CN111914953A - Food ingredient flow monitoring system based on Internet of things - Google Patents
Food ingredient flow monitoring system based on Internet of things Download PDFInfo
- Publication number
- CN111914953A CN111914953A CN202010875210.0A CN202010875210A CN111914953A CN 111914953 A CN111914953 A CN 111914953A CN 202010875210 A CN202010875210 A CN 202010875210A CN 111914953 A CN111914953 A CN 111914953A
- Authority
- CN
- China
- Prior art keywords
- batching
- module
- information
- image
- standard
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a food batching flow monitoring system based on the Internet of things, wherein a video acquisition module acquires batching video information at a batching port, sends the batching video information to a video processing module to extract key frame images X in the batching video information, sends the key frame images X to an image processing module to obtain image hash values of all single sub-areas, sends the image hash values to a data fusion module, a data analysis module calls corresponding standard data packets according to fusion data packets and carries out comparison analysis, sends analysis result data packets to a monitoring terminal, the monitoring terminal receives the analysis result data packets and carries out data interaction with a consumer query module, an enterprise early warning module and a supervision department monitoring module, the transparency of food production is increased, a guarantee is set for some non-publicable production flows, and the secret production flow process of an enterprise is protected, but also can improve the trust of consumers on food safety.
Description
Technical Field
The invention relates to the field of monitoring of the Internet of things, in particular to a food ingredient flow monitoring system based on the Internet of things.
Background
Along with the continuous improvement of the living standard of people, people pay more and more attention to food safety problems, the source of food safety events is that the food production process is opaque and the sanitation is not up to the standard, the abuse of food preservatives, coloring agents, oxidizing agents and illegal additives is avoided, the quality of purchased raw materials is not relevant, and the phenomenon of sub-quality exists, some food enterprises disclose some production process videos for the purpose of ensuring consumers to be relieved to achieve the purpose of sales promotion, but the production process relates to a secret product process flow, particularly, when some processes are required to be operated by people, some food sanitation safety hazards are inevitable, even if the consumers can see partial production processes and the content of nutrient components of food, the consumers cannot confirm that the whole production process is standard production, the phenomenon that monitoring probes are installed in each production link is very common, the installation monitoring devices are mostly used for helping the management of the food production enterprises, the problems of unqualified sanitation and irregular operation of operators are solved, but the personnel in the enterprise still are responsible for monitoring and managing, and the production process is still opaque for consumers.
The Internet of things is an important component of a new generation of information technology and is also an important development stage of an 'informatization' era, a food ingredient flow monitoring system is combined with the Internet of things for use, and an informatization, remote management control and intelligentization network is realized.
Disclosure of Invention
In view of the above situation, the present invention aims to provide a food ingredient flow monitoring system based on the internet of things, which aims to solve the problem of food safety in the ingredient process of food production, increase the monitoring strength of the supervision department, and improve the trust of consumers on food safety.
The technical scheme includes that the food ingredient flow monitoring system based on the Internet of things comprises a video acquisition module, a position information module and a quality acquisition module, wherein the video acquisition module acquires ingredient video information at an ingredient opening and sends the ingredient video information to a video processing module, the video processing module extracts a key frame image X in the ingredient video information and sends the key frame image X to an image processing module, the image processing module calculates image hash values of sub-regions of all frame images in the key frame image X and combines the image hash values into an image hash value sum X-I, then the image hash value sum X-I is sent to a data fusion module, the position acquisition module sends positioned position information to the data fusion module, the quality acquisition module sends all ingredient quality information and production batch information in a production batch material feeding process to the data fusion module, and the data fusion module fuses the received information into a model by taking the position information as a mark, the system comprises a data analysis module, a monitoring terminal and a data interaction module, wherein the data analysis module takes position information as a mark to call a standard data packet in a database for analysis and sends an analysis result data packet to the monitoring terminal, and the monitoring terminal receives the analysis result data packet and performs data interaction with a consumer query module, an enterprise early warning module and a supervision department monitoring module;
the video processing module receives the batching video information collected by the video collecting module and carries out video processing, and the video processing method comprises the following specific steps:
1) taking a feeding start frame image to a feeding end frame image as a first frame image of the batching video lens, taking the frame image of the feeding start frame image as a last frame image of the batching video lens, adopting a video lens boundary detection method to detect the batching video lens, and extracting the first frame image and the last frame image of the batching video lens as boundary key frame images;
2) on the basis of the step 1, a video lens segmentation technology is utilized to segment the detected batching video lens, and a color histogram difference A of all adjacent two frames of images in the batching video lens is calculated by adopting a color histogram difference method based on the color characteristics of a batching port on a batching device;
setting a threshold value T =0.5, wherein the threshold value T represents a critical value of a color histogram difference A, extracting frame images when the color histogram difference A is larger than the threshold value T, arranging the frame images into an intermediate key frame image sequence, and eliminating the frame images when the color histogram difference A is smaller than or equal to the threshold value T;
3) and sequencing the boundary key frame images and the middle key frame image sequence to obtain a key frame sequence, extracting a key frame image X in the key frame sequence by adopting a clustering algorithm taking the color characteristics of a batching port on the first frame image batching device as a clustering center, wherein the key frame image X is a combination of five frames of images, and sending the key frame image X to an image processing module.
The image processing module performs gray processing on the received key frame image X, then sequentially divides each frame image in the key frame image X into three subregions, namely a batching port a on a batching device, a batching vehicle b and a batching device ground c, according to gray value characteristics by using a gray threshold segmentation method, respectively calculates image hash values a-I, b-I and c-I (I =1,2,3,4 and 5) of each subregion, finally obtains the sum of the image hash values of all subregions of the five frames of images in the key frame image X, defines the sum as X-I, and transmits the X-I to the data fusion module.
The data analysis module receives the fusion data sent by the data fusion module, extracts the position information in the fusion data, extracts a standard data packet of corresponding standard position information in the database according to the position information in the fusion data, and extracts the sum X of standard ingredient quality information and the standard image Hash value in the standard data packet’I, comparing the ingredient quality information with standard ingredient quality information to obtain a quality comparison result, firstly adding all the qualities of the material putting processes of one production batch to obtain a total quality sum, subtracting the standard total quality of the material putting processes of one production batch in the standard ingredient information to obtain a material quality difference, and dividing the material quality difference by the standard total quality to obtain a percentage, wherein if the percentage is more than one percent, the quality comparison result is unqualified, and if the percentage is less than or equal to one percent, the quality comparison result is comparedThe result is that the quality is qualified; comparing the image hash value sum X-I with the standard image hash value sum X '-I, namely comparing the sub-region image hash values a-I, b-I, c-I (I =1,2,3,4,5) of each frame image in the key frame image X with the a in the standard image hash value sum X' -I’-i、b’-i、c’I (i =1,2,3,4,5), comparing one by one, if the comparison result is that the number of different data bits of each hash value is within the range of 0-2, the image comparison result is safe in the batching process, otherwise, if the number of different data bits of one hash value is greater than 2, the image comparison result is unsafe in the batching process, combining the quality comparison result, the image comparison result and the production batch information into an analysis result data packet and sending the analysis result data packet to the monitoring terminal, wherein the analysis result data packet takes the production batch information as a mark, and takes the image comparison result and the quality comparison result as contents.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages;
1. the video processing module extracts the ingredient video shots by using a video shot boundary detection and video shot cutting method, then extracts boundary frame images and middle key frame sequences of the ingredient video shots respectively and arranges the boundary frame images and the middle key frame sequences as the key frame sequences, and then extracts the key frame images X by using a clustering method based on color characteristics at an ingredient port, so that useless frame image information is filtered out by the video processing module, and the problems of large video information amount and information redundancy are solved.
2. The image processing module divides each frame image in the key frame image X into different sub-regions, and then calculates the image hash value of the sub-region, so that the corresponding sub-region can be accurately obtained according to the image hash value.
3. By adopting the technical scheme, the supervision of the supervision department can be enhanced, a large amount of human resources are saved for the supervision department, a consumer can inquire the production information of food, the undisclosed food blending process can also determine whether the food is safe or not according to the inquiry result, the transparency of food production is increased, some production processes which are not publicized are guaranteed, the secret production process of an enterprise is protected, and meanwhile the trust of the consumer on the food safety can be improved.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a block flow diagram of a video processing module according to the present invention;
FIG. 3 is a block diagram of a flow diagram of an image processing module of the present invention;
FIG. 4 is a block diagram of a data analysis module according to the present invention.
Detailed Description
The foregoing and other aspects, features and advantages of the invention will be apparent from the following more particular description of embodiments of the invention, as illustrated in the accompanying drawings in which reference is made to figures 1 to 4. The structural contents mentioned in the following embodiments are all referred to the attached drawings of the specification.
The utility model provides a food batching flow monitored control system based on thing networking, the system includes video acquisition module, video processing module, image processing module, positional information module, quality acquisition module, data fusion module, data analysis module, monitor terminal, database, consumer inquiry module, enterprise's early warning module and supervision department monitoring module:
the video acquisition module is used for acquiring batching video information of the material feeding process at the batching port and sending the batching video information to the video processing module, wherein the batching video information comprises all production batch material feeding processes fed into the batching device, and if a food safety problem occurs, the video acquisition module can be traced back to prevent the material feeding sequence error in the batching process and the sanitation problem in the feeding process;
the video processing module extracts a key frame image X in the batching video information and sends the key frame image X to the image processing module, the batching video information contains a large amount of redundant information, so that the problem of difficulty in searching the video information is solved, and in order to solve the problem of information redundancy, a representative key frame image X in the batching video is selected by using a key frame extraction method;
the image processing module calculates image hash values of sub-regions of all frame images in the key frame image X and combines the image hash values into an image hash value sum X-I, then the X-I is sent to the data fusion module, the table, the batching vehicle and the batching residue and the garbage residue on the ground of a batching port of the batching device can be observed through the frame images, the position acquisition module sends the positioned position information to the data fusion module, the position of the batching device batching port can be found through the position information, the position information can also be used for corresponding to the standard position information, a standard data packet is taken to be compared with a fusion data packet, the quality acquisition module sends all batching quality information and production batch information of a production batch material feeding process to the data fusion module, and the production batch material feeding process refers to a whole batching process, the quality acquisition module uploads the quality of each feeding and the production batch information together, the data fusion module fuses the received information into a fusion data packet which takes position information as a mark and takes the batching quality information, the production batch information and the image Hash value sum X-I as contents and sends the fusion data packet to the data analysis module, namely, the data analysis module takes the position information as the mark to call a standard data packet in a database for analysis and sends an analysis result data packet to the monitoring terminal, and the monitoring terminal receives the analysis result data packet and performs data interaction with the consumer query module, the enterprise early warning module and the monitoring department monitoring module;
the video processing module receives the batching video information collected by the video collecting module and carries out video processing, and the video processing method comprises the following specific steps:
1) the batching video information is a video of each production batch material throwing process, the video comprises a video clip of the throwing process and redundant video information without throwing motion, so that a batching video shot is formed in the batching video information from the beginning of throwing of one production batch to the end of throwing of one production batch, a frame image at the beginning of throwing is taken as a first frame image of the batching video shot, a frame image at the end of throwing is taken as a last frame image of the batching video shot, the material throwing process is that materials are thrown in a batching port of a batching truck, a video shot boundary detection method is adopted to detect the boundary of the batching video shot, and the first frame image and the last frame image of the batching video shot are extracted as boundary key frame images;
2) on the basis of step 1, only the boundary of the batching video shot is detected, but redundant video information in the batching video information is not removed, therefore, the detected batching video shots are segmented by utilizing a video shot segmentation technology, the extracted batching video shots are processed, the video information amount of video processing is reduced, one batching video shot is composed of a plurality of frame images, the information variation amount between the adjacent frame images can be judged by colors, in order to remove redundant frame images with small information variation in the batching video lens, key frames in the batching video lens are extracted by using a color histogram difference method, so that the video information amount to be processed is further reduced, and the color histogram difference A of all adjacent two frame images in the batching video lens is calculated by using the color histogram difference method based on the color characteristics of a batching port on a batching device;
setting a threshold value T =0.5, wherein the threshold value T represents a critical value of the color histogram difference A, extracting the frame images when the color histogram difference A is larger than the threshold value T, and arranging the frame images into an intermediate key frame image sequence, namely two adjacent frame images P1And P2，P2If the color histogram difference value from the previous frame image P1 is greater than the threshold value T, the frame image P is extracted2Calculating color histogram difference of all frame images in the key frame sequence in this way, and eliminating the frame images when the color histogram difference A is less than or equal to a threshold value T;
3) the method comprises the steps of sequencing a boundary key frame image and an intermediate key frame image sequence to obtain a key frame sequence, wherein the first frame image of the boundary key frame is used as the first frame of the key frame sequence, the last frame image is used as the last frame of the key frame sequence, and the intermediate key frame image sequence is an intermediate frame of the key frame sequence, because the boundary key frame image can only reflect the start and the end of an ingredient video shot and can not reflect the information in the ingredient video shot, although the intermediate frame image sequence can reflect the change in the middle of the ingredient video shot, the intermediate frame image sequence extracts too many frame images by a color histogram difference method, the image processing process becomes complex, so the key frame image X in the key frame sequence is extracted by adopting a clustering algorithm which takes the color characteristics of an ingredient port on a first frame image ingredient device as a clustering center, and the key frame image X is a combination of five frame images, and the five frames of images are extracted from a fixed time period and a production batching flow, can be compared with data in a standard data packet in a database, and judge the batching process.
The video acquisition module be monitoring device, the batching video information of each production batch material feeding process of batching mouth on the proportioning device is gathered to monitoring device, a production batch represents a feeding process, the monitoring device monitors the feeding sequence of each feeding process and the health of batching mouth department.
The key frame image X collected from the batching video lens represents the change of key information in the batching process, if a standard image is directly compared with the key frame image X, the comparison result is difficult to determine, so the image processing module further processes the received key frame image X, grays the key frame image X, then sequentially divides each frame image in the key frame image X into three subregions of a batching port a on the batching device, a batching vehicle b and a batching device ground c according to gray value characteristics by using a gray threshold value division method, respectively calculates image hash values a-I, b-I and c-I (I =1,2,3,4 and 5) of each subregion, finally obtains the image hash value sum of all subregions of five frame images in the key frame image X and defines the image hash values as X-I, and transmits the X-I to the data fusion module, the safety of the batching process is determined by determining the image of each sub-area.
The quality sensor module transmits the batching quality information and the production batch information entering the batching port to the data fusion module, and a production batch material is put in and can be divided into a plurality of times, and a quality can be generated once, and the batching quality information comprises all material qualities of a production batch material putting process, position information include enterprise position information, workshop position information, batching port position information and monitoring device position information, a monitoring device is installed at a batching port, and batching port position information and monitoring device's position information phase-match.
And the data fusion module fuses the position information, the batching quality information, the production batch information and the image hash value sum X-I into a fusion data packet and sends the fusion data packet to the data analysis module, the position information is used as a mark, and the batching quality information, the production batch information and the X-I are used as the fusion data packet content.
The standard data packet is acquired in the same acquisition mode, the standard data packet is standard data acquired when the quality of the standard data packet reaches the standard, the sanitation of the standard data packet reaches the standard and no operation abnormity occurs in the feeding process, the standard data packet is a standard for judging the result of the fusion data packet, and the standard data packet comprises standard position information, standard ingredient quality information and a standard image Hash value X’And I, marking standard position information as a mark of a standard data packet, and marking standard batching quality information and a standard image hash value sum X' -I as the content of the standard data packet, wherein the standard position information comprises standard enterprise position information, standard production workshop position information, standard batching port position information and standard monitoring device position information, the standard position information corresponds to the position information, and the standard position information further comprises each batching name, batching proportion and batching duration of the whole food production process.
The data analysis module receives the fusion data packet sent by the data fusion module, extracts the position information in the fusion data packet, extracts a standard data packet of corresponding standard position information in the database according to the position information in the fusion data packet, and extracts the standard ingredient quality information and the standard image hash value sum X in the standard data packet’-I, comparing the ingredient quality information with the standard ingredient quality information and obtaining a quality comparison result, the ingredient quality information comprising the quality of all the fed materials of a production batch, and the standard data packet comprising the standard total quality of all the fed materials of a production batch, so that the total quality sum is obtained by adding all the qualities of the material feeding processes of a production batch, the material quality difference is obtained by subtracting the standard total quality of the material feeding processes of a production batch in the standard ingredient information, and the material quality difference is obtained by dividing the material quality sum by the standard total qualityIf the percentage is more than one percent, the quality comparison result is that the quality is unqualified, and if the percentage is less than or equal to one percent, the quality comparison result is that the quality is qualified; comparing the image hash value sum X-I with the standard image hash value sum X' -I, namely comparing the sub-region image hash values a-I, b-I, c-I (I =1,2,3,4,5) of each frame image in the key frame image X with the standard image hash value sum X `’A in-I’-i、b’-i、c’I (i =1,2,3,4,5), comparing one by one, if the comparison result is that the number of different data bits of each hash value is within the range of 0-2, the image comparison result is safe in the batching process, otherwise, if the number of different data bits of one hash value is greater than 2, the image comparison result is unsafe in the batching process, combining the quality comparison result, the image comparison result and the production batch information into an analysis result data packet and sending the analysis result data packet to the monitoring terminal, wherein the analysis result data packet takes the production batch information as a mark, and takes the image comparison result and the quality comparison result as contents.
The monitoring terminal receives the analysis result data packet and performs information interaction with the consumer query module, the enterprise early warning module and the monitoring module of the monitoring department, and the consumer can query an image comparison result and a quality comparison result of the batching process corresponding to the product batch information through the consumer query module; the consumer inquires the comparison result in the batching process, the consumer cannot inquire the batching video information in the batching process, and the consumer can inquire the batching video information through a mobile phone and a computer; when the image comparison result is that the batching process is unsafe, the analysis result data packet is sent to the inquiry mobile equipment of the enterprise personnel related to the enterprise early warning module, when the image comparison result is that the batching process is safe, the analysis result data packet is not sent to the enterprise early warning module, the inquiry mobile equipment can be a mobile phone, a computer and special alarm equipment, and when the quality comparison result is that the quality is not qualified, the analysis result data packet is also sent to the enterprise early warning module to inform the related enterprise personnel; the monitoring department monitoring module can call information received by the monitoring terminal, and can also directly extract batching video information, key frame image X, position information, batching quality information and product batch information in the system, the monitoring department monitoring module occupies an important position in the monitoring system of the whole food batching process, if a food safety problem occurs, the monitoring department can trace any module in the system, call information in the module and inquire batching processes of different production batches.
When the automatic batching system is used specifically, the video acquisition module acquires batching video information of a material throwing process at a batching port and sends the batching video information to the video processing module, wherein the batching video information comprises all production batch material throwing processes thrown into a batching device; in order to solve the problem of information redundancy, a representative key frame image X in the batching video is selected by using a key frame extraction method, the image processing module calculates image hash values of subregions of all frame images in the key frame image X and combines the image hash values into an image hash value sum X-I, then the X-I is sent to a data fusion module, batching residues and garbage residues on the ground of a table, a batching truck and a batching port at the batching port of a batching device can be observed through the frame images, a position acquisition module sends the positioned position information to the data fusion module, and the position of the concrete batching device batching port can be found through the position information, or the position information corresponds to the standard position information, a standard data packet is called to be compared with a fusion data packet, a quality acquisition module sends all ingredient quality information and production batch information of a production batch material putting process to a data fusion module, the production batch material putting process refers to the whole process of one-time ingredient distribution, the quality acquisition module uploads the quality and product batch information of each time of material putting, the data fusion module fuses the received information into a fusion data packet which takes the position information as a mark and takes the ingredient quality information, the production batch information and the sum X-I of the image hash values as contents and sends the fusion data packet to a data analysis module, namely the data analysis module takes the position information as the mark to call the standard data packet in a database for analysis and sends the analysis result data packet to a monitoring terminal, and the monitoring terminal receives the analysis result data packet and compares the analysis result data packet with a consumer query module, And the enterprise early warning module and the monitoring module of the supervision department perform data interaction.
While the invention has been described in further detail with reference to specific embodiments thereof, it is not intended that the invention be limited to the specific embodiments thereof; for those skilled in the art to which the present invention pertains and related technologies, the extension, operation method and data replacement should fall within the protection scope of the present invention based on the technical solution of the present invention.
Claims (8)
1. A food batching flow monitoring system based on the Internet of things is characterized by comprising a video acquisition module, a position information module and a quality acquisition module, wherein the video acquisition module acquires batching video information at a batching port and sends the batching video information to a video processing module, the video processing module extracts a key frame image X in the batching video information and sends the key frame image X to an image processing module, the image processing module calculates image hash values of sub-regions of all frame images in the key frame image X and combines the image hash values into an image hash value sum X-I, then the image hash value sum X-I is sent to a data fusion module, the position acquisition module sends the positioned position information to the data fusion module, the quality acquisition module sends all batching quality information and production batch information of a production batch material putting process to the data fusion module, and the data fusion module fuses the received information into a state marked by using the position information, the system comprises a data analysis module, a monitoring terminal and a data interaction module, wherein the data analysis module takes position information as a mark to call a standard data packet in a database for analysis and sends an analysis result data packet to the monitoring terminal, and the monitoring terminal receives the analysis result data packet and performs data interaction with a consumer query module, an enterprise early warning module and a supervision department monitoring module;
the video processing module receives the batching video information collected by the video collecting module and carries out video processing, and the video processing method comprises the following specific steps:
1) taking a feeding start frame image to a feeding end frame image as a first frame image of the batching video lens, taking the frame image of the feeding start frame image as a last frame image of the batching video lens, adopting a video lens boundary detection method to detect the batching video lens, and extracting the first frame image and the last frame image of the batching video lens as boundary key frame images;
2) on the basis of the step 1, a video lens segmentation technology is utilized to segment the detected batching video lens, and a color histogram difference A of all adjacent two frames of images in the batching video lens is calculated by adopting a color histogram difference method based on the color characteristics of a batching port on a batching device;
setting a threshold value T =0.5, wherein the threshold value T represents a critical value of a color histogram difference A, extracting frame images when the color histogram difference A is larger than the threshold value T, arranging the frame images into an intermediate key frame image sequence, and eliminating the frame images when the color histogram difference A is smaller than or equal to the threshold value T;
3) and sequencing the boundary key frame images and the middle key frame image sequence to obtain a key frame sequence, extracting a key frame image X in the key frame sequence by adopting a clustering algorithm taking the color characteristics of a batching port on the first frame image batching device as a clustering center, wherein the key frame image X is a combination of five frames of images, and sending the key frame image X to an image processing module.
2. The Internet of things-based food ingredient flow monitoring system according to claim 1, wherein the video acquisition module is a monitoring device, and the monitoring device acquires ingredient video information of each production batch material feeding process of an ingredient port of the ingredient device.
3. The internet-of-things-based food ingredient flow monitoring system according to claim 1, wherein the image processing module performs graying processing on the received key frame image X, then sequentially divides each frame image in the key frame image X into three sub-areas, namely an ingredient opening a on an ingredient device, an ingredient vehicle b and an ingredient device ground c, according to gray value characteristics by using a gray threshold segmentation method, calculates image hash values a-I, b-I and c-I (I =1,2,3,4 and 5) of each sub-area, finally obtains the sum of the image hash values of all the sub-areas of the five frame images in the key frame image X, defines the sum as X-I, and transmits the X-I to the data fusion module.
4. The Internet of things-based food ingredient flow monitoring system according to claim 1, wherein the quality sensor module transmits ingredient quality information and production batch information entering the ingredient opening to the data fusion module, and the position information comprises enterprise position information, production workshop position information, ingredient opening position information and monitoring device position information.
5. The food ingredient flow monitoring system based on the internet of things as claimed in claim 3, wherein the data fusion module fuses position information, ingredient quality information, production batch information and the image hash value sum X-I into a fusion data packet and sends the fusion data packet to the data analysis module, the position information is used as a mark, and the ingredient quality information, the production batch information and the X-I are used as the content of the fusion data packet.
6. The Internet of things-based food ingredient flow monitoring system according to claim 5, wherein a standard data packet is stored in the database, and the standard data packet comprises standard position information, standard ingredient quality information and a standard image hash value X’I, marking standard data packets by using standard position information, and adding standard ingredient quality information and standard image hash value sum X’I is the content of a standard data packet, and standard position information comprises standard enterprise position information, standard production workshop position information, standard batching port position information, standard monitoring device position information, and further comprises the names, batching proportions and batching duration of all the batching processes of the whole food production process.
7. The Internet of things-based food ingredient flow monitoring system according to claim 6, wherein the data analysis module receives the data fusion moduleThe sent fusion data packet extracts the position information in the fusion data packet, extracts a standard data packet of corresponding standard position information in a database according to the position information in the fusion data packet, and extracts the sum X of standard ingredient quality information and a standard image Hash value in the standard data packet’I, comparing the batching quality information with standard batching quality information to obtain a quality comparison result, firstly adding all the qualities of a production batch material throwing process to obtain a total quality sum, subtracting the standard total quality of the production batch material throwing process in the standard batching information to obtain a material quality difference, and dividing the material quality difference by the standard total quality to obtain a percentage, wherein if the percentage is more than one percent, the quality comparison result is unqualified, and if the percentage is less than or equal to one percent, the quality comparison result is qualified; the image hash value sum X-I and the standard image hash value sum X’I-contrast, i.e. sum of sub-region image hash values a-I, b-I, c-I (I =1,2,3,4,5) of each frame image in the key frame image X with the standard image hash value X’A in-I’-i、b’-i、c’I (i =1,2,3,4,5), comparing one by one, if the comparison result is that the number of different data bits of each hash value is within the range of 0-2, the image comparison result is safe in the batching process, otherwise, if the number of different data bits of one hash value is greater than 2, the image comparison result is unsafe in the batching process, combining the quality comparison result, the image comparison result and the production batch information into an analysis result data packet and sending the analysis result data packet to the monitoring terminal, wherein the analysis result data packet takes the production batch information as a mark, and takes the image comparison result and the quality comparison result as contents.
8. The internet-of-things-based food ingredient flow monitoring system according to claim 7, wherein the monitoring terminal receives the analysis result data packet and performs information interaction with the consumer query module, the enterprise early warning module and the supervision department monitoring module, and a consumer can query an image comparison result and a quality comparison result of an ingredient process corresponding to product batch information through the consumer query module; when the image comparison result is that the batching process is not safe, the analysis result data packet is sent to the mobile inquiry equipment of the related enterprise personnel of the enterprise early warning module, and when the image comparison result is that the batching process is safe, the analysis result data packet is not sent to the enterprise early warning module; the monitoring department monitoring module can call the information received by the monitoring terminal, and can also directly extract the batching video information, the key frame image X, the position information, the batching quality information and the product batch information in the system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010875210.0A CN111914953A (en) | 2020-08-27 | 2020-08-27 | Food ingredient flow monitoring system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010875210.0A CN111914953A (en) | 2020-08-27 | 2020-08-27 | Food ingredient flow monitoring system based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914953A true CN111914953A (en) | 2020-11-10 |
Family
ID=73278846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010875210.0A Withdrawn CN111914953A (en) | 2020-08-27 | 2020-08-27 | Food ingredient flow monitoring system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914953A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822440A (en) * | 2020-12-30 | 2021-05-18 | 深圳赛动生物自动化有限公司 | Biological sample preparation monitoring method, application server, system and storage medium |
| CN116090812A (en) * | 2022-11-08 | 2023-05-09 | 成都市食品检验研究院 | Intelligent remote service system for risk prevention and control early warning of food enterprises |
| CN116362564A (en) * | 2023-04-04 | 2023-06-30 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
| CN117831028A (en) * | 2024-03-06 | 2024-04-05 | 深圳鸿博智成科技有限公司 | Processing method, device, equipment and storage medium for food processing data |
-
2020
- 2020-08-27 CN CN202010875210.0A patent/CN111914953A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822440A (en) * | 2020-12-30 | 2021-05-18 | 深圳赛动生物自动化有限公司 | Biological sample preparation monitoring method, application server, system and storage medium |
| CN112822440B (en) * | 2020-12-30 | 2023-09-22 | 深圳赛动智造科技有限公司 | Biological sample preparation monitoring method, application server, system and storage medium |
| CN116090812A (en) * | 2022-11-08 | 2023-05-09 | 成都市食品检验研究院 | Intelligent remote service system for risk prevention and control early warning of food enterprises |
| CN116090812B (en) * | 2022-11-08 | 2024-01-26 | 成都市食品检验研究院 | Intelligent remote service system for risk prevention and control early warning of food enterprises |
| CN116362564A (en) * | 2023-04-04 | 2023-06-30 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
| CN116362564B (en) * | 2023-04-04 | 2023-09-08 | 重庆海辉星科技有限公司 | Method and system for generating hotel public health video supervision result |
| CN117831028A (en) * | 2024-03-06 | 2024-04-05 | 深圳鸿博智成科技有限公司 | Processing method, device, equipment and storage medium for food processing data |
| CN117831028B (en) * | 2024-03-06 | 2024-05-07 | 深圳鸿博智成科技有限公司 | Processing method, device, equipment and storage medium for food processing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914953A (en) | Food ingredient flow monitoring system based on Internet of things | |
| CN109460744B (en) | Video monitoring system based on deep learning | |
| CN108965340B (en) | Industrial control system intrusion detection method and system | |
| CN102348128A (en) | Surveillance camera system having camera malfunction detection function | |
| CN103544093A (en) | Monitoring and alarm control method and system | |
| CN112583642B (en) | Abnormality detection method, abnormality detection model, electronic device, and computer-readable storage medium | |
| CN104267346A (en) | Remote fault diagnosis method of generator excitation system | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
| CN108174198A (en) | A kind of video image quality diagnostic analysis detection device and application system | |
| CN113938306B (en) | Trusted authentication method and system based on data cleaning rule | |
| CN110716973A (en) | Big data based security event reporting platform and method | |
| CN110930707A (en) | Non-motor vehicle traffic violation supervision system and supervision method | |
| CN113437801B (en) | Method and device for alarming abnormal equipment in digital twin system of transformer substation | |
| CN117173613B (en) | Intelligent management system and method for whole process informatization of engineering construction project | |
| CN106067963B (en) | Distributed automatic report method for remote large monitor abnormity | |
| CN117129796A (en) | Power grid fault identification system based on big data | |
| WO2023280117A1 (en) | Indication signal recognition method and device, and computer storage medium | |
| CN110324588A (en) | Video analysis Warning Event information storage means based on dictionary structure | |
| CN109344705A (en) | A kind of pedestrian behavior detection method and system | |
| CN101673472A (en) | Method for monitoring operating system, device and system therefor | |
| CN114882589A (en) | Granary safety operation early warning system and method based on intelligent video analysis | |
| CN113837408A (en) | Traffic facility operation and maintenance management system based on equipment full-life-cycle supervision | |
| CN113473092A (en) | Production workshop management system, method, equipment and computer program product | |
| CN115660613B (en) | Abnormal data monitoring method, device, equipment, storage medium and program product |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201110 |
|
| WW01 | Invention patent application withdrawn after publication |