CN110647851A - Production line capacity monitoring method, device and system - Google Patents
Production line capacity monitoring method, device and system Download PDFInfo
- Publication number
- CN110647851A CN110647851A CN201910921947.9A CN201910921947A CN110647851A CN 110647851 A CN110647851 A CN 110647851A CN 201910921947 A CN201910921947 A CN 201910921947A CN 110647851 A CN110647851 A CN 110647851A
- Authority
- CN
- China
- Prior art keywords
- image
- tray
- detected
- frame
- material type
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
The application belongs to the technical field of machine vision, and provides a production line capacity monitoring method, a device and a system, wherein the method comprises the following steps: extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of a camera device; carrying out image preprocessing on the frame to be detected; screening a tray image containing material information from the processed frame to be detected; segmenting the tray image according to a preset image segmentation rule; classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types; and generating a capacity balance scheme according to the counting result of each material type. The method and the device solve the problems that the productivity of various materials cannot be counted and the capacity optimization suggestion cannot be provided.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a method, a device and a system for monitoring production capacity of a production line.
Background
The assembly line operation is a common operation means for improving the industrial production efficiency of a factory, and each station is only responsible for completing one kind of work when the assembly line operation is carried out. The assembly line operation has the characteristics of high flexibility and strong expansibility, and is widely used in industrial production. The capacity counting of different sections of the assembly line is one of important means for controlling the current production condition of the assembly line, however, due to the low automation degree, most factories still rely on the self-counting number report of workers to complete the capacity counting work.
In order to avoid statistical errors caused by autonomous counting of workers, in the prior art, correlation sensors are arranged on two sides of a testing working section, a transmitter continuously transmits light beams to a receiver, and when no product passes through, the receiver can normally receive signals; when a product is placed, the light beam is interrupted, the receiver cannot receive signals, and the counter is triggered to count. However, the method adopts a specialized topological structure for chip products, cannot adapt to other products, cannot complete the productivity counting task of various workpieces when the types of incoming materials at the counting point are more, and cannot provide suggestions for productivity optimization.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and a system for monitoring productivity of a production line, so as to solve the problem that statistics on the productivity of multiple materials cannot be performed and a proposal for optimizing the productivity cannot be provided.
A first aspect of an embodiment of the present invention provides a production line capacity monitoring method, including:
extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of a camera device;
carrying out image preprocessing on the frame to be detected;
screening a tray image containing material information from the processed frame to be detected;
segmenting the tray image according to a preset image segmentation rule;
classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
and generating a capacity balance scheme according to the counting result of each material type.
In an implementation example, the extracting, from video data obtained by a shooting pipeline of a camera device, a plurality of frames to be detected includes:
detecting whether each frame of image in video data obtained by a shooting assembly line of a camera device contains tray information or not in real time;
if any frame of image contains tray information, determining the image containing the tray information and N-1 frames of images which are continuous behind the image in the video data as frames to be detected; n is greater than 1;
after the frame to be detected is determined, detecting whether each frame of image in the video data contains tray information in real time at preset time intervals; the preset time is set according to the time consumed when the tray passes through the camera device.
In one example implementation, the method further comprises:
and controlling the camera device to acquire the background image of the assembly line at a preset sampling frequency, and updating the stored background image.
In one embodiment, the segmenting the tray image according to a preset image segmentation rule includes:
extracting a material area from the tray image according to the color distinguishing characteristics of the material and the tray;
and carrying out grid segmentation on the material area according to preset grid parameters.
In an implementation example, the classifying and counting materials of each partition area in the tray image through an image classification model, and outputting a material type and a counting result corresponding to the material type includes:
and performing image recognition on each segmentation area in the material area through a feature recognition network, outputting the material type, and adding one to the counting result of the material type.
In an implementation example, the image preprocessing on the frame to be detected includes:
removing the background of the frame to be detected according to the background image;
and carrying out binarization processing on the frame to be detected after the background is removed to highlight the tray area in the image.
In one embodiment, the generating the capacity balancing scheme according to the counting result of each material type includes:
generating a productivity curve according to the counting result of each material type;
obtaining the production dependency relationship and the production index of each material type;
determining the material type with slow production procedure according to the production index and the counting result of each material type, and generating prompt information of the slow material type;
searching an upstream material type associated with the slow material type according to the production dependency relationship;
and generating a capacity balance scheme for adjusting the production efficiency of the upstream material type.
A second aspect of an embodiment of the present invention provides a production line capacity monitoring device, including:
the frame extraction module to be detected is used for extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of the camera device;
the image preprocessing module is used for preprocessing the image of the frame to be detected;
the screening module is used for screening the tray image containing the material information from the processed frame to be detected;
the image segmentation module is used for segmenting the tray image according to a preset image segmentation rule;
the classification counting module is used for classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
and the scheme generation module is used for generating a productivity balance scheme according to the counting result of each material type.
A third aspect of an embodiment of the present invention provides a production line capacity monitoring system, including: the device comprises a camera device and a control device which is in communication connection with the camera device; wherein the content of the first and second substances,
the camera device is arranged above the assembly line and is used for shooting the assembly line;
the control device executes the production line capacity monitoring method in the first aspect.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method of the first aspect.
A fifth aspect of an embodiment of the present invention provides a production line capacity monitoring device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the production line capacity monitoring method in the first aspect.
According to the production line capacity monitoring method, the production line capacity monitoring device, the production line capacity monitoring system and the storage medium, a plurality of frames to be detected are extracted from video data obtained by a shooting assembly line of a camera device; carrying out image preprocessing on the frame to be detected; screening a tray image containing material information from the processed frame to be detected; segmenting the tray image according to a preset image segmentation rule; classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types; and generating a capacity balance scheme according to the counting result of each material type. A plurality of frames to be detected are extracted from video data shot by a camera device to realize non-contact type assembly line monitoring, and each frame to be detected corresponds to one tray which is transported by the assembly line and is used for containing materials, so that material information in the trays transported on the assembly line is not omitted. Screening out image frames without material information in the frames to be detected, segmenting tray images in the frames to be detected according to preset image segmentation rules, inputting each segmentation area into an image classification model, outputting material types and counting results corresponding to the material types, and completing capacity statistics of various materials on the production line. And generating a capacity balance scheme according to the counting result of each material type, thereby effectively optimizing the production capacity of the production line.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive work.
FIG. 1 is a flowchart illustrating a method for monitoring productivity of a production line according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for monitoring productivity of a production line according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a production line capacity monitoring apparatus according to a third embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a production line capacity monitoring system according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a production line capacity monitoring device according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "comprises" and "comprising," and any variations thereof, in the description and claims of this invention and the above-described drawings are intended to cover non-exclusive inclusions. For example, a process, method, or system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Furthermore, the terms "first," "second," and "third," etc. are used to distinguish between different objects and are not used to describe a particular order.
Example one
Fig. 1 is a schematic flow chart of a production line capacity monitoring method according to an embodiment of the present invention. The method can be executed by a control device, and the control device can be a server, an intelligent terminal, a tablet or a PC (personal computer) and the like; in the embodiment of the present invention, a control device is used as an execution main body for explanation, and the method specifically includes the following steps:
s110, extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of a camera device;
in order to solve the problem that an infrared counting device arranged on a transmission belt of the production line occupies the space of the production line, a camera device can be arranged above the transmission belt of the production line to shoot the production line, and the camera device is in communication connection with a control device. The control device receives and analyzes the video data shot by the camera device to realize the statistics of the capacity of the product production line and the statistics of the quantity of the materials transmitted by each production line. Optionally, the camera device can be erected above a plurality of preset counting points of the assembly line through the telescopic bracket, and does not occupy the operation space of the assembly line. The plurality of image pickup devices may be connected to the control device through the switch.
After the control device receives video data obtained by shooting the assembly line by the camera device, the material yield needs to be counted for counting the production capacity of the assembly line. The control device can extract a plurality of frames to be detected from the video data, and each frame to be detected contains tray information which is transmitted on the production line and correspondingly shot by the camera device and is used for containing materials. One or more trays may be present in each frame to be detected; if the frame to be detected has a plurality of trays; and the control device selects one tray which is closest to the center of the image in each frame to be detected as a target tray and performs detection analysis on the target tray.
In one embodiment, the process of the control device extracting a number of frames to be detected from the video data may be: detecting whether each frame of image in video data obtained by a shooting assembly line of a camera device contains tray information or not in real time; if any frame of image contains tray information, determining the image containing the tray information and N-1 frames of images which are continuous behind the image in the video data as frames to be detected; n is greater than 1; after the frame to be detected is determined, detecting whether each frame image in the video data contains tray information or not at intervals of preset time in real time; the preset time is set according to the time consumed when the tray passes through the camera device.
Camera device can erect in the predetermined statistics point top of assembly line, and predetermined statistics point can be located material output position in the assembly line, and the tray of transportation material is placed by machine or production personnel and is transmitted to warehouse or next process on the transmission band of material output position, and every tray homoenergetic is erect the camera device above the assembly line and is gathered at this transmission course. The control device detects whether each frame of image in video data obtained by a shooting assembly line of the shooting device contains tray information or not in real time to judge whether the tray transmitted by the assembly line passes through a shooting area of the shooting device or not because the time when the tray passes through the shooting device is uncertain; when any frame of image is detected to contain tray information, determining the frame of image containing tray information and N-1 frames of images which are continuous behind the frame of image in the video data as frames to be detected; n is greater than 1; so as to complete the extraction of the frame to be detected corresponding to the tray passing through the shooting area of the camera device at this time in the video data. Wherein, the extracted N frames (for example, 5 frames) effective frames to be detected all contain information of the same tray for containing the materials.
In order to avoid detecting the same tray on the production line for multiple times, after each continuous effective N frames of images are detected, the control device needs to wait for a certain time, namely, the tray passes through the camera device and then continues to detect each frame of image in the video data in real time. The preset time can be preset according to the consumed time of the assembly line transportation tray passing through the camera device. When the control device determines that the N frames of frames to be detected are to be detected, the control device detects whether each frame of image in the video data obtained from the shooting assembly line of the camera device contains tray information in real time again after a preset time (such as 2 seconds) is set.
Specifically, whether each frame of image in video data obtained by a shooting assembly line of the camera device contains tray information or not is detected, whether the image contains complete tray information or not can be judged by comparing the background color in each frame of image with the tray color or comparing the tray shape in the image with the original tray shape, and therefore whether each frame of image contains tray information or not is determined. Optionally, the background color in each frame of image and the tray color or the tray shape in the image and the original tray shape can be compared by judging whether the gray value, texture, frequency domain and other data of each frame of image meet a preset threshold.
S120, preprocessing the image of the frame to be detected;
after the control device extracts a plurality of frames to be detected from the acquired video data, image preprocessing needs to be performed on the extracted frames to be detected before image analysis is performed on the frames to be detected so as to highlight the tray area in the frames to be detected, and therefore the control device can acquire material information in the frames to be detected more quickly and accurately.
In an embodiment, the specific process of the control device performing image preprocessing on the frame to be detected may be: and removing the background of the frame to be detected according to the background image, and performing binarization processing on the frame to be detected after the background is removed to highlight the tray area in the image.
Since the trays transported on the assembly line can contain a plurality of materials, optionally, a green assembly line can be used in advance to distinguish colors from red trays. Therefore, the control device can input the frame to be detected into the (R + R-B-G) channel (R: red channel, G: green channel and B: blue channel) to carry out graying to obtain a grayscale image, so as to ensure that when a tray containing materials on the production line passes through, effective searching can be carried out according to the protruding part of the color (red) of the tray. And then, removing the background of the frame to be detected after the graying treatment by adopting a background difference method, specifically, obtaining a background image stored in the control device, and subtracting the background image from the frame to be detected after the graying treatment so as to remove the background of the frame to be detected. The control device performs binarization processing on the frame to be detected after the background is removed to highlight a tray area in the image, particularly a tray area in which materials are placed. Optionally, the background in each frame to be detected can be removed according to the background image by using an inter-frame difference method, a ViBe algorithm, a ViBe + algorithm and other methods.
In an implementation example, the control device can also control the camera device, and the control device controls the camera device to acquire the background image of the pipeline at a preset sampling frequency and update the stored background image. Specifically, when no material flows through the statistical point, the control device controls the camera device to continuously capture multiple frames of preset statistical point images, and the control device takes the average value of the captured multiple frames of images as the background image. Aiming at the condition that the background of the assembly line may change within a period of time, the control device automatically acquires a new background image at a preset sampling frequency and updates the stored background image in a mode of presetting background image refreshing frequency. The background image is reacquired and refreshed to adapt to the complex and changeable condition of the production line.
S130, screening out tray images containing material information from the processed frames to be detected;
because the plurality of frames to be detected after image preprocessing more highlights the tray area containing the materials in the image, the control device can judge whether the tray in each frame to be detected contains the materials or not by judging whether the processed frames to be detected contain the materials information or not, and therefore the tray image not containing the materials information can be eliminated.
Specifically, the control device may determine whether each frame to be detected contains the material information by determining whether the processed gray value of each frame to be detected is greater than a gray threshold. And judging each processed frame to be detected, wherein if the gray value of the processed frame to be detected is greater than a preset gray threshold value, the gray threshold value is met, and the frame to be detected contains material information. The control device screens the tray images meeting the gray threshold value from the processed frames to be detected, so that the tray images containing material information, namely the tray containing the materials, in the frames to be detected are screened, and the material statistics is facilitated. Optionally, the control device may further determine whether each frame to be detected contains material information according to other image information such as texture of each frame to be detected.
S140, segmenting the tray image according to a preset image segmentation rule;
optionally, the tray for containing the materials on the production line can adopt a cotton tray made of antistatic cotton; wherein the trays have different specifications (different width, length, height, etc.) resulting in differences in the amount of material contained on the trays. The control device divides the tray image obtained by screening to count the material quantity. Specifically, the control device may select a corresponding preset image segmentation rule according to the tray specification to segment each tray image.
In an embodiment, the control device divides the tray image according to a preset image division rule, and the specific process includes: extracting a material area from the tray image according to the color distinguishing characteristics of the material and the tray; and carrying out grid segmentation on the material area according to preset grid parameters. Before the control device carries out image segmentation on the tray images, extracting material areas from each tray image according to the color distinguishing characteristics of the materials and the trays. And determining corresponding preset grid parameters according to the tray specification to perform grid segmentation on the material area. Specifically, if the specification of the tray in the tray image is width M and length N; the preset grid parameters corresponding to the specification can be preset to be M multiplied by N grids, so that the control device divides the material area into M equal parts in the transverse direction according to the preset grid parameters, and divides the material area into N equal parts in the longitudinal direction to obtain M multiplied by N divided areas. The realization carries out the meshing with the material that holds on the tray for the locating place of a material on each partition region correspondence tray, if place the material on this locating place then should partition the region and include corresponding material information.
S150, classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
after the control device divides each tray image according to a preset image division rule to obtain a plurality of division areas corresponding to each tray image, the control device inputs the division areas of each tray image into an image classification model one by one, classifies and counts materials of each division area in the tray image through the image classification model, and outputs the material type contained in each tray image and the counting result corresponding to the material type. And determining the material classification and counting result of any tray image which contains the most material types and has the most counting result corresponding to the material types as the detection result of the tray corresponding to the N frames of frames to be detected. The production capacity monitoring of various materials of the production line is realized, the condition that the types of incoming materials on the upstream of the production line are not single can be coped with, and different types of materials flowing through the statistical points are classified and counted.
In one implementation example, the control device may perform image recognition on each segmented area in the material area through the feature recognition network, output a material type, and add one to a counting result of the material type. In particular, the feature recognition network may be composed of two parts, a feature extraction network and a classifier. The convolutional network structure for feature extraction may be determined according to the complexity of the detection problem, and the network structures that may be used are VGG16, google net, ResNet, and the like. The classifier can adopt a Softmax loss function, and if the material types possibly passing through the statistic point are i types in the pipeline, the classifier has i types of possible classification results. And inputting the segmentation areas of the tray image into the trained feature recognition network one by one to obtain image feature data, inputting the image feature data into a classifier to obtain a material type, and adding one to a counting result corresponding to the material type. For example, if the material classification is performed on the segmented area 1 in the tray image through the image classification model and the output material type is a battery, the counting result of the battery is increased by one.
And S160, generating a productivity balance scheme according to the counting result of each material type.
Different materials (products) can be produced in different time periods of the same assembly line, the control device is used for processing and analyzing the video data generated by the plurality of assembly lines collected by the image pickup device in real time, so that the counting result of each material type produced in the current assembly line is obtained, and the capacity balancing scheme is generated.
According to the production line capacity monitoring method provided by the embodiment of the invention, a plurality of frames to be detected are extracted from video data obtained by shooting a production line by a camera device; carrying out image preprocessing on the frame to be detected; screening a tray image containing material information from the processed frame to be detected; segmenting the tray image according to a preset image segmentation rule; classifying and counting materials of each partition area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types; and generating a capacity balance scheme according to the counting result of each material type. A plurality of frames to be detected are extracted from video data shot by a camera device to realize non-contact type assembly line monitoring, and each frame to be detected corresponds to a tray which is transported by the assembly line and is used for containing materials, so that material information in the tray transported on the assembly line is not omitted. Screening out image frames without material information in the frames to be detected, segmenting tray images in the frames to be detected according to preset image segmentation rules, inputting each segmentation area into an image classification model, outputting material types and counting results corresponding to the material types, and completing capacity statistics of various materials on the production line. And generating a capacity balance scheme according to the counting result of each material type, thereby effectively optimizing the capacity of the production line.
Example two
Fig. 2 is a schematic flow chart illustrating a production line capacity monitoring method according to a second embodiment of the present invention. On the basis of the first embodiment, the present embodiment further provides a process of generating a capacity balancing scheme according to the counting result of each material type, so as to perform capacity optimization. The method specifically comprises the following steps:
s210, generating a productivity curve according to the counting result of each material type;
when the control device collects video data generated by a plurality of assembly lines in real time for processing and analyzing to obtain the counting result of each material type produced in each assembly line, the control device can generate the capacity curve of each material type according to the counting result of each material type.
In particular, the control device may have a display screen thereon to display a software display window. Optionally, the software display window may be composed of five parts, namely a video shooting device configuration interface, a pipeline real-time display picture, a capacity curve drawing interface, a capacity data display interface and a suggestion window. The video configuration interface is used for configuring parameters of a camera device (such as a USB camera) or setting an IPC address; the assembly line display picture displays a real-time production picture of each statistic point on the current assembly line; the productivity curve drawing interface is used for respectively drawing the productivity curves of each statistical point in the current hour and the current day according to the counting result of each material type, so that the production line manager can visually observe the productivity change condition of the production line; the productivity data display interface displays the productivity of each procedure in a digital mode.
S220, obtaining the production dependency relationship and the production index of each material type;
and acquiring the production dependency corresponding to each material type and the production index or the production plan corresponding to each material type from a storage device or a database.
S230, determining the material type with slow production process according to the production index and the counting result of each material type, and generating prompt information of the slow material type;
and the control device determines the material type with the production capacity lower than the preset capacity early warning value according to the acquired production index and the counting result of each material type, so as to generate prompt information or alarm information of the production procedure corresponding to the material type. Specifically, a software advice window displayed on the display screen of the control device may issue prompt information or alarm information. Specifically, if the current process of the material B is slow, prompt information can be thrown out to inform a manager that the process is slow; and the person to be dispatched and the number of the person to be dispatched can be directly prompted.
S240, searching an upstream material type associated with the retarded material type according to the production dependency relationship;
the production dependency relationship comprises an assembly level and a sequential logic among different workpieces, and the upstream material type associated with the slow material type can be searched according to the production dependency relationship.
And S250, generating a capacity balance scheme for adjusting the production efficiency of the upstream material type.
Due to the materials (workpieces) assembled at the same level in the production process, the low production capacity is easy to become a production capacity bottleneck. And the materials (workpieces) with high assembly levels need to comprehensively judge whether the productivity is insufficient according to the preorder, namely the productivity of the upstream materials (workpieces) and the time consumption of the process. And the control device generates a capacity balance scheme for adjusting the production efficiency of the upstream material type according to the production dependency relationship and the production index. Specifically, if the assembly of the material a depends on the completion of the material B process and the material C process, and the materials B and C processes are independent processes without dependency, the control device can generate a suggestion for balancing the capacities of the materials B and C, thereby improving the production efficiency of the process a. Optionally, the control device may be displayed in a suggestion window displayed on a display screen of the control device to generate a capacity balance scheme when monitoring that severe efficiency mismatch occurs in a production process of a production line according to a counting result of each material type, so as to optimize productivity of the production line.
EXAMPLE III
Fig. 3 shows a production line capacity monitoring apparatus according to a third embodiment of the present invention. On the basis of the first or second embodiment, the embodiment of the present invention further provides a production line capacity monitoring apparatus 3, which includes:
the frame to be detected extraction module 301 is configured to extract a plurality of frames to be detected from video data obtained by a shooting pipeline of the camera device;
in one embodiment, when extracting a plurality of frames to be detected from video data obtained from a shooting pipeline of an image capturing device, the frame to be detected extraction module 301 includes:
the first detection unit is used for detecting whether each frame of image in video data obtained by a shooting assembly line of the camera device contains tray information or not in real time;
a frame to be detected determining unit configured to determine, if any one of the frames of images contains tray information, the image containing the tray information and N-1 frames of images consecutive after the image in the video data as a frame to be detected; n is greater than 1;
the second detection unit is used for detecting whether each frame of image in the video data contains tray information or not at preset time intervals in real time after the frame to be detected is determined; the preset time is set according to the time consumed when the tray passes through the camera device.
An image preprocessing module 302, configured to perform image preprocessing on the frame to be detected;
in an implementation example, when performing image preprocessing on the frame to be detected, the image preprocessing module 302 includes:
the background removing unit is used for removing the background of the frame to be detected according to the background image;
and the tray area highlighting unit is used for highlighting the tray area in the image by carrying out binarization processing on the frame to be detected after the background is removed.
The screening module 303 is used for screening a tray image containing material information from the processed frame to be detected;
an image segmentation module 304, configured to segment the tray image according to a preset image segmentation rule;
in one embodiment, when the tray image is segmented according to a preset image segmentation rule, the image segmentation module 304 includes:
the material area extracting unit is used for extracting a material area from the tray image according to the color distinguishing characteristics of the material and the tray;
and the image segmentation unit is used for carrying out grid segmentation on the material area according to preset grid parameters.
A classification counting module 305, configured to classify and count materials in each partition area in the tray image through an image classification model, and output a material type and a counting result corresponding to the material type;
in an embodiment, when the image classification model classifies and counts materials for each segmented area in the tray image and outputs a material type and a counting result corresponding to the material type, the classification counting module 305 includes:
and the material classifying and counting unit is used for carrying out image recognition on each segmentation area in the material area through a feature recognition network, outputting the material type and adding one to the counting result of the material type.
And the scheme generating module 306 is used for generating a capacity balancing scheme according to the counting result of each material type.
In one embodiment, the plan generating module 306 for generating the capacity balancing plan according to the counting result of each material type includes:
the productivity curve generating unit is used for generating a productivity curve according to the counting result of each material type;
the data acquisition unit is used for acquiring the production dependency relationship and the production index of each material type;
the prompt information generating unit is used for determining the material type with slow production procedures according to the production index and the counting result of each material type and generating prompt information of the slow material type;
the upstream material type searching unit is used for searching an upstream material type associated with the retarded material type according to the production dependency relationship;
and the productivity balance scheme generating unit is used for generating a productivity balance scheme for adjusting the production efficiency of the upstream material type.
In one embodiment, the production line capacity monitoring apparatus further includes: and the background image updating module is used for controlling the camera device to acquire the background image of the assembly line at a preset sampling frequency and updating the stored background image.
According to the production line capacity monitoring device provided by the embodiment of the invention, a plurality of frames to be detected are extracted from video data obtained by shooting a production line by a camera device; carrying out image preprocessing on the frame to be detected; screening a tray image containing material information from the processed frame to be detected; segmenting the tray image according to a preset image segmentation rule; classifying and counting materials of each partition area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types; and generating a capacity balance scheme according to the counting result of each material type. A plurality of frames to be detected are extracted from video data shot by a camera device to realize non-contact type assembly line monitoring, and each frame to be detected corresponds to a tray which is transported by the assembly line and is used for containing materials, so that material information in the tray transported on the assembly line is not omitted. Screening out image frames without material information in the frames to be detected, segmenting tray images in the frames to be detected according to preset image segmentation rules, inputting each segmentation area into an image classification model, outputting material types and counting results corresponding to the material types, and completing capacity statistics of various materials on the production line. And generating a capacity balance scheme according to the counting result of each material type, thereby effectively optimizing the capacity of the production line.
Example four
Fig. 4 is a schematic structural diagram of a production line capacity monitoring system according to a fourth embodiment of the present invention. The embodiment of the invention also provides a production line capacity monitoring system, which comprises: an imaging device 41 and a control device 42 connected in communication with the imaging device; wherein the content of the first and second substances,
the imaging device 41 is provided above the assembly line and is used for shooting the assembly line.
The control device 42 implements the steps of the method for monitoring the capacity of the production line according to the first embodiment or the second embodiment.
Of course, the control device 42 provided in the embodiment of the present invention includes a computer-readable storage medium containing processor-executable instructions, and the processor-executable instructions are not limited to the method operations described above, but can also perform related operations in the production line capacity monitoring method provided in any embodiment of the present invention.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a production line capacity monitoring device according to a fifth embodiment of the present invention. The device 5 comprises: a processor 1, a memory 2 and a computer program 3 stored in said memory 2 and executable on said processor 1, such as a program for a production line capacity monitoring method. The processor 1 executes the computer program 3 to implement the steps of the above-mentioned method for monitoring production capacity of a production line, such as the steps S110 to S160 shown in fig. 1.
Illustratively, the computer program 3 may be partitioned into one or more modules, which are stored in the memory 2 and executed by the processor 1 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 3 in the apparatus. For example, the computer program 3 may be divided into a frame to be detected extraction module, an image preprocessing module, a screening module, an image segmentation module, a classification and counting module, and a scheme generation module, where the specific functions of each module are as follows:
the frame extraction module to be detected is used for extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of the camera device;
the image preprocessing module is used for preprocessing the image of the frame to be detected;
the screening module is used for screening the tray image containing the material information from the processed frame to be detected;
the image segmentation module is used for segmenting the tray image according to a preset image segmentation rule;
the classification counting module is used for classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
and the scheme generation module is used for generating a productivity balance scheme according to the counting result of each material type.
The apparatus may include, but is not limited to, a processor 1, a memory 2, and a computer program 3 stored in the memory 2. Those skilled in the art will appreciate that fig. 5 is merely an example of a production line capacity monitoring apparatus and does not constitute a limitation of the apparatus, and may include more or less components than those shown, or combine some components, or different components, for example, the apparatus may further include input output devices, network access devices, buses, etc.
The Processor 1 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 2 may be an internal storage unit of the control device, such as a hard disk or a memory of the control device. The memory 2 may be an external storage device such as a plug-in hard disk provided in the image pickup apparatus, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like. Further, the memory 2 may also include both an internal storage unit of the apparatus and an external storage device. The memory 2 is used for storing the computer program and other programs and data required by the production line capacity monitoring method. The memory 2 may also be used for temporarily storing data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned functional units and modules are illustrated as being divided, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the apparatus may be divided into different functional units or modules to complete all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit, and the integrated unit may be implemented in the form of a hardware or a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. For the specific working processes of the units and modules in the system, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described or recited in detail in a certain embodiment, reference may be made to the descriptions of other embodiments.
Those of ordinary skill in the art would appreciate that the elements and algorithm steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when the actual implementation is performed, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the method according to the embodiments of the present invention may also be implemented by instructing related hardware through a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, and software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; 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; such modifications and substitutions do not substantially depart from the spirit and scope of the present invention, and are intended to be included within the scope thereof.
Claims (10)
1. A production line capacity monitoring method is characterized by comprising the following steps:
extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of a camera device;
carrying out image preprocessing on the frame to be detected;
screening a tray image containing material information from the processed frame to be detected;
segmenting the tray image according to a preset image segmentation rule;
classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
and generating a capacity balance scheme according to the counting result of each material type.
2. The production line capacity monitoring method as claimed in claim 1, wherein the extracting a plurality of frames to be detected from the video data obtained from the camera shooting pipeline comprises:
detecting whether each frame of image in video data obtained by a shooting assembly line of a camera device contains tray information or not in real time;
if any frame of image contains tray information, determining the image containing the tray information and N-1 frames of images which are continuous behind the image in the video data as frames to be detected; n is greater than 1;
after the frame to be detected is determined, detecting whether each frame image in the video data contains tray information or not at intervals of preset time in real time; the preset time is set according to the time consumed when the tray passes through the camera device.
3. The production line capacity monitoring method of claim 1, further comprising:
and controlling the camera device to acquire the background image of the assembly line at a preset sampling frequency, and updating the stored background image.
4. The production line capacity monitoring method of claim 1, wherein the segmenting the tray image according to preset image segmentation rules comprises:
extracting a material area from the tray image according to the color distinguishing characteristics of the material and the tray;
and carrying out grid segmentation on the material area according to preset grid parameters.
5. The production line capacity monitoring method of claim 4, wherein the classifying and counting the materials in each divided area of the tray image by the image classification model and outputting the material type and the counting result corresponding to the material type comprises:
and performing image recognition on each segmentation area in the material area through a feature recognition network, outputting a material type, and adding one to the counting result of the material type.
6. The production line capacity monitoring method of claim 1, wherein the image preprocessing of the frames to be detected comprises:
removing the background of the frame to be detected according to the background image;
and carrying out binarization processing on the frame to be detected after the background is removed to highlight the tray area in the image.
7. The production line capacity monitoring method of any one of claims 1 to 6, wherein the generating the capacity balancing plan according to the counting result of each material type comprises:
generating a productivity curve according to the counting result of each material type;
obtaining the production dependency relationship and the production index of each material type;
determining the material type with slow production procedure according to the production index and the counting result of each material type, and generating prompt information of the slow material type;
searching an upstream material type associated with the slow material type according to the production dependency relationship;
and generating a capacity balance scheme for adjusting the production efficiency of the upstream material type.
8. A production line capacity monitoring device, comprising:
the frame extraction module to be detected is used for extracting a plurality of frames to be detected from video data obtained by a shooting assembly line of the camera device;
the image preprocessing module is used for preprocessing the image of the frame to be detected;
the screening module is used for screening the tray image containing the material information from the processed frame to be detected;
the image segmentation module is used for segmenting the tray image according to a preset image segmentation rule;
the classification counting module is used for classifying and counting materials of each segmentation area in the tray image through an image classification model, and outputting material types and counting results corresponding to the material types;
and the scheme generation module is used for generating a productivity balance scheme according to the counting result of each material type.
9. A production line capacity monitoring system is characterized by comprising a camera device and a control device in communication connection with the camera device; wherein the content of the first and second substances,
the camera device is arranged above the assembly line and is used for shooting the assembly line;
the control device executes the production line capacity monitoring method according to any one of claims 1 to 7.
10. A production line capacity monitoring apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the steps of the production line capacity monitoring method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921947.9A CN110647851B (en) | 2019-09-27 | 2019-09-27 | Production line capacity monitoring method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921947.9A CN110647851B (en) | 2019-09-27 | 2019-09-27 | Production line capacity monitoring method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110647851A true CN110647851A (en) | 2020-01-03 |
| CN110647851B CN110647851B (en) | 2022-12-09 |
Family
ID=69011608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910921947.9A Active CN110647851B (en) | 2019-09-27 | 2019-09-27 | Production line capacity monitoring method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647851B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427323A (en) * | 2020-04-22 | 2020-07-17 | Oppo（重庆）智能科技有限公司 | Capacity bottleneck monitoring method, device, equipment and storage medium |
| CN113009895A (en) * | 2021-03-08 | 2021-06-22 | 联想(北京)有限公司 | Dynamic production control method, system and storage medium |
| CN114115162A (en) * | 2021-11-29 | 2022-03-01 | 扬州三星塑胶有限公司 | PET production process material feeding control method and system |
| CN114213975A (en) * | 2021-11-15 | 2022-03-22 | 三峡大学 | Full-type rosin dissolving and separating process measurement and control and automatic production system |
| CN115019578A (en) * | 2022-05-18 | 2022-09-06 | 湖南铁道职业技术学院 | Component dismounting training method and system |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030170357A1 (en) * | 1997-03-13 | 2003-09-11 | Garwood Anthony J.M. | Processing meat products responsive to customer orders |
| US20030185948A1 (en) * | 1997-03-13 | 2003-10-02 | Garwood Anthony J.M. | Packages and methods for processing food products |
| CN1477589A (en) * | 2002-07-31 | 2004-02-25 | ������������ʽ���� | Image processing method and device |
| WO2006012160A2 (en) * | 2004-06-25 | 2006-02-02 | Michael Seubert | Consistent set of interfaces derived from a business object model |
| CN103020707A (en) * | 2012-10-19 | 2013-04-03 | 浙江工业大学 | Flow type high-precision and high-speed automatic counting device for particle matters based on machine vision |
| CN103028945A (en) * | 2012-12-31 | 2013-04-10 | 南京奥特电气股份有限公司 | System, method and device for prefabricating informatization whole-lifecycle pipeline |
| CN104992218A (en) * | 2015-07-10 | 2015-10-21 | 天津大学 | Production line output real-time automatic counting device and counting method thereof |
| CN105366249A (en) * | 2015-11-16 | 2016-03-02 | 江苏力星通用钢球股份有限公司 | Intelligent workshop for producing steel balls |
| CN105741288A (en) * | 2016-01-29 | 2016-07-06 | 北京正齐口腔医疗技术有限公司 | Tooth image segmentation method and apparatus |
| CN106295705A (en) * | 2016-08-17 | 2017-01-04 | 汕头市三三智能科技有限公司 | A kind of many colors material screening number system under movement background |
| CN106738963A (en) * | 2017-01-06 | 2017-05-31 | 宁波海迈克自动化科技有限公司 | A kind of plastic pallet automatic assembly line |
| CN108734731A (en) * | 2018-05-29 | 2018-11-02 | 中科院广州电子技术有限公司 | A kind of class rounded grain object count method based on machine vision |
| CN109230580A (en) * | 2018-10-11 | 2019-01-18 | 西安中科光电精密工程有限公司 | It is a kind of based on the mixed unstacking robot system and method for putting material information acquisition |
| CN109550712A (en) * | 2018-12-29 | 2019-04-02 | 杭州慧知连科技有限公司 | A kind of chemical fiber wire tailfiber open defect detection system and method |
| CN110146019A (en) * | 2019-06-13 | 2019-08-20 | 哈工大机器人（合肥）国际创新研究院 | A kind of workpiece size on-line checking and automatic compensating method based on industrial camera |
| CN110203600A (en) * | 2019-06-06 | 2019-09-06 | 北京卫星环境工程研究所 | Suitable for spacecraft material be automatically stored and radio frequency |
-
2019
- 2019-09-27 CN CN201910921947.9A patent/CN110647851B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030170357A1 (en) * | 1997-03-13 | 2003-09-11 | Garwood Anthony J.M. | Processing meat products responsive to customer orders |
| US20030185948A1 (en) * | 1997-03-13 | 2003-10-02 | Garwood Anthony J.M. | Packages and methods for processing food products |
| CN1477589A (en) * | 2002-07-31 | 2004-02-25 | ������������ʽ���� | Image processing method and device |
| WO2006012160A2 (en) * | 2004-06-25 | 2006-02-02 | Michael Seubert | Consistent set of interfaces derived from a business object model |
| CN103020707A (en) * | 2012-10-19 | 2013-04-03 | 浙江工业大学 | Flow type high-precision and high-speed automatic counting device for particle matters based on machine vision |
| CN103028945A (en) * | 2012-12-31 | 2013-04-10 | 南京奥特电气股份有限公司 | System, method and device for prefabricating informatization whole-lifecycle pipeline |
| CN104992218A (en) * | 2015-07-10 | 2015-10-21 | 天津大学 | Production line output real-time automatic counting device and counting method thereof |
| CN105366249A (en) * | 2015-11-16 | 2016-03-02 | 江苏力星通用钢球股份有限公司 | Intelligent workshop for producing steel balls |
| CN105741288A (en) * | 2016-01-29 | 2016-07-06 | 北京正齐口腔医疗技术有限公司 | Tooth image segmentation method and apparatus |
| CN106295705A (en) * | 2016-08-17 | 2017-01-04 | 汕头市三三智能科技有限公司 | A kind of many colors material screening number system under movement background |
| CN106738963A (en) * | 2017-01-06 | 2017-05-31 | 宁波海迈克自动化科技有限公司 | A kind of plastic pallet automatic assembly line |
| CN108734731A (en) * | 2018-05-29 | 2018-11-02 | 中科院广州电子技术有限公司 | A kind of class rounded grain object count method based on machine vision |
| CN109230580A (en) * | 2018-10-11 | 2019-01-18 | 西安中科光电精密工程有限公司 | It is a kind of based on the mixed unstacking robot system and method for putting material information acquisition |
| CN109550712A (en) * | 2018-12-29 | 2019-04-02 | 杭州慧知连科技有限公司 | A kind of chemical fiber wire tailfiber open defect detection system and method |
| CN110203600A (en) * | 2019-06-06 | 2019-09-06 | 北京卫星环境工程研究所 | Suitable for spacecraft material be automatically stored and radio frequency |
| CN110146019A (en) * | 2019-06-13 | 2019-08-20 | 哈工大机器人（合肥）国际创新研究院 | A kind of workpiece size on-line checking and automatic compensating method based on industrial camera |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427323A (en) * | 2020-04-22 | 2020-07-17 | Oppo（重庆）智能科技有限公司 | Capacity bottleneck monitoring method, device, equipment and storage medium |
| CN111427323B (en) * | 2020-04-22 | 2021-09-24 | Oppo（重庆）智能科技有限公司 | Capacity bottleneck monitoring method, device, equipment and storage medium |
| CN113009895A (en) * | 2021-03-08 | 2021-06-22 | 联想(北京)有限公司 | Dynamic production control method, system and storage medium |
| CN114213975A (en) * | 2021-11-15 | 2022-03-22 | 三峡大学 | Full-type rosin dissolving and separating process measurement and control and automatic production system |
| CN114213975B (en) * | 2021-11-15 | 2023-04-07 | 三峡大学 | Full-type rosin dissolving and separating process measurement and control and automatic production system |
| CN114115162A (en) * | 2021-11-29 | 2022-03-01 | 扬州三星塑胶有限公司 | PET production process material feeding control method and system |
| CN115019578A (en) * | 2022-05-18 | 2022-09-06 | 湖南铁道职业技术学院 | Component dismounting training method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110647851B (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647851B (en) | Production line capacity monitoring method, device and system | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| WO2022088620A1 (en) | State detection method and apparatus for camera lens, device and storage medium | |
| CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| CN112347887B (en) | Object detection method, object detection device and electronic equipment | |
| CN111598827A (en) | Appearance flaw detection method, electronic device and storage medium | |
| CN109740533A (en) | Masking ratio determines method, apparatus and electronic system | |
| CN105869175A (en) | Image segmentation method and system | |
| US20200013169A1 (en) | Image processing device, image processing method, and recording medium | |
| KR101030257B1 (en) | Method and System for Vision-Based People Counting in CCTV | |
| CN110677585A (en) | Target detection frame output method and device, terminal and storage medium | |
| Malhi et al. | Vision based intelligent traffic management system | |
| CN108171135A (en) | Method for detecting human face, device and computer readable storage medium | |
| CN114155241A (en) | Foreign matter detection method and device and electronic equipment | |
| US11430154B2 (en) | Classification of change related to display rack | |
| CN110119675B (en) | Product identification method and device | |
| CN109030499B (en) | Device and method suitable for continuous online detection of target defects and preventing repeated counting of defect number | |
| CN110070558A (en) | It is a kind of that method and device is sorted based on the statistics of image procossing and Subarea detecting | |
| Sudana et al. | Mobile Application for Identification of Coffee Fruit Maturity using Digital Image Processing | |
| CN117351472A (en) | Tobacco leaf information detection method and device and electronic equipment | |
| CN116823795A (en) | Defect detection method and device for rubber product, electronic equipment and storage medium | |
| CN111783528A (en) | Method, computer and system for monitoring items on a shelf | |
| CN112488986A (en) | Cloth surface flaw identification method, device and system based on Yolo convolutional neural network | |
| CN113012137B (en) | Panel defect inspection method, system, terminal device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |