CN114241427A - Method for detecting sanitary state of three-bird-shelves, electronic equipment and storage medium - Google Patents
Method for detecting sanitary state of three-bird-shelves, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114241427A CN114241427A CN202210174091.5A CN202210174091A CN114241427A CN 114241427 A CN114241427 A CN 114241427A CN 202210174091 A CN202210174091 A CN 202210174091A CN 114241427 A CN114241427 A CN 114241427A
- Authority
- CN
- China
- Prior art keywords
- bird
- personnel
- score
- killing
- file
- 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
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000004140 cleaning Methods 0.000 claims description 88
- 238000004659 sterilization and disinfection Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 24
- 230000000694 effects Effects 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 241001314440 Triphora trianthophoros Species 0.000 claims description 5
- 210000001981 hip bone Anatomy 0.000 claims description 4
- 230000001954 sterilising effect Effects 0.000 claims description 4
- 210000000988 bone and bone Anatomy 0.000 claims description 3
- 230000000249 desinfective effect Effects 0.000 claims description 3
- 230000003749 cleanliness Effects 0.000 claims 1
- 241000272517 Anseriformes Species 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 2
- 235000013330 chicken meat Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002301 combined effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application relates to a method for detecting the sanitary state of a three-bird file, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring videos of three bird file areas; determining a kill job score from images in a video of a three bird file regionClean scoreAnd an effectiveness score(ii) a According to the killing job scoreClean scoreAnd an effectiveness scoreDetermining three bird shift hygiene scores; comparing the sanitary score of the three bird grades with a first threshold value to obtain a comparison result; and determining whether the sanitation of the three bird grades reaches the standard or not according to the comparison result. The method first determines the killing work score through the images in the video of the three bird file areasClean scoreAnd an effectiveness scoreThen determining a killing job scoreClean scoreAnd an effectiveness scoreThe three-bird-grade sanitation score is determined, the three-bird-grade sanitation score is compared with a first threshold value to obtain a comparison result, whether the three-bird-grade sanitation of the three bird-grade is up to the standard or not is determined according to the comparison result, and the determination method is simple and rapid, high in accuracy and high in user experience.
Description
Technical Field
The present disclosure relates to the field of three-bird-shelves technology, and more particularly, to a method for detecting a hygiene state of three-bird-shelves, an electronic device, and a storage medium.
Background
At present, whether three bird shelves health is up to standard, it is usually that managers go the scene and look over manually, perhaps at the key region installation camera of three bird shelves, look over whether three bird shelves health is up to standard through the camera, the manual work is looked over and is to go the scene and see, supervision inefficiency, look over through the camera and look over in order that managers look over, look over inefficiency, managers experience is poor to each corner of three bird shelves can not necessarily be looked over to the camera, the rate of accuracy is high inadequately.
Disclosure of Invention
In view of the above problems, the present application provides a method for detecting a hygienic status of a three-bird file, an electronic device, and a storage medium.
In a first aspect, an embodiment of the present application provides a method for detecting a sanitary state of a three-bird file, including:
acquiring videos of three bird file areas;
determining a kill job score from images in a video of a three bird file regionClean scoreAnd an effectiveness score;
According to the killing job scoreClean scoreAnd an effectiveness scoreDetermining three bird shift hygiene scores;
comparing the sanitary score of the three bird grades with a first threshold value to obtain a comparison result;
and determining whether the sanitation of the three bird grades reaches the standard or not according to the comparison result.
Further, in the method for detecting the sanitary state of the three-bird-shelves, the killing work score is determined according to the video image of the three-bird-shelf areaThe method comprises the following steps:
detecting whether a killing instrument is included in the images in the video of the three bird file areas by using a pre-trained instrument detection model;
when detecting that the images in the videos of the three bird file areas comprise killing instruments, acquiring personnel information in the images in the videos of the three bird file areas;
calculating the distance from the personnel center to the killing instrument according to the personnel information;
judging whether a person with the distance from the center of the person to the killing instrument smaller than a second threshold value exists,
when the judgment result is that the person exists, wherein the distance from the center of the person to the killing instrument is smaller than a second threshold value, judging whether the person is a killing person by using a pre-trained killing person detection model;
when the judgment result shows that the person is a disinfection person, judging whether the disinfection person is in a working state;
if the judgment result is that the killing personnel is in the working state, judging whether the killing personnel finishes the killing work of the three-bird-gear area or not according to the moving track information of the killing personnel and the three-bird-gear cage area information;
if the judgment result is that the killing personnel complete the killing work on the three-bird-level area, judging whether the killing personnel complete the killing work on the three-bird-level area within a preset time period;
if the judgment result is that the killing personnel complete the killing work of the three-bird-level region within the preset time period, determining the killing work scoreIf the judgment result is that the killing personnel do not complete the killing work on the three-bird-grade area within the preset time period, determining the killing work score。
Further, in the method for detecting the sanitary status of the three bird shelves, when the person is a killer, the method for judging whether the killer is in a working state includes:
extracting head position information of a sterilizerHip position informationAnd disinfecting apparatusDetermining the head position informationThe hip bone position informationAnd the sterilizing apparatusWhether a first preset condition is satisfied as follows,
wherein the content of the first and second substances,,is a set threshold value;to eliminate the coordinates of the left vertex of the head box of the person,to kill the width of the person's head box,the height of the square frame of the head of the killer is;to eliminate the left vertex coordinates of the crotch bone box of the person,to eliminate the width of the crotch frame of a person,the height of a crotch frame of a person is killed;to kill the coordinates of the left vertex of the instrument box,in order to kill the width of the box of the instrument,the height of the box of the killing instrument is high;
if the judgment result is the head position informationHip position informationAnd killing apparatusWhen the first preset condition is met, the judgment result shows that the disinfection personnel is in the working state;
if the judgment result is the head position informationHip position informationAnd killing apparatusIf the first preset condition is not met, the judgment result is that the disinfection personnel are not in the working state.
Further, in the method for detecting the hygienic state of the three-bird-shelves, whether the killer finishes killing the three-bird-shelf area or not is judged according to the moving track information of the killer and the three-bird-shelf cage area information, and the method includes the following steps:
judging moving track information of disinfection personnelInner set of four pointsThree bird shelves cage area informationWhether the following second preset condition is met:
wherein the content of the first and second substances,,i is a serial number for a set threshold value;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThree bird shelves cage area informationIf the second preset condition is met, the judgment result shows that the killing personnel complete the killing work of the three-bird-level area;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThree-gear cage area informationAnd if the second preset condition is met, the judgment result shows that the killing personnel do not complete the killing work on the three bird file areas.
Further, in the method for detecting the sanitary state of the three-bird-shelves, the cleaning score is determined according to the images in the video of the three-bird-shelf areaThe method comprises the following steps:
detecting whether cleaning instruments are included in images in a video of a three-bird file region using a pre-trained instrument detection model;
Including cleaning implements within images in video when three bird file regions are detectedThen, acquiring personnel information in the images in the video of the three bird file areas;
computing staff centric to cleaning implement from staff information within images in video of three bird file regionsThe distance of (d);
determine if there is a center of people to cleaning implementIs less than a second threshold value,
when the judgment result shows that the personnel center is present in the cleaning instrumentWhen the distance of the second threshold value is less than the distance of the first threshold value, judging whether the personnel is in a clean state;
if the judgment result is that the personnel is in a cleaning state, acquiring the characteristics of the cleaning personnel and the track information of the cleaning personnel;
judging whether the cleaning personnel finish the cleaning work of the three bird shelves or not according to the characteristics of the cleaning personnel and the track information of the cleaning personnel;
if the judgment result is that the cleaning staff finishes the cleaning work on the three bird shelves, determining the cleaning score according to the times of the cleaning staff finishing the cleaning work on the three bird shelves in one day。
Further, in the method for detecting the sanitary status of the three bird shelves, the step of judging whether the person is in a clean status includes: extracting personnel hand informationJudging the hand information of the personAnd a cleaning deviceWhether the following third preset condition is met:
or
if the personnel hand informationAnd a cleaning deviceWhen a third preset condition is met, judging that the personnel is in a clean state;
if the personnel hand informationAnd a cleaning deviceNot meet the requirements ofAnd judging that the personnel is in a non-clean state under a third preset condition.
Further, in the method for detecting the sanitary status of the three-bird-shelves, the effect score is determined according to the images in the video of the three-bird-shelf areaThe method comprises the following steps:
extracting three bird file images in the three bird file closing time period;
comparing the similarity of the three bird file images and the standard sanitary scene image set to obtain similarity scoreThe standard hygiene scene image set at least comprises: the three bird file images at least comprise a wall standard sanitary scene area image, a cage area standard sanitary scene area image and a ground standard sanitary scene area image: wall area images, cage area images, ground area images; the similarity scoreIs based on the similarity score of the wall regionCage zone region similarity scoreGround area similarity scoreAre determined together;
wherein the content of the first and second substances,a correction constant trained for historical data;
the wall region similarity scoreThe similarity between the standard sanitary scene area image of the wall and the wall area image is calculated to determine the similarity; the cage region similarity scoreThe method is determined by calculating the similarity between the images of the standard sanitary scene areas of the cage area and the images of the cage area; the ground region similarity scoreIs determined by calculating the similarity between the ground standard sanitary scene area image and the ground area image;
similarity score between standard sanitary scene image and three bird file imagesWhen the value is larger than a third preset threshold value, the effect score is given(ii) a Otherwise, the reverse is carried out。
Further, in the method for detecting the sanitary state of the three bird files, the killing work score is usedClean scoreAnd an effectiveness scoreDetermining three bird shift hygiene scoresIs according to the formulaIn the case of a certain number of times,
wherein the content of the first and second substances,and obtaining a correction constant for historical training.
In a second aspect, an embodiment of the present invention further provides an electronic device, including: a processor and a memory;
the processor is used for executing the method for detecting the health state of the three-bird file by calling the program or the instructions stored in the memory.
In a third aspect, the present invention also provides a computer-readable storage medium, which stores a program or instructions for causing a computer to execute the method for detecting a sanitary status of a three-bird file as described in any one of the above.
The embodiment of the application has the advantages that: the method first determines the killing work score through the images in the video of the three bird file areasClean scoreAnd an effectiveness scoreThen determining a killing job scoreClean scoreAnd an effectiveness scoreDetermining three bird grade sanitation scores, comparing the three bird grade sanitation scores with a first threshold value to obtain a comparison result, and determining whether the three bird grade sanitation reaches the standard or not according to the comparison result; the application determines whether the three-bird-grade sanitation reaches the standard, and not only combines the killing work scoreClean scoreAnd a combined effect scoreThe obtained three-bird-gear hygiene score is high in accuracy, and a user does not need to go to a site to check whether the three-bird-gear hygiene score reaches the standard or check cage data clearly through monitoring, so that the user experience degree is high.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a first schematic view illustrating a method for detecting a sanitary status of a three-bird file according to an embodiment of the present application;
fig. 2 is a schematic view illustrating a method for detecting a sanitary status of a third bird file according to an embodiment of the present application;
fig. 3 is a third schematic view illustrating a method for detecting a sanitary status of a third bird file according to an embodiment of the present application;
fig. 4 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanying the present application are described in detail below with reference to the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of embodiments in many different forms than those described herein and those skilled in the art will be able to make similar modifications without departing from the spirit of the application and it is therefore not intended to be limited to the embodiments disclosed below.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Fig. 1 is a first schematic view of a method for detecting a sanitary status of a three-bird file according to an embodiment of the present application.
In a first aspect, an embodiment of the present application provides a method for detecting a sanitary status of a third bird file, which, with reference to fig. 1, includes five steps S101 to S105:
s101: and acquiring videos of the three bird file areas.
Specifically, in the embodiment of the present application, the three-bird-grade area refers to an area for feeding chickens, ducks and geese, and the video of the three-bird-grade area may be the video of the area for feeding chickens, ducks and geese, which is acquired through the camera.
S102: determining a kill job score from images in a video of a three bird file regionClean scoreAnd an effectiveness score。
Specifically, in the embodiment of the present application, the following describes the determination of the killing job score based on the images in the video of the three bird's-file regionsClean scoreAnd an effectiveness scoreThe detailed steps of (1).
S103: according to the killing job scoreClean scoreAnd an effectiveness scoreThree bird shift hygiene scores were determined.
Specifically, in the examples of the present application, the following description will be made on the basis of the killing job scoreClean scoreAnd an effectiveness scoreDetailed steps for determining the hygiene scores of the three birds.
S104: and comparing the sanitary score of the three bird grades with a first threshold value to obtain a comparison result.
Specifically, in the embodiment of the present application, the first threshold is a threshold flexibly set according to an actual situation, and the comparison result is obtained by comparing the hygiene scores of the three bird files with the first threshold, where the comparison result may be three results, that is, greater than 0, equal to 0, and less than 0.
S105: and determining whether the sanitation of the three bird grades reaches the standard or not according to the comparison result.
Specifically, in the embodiment of the application, when the comparison result is greater than 0, it is determined that the hygiene of the three bird files reaches the standard, otherwise, when the comparison result is less than or equal to 0, it is determined that the hygiene of the three bird files does not reach the standard, and alarm information that the hygiene of the three bird files does not reach the standard and a corresponding picture are sent to prompt a manager to process the alarm information.
Fig. 2 is a schematic view illustrating a method for detecting a sanitary status of a third bird file according to an embodiment of the present application.
Further, in the method for detecting the sanitary state of the three-bird-shelves, the killing work score is determined according to the video image of the three-bird-shelf areaWith reference to fig. 2, the method includes nine steps S201 to S209:
s201: and detecting whether the killing instruments are included in the images in the video of the three bird file areas by using a pre-trained instrument detection model.
Specifically, in the embodiment of the application, the pre-trained instrument detection model is used for collecting images of the killing instrument and labeling the killing instrument, the labeled images of the killing instrument are used for training to obtain the instrument detection model, and the method for detecting whether the killing instrument is included in the images in the videos of the three bird-level areas through the instrument detection model is fast and simple.
S202: and when detecting that the images in the video of the three bird file areas comprise the killing instruments, acquiring personnel information in the images in the video of the three bird file areas.
Specifically, in this embodiment of the application, when the instrument detection model detects that the images in the video of the three-bird-archive region include the killing instrument, the person information in the images in the video of the three-bird-archive region is acquired, and the person information may specifically include: position information of the person in the three bird-shelves area.
S203: and calculating the distance from the personnel center to the killing instrument according to the personnel information.
Specifically, in the embodiment of the application, after the personnel information in the image is acquired, the personnel center is calculated to the killing instrumentThe distance may be 0.4m, 0.2m, etc., and the person may be one person or a plurality of persons.
S204: and judging whether the personnel with the distance from the personnel center to the killing instrument smaller than a second threshold value exist.
Specifically, in the embodiment of the application, whether a person center arrives at the killing apparatus or not is judgedIs smaller than a second threshold value, e.g. 0.1 m.
S205: and when the judgment result is that the person exists, wherein the distance from the center of the person to the killing instrument is smaller than a second threshold value, judging whether the person is a killing person by using a pre-trained killing person detection model.
Specifically, in the embodiment of the application, when the judgment result shows that there is a person whose distance from the center of the person to the killing apparatus is smaller than a second threshold value, for example, 0.1m, a pre-trained detection model of the killing person is used to judge whether the person is the killing person; the training step of the pre-trained killer detection model comprises the following steps: collecting images of the disinfection personnel, labeling the clothing of the disinfection personnel, and training by using the labeled images to obtain a pre-trained detection model of the disinfection personnel.
S206: and when the judgment result is that the person is a disinfection person, judging whether the disinfection person is in a working state.
Specifically, in the embodiment of the present application, when the pre-trained detection model for the disinfection personnel is used to determine that the personnel is the disinfection personnel, whether the disinfection personnel is in a working state is further determined, and the specific determination steps are described in detail below.
S207: and if the judgment result is that the killing personnel is in the working state, judging whether the killing personnel finishes the killing work of the three-bird-gear area or not according to the moving track information of the killing personnel and the three-bird-gear cage area information.
Specifically, in the embodiment of the present application, if the determination result is that the killing person is in the working state, whether the killing person completes the killing work in the three-bird-gear area is determined according to the moving track information of the killing person and the three-bird-gear cage area information.
S208: and if the judgment result is that the killing personnel complete the killing work on the three-bird-level area, judging whether the killing personnel complete the killing work on the three-bird-level area within a preset time period.
Specifically, in the embodiment of the application, if the judgment result is that the killing staff completes the killing work on the three-bird-level region, whether the killing staff completes the killing work on the three-bird-level region within a preset time period is further judged, for example, one hour or half an hour, and the specific preset time period is flexibly determined according to the actual situation.
S209: if the judgment result is that the killing personnel complete the killing work of the three-bird-level region within the preset time period, determining the killing work scoreIf the judgment result is that the killing personnel do not complete the killing work on the three-bird-grade area within the preset time period, determining the killing work score。
Specifically, in the embodiment of the present application, if the determination result is that the killer completes killing work on the three bird-level areas within one hour, the killing work score is determinedIf the judgment result is that the killing personnel do not complete the killing work on the three-bird-grade area within one hour, determining the killing work score。
Further, in the method for detecting the sanitary status of the three bird shelves, when the person is a killer, the method for judging whether the killer is in a working state includes:
extracting head position information of a sterilizerHip position informationAnd disinfecting apparatusJudging head position informationHip position informationAnd killing apparatusWhether a first preset condition is satisfied as follows,
wherein the content of the first and second substances,,in order to be the threshold value set, the threshold value is set,coordinates of the left vertex of the head square frame of the killer,for killing peopleThe width of the box of the head of the person,to kill the height of the person's head box,to eliminate the left vertex coordinates of the crotch bone box of the person,to eliminate the width of the crotch frame of a person,to eliminate the height of the crotch frame of a person.
If the judgment result is the head position informationHip position informationAnd killing apparatusWhen the first preset condition is met, the judgment result is that the disinfection personnel are in the working state;
if the judgment result is the head position informationHip position informationAnd killing apparatusIf the first preset condition is not met, the judgment result is that the disinfection personnel are not in the working state.
Further, in the method for detecting the hygienic state of the three-bird-shelves, whether the killer finishes killing the three-bird-shelf area or not is judged according to the moving track information of the killer and the three-bird-shelf cage area information, and the method includes the following steps:
judging moving track information of disinfection personnelInner set of four pointsThree bird shelves cage area informationWhether or not the following second preset condition is satisfied,
wherein the content of the first and second substances,,i is a serial number for a set threshold value;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThree-gear cage area informationIf the second preset condition is met, the judgment result shows that the killing personnel complete the killing work of the three-bird-level area;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThree-gear cage area informationIf the second preset condition is not met, the judgment result shows that the killing personnel do not complete the killing work on the three bird file areas.
Fig. 3 is a third schematic view of a method for detecting a sanitary status of three bird files according to an embodiment of the present application.
Further, in the method for detecting the sanitary state of the three-bird-shelves, the cleaning score is determined according to the images in the video of the three-bird-shelf areaWith reference to fig. 3, the method includes eight steps S301 to S308:
s301: detecting whether cleaning instruments are included in images in a video of a three-bird file region using a pre-trained instrument detection model。
Specifically, in the embodiment of the present application, the pre-trained instrument detection model is to collect an image of a cleaning instrument and label the cleaning instrument, train the image of the cleaning instrument after labeling to obtain the instrument detection model, and detect whether the image in the video of the three bird-shelves region includes the cleaning instrument or not through the instrument detection modelThe method is quick and simple.
S302: including cleaning implements within images in video when three bird file regions are detectedAnd acquiring personnel information in the images in the video of the three bird file areas.
In particular, in the embodiment of the present application, when the instrument detection model detects that the image in the video of the three bird's-file region includes the cleaning instrumentWhen the method is used, the personnel information in the images in the video of the three bird file areas is obtained, and the personnel information specifically comprises the following steps: position information of the person in the three bird-shelves area.
S303: computing staff centric to cleaning implement from staff information within images in video of three bird file regionsDistance.
Specifically, in the embodiment of the application, after the personnel information in the image is acquired, the personnel center is calculated to reach the cleaning instrumentThe distance may be 0.5m, 0.2m, etc., and the person may be one person or a plurality of persons.
S304: determine if there is a center of people to cleaning implementIs less than a second threshold.
Specifically, in the embodiment of the application, whether a person from center to cleaning instrument exists in a plurality of persons or one person is judgedIs smaller than a second threshold value, e.g. 0.1 m.
S305: when the judgment result shows that the personnel center is present in the cleaning instrumentIs less than the second threshold, it is determined whether the person is in a clean state.
Specifically, in the embodiment of the present application, when the determination result is that there is a center of people arriving at the cleaning apparatusIs less than a second threshold, e.g., 0.1m, then a further determination is made as to whether the person is in a clean state, with the specific determination steps described in detail below.
S306: and if the judgment result is that the personnel is in a cleaning state, acquiring the characteristics of the cleaning personnel and the track information of the cleaning personnel.
Specifically, in the embodiment of the present application, the feature of the cleaning person may be a facial feature of the cleaning person, and the trajectory information of the cleaning person may be trajectory information of the cleaning person during cleaning.
S307: and judging whether the cleaning personnel finish the cleaning work of the three bird shelves or not according to the characteristics of the cleaning personnel and the track information of the cleaning personnel.
Specifically, in the embodiment of the present application, the three-bird-shelves area is divided into m areas, when it is determined that the person meets the characteristics of the cleaning person, it is determined that the number of frames of the track of the cleaning person in one area of the m areas is greater than a set threshold, and the total number of track frames is greater than the set threshold, and when the track information of the cleaning person meets the requirements that the number of frames of the track of the area of the m areas is greater than the set threshold, and the total number of track frames is greater than the set threshold, it is determined that the cleaning person completes the cleaning work on the three-bird-shelves.
S308: if the judgment result is that the cleaning staff finishes the cleaning work on the three bird shelves, determining the cleaning score according to the times of the cleaning staff finishing the cleaning work on the three bird shelves in one day。
Specifically, in the embodiment of the present application, when the number of times that the cleaning staff completes the cleaning work on the three bird shelves within one day is greater than the set threshold, for example, 2 times, the cleaning score is addedWhen the number of cleaning operations is 0, the cleaning score is obtainedDefault cleaning score。
Further, in the method for detecting the sanitary status of the three bird shelves, the step of judging whether the person is in a clean status includes: extracting personnel hand informationJudging the hand information of the personAnd a cleaning deviceWhether the following third preset condition is met:
or
If the personnel hand informationAnd a cleaning deviceJudging that the personnel is in a clean state under a third preset condition;
if the personnel hand informationAnd a cleaning deviceAnd when the third preset condition is met, judging that the personnel is in a non-cleaning state.
Further, in the method for detecting the sanitary status of the three-bird-shelves, the effect score is determined according to the images in the video of the three-bird-shelf areaThe method comprises the following steps:
further, in the method for detecting the sanitary status of the three-bird-shelves, the effect score is determined according to the images in the video of the three-bird-shelf areaThe method comprises the following steps:
extracting three bird file images in the three bird file closing time period;
comparing three bird file images to a standardSimilarity of sanitary scene image set is obtained to similarity score;
The standard hygiene scene image set comprises at least: the three bird file images at least comprise a wall standard sanitary scene area image, a cage area standard sanitary scene area image and a ground standard sanitary scene area image: wall area images, cage area images, ground area images; the similarity scoreIs based on the similarity score of the wall regionCage zone region similarity scoreGround area similarity scoreAre determined together;
wherein the content of the first and second substances,a correction constant trained for historical data;
wall area similarity scoreThe method is determined by calculating the similarity between a wall standard sanitary scene area image and the wall area image; cage region similarity scoreIs determined by calculating the similarity between the images of the standard sanitary scene areas of the cage area and the images of the cage areaOf (1); ground area similarity scoreThe method is determined by calculating the similarity between the ground standard sanitary scene area image and the ground area image;
similarity score between standard sanitary scene image and three bird file imagesWhen the value is larger than a third preset threshold value, the effect score is given(ii) a Otherwise, the reverse is carried out。
Specifically, in the embodiment of the application, the three-bird-file closing time period may be a time period when no person enters the three-bird-file region, and after the three-bird-file image is extracted in the three-bird-file closing time period, the brightness and the chromaticity of the three-bird-file image are normalized; comparing the similarity of the three bird-stock images with the similarity of the standard sanitary scene image set to obtain a similarity score, wherein the standard sanitary scene image set can be a three bird-stock regional image which is qualified in artificial sanitary detection within one year of a collected detection scene, and the brightness and the chroma of the three bird-stock images are normalized to obtain a standard sanitary scene image set; respectively determining the similarity scores of the wall area, the cage area and the ground area to obtain the similarity scoresDetermining an effect score by comparing the similarity score with a third preset threshold, and determining the effect score when the similarity score is greater than the third preset thresholdWhen the value is larger than a third preset threshold value, the effect score is givenSimilarity scoreWhen the threshold value is less than or equal to a third preset threshold value,。
further, in the method for detecting the sanitary state of the three bird files, the killing work score is usedClean scoreAnd an effectiveness scoreDetermining three bird shift hygiene scoresIs according to the formulaThe method comprises the steps of determining, wherein,and obtaining a correction constant for historical training.
In a second aspect, an embodiment of the present invention further provides an electronic device, including: a processor and a memory;
the processor is used for executing the method for detecting the health state of the three-bird file by calling the program or the instructions stored in the memory.
In a third aspect, the present invention also provides a computer-readable storage medium, which stores a program or instructions for causing a computer to execute the method for detecting a sanitary status of a three-bird file as described in any one of the above.
Fig. 4 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure.
As shown in fig. 4, the electronic apparatus includes: at least one processor 401, at least one memory 402, and at least one communication interface 403. The various components in the electronic device are coupled together by a bus system 404. A communication interface 403 for information transmission with an external device. It is understood that the bus system 404 is used to enable communications among the components. The bus system 404 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, the various buses are labeled as bus system 404 in fig. 4.
It will be appreciated that the memory 402 in this embodiment can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory.
In some embodiments, memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system and an application program.
The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application programs, including various application programs such as a Media Player (Media Player), a Browser (Browser), etc., are used to implement various application services. The program for implementing any one of the methods for detecting the sanitary state of the three-bird file provided by the embodiments of the present application may be included in the application program.
In this embodiment of the present application, the processor 401 is configured to execute the steps of the embodiments of the method for detecting a hygiene state of a three-bird file provided by the embodiments of the present application by calling a program or an instruction stored in the memory 402, which may be specifically a program or an instruction stored in an application program.
Acquiring videos of three bird file areas;
determining a kill job score from images in a video of a three bird file regionClean scoreAnd an effectiveness score;
According to the killing job scoreClean scoreAnd an effectiveness scoreDetermining three bird shift hygiene scores;
comparing the sanitary score of the three bird grades with a first threshold value to obtain a comparison result;
and determining whether the sanitation of the three bird grades reaches the standard or not according to the comparison result.
Any one of the three-bird-file hygiene state detection methods provided by the embodiments of the present application may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 401. The Processor 401 may be a 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, discrete Gate or transistor logic device, or discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The steps of any one of the methods for detecting the sanitary state of the three bird files provided by the embodiments of the present application can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software units in the hardware decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402, and completes the steps of a method for detecting the sanitary status of the three-bird file in combination with the hardware thereof.
Those skilled in the art will appreciate that although some embodiments described herein include some features included in other embodiments instead of others, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments.
Those skilled in the art will appreciate that the description of each embodiment has a respective emphasis, and reference may be made to the related description of other embodiments for those parts of an embodiment that are not described in detail.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for detecting the sanitary state of a three-bird-shelves is characterized by comprising the following steps:
acquiring videos of three bird file areas;
determining a kill job score from images in the video of the three bird file regionsClean scoreAnd an effectiveness score;
According to the killing job scoreThe cleaning scoreAnd the effect scoreDetermining three bird shift hygiene scores;
comparing the three bird file hygiene scores with a first threshold value to obtain a comparison result;
and determining whether the sanitation of the three bird grades reaches the standard or not according to the comparison result.
2. The method of claim 1, wherein determining a kill job score based on the image of the video of the three bird file regionThe method comprises the following steps:
detecting whether a killing instrument is included in the images in the video of the three bird file areas by using a pre-trained instrument detection model;
when detecting that the images in the videos of the three bird file areas comprise killing instruments, acquiring personnel information in the images in the videos of the three bird file areas;
calculating the distance from the personnel center to the killing instrument according to the personnel information;
judging whether a person with the distance from the person center to the killing instrument being smaller than a second threshold value exists,
when the judgment result is that the personnel with the distance from the personnel center to the killing instrument smaller than the second threshold value exist, judging whether the personnel is the killing personnel by using a pre-trained killing personnel detection model;
when the judgment result shows that the person is a disinfection person, judging whether the disinfection person is in a working state;
if the judgment result is that the killing personnel is in the working state, judging whether the killing personnel finishes killing work on the three-bird-gear area or not according to the moving track information of the killing personnel and the three-bird-gear cage area information;
if the judgment result is that the killing personnel complete the killing work on the three-bird-level area, judging whether the killing personnel complete the killing work on the three-bird-level area within a preset time period;
if the judgment result is that the killing personnel complete the killing work of the three-bird-level region within the preset time period, determining the killing work scoreIf the judgment result is that the killing personnel do not complete the killing work on the three-bird-grade area within the preset time period, determining the killing work score。
3. The method for detecting the sanitary status of a third bird file according to claim 2, wherein the step of judging whether the killer is in a working status when the person is a killer comprises the steps of:
extracting head position information of a sterilizerHip position informationAnd disinfecting apparatusJudging the position of the headInformationThe hip bone position informationAnd the sterilizing apparatusWhether the following first preset condition is met:
wherein the content of the first and second substances,,is a set threshold value;to eliminate the coordinates of the left vertex of the head box of the person,to kill the width of the person's head box,the height of the square frame of the head of the killer is;
to eliminate the left vertex coordinates of the crotch bone box of the person,to eliminate the width of the crotch frame of a person,the height of a crotch frame of a person is killed;to kill the coordinates of the left vertex of the instrument box,in order to kill the width of the box of the instrument,the height of the box of the killing instrument is high;
if the judgment result is the head position informationThe hip bone position informationAnd the sterilizing apparatusWhen the first preset condition is met, the judgment result shows that the disinfection personnel is in the working state;
4. The method for detecting the sanitary status of three birds shelves according to claim 2, wherein the step of judging whether the killer completes the killing work of the three birds shelves according to the moving track information of the killer and the cage area information of the three birds shelves comprises the steps of:
judging the moving track information of the disinfection personnelInner set of four pointsThe three bird shelves cage area informationWhether the following second preset condition is met:
wherein the content of the first and second substances,,i is a serial number for a set threshold value;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThe three bird shelves cage area informationIf the second preset condition is met, the judgment result shows that the killing personnel complete the killing work of the three-bird-shelves area;
if the judgment result is the moving track information of the disinfection personnelInner set of four pointsThe three bird shelves cage area informationIf the second preset condition is not met, the judgment result shows that the killing personnel do not complete the killing work of the three bird file areas.
5. The method of claim 1, wherein determining a cleanliness score from an image in a video of the three-bird file regionThe method comprises the following steps:
detecting whether a cleaning instrument is included in an image in the video of the three bird file region by using a pre-trained instrument detection model;
Including a cleaning instrument within an image in the video of the three bird file region when detectedThen, acquiring personnel information in the images in the video of the three bird file areas;
calculating staff center to the cleaning instrument according to staff information in the images in the video of the three bird file areasThe distance of (d);
determining whether the center of the person is present on the cleaning instrumentIs less than a second threshold value,
when the judgment result is that the personnel center arrives at the cleaning instrumentWhen the distance of the second threshold value is less than the distance of the second threshold value, judging whether the personnel is in a clean state;
if the judgment result is that the personnel is in a cleaning state, acquiring the characteristics of the cleaning personnel and the track information of the cleaning personnel;
judging whether the cleaning personnel finish the cleaning work of the three bird shelves or not according to the characteristics of the cleaning personnel and the track information of the cleaning personnel;
6. The method for detecting the sanitary status of three birds shelves according to claim 5, wherein determining whether the person is in a clean status comprises: extracting personnel hand informationJudging the hand information of the personAnd a cleaning deviceWhether the following third preset condition is met:
or
if the personnel hand informationAnd a cleaning deviceWhen the third preset condition is met, judging that the personnel is in a clean state;
7. The method for detecting hygiene status of three-bird file of claim 1, wherein the determining the effectiveness score according to the image in the video of the three-bird file regionThe method comprises the following steps:
extracting three bird file images in the three bird file closing time period;
comparing the similarity of the three bird file images and the standard sanitary scene image set to obtain similarity score(ii) a The standard hygiene scene image set comprises at least: the three-bird-shelves image at least comprises a wall standard sanitation scene area, a cage area standard sanitation scene area and a ground standard sanitation scene area: wall area images, cage area images, ground area images; the similarity scoreIs based on the similarity score of the wall regionCage zone region similarity scoreGround area similarity scoreAre determined together;
wherein the content of the first and second substances,a correction constant trained for historical data;
the wall region similarity scoreThe similarity between the standard sanitary scene area image of the wall and the wall area image is calculated to determine the similarity; the cage region similarity scoreThe method is determined by calculating the similarity between the images of the standard sanitary scene areas of the cage area and the images of the cage area; the ground region similarity scoreIs determined by calculating the similarity between the ground standard sanitary scene area image and the ground area image;
8. The method of claim 1, wherein said scoring a kill job is based on said hygiene status of three birdsThe cleaning scoreAnd the effect scoreDetermining three bird shift hygiene scoresIs according to the formulaThe method comprises the steps of determining, wherein,and obtaining a correction constant for historical training.
9. An electronic device, comprising: a processor and a memory;
the processor is used for executing the method for detecting the sanitary state of the three-bird file according to any one of claims 1 to 8 by calling the program or the instructions stored in the memory.
10. A computer-readable storage medium storing a program or instructions for causing a computer to perform a method of detecting a sanitary status of a tri-bird file according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210174091.5A CN114241427B (en) | 2022-02-25 | 2022-02-25 | Method for detecting sanitary state of three-bird-shelves, electronic device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210174091.5A CN114241427B (en) | 2022-02-25 | 2022-02-25 | Method for detecting sanitary state of three-bird-shelves, electronic device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114241427A true CN114241427A (en) | 2022-03-25 |
CN114241427B CN114241427B (en) | 2022-05-27 |
Family
ID=80748131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210174091.5A Active CN114241427B (en) | 2022-02-25 | 2022-02-25 | Method for detecting sanitary state of three-bird-shelves, electronic device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114241427B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107703093A (en) * | 2017-08-31 | 2018-02-16 | 维沃移动通信有限公司 | The detection method and mobile terminal of a kind of microorganism |
CN110490175A (en) * | 2019-08-30 | 2019-11-22 | 上海秒针网络科技有限公司 | Food safety inspection method and system |
CN111724013A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining cleanliness of vehicle |
CN212541126U (en) * | 2020-08-19 | 2021-02-12 | 藏乡情(香格里拉市)农业综合开发有限公司 | Real-time monitoring system for livestock and poultry growth environment |
CN112465460A (en) * | 2020-12-03 | 2021-03-09 | 中国联合网络通信集团有限公司 | Stall management method, stall management device, stall management system and storage medium |
US20210110700A1 (en) * | 2019-10-09 | 2021-04-15 | Visualq | Hand sanitation compliance enforcement systems and methods |
CN113196409A (en) * | 2018-12-05 | 2021-07-30 | 梦莲株式会社 | Health evaluation device, health evaluation imaging system, imaging base, and health evaluation method |
CN113511152A (en) * | 2021-09-15 | 2021-10-19 | 李斯特技术中心(上海)有限公司 | Vehicle sanitation evaluation method and device, vehicle and electronic equipment |
CN113592691A (en) * | 2021-08-16 | 2021-11-02 | 湖北致格意诚科技有限公司 | Standardized kitchen management system |
CN113769137A (en) * | 2021-08-26 | 2021-12-10 | 北京市农林科学院智能装备技术研究中心 | Inspection and epidemic prevention method and system for livestock and poultry breeding |
-
2022
- 2022-02-25 CN CN202210174091.5A patent/CN114241427B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107703093A (en) * | 2017-08-31 | 2018-02-16 | 维沃移动通信有限公司 | The detection method and mobile terminal of a kind of microorganism |
CN113196409A (en) * | 2018-12-05 | 2021-07-30 | 梦莲株式会社 | Health evaluation device, health evaluation imaging system, imaging base, and health evaluation method |
CN111724013A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining cleanliness of vehicle |
CN110490175A (en) * | 2019-08-30 | 2019-11-22 | 上海秒针网络科技有限公司 | Food safety inspection method and system |
US20210110700A1 (en) * | 2019-10-09 | 2021-04-15 | Visualq | Hand sanitation compliance enforcement systems and methods |
CN212541126U (en) * | 2020-08-19 | 2021-02-12 | 藏乡情(香格里拉市)农业综合开发有限公司 | Real-time monitoring system for livestock and poultry growth environment |
CN112465460A (en) * | 2020-12-03 | 2021-03-09 | 中国联合网络通信集团有限公司 | Stall management method, stall management device, stall management system and storage medium |
CN113592691A (en) * | 2021-08-16 | 2021-11-02 | 湖北致格意诚科技有限公司 | Standardized kitchen management system |
CN113769137A (en) * | 2021-08-26 | 2021-12-10 | 北京市农林科学院智能装备技术研究中心 | Inspection and epidemic prevention method and system for livestock and poultry breeding |
CN113511152A (en) * | 2021-09-15 | 2021-10-19 | 李斯特技术中心(上海)有限公司 | Vehicle sanitation evaluation method and device, vehicle and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN114241427B (en) | 2022-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109101923B (en) | Method and device for detecting mask wearing condition of person | |
CN111383421A (en) | Privacy protection fall detection method and system | |
US6970574B1 (en) | Pattern recognition system and method for monitoring hand washing or application of a disinfectant | |
US9076044B2 (en) | Apparatus and method for monitoring hand washing | |
WO2019072243A1 (en) | Motion recognition and gesture prediction method and device | |
CN111695542A (en) | Video monitoring fine-grained analysis method and system | |
JP6481400B2 (en) | Cleaning status evaluation method, cleaning status evaluation program, and cleaning status evaluation device | |
CN111814646A (en) | Monitoring method, device, equipment and medium based on AI vision | |
CN107517391A (en) | A kind of method and apparatus for being used to differentiate abnormal live information in net cast | |
CN115043285A (en) | Method, electronic device and storage medium for determining illegal operation of elevator by child | |
CN112668423A (en) | Corridor sundry detection method and device, terminal equipment and storage medium | |
CN114241427B (en) | Method for detecting sanitary state of three-bird-shelves, electronic device and storage medium | |
CN113111733B (en) | Posture flow-based fighting behavior recognition method | |
CN108338748A (en) | A kind of automatic cleaning method, device and clean robot based on video monitoring | |
KR101225366B1 (en) | System and method for managing toilet by image | |
JP2019022580A5 (en) | ||
CN115006566B (en) | Intelligent killing method, device, equipment and storage medium | |
CN116524435A (en) | Online invigilation method based on electronic fence and related equipment | |
CN115223202A (en) | Building corridor personnel abnormal contact detection method, equipment and medium | |
Canning et al. | Use of digital photography and image analysis techniques to quantify erythema in health care workers | |
CN115731563A (en) | Method for identifying falling of remote monitoring personnel | |
WO2022056356A1 (en) | Disinfection monitoring system and method | |
CN113920544A (en) | Safety management system and method for stamping workshop and electronic equipment | |
CN113327592A (en) | Air conditioning system control method and device, electronic equipment and storage medium | |
CN111776524A (en) | Medical waste treatment system |
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 | ||
CP03 | Change of name, title or address |
Address after: Building 7, No. 124 Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523128 Patentee after: Guangdong Prophet Big Data Co.,Ltd. Country or region after: China Address before: 523128 Room 401, building 6, No.5 Weifeng Road, Dongcheng Street, Dongguan City, Guangdong Province Patentee before: Dongguan prophet big data Co.,Ltd. Country or region before: China |
|
CP03 | Change of name, title or address |