned clothing piece counting method. Specifically, the piece counting device may include:

The obtaining module 11 is used to obtain at least one frame of image data for quality inspection of clothing;

The recognition module 12 is used to recognize a moving object in the image data and a working area where the moving object is located;

The piece-counting module 13 is used to perform piece-counting operations on the garments after quality inspection according to the moving objects and the working area.

Wherein, when the recognition module 12 recognizes a moving object in the image data, the recognition module 12 can be used to perform: establish a background model image based on at least one frame of image data; recognize each frame of image based on at least one frame of image data and the background model image The moving objects in the data.

Optionally, when the recognition module 12 recognizes a moving object in each frame of image data based on at least one frame of image data and a background model image, the recognition module 12 may be used to perform: obtain the information of each pixel in at least one frame of image data The first pixel value and the second pixel value of the same pixel in the background model image; the moving object in the image data is determined according to the first pixel value and the second pixel value.

Optionally, when the identification module 12 determines the moving object in the image data according to the first pixel value and the second pixel value, the identification module 12 may be used to perform: obtain the difference value between the first pixel value and the second pixel value; Find all pixels with a difference value greater than or equal to a preset pixel threshold in the image data, where all the pixels constitute a moving object in the image data.

Optionally, when the recognition module 12 recognizes the working area of the moving object in the image data, the recognition module 12 can be used to perform: establish a statistical matrix for reflecting the movement frequency of the moving object, and the size of the statistical matrix and the image data The size is the same; according to the statistical matrix to determine the working area where the moving object is located.

Wherein, when the identification module 12 establishes a statistical matrix for reflecting the frequency of motion changes of the moving object, the identification module 12 can be used to perform: obtain a statistical value corresponding to each pixel in at least one frame of image data; Statistic values create a statistical matrix.

In addition, when the identification module 12 determines the working area where the moving object is located according to the statistical matrix, the identification module 12 can be used to perform: normalize the statistical matrix to obtain the pixel gray corresponding to each statistical value in the statistical matrix. Degree value; when the pixel gray value is greater than or equal to the preset gray threshold, the pixel area corresponding to the pixel gray value is determined as the working area where the moving object is located.

Optionally, the identification module 12 in this embodiment is also used to perform: update the statistical matrix.

Specifically, when the identification module 12 updates the statistical matrix, the identification module 12 can be used to perform: obtain a preset update coefficient, where the update coefficient is a positive number less than 1; and all statistical values included in the statistical matrix Multiply with the updated coefficients to obtain the updated value; obtain the updated statistical matrix based on the updated value.

Optionally, when the piece-counting module 13 performs a piece-counting operation on the clothes after quality inspection according to the moving object and the working area, the piece-counting module 13 can be used to perform: detecting whether the moving object is located in the working area; if the moving object is not in the working area , Then perform piece counting operations on the garments after quality inspection.

Optionally, after the moving object is not in the working area, the piece counting module 13 in this embodiment can also be used to perform: if the moving object is located in the preset first area, perform a piece counting operation on qualified clothing after quality inspection ; Or, if the moving object is located in the preset second area, perform a piece counting operation on the unqualified clothing after quality inspection.

Optionally, the acquiring module 11 in this embodiment is further configured to adjust the resolution of the at least one frame of image data after acquiring at least one frame of image data for quality inspection of the clothing, so that the resolution of the image data meets a preset standard .

Optionally, the acquisition module 11 in this embodiment is further configured to perform filtering and denoising processing on at least one frame of image data before identifying the moving object in the image data and the working area where the moving object is located.

Optionally, the piece counting module 13 in this embodiment is further configured to perform: storing at least one frame of image data of a moving object performing a quality inspection operation on clothing.

The device shown in FIG. 10 can execute the method of the embodiment shown in FIG. 1 to FIG. 9. For parts that are not described in detail in this embodiment, please refer to the related description of the embodiment shown in FIG. 1 to FIG. 9. For the implementation process and technical effects of this technical solution, please refer to the description in the embodiment shown in FIG. 1 to FIG. 9, and will not be repeated here.

In a possible design, the structure of the piece counting device for clothing shown in FIG. 10 can be implemented as an electronic device, which can be various devices such as a mobile phone, a tablet computer, and a server. As shown in FIG. 11, the electronic device may include a processor 21 and a memory 22. The memory 22 is used to store a program that supports the electronic device to execute the clothing piece counting method provided in the embodiments shown in FIGS. 1 to 9 above, and the processor 21 is configured to execute the program stored in the memory 22.

The program includes one or more computer instructions, where one or more computer instructions can implement the following steps when executed by the processor 21:

Identify the moving objects in the image data and the working area where the moving objects are located;

According to the moving objects and work area, the garments after quality inspection are counted.

Optionally, the processor 21 is further configured to execute all or part of the steps in the embodiments shown in FIGS. 1 to 9 above.

The structure of the electronic device may also include a communication interface 23 for the electronic device to communicate with other devices or a communication network.

In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by electronic devices, which includes programs for executing the garment piece counting method in the method embodiments shown in FIGS. 1-9. .

The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.

Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, it can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solutions essentially or the part that contributes to the prior art can be embodied in the form of computer products, and the present invention can be used in one or more computer usable storage containing computer usable program codes. The form of a computer program product implemented on a medium (including but not limited to disk storage, CD-ROM, optical storage, etc.).

The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable devices are generated for realizing the process Figure a process or multiple processes and/or a block diagram of a device with functions specified in one block or multiple blocks.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device, and the instruction device implements A function specified in a flow or multiple flows in a flowchart and/or a block or multiple blocks in a block diagram.

These computer program instructions can also be loaded on a computer or other programmable equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so that the instructions executed on the computer or other programmable equipment provide Steps used to implement the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

In a typical configuration, the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in a computer readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.

Computer-readable media includes permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

A piece counting method for clothing, characterized in that it comprises:

Acquiring at least one frame of image data for performing quality inspection operations on clothing;

Identifying a moving object in the image data and a working area where the moving object is located;

Perform a piece counting operation on the clothing after quality inspection according to the moving object and the working area.
The method according to claim 1, wherein identifying a moving object in the image data comprises:

Establishing a background model image based on at least one frame of the image data;

Recognizing a moving object in each frame of the image data according to at least one frame of the image data and the background model image.
The method according to claim 2, wherein identifying a moving object in each frame of the image data according to at least one frame of the image data and the background model image comprises:

Acquiring a first pixel value of each pixel in at least one frame of the image data and a second pixel value of the same pixel in the background model image;

The moving object in the image data is determined according to the first pixel value and the second pixel value.
The method according to claim 3, wherein determining the moving object in the image data according to the first pixel value and the second pixel value comprises:

Obtaining a difference value between the first pixel value and the second pixel value;

Searching for all pixels with the difference value greater than or equal to a preset pixel threshold in the image data, where all the pixels constitute a moving object in the image data.
The method according to claim 1, wherein identifying a working area where a moving object in the image data is located comprises:

Establishing a statistical matrix for reflecting the frequency of motion changes of the moving object, the size of the statistical matrix being the same as the size of the image data;

Determine the working area where the moving object is located according to the statistical matrix.
The method according to claim 5, wherein establishing a statistical matrix for reflecting the frequency of movement changes of the moving object comprises:

Obtaining a statistical value corresponding to each pixel in at least one frame of the image data;

A statistical matrix is established based on the statistical values.
The method according to claim 5, wherein determining the working area where the moving object is located according to the statistical matrix comprises:

Performing normalization processing on the statistical matrix to obtain a pixel gray value corresponding to each statistical value in the statistical matrix;

When the pixel gray value is greater than or equal to a preset gray threshold value, the pixel area corresponding to the pixel gray value is determined as the working area where the moving object is located.
The method of claim 5, wherein the method further comprises:

The statistical matrix is updated.
The method according to claim 8, wherein updating the statistical matrix comprises:

Obtaining a preset update coefficient, where the update coefficient is a positive number less than 1;

Multiply all the statistical values included in the statistical matrix with the update coefficients to obtain updated values;

The updated statistical matrix is obtained based on the updated values.
The method according to any one of claims 1-9, wherein performing a piece counting operation on the garment after quality inspection according to the moving object and the work area comprises:

Detecting whether the moving object is located in the working area;

If the moving object is not in the working area, a piece counting operation is performed on the clothing after quality inspection.
The method according to claim 10, wherein after the moving object is not in the working area, the method further comprises:

If the moving object is located in the preset first area, perform a piece counting operation on qualified clothing after quality inspection; or,

If the moving object is located in the preset second area, a piece counting operation is performed on the unqualified clothing after quality inspection.
The method according to any one of claims 1-9, wherein after acquiring at least one frame of image data for quality inspection of clothing, the method further comprises:

The resolution of at least one frame of the image data is adjusted so that the resolution of the image data meets a preset standard.
The method according to any one of claims 1-9, characterized in that, before identifying the moving object in the image data and the working area where the moving object is located, the method further comprises:

Perform filtering and denoising processing on at least one frame of the image data.
The method according to any one of claims 1-9, wherein the method further comprises:

At least one frame of image data in which the moving object performs a quality inspection operation on the clothing is stored.
A piece counting device for clothing, characterized in that it comprises:

The acquisition module is used to acquire at least one frame of image data for quality inspection of clothing;

Recognition module for recognizing the moving object in the image data and the working area where the moving object is located;

The piece-counting module is used to perform piece-counting operations on the clothing after quality inspection according to the moving object and the working area.
An electronic device, characterized by comprising: a memory and a processor; wherein the memory is used to store one or more computer instructions, where the one or more computer instructions are executed by the processor to achieve The garment piece counting method according to any one of claims 1 to 14.