CN116503797B - Medical waste treatment personnel protection tool wearing detection method based on target detection - Google Patents
Medical waste treatment personnel protection tool wearing detection method based on target detection Download PDFInfo
- Publication number
- CN116503797B CN116503797B CN202310385669.6A CN202310385669A CN116503797B CN 116503797 B CN116503797 B CN 116503797B CN 202310385669 A CN202310385669 A CN 202310385669A CN 116503797 B CN116503797 B CN 116503797B
- Authority
- CN
- China
- Prior art keywords
- medical waste
- personnel
- wearing
- target
- reminding
- 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.)
- Active
Links
- 239000002906 medical waste Substances 0.000 title claims abstract description 188
- 238000001514 detection method Methods 0.000 title claims abstract description 103
- 230000001681 protective effect Effects 0.000 claims abstract description 146
- 238000000034 method Methods 0.000 claims abstract description 108
- 230000008569 process Effects 0.000 claims abstract description 84
- 230000007613 environmental effect Effects 0.000 claims abstract description 60
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 103
- 238000000605 extraction Methods 0.000 claims description 65
- 238000012544 monitoring process Methods 0.000 claims description 56
- 230000001788 irregular Effects 0.000 claims description 31
- 238000003745 diagnosis Methods 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 20
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000012546 transfer Methods 0.000 claims description 15
- 230000036541 health Effects 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000001815 facial effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 208000015181 infectious disease Diseases 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 9
- 239000002699 waste material Substances 0.000 description 7
- 208000035473 Communicable disease Diseases 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000001954 sterilising effect Effects 0.000 description 4
- 238000004659 sterilization and disinfection Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002458 infectious effect Effects 0.000 description 2
- 239000010781 infectious medical waste Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 239000010826 pharmaceutical waste Substances 0.000 description 2
- 208000019838 Blood disease Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000002894 chemical waste Substances 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000002920 hazardous waste Substances 0.000 description 1
- 208000014951 hematologic disease Diseases 0.000 description 1
- 208000018706 hematopoietic system disease Diseases 0.000 description 1
- 239000004816 latex Substances 0.000 description 1
- 229920000126 latex Polymers 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000010825 pathological waste Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W90/00—Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Accommodation For Nursing Or Treatment Tables (AREA)
Abstract
The invention provides a method and a system for detecting the wearing of medical waste treatment personnel protective equipment based on target detection, wherein the method comprises the following steps: step 1: acquiring a flow image of a medical waste treatment area; step 2: based on a target detection technology, carrying out wearing detection on the protective tool by medical waste treatment personnel in the flow image to obtain a detection result; step 3: if the detection result is that the wearing is not standard, taking the corresponding medical waste treatment personnel as target personnel; step 4: the method comprises the steps of obtaining an environmental risk factor and a risk exposure degree of a first position of a target person in a medical waste treatment area, and reminding the target person according to the environmental risk factor and the risk exposure degree. According to the method and the system for detecting the wearing of the medical waste treatment personnel protective tool based on the target detection, the target detection technology is introduced, the process image is acquired to carry out the wearing detection of the protective tool, and the detection efficiency is higher; and reminding target personnel according to the environmental risk factors and the risk exposure degree, wherein the personnel reminding is more suitable.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a method and a system for detecting wearing of medical waste treatment personnel protection tools based on target detection.
Background
Medical waste is hazardous waste generated by medical institutions during performance of medical related activities, and mainly comprises five types: infectious waste (e.g., waste generated from blood and infectious disease patients, etc.), pathological waste (e.g., discarded human tissue, pathological wax, etc.), damaging waste (e.g., medical consumables, etc.), pharmaceutical waste (e.g., expired-discard medicines), and chemical waste (e.g., mercury thermometer), and medical waste disposal personnel need to wear protective equipment (e.g., surgical masks, latex gloves, work clothes, etc.) when disposing of these medical waste, and the safety of the medical waste disposal personnel is greatly affected by the standardization of the wearing of the protective equipment, and thus, corresponding detection is required.
The application number is: the invention patent of CN202210873994.2 discloses a method, a system, equipment and a storage medium for detecting the wearing of a protective tool of medical waste treatment personnel, which are used for modifying the existing medical health video monitoring system, integrating intelligent algorithms such as target detection and the like, and intelligently monitoring the wearing and the behavior of the protective tool of medical waste treatment personnel and receiving personnel, so as to avoid hospital-sensing events caused by improper operation and the fact that the protective tool is not worn in place. The target detection task of the medical waste transfer room generally comprises the wearing detection of protective equipment of medical waste treatment staff, such as whether to correctly wear a mask, a cap, a working clothes, a waterproof apron, waterproof boots, gloves and the like according to the specification. The detection method can automatically detect whether the protective appliance of medical waste treatment personnel is normal in wearing or not in real time, and even if the difference of the scale of each identification target is large, the detection method can also have higher identification precision and identification effect, thereby providing a digital supervision means for supervision departments.
However, the prior art carries out target detection on all medical and health videos, has low detection efficiency, and meanwhile, when the medical waste treatment personnel protection appliance is detected to be out of specification, the corresponding medical waste treatment personnel are not timely reminded, and the suitability is poor.
In view of the above, the present invention provides a wearing detection method for medical waste treatment personnel protection tools based on target detection, so as to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to provide a wearing detection method of medical waste treatment personnel protective equipment based on target detection, which introduces a target detection technology, carries out wearing detection of the protective equipment on medical waste treatment personnel according to a flow chart of a medical waste treatment area, and improves detection efficiency; the target personnel are reminded according to the introduced environmental risk factors and the risk exposure degree, so that the suitability of reminding is improved.
The medical waste treatment personnel protection tool wearing detection method based on target detection provided by the embodiment of the invention comprises the following steps:
step 1: acquiring a flow image of a medical waste treatment area;
step 2: based on a target detection technology, carrying out wearing detection on the protective tool by medical waste treatment personnel in the flow image to obtain a detection result;
Step 3: if the detection result is that the wearing is not standard, taking the corresponding medical waste treatment personnel as target personnel;
step 4: the method comprises the steps of obtaining an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in a medical waste treatment area, and reminding the target person according to the environmental risk factor and the risk exposure degree.
Preferably, the step 1: acquiring a flow image of a medical waste treatment area, comprising:
acquiring a monitoring node set of a preset medical and health site;
according to the monitoring area information of each monitoring node in the monitoring node set, determining the monitoring node for monitoring each medical waste treatment area and taking the monitoring node as a target node;
acquiring shooting images and shooting time of a target node corresponding to a medical waste treatment area, sequencing the shooting images according to the shooting time, and acquiring an image sequence;
and integrating all the image sequences to obtain a flow image.
Preferably, the step 2: based on the target detection technology, carry out protection apparatus dress detection to medical waste treatment personnel in the flow image, obtain the testing result, include:
determining a sub-image of the process personnel belonging to different medical waste treatment personnel according to different facial features of each medical waste treatment personnel in the process image;
Acquiring a medical waste treatment area where medical waste treatment personnel in a flow personnel sub-image are located, and taking the medical waste treatment area as a first target area;
acquiring medical waste source information of a first target area;
determining a first medical waste type for the first target area based on the medical waste source information;
determining a first protective tool required by medical waste treatment personnel for medical waste treatment operation of a first target area according to a first medical waste type of medical waste;
constructing a standard protective tool wearing feature matrix of the first protective tool;
according to the standard protective equipment wearing feature matrix of the first target area and the image features of the flow personnel sub-images of the medical waste treatment personnel in the first target area, carrying out protective equipment wearing standardization judgment on the corresponding medical waste treatment personnel to obtain a judgment result;
and integrating all the judging results to obtain a detection result.
Preferably, the step of performing wearing normalization determination of the protective gear on the corresponding medical waste treatment personnel according to the standard wearing feature matrix of the protective gear in the first target area and the image features of the flow personnel sub-images of the medical waste treatment personnel in the first target area to obtain a determination result includes:
Acquiring different extraction parts of medical waste treatment personnel corresponding to a first target area when extracting image features;
acquiring a corresponding preset wearing part of the first protective tool;
if the extraction part is consistent with the wearing part, the corresponding first protective tool is used as a second protective tool corresponding to the extraction part;
acquiring a standard protective tool wearing feature matrix of the second protective tool and taking the standard protective tool wearing feature matrix as a first matching matrix;
dividing the image features according to the differences of the extracted parts to obtain the part features of each extracted part;
acquiring a preset matrix construction frame and matrix element positions of which the position features correspond to the matrix construction frame;
constructing a second matching matrix according to the part characteristics and the matrix element positions;
calculating matrix distance values of a first matching matrix and a second matching matrix of the same extraction part, and simultaneously, acquiring a preset matrix distance value threshold value corresponding to a second protection tool;
if all the matrix distance values are smaller than or equal to the corresponding matrix distance threshold values, the corresponding medical waste treatment personnel protective appliance wear specifications;
otherwise, the wear is not normal.
Preferably, the construction of the standard protective gear wearing feature matrix of the first protective gear includes:
Acquiring a first wearing record of a plurality of first protective gear;
extracting a template and a first wearing record according to a preset standard evaluation factor, and determining the standard evaluation factor of the first wearing record;
acquiring a preset standard evaluation factor-approval value library, determining approval values corresponding to the standard evaluation factors, correlating the approval values with corresponding first wearing records, and carrying out summation calculation on the approval values corresponding to the first wearing records to obtain approval coefficients;
if the approval coefficient is greater than or equal to a preset approval coefficient threshold, taking the corresponding first wearing record as a second wearing record;
analyzing the second wearing record to obtain a plurality of wearing processes;
according to the difference of the importance degree of the wearing process, a standard protective tool wearing feature matrix of the first protective tool is constructed.
Preferably, the constructing the standard protection tool wearing feature matrix of the first protection tool according to the difference of the importance degree of the wearing process includes:
acquiring a process type of a wearing process;
determining important coefficients of the wearing process of each process type based on a preset process type-important coefficient library;
determining the feature extraction depth of the wearing process of each process type according to the importance coefficient and a preset importance coefficient-feature extraction depth comparison table;
Acquiring a preset feature extraction template to be set;
traversing each wearing process in sequence, setting the feature extraction depth of the feature extraction template to be set corresponding to the wearing process being traversed every time, and obtaining an initialized feature extraction template;
extracting process features of the wearing process being traversed based on the initialized feature extraction template;
integrating all process characteristics to obtain matrix construction characteristics;
based on a preset matrix construction rule, constructing a standard protective tool wearing feature matrix of the first protective tool according to the matrix construction feature.
Preferably, the step 4: acquiring an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in a medical waste treatment area, and correspondingly reminding the target person according to the environmental risk factor and the risk exposure degree, wherein the method comprises the following steps:
acquiring nonstandard characteristics of a third nonstandard protective appliance worn by a target person;
acquiring a second target area where target personnel are located, and simultaneously acquiring a preset environment risk factor extraction rule;
according to the environmental risk factor extraction rule and the second target area, attempting to acquire the environmental risk factor;
If the acquisition attempt fails, the corresponding target person is used as a first reminding person, and the first reminding person is reminded according to the nonstandard characteristic;
if the attempt is successful, the corresponding target person is used as a second reminding person, and the dangerous exposure degree of the second reminding person is determined according to the nonstandard characteristics;
determining the risk of the second reminding personnel according to the environmental risk factors and the risk exposure degree;
and carrying out second reminding on corresponding second reminding personnel according to different dangerous types of the dangerous risks.
Preferably, the second reminding of the corresponding second reminding person according to the different risk types of the risk includes:
if the dangerous type of the dangerous risk is a preset first dangerous type, the corresponding second reminding personnel are used as third reminding personnel;
obtaining an irregular type of irregular wearing of the protective appliance by a third reminding person, wherein the irregular type comprises the following components: unworn and irregular wear;
if the non-standard type is not worn, the transfer robot is scheduled to take a third protection tool at a preset second position, the transfer robot is controlled to go to the third position of a third reminding person according to the shortest route, and after the transfer robot reaches the third position, the third reminding person is reminded of taking the third protection tool based on a preset protection tool taking reminding rule;
If the irregular type is irregular in wearing, carrying out second reminding according to irregular characteristics of the third reminding personnel;
if the risk type of the risk is a preset second risk type, a corresponding second reminder is used as an emergency diagnosis and treatment person;
and determining an emergency diagnosis and treatment scheme according to the environmental risk factors and the risk exposure degree corresponding to the emergency diagnosis and treatment personnel, and performing emergency diagnosis and treatment.
The medical waste treatment personnel protection appliance wearing detection system based on target detection provided by the embodiment of the invention comprises:
the flow image acquisition module is used for acquiring a flow image of the medical waste treatment area;
the detection result determining module is used for carrying out wearing detection on the protective appliance by medical waste treatment personnel in the flow image based on a target detection technology to obtain a detection result;
the target personnel determining module is used for taking the corresponding medical waste treatment personnel as target personnel if the detection result is that the wearing is not standard;
the target personnel reminding module is used for acquiring the environmental risk factors of the first position of the target personnel in the medical waste treatment area and the risk exposure degree corresponding to the environmental risk factors, and carrying out corresponding reminding on the target personnel according to the environmental risk factors and the risk exposure degree.
Preferably, the process image acquisition module includes:
the monitoring node set acquisition sub-module is used for acquiring a monitoring node set of a preset medical and health site;
the target node determining submodule is used for determining the monitoring node for monitoring each medical waste treatment area according to the monitoring area information of each monitoring node in the monitoring node set and taking the monitoring node as a target node;
the image sequence acquisition sub-module is used for acquiring shooting images and shooting time of the target node corresponding to the medical waste treatment area, sequencing the shooting images according to the shooting time and acquiring an image sequence;
and the integration sub-module is used for integrating all the image sequences to obtain a flow image.
The invention has the technical effects that: the target detection technology is introduced, and the medical waste treatment personnel are subjected to wearing detection of the protection tool according to the flow chart of the medical waste treatment area, so that the detection efficiency is improved; the target personnel are reminded according to the introduced environmental risk factors and the risk exposure degree, so that the suitability of reminding is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic diagram of a method for detecting wearing of medical waste treatment personnel protective equipment based on target detection in an embodiment of the invention;
fig. 2 is a schematic diagram of a wearing detection system of medical waste treatment personnel protection appliances based on target detection in an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides a medical waste treatment personnel protective tool wearing detection method based on target detection, which is shown in fig. 1 and comprises the following steps:
step 1: acquiring a flow image of a medical waste treatment area; the medical waste treatment area is as follows: a site for treatment of medical waste; the flow image is as follows: sequencing the photographed images of the medical waste treatment area according to the photographing time and the sequence of the photographing time;
Step 2: based on a target detection technology, carrying out wearing detection on the protective tool by medical waste treatment personnel in the flow image to obtain a detection result; the target detection technology belongs to the prior art and can be realized; the medical waste treatment personnel are: a worker who processes medical waste; the wear detection of the protective appliance is as follows: judging whether to wear the required protective equipment (such as protective clothing and the like) and whether to normalize the flow of wearing the protective equipment; the detection result comprises: protective gear wear specifications and protective gear wear non-specifications;
step 4: acquiring an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in the medical waste treatment area, and correspondingly reminding the target person according to the environmental risk factor and the risk exposure degree; the target personnel are: medical waste disposal personnel wearing nonstandard protective appliances; the first position is: the position of the target personnel in the medical waste treatment area; the environmental risk factors are: what type and amount of medical waste, the degree of risk exposure is: the exposure degree of the protection part of the protection tool which is worn by the target personnel and can protect the influence caused by the environmental risk factors; the corresponding reminding of the target personnel is as follows: in the face of some scenes with small potential safety influence (for example, the problem of the process of wearing the protective tool by medical waste treatment personnel is detected in a sterilizing room), corresponding reminding is directly carried out; however, in the face of some scenes with a large potential safety impact (for example, medical waste treatment personnel are in direct contact with blood of infected patients), the work of the corresponding medical waste treatment personnel needs to be stopped, and the medical waste treatment personnel are subjected to subsequent examination.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, a process image of a medical waste treatment area is acquired, a target detection technology is introduced, medical waste treatment personnel are subjected to wearing detection of protective tools according to the process image, a detection result is determined, and when the detection result is that wearing is irregular, adaptive reminding is carried out on the target personnel based on the acquired environmental risk factors of the target personnel and the risk exposure degrees corresponding to the environmental risk factors.
According to the application, a target detection technology is introduced, and the medical waste treatment personnel are subjected to wearing detection of protective appliances according to the flow chart of the medical waste treatment area, so that the detection efficiency is improved; the target personnel are reminded according to the introduced environmental risk factors and the risk exposure degree, so that the suitability of reminding is improved.
In one embodiment, the step 1: acquiring a flow image of a medical waste treatment area, comprising:
acquiring a monitoring node set of a preset medical and health site; preset medical and health sites are, for example: a certain hospital; the monitoring node set is as follows: a collection of communication nodes of monitoring equipment of a medical and health site;
according to the monitoring area information of each monitoring node in the monitoring node set, determining the monitoring node for monitoring each medical waste treatment area and taking the monitoring node as a target node; the monitoring area information is, for example: the monitoring device monitors which area of the medical and health site; the target node is: a communication node of equipment for monitoring the medical waste treatment area;
Acquiring shooting images and shooting time of a target node corresponding to a medical waste treatment area, sequencing the shooting images according to the shooting time, and acquiring an image sequence; photographing a portrait, for example: an image containing a human body is shot by monitoring equipment of the medical waste treatment area; the shooting time is, for example: sometime; image sequence: an image sequence comprising photographed portraits of a time-sequenced target node;
and integrating all the image sequences to obtain a flow image.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, the monitoring node set is introduced, the target node which can monitor the medical waste treatment area is determined according to the monitoring area information of the monitoring nodes in the monitoring node set, and the rationality of the acquisition of the target node is improved; according to the shooting human images and shooting time of the target node corresponding to the medical waste treatment area, the image sequence is determined, and the acquisition suitability of the image sequence is improved.
In one embodiment, further comprising:
acquiring a first gray function of a photographed image;
mapping the first gray functions into different ranges respectively, and obtaining a second gray function for enhancing the contrast of the photographed image, wherein the second gray function is specifically as follows:
Wherein T (m, n) is a second gray function at a pixel position of an mth row and an nth column of the photographed image, f (m, n) is a first gray function at a pixel position of the mth row and the nth column of the photographed image, T (a) is a gray value corresponding to the second gray function at a preset a pixel position of the photographed image, T (b) is a gray value corresponding to the second gray function at a preset b pixel position of the photographed image, f (a) is a gray value corresponding to the first gray function at the preset a pixel position of the photographed image, and f (b) is a gray value corresponding to the first gray function at the preset b pixel position of the photographed image.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, the second gray function is introduced to enhance the contrast of the photographed image, so that the wearing detection precision of the subsequent protective tool is improved.
In one embodiment, the step 2: based on the target detection technology, carry out protection apparatus dress detection to medical waste treatment personnel in the flow image, obtain the testing result, include:
determining a sub-image of the process personnel belonging to different medical waste treatment personnel according to different facial features of each medical waste treatment personnel in the process image; facial features are, for example: face I D, based on face recognition technology extraction, can be realized;
Acquiring a medical waste treatment area where medical waste treatment personnel in a flow personnel sub-image are located, and taking the medical waste treatment area as a first target area; the first target area is: the medical waste treatment area where each medical waste treatment personnel is located;
acquiring medical waste source information of a first target area; medical waste source information is, for example: a department;
determining a first medical waste type for the first target area based on the medical waste source information; the first medical waste category is, for example: infectious medical waste, again for example: pathological medical waste;
determining a first protective tool required by medical waste treatment personnel for medical waste treatment operation of a first target area according to a first medical waste type of medical waste; the first medical waste category is, for example: pharmaceutical waste; the first protective gear is, for example: protective gloves;
constructing a standard protective tool wearing feature matrix of the first protective tool; the standard protective equipment wear characteristic matrix is: a matrix of standard wear characteristics of the first protective gear based on a matrix construction technique;
according to the standard protective equipment wearing feature matrix of the first target area and the image features of the flow personnel sub-images of the medical waste treatment personnel in the first target area, carrying out protective equipment wearing standardization judgment on the corresponding medical waste treatment personnel to obtain a judgment result; the image features are obtained based on feature extraction technology; the wear standardization of the protective device is determined as, for example: judging whether to wear the protective appliance or not/judging whether to wear the protective appliance normally or not; the determination result is, for example: the wear specification of the protective appliance;
And integrating all the judging results to obtain a detection result.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the facial features of the introduced medical waste treatment personnel, the sub-images of the process personnel belonging to different medical waste treatment personnel are determined, and the accuracy of the sub-image acquisition of the process personnel is improved; determining a first target area where medical waste treatment personnel are located in the flow personnel sub-image, acquiring medical waste source information of the first target area, and determining a first medical waste type of the first target area according to the medical waste source information, so that the method is more reasonable; according to the first medical waste type, determining a first protection tool required for medical waste treatment work of the first target area, so that the acquisition suitability of the first protection tool is improved; and the standard protective tool wearing feature matrix of the first protective tool is introduced, and according to the standard protective tool wearing feature matrix of the first target area and the image features of the flow personnel sub-images of the medical waste treatment personnel in the first target area, the corresponding medical waste treatment personnel are subjected to protective tool wearing normalization judgment, so that a judgment result is obtained, and the judgment accuracy is improved.
In one embodiment, the determining the wearing normalization of the protective device for the corresponding medical waste treatment personnel according to the wearing feature matrix of the standard protective device in the first target area and the image features of the sub-images of the procedure personnel of the medical waste treatment personnel in the first target area to obtain the determination result includes:
Acquiring different extraction parts of medical waste treatment personnel corresponding to a first target area when extracting image features; the extraction sites are, for example: face, again for example: a torso;
acquiring a corresponding preset wearing part of the first protective tool; the first protective tool is preset by a person corresponding to a preset wearing part, for example: the mask corresponds to the preset wearing part and is: a face;
if the extraction part is consistent with the wearing part, the corresponding first protective tool is used as a second protective tool corresponding to the extraction part; the second protective appliance is as follows: a protective tool to be worn on the extraction part;
acquiring a standard protective tool wearing feature matrix of the second protective tool and taking the standard protective tool wearing feature matrix as a first matching matrix;
dividing the image features according to the differences of the extracted parts to obtain the part features of each extracted part; for example: facial features, again for example: torso features;
constructing a second matching matrix according to the part characteristics; the second matching matrix is: a matrix of site features;
acquiring a preset matrix construction frame and matrix element positions of which the position features correspond to the matrix construction frame; the matrix construction frame is preset manually; the matrix element positions are: the position of the part feature in the matrix constructed under the matrix construction frame;
Constructing a second matching matrix according to the part characteristics and the matrix element positions;
calculating matrix distance values of a first matching matrix and a second matching matrix of the same extraction part, and simultaneously, acquiring a preset matrix distance value threshold value corresponding to a second protection tool; the matrix distance value is, for example: the sum of the differences of matrix elements of each corresponding position of the first matching matrix and the second matching matrix of the same extraction part, the matrix distance value represents the standard degree of wearing of the second protective appliance, and the smaller the matrix distance value is, the more standard the corresponding second protective appliance is worn; the matrix distance value threshold corresponding to the second protective tool is preset manually;
if all the matrix distance values are smaller than or equal to the corresponding matrix distance threshold values, the corresponding medical waste treatment personnel protective appliance wear specifications; if all the matrix distance values are smaller than or equal to the corresponding matrix distance threshold values, indicating that each protective tool of the corresponding medical waste treatment personnel is in a wearing specification;
otherwise, the wear is not normal.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, the extraction area of the image features and the wearing part of the first protective tool are introduced, the second protective tool of the extraction part is determined, the first matching matrix of the second protective tool and the second matching matrix of the extraction part are obtained, the matrix distance values of the first matching matrix and the second matching matrix of the same extraction part are calculated, the threshold value of the preset matrix distance value corresponding to the second protective tool is introduced, the wearing normalization of the protective tool is judged for medical waste treatment personnel, and the judging efficiency is improved.
In one embodiment, the building of the standard protective gear wear feature matrix of the first protective gear comprises:
acquiring a first wearing record of a plurality of first protective gear; the first wear record is: a process record of wearing the first protective appliance is acquired by big data;
extracting a template and a first wearing record according to a preset standard evaluation factor, and determining the standard evaluation factor of the first wearing record; the template constraint for extracting the standard evaluation factors only extracts the standard evaluation factors; the specification evaluation factors are, for example: whether to be disinfected and then dressed;
acquiring a preset standard evaluation factor-approval value library, determining approval values corresponding to the standard evaluation factors, correlating the approval values with corresponding first wearing records, and carrying out summation calculation on the approval values corresponding to the first wearing records to obtain approval coefficients; canonical rating factor-approval value is a database; the larger the approval value is, the more normative the wearing process corresponding to the first wearing record is; the larger the approval coefficient is, the more the corresponding first wearing record can be used for constructing a wearing feature matrix of the standard protective appliance;
if the approval coefficient is greater than or equal to a preset approval coefficient threshold, taking the corresponding first wearing record as a second wearing record; the preset approval coefficient threshold value is preset manually;
Analyzing the second wearing record to obtain a plurality of wearing processes; wearing processes, such as: the hands are disinfected, then worn, and finally the wearing tightness is detected;
according to the difference of the importance degree of the wearing process, a standard protective tool wearing feature matrix of the first protective tool is constructed. The higher the importance degree, the deeper the feature extraction depth corresponding to the wearing process.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, the first wearing record of the first protective tool is obtained, and the standard evaluation factors of the first wearing record are extracted according to the introduced standard evaluation factor extraction template, so that the obtaining efficiency of the standard evaluation factors is improved; a standard evaluation factor-approval value library is introduced to determine approval coefficients of the first wearing record, so that accuracy of obtaining the approval coefficients is improved; and the approval coefficient threshold value is introduced to determine the second wearing record, and the standard protection tool wearing feature matrix of the first protection tool is constructed according to the difference of the importance degree of the wearing process analyzed by the second wearing record, so that the suitability of the standard protection tool wearing feature matrix is improved.
In one embodiment, the constructing the standard protection tool wearing feature matrix of the first protection tool according to the difference of the importance degree of the wearing process includes:
Acquiring a process type of a wearing process; the process types are, for example: sterilization process, again for example: a tightness detection process;
determining important coefficients of the wearing process of each process type based on a preset process type-important coefficient library; the process type-importance coefficient library is: a database storing a plurality of process types and corresponding importance coefficients; the higher the importance coefficient is, the deeper the feature extraction depth of the process features extracted by the wearing process of the corresponding process type is;
determining the feature extraction depth of the wearing process of each process type according to the importance coefficient and a preset importance coefficient-feature extraction depth comparison table;
acquiring a preset feature extraction template to be set; the feature extraction template to be set is preset manually, and the feature extraction depth can be set in a self-defined mode;
traversing each wearing process in sequence, setting the feature extraction depth of the feature extraction template to be set corresponding to the wearing process being traversed every time, and obtaining an initialized feature extraction template; initializing a feature extraction template as follows: the wearing process being traversed is characterized by extracting templates according to the determined importance degree of the process;
extracting process features of the wearing process being traversed based on the initialized feature extraction template; the process is characterized by, for example: a sterilization mode, a sterilization duration, a wearing action and a tightness detection action;
Integrating all process characteristics to obtain matrix construction characteristics;
based on a preset matrix construction rule, constructing a standard protective tool wearing feature matrix of the first protective tool according to the matrix construction feature. The matrix construction rules are preset manually.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the method, a process type-important coefficient library is introduced, the important coefficient of the wearing process of each process type is determined, then the feature extraction depth of the wearing process is determined according to the introduced important coefficient-feature extraction depth comparison table, the feature extraction depth of the wearing process to be set corresponding to the traversing wearing process is set, an initialization feature extraction template is obtained, the process feature extraction is carried out on the traversing wearing process based on the initialization feature extraction template, the accuracy and the comprehensiveness of feature extraction are improved, and the rationality of subsequent wearing detection is also improved.
In one embodiment, the step 4: acquiring an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in a medical waste treatment area, and correspondingly reminding the target person according to the environmental risk factor and the risk exposure degree, wherein the method comprises the following steps:
Acquiring nonstandard characteristics of a third nonstandard protective appliance worn by a target person; non-canonical features are, for example: the nose seal is not pinched by the mask;
acquiring a second target area where target personnel are located, and simultaneously acquiring a preset environment risk factor extraction rule; the second target area is: the area where the first location is located, for example: a protective tool wearing sub-area and a waste treatment sub-area in the medical waste treatment area; the protective tool wearing subareas are as follows: wearing areas for wearing the protective appliances before medical waste treatment; the waste treatment subareas are: a region where medical treatment waste work is actually performed;
according to the environmental risk factor extraction rule and the second target area, attempting to acquire the environmental risk factor; environmental risk factors are, for example: what type and what amount of medical waste;
if the acquisition attempt fails, the corresponding target person is used as a first reminding person, and the first reminding person is reminded according to the nonstandard characteristic; the first reminder is, for example: a target person in the protective gear wearing sub-area; the first reminder is, for example: extracting a nose seal of the mask which is pinched by a first reminding person;
if the attempt is successful, the corresponding target person is used as a second reminding person, and the dangerous exposure degree of the second reminding person is determined according to the nonstandard characteristics; the second reminder is, for example: target personnel in the waste treatment sub-area; the risk exposure is determined based on non-canonical characteristics, such as: when the non-standard features are: when the nose is exposed, the dangerous exposure degree is as follows: three-level exposure, when the nonstandard characteristic is that the nose is not exposed, and the nose seal is not pinched, the dangerous exposure degree is: primary exposure;
Determining the risk of the second reminding personnel according to the environmental risk factors and the risk exposure degree; the risk of danger is: the second reminder person may be at risk, for example: infection with an infectious disease;
and carrying out second reminding on corresponding second reminding personnel according to different dangerous types of the dangerous risks. For example: when the risk type is the risk of infection by an infectious disease, the second reminder is: detection of a corresponding infectious disease infection, for example: when the dangerous type is that the medical consumable (such as a needle tube) is in the risk of cutting, the second reminding is that: wearing gloves.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the method, the environment risk factor extraction rule is introduced, the environment risk factor of the second target area is tried to be acquired according to the environment risk factor extraction rule, if the acquisition attempt fails, the first reminder is introduced to remind corresponding second reminder personnel, if the acquisition attempt fails, the risk exposure degree of the second reminder is introduced, and according to the difference of the risk types of the risk factors and the risk risks determined by the corresponding risk exposure degree, the second reminder is introduced to remind the corresponding second reminder, so that the suitability of reminding is improved, and the safety of medical waste disposal personnel is improved.
In one embodiment, the different risk types of the risk risks perform a second reminder to the corresponding second reminder personnel, including:
if the dangerous type of the dangerous risk is a preset first dangerous type, the corresponding second reminding personnel are used as third reminding personnel; the first hazard type is: no risk of physical security damage to the second reminder personnel;
obtaining an irregular type of irregular wearing of the protective appliance by a third reminding person, wherein the irregular type comprises the following components: unworn and irregular wear; not worn as, for example: the mask is not worn; wear non-norms are, for example: the protective garment does not cover the whole body skin;
if the non-standard type is not worn, the transfer robot is scheduled to take a third protection tool at a preset second position, the transfer robot is controlled to go to the third position of a third reminding person according to the shortest route, and after the transfer robot reaches the third position, the third reminding person is reminded of taking the third protection tool based on a preset protection tool taking reminding rule; if the non-standard type is that the protective tool is not worn and the third reminding person enters the waste treatment subarea, the third reminding person is led to go to a preset second position (the protective tool wears the subarea) again, so that the taking convenience is poor, and meanwhile, repeated infection can be caused, and therefore, the transfer robot is introduced, and the transfer robot is controlled to plan the shortest route (the shortest route is obtained according to the first position and the second position planning based on the path planning technology) to go to the third position (the position where the third reminding person is located); the preset reminding rules for the taking of the protective appliances are preset by manual work.
If the irregular type is irregular in wearing, carrying out second reminding according to irregular characteristics of the third reminding personnel; when the irregular type is irregular in wearing, performing second reminding adjustment; when the second reminding is carried out, reminding information generated based on the nonstandard characteristics is sent to a third reminding person;
if the risk type of the risk is a preset second risk type, a corresponding second reminder is used as an emergency diagnosis and treatment person; the second preset hazard type is: the risk of physical security damage to the second reminder personnel; emergency medical personnel: medical waste treatment personnel who need to stop medical waste treatment operation immediately to carry out diagnosis and treatment detection;
and determining an emergency diagnosis and treatment scheme according to the environmental risk factors and the risk exposure degree corresponding to the emergency diagnosis and treatment personnel, and performing emergency diagnosis and treatment. When determining the emergency diagnosis and treatment scheme, determining according to the environmental risk factors and the risk exposure degrees corresponding to the emergency diagnosis and treatment personnel, for example, the environmental risk factors are: xx milliliters of infectious patient blood, the dangerous exposure level is: the corresponding emergency diagnosis and treatment scheme is as follows: immediately performing blood drawing test to detect whether the same disease is infected with the infectious patient.
The working principle and the beneficial effects of the technical scheme are as follows:
according to the application, the dangerous types of the dangerous risks are introduced, different reminding modes of the second reminding person are determined according to different dangerous types, when the dangerous types are the first dangerous types and the third reminding person forgets to wear the protective tool, the conveying robot is introduced for conveying, when the dangerous types of the dangerous risks are the preset second dangerous types, the emergency diagnosis and treatment scheme is introduced for diagnosing the second reminding person judged to be the emergency diagnosis and treatment person, the reminding suitability and the safety of the person are improved, and the reminding effect is further improved.
The embodiment of the application provides a medical waste treatment personnel protective appliance wearing detection system based on target detection, which is shown in fig. 2 and comprises the following steps:
the flow image acquisition module is used for acquiring a flow image of the medical waste treatment area;
the detection result determining module is used for carrying out wearing detection on the protective appliance by medical waste treatment personnel in the flow image based on a target detection technology to obtain a detection result;
the target personnel determining module is used for taking the corresponding medical waste treatment personnel as target personnel if the detection result is that the wearing is not standard;
the target personnel reminding module is used for acquiring the environmental risk factors of the first position of the target personnel in the medical waste treatment area and the risk exposure degree corresponding to the environmental risk factors, and carrying out corresponding reminding on the target personnel according to the environmental risk factors and the risk exposure degree.
In one embodiment, the process image acquisition module includes:
the monitoring node set acquisition sub-module is used for acquiring a monitoring node set of a preset medical and health site;
the target node determining submodule is used for determining the monitoring node for monitoring each medical waste treatment area according to the monitoring area information of each monitoring node in the monitoring node set and taking the monitoring node as a target node;
the image sequence acquisition sub-module is used for acquiring shooting images and shooting time of the target node corresponding to the medical waste treatment area, sequencing the shooting images according to the shooting time and acquiring an image sequence;
and the integration sub-module is used for integrating all the image sequences to obtain a flow image.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The method for detecting the wearing of the medical waste treatment personnel protective appliance based on the target detection is characterized by comprising the following steps of:
step 1: acquiring a flow image of a medical waste treatment area;
Step 2: based on a target detection technology, carrying out wearing detection on the protective tool by medical waste treatment personnel in the flow image to obtain a detection result;
step 3: if the detection result is that the wearing is not standard, taking the corresponding medical waste treatment personnel as target personnel;
step 4: acquiring an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in the medical waste treatment area, and correspondingly reminding the target person according to the environmental risk factor and the risk exposure degree; the environmental risk factors are: the amount of medical waste corresponding to the medical waste of the different medical waste types; the degree of risk exposure is: the exposure degree of the protection part of the protection tool which is worn by the target personnel and can protect the influence caused by the environmental risk factors;
the step 4: acquiring an environmental risk factor and a risk exposure degree corresponding to the environmental risk factor of a first position of a target person in a medical waste treatment area, and correspondingly reminding the target person according to the environmental risk factor and the risk exposure degree, wherein the method comprises the following steps:
acquiring nonstandard characteristics of a third nonstandard protective appliance worn by a target person;
acquiring a second target area where target personnel are located, and simultaneously acquiring a preset environment risk factor extraction rule;
According to the environmental risk factor extraction rule and the second target area, attempting to acquire the environmental risk factor;
if the acquisition attempt fails, the corresponding target person is used as a first reminding person, and the first reminding person is reminded according to the nonstandard characteristic;
if the attempt is successful, the corresponding target person is used as a second reminding person, and the dangerous exposure degree of the second reminding person is determined according to the nonstandard characteristics;
determining the risk of the second reminding personnel according to the environmental risk factors and the risk exposure degree;
according to different dangerous types of the dangerous risks, carrying out second reminding on corresponding second reminding personnel;
according to the different dangerous types of dangerous risks, carrying out second reminding on corresponding second reminding personnel, wherein the method comprises the following steps:
if the dangerous type of the dangerous risk is a preset first dangerous type, the corresponding second reminding personnel are used as third reminding personnel;
obtaining an irregular type of irregular wearing of the protective appliance by a third reminding person, wherein the irregular type comprises the following components: unworn and irregular wear;
if the non-standard type is not worn, the transfer robot is scheduled to take a third protection tool at a preset second position, the transfer robot is controlled to go to the third position of a third reminding person according to the shortest route, and after the transfer robot reaches the third position, the third reminding person is reminded of taking the third protection tool based on a preset protection tool taking reminding rule;
If the irregular type is irregular in wearing, carrying out second reminding according to irregular characteristics of the third reminding personnel;
if the risk type of the risk is a preset second risk type, a corresponding second reminder is used as an emergency diagnosis and treatment person;
and determining an emergency diagnosis and treatment scheme according to the environmental risk factors and the risk exposure degree corresponding to the emergency diagnosis and treatment personnel, and performing emergency diagnosis and treatment.
2. The method for detecting the wearing of medical waste disposal personnel protective equipment based on the target detection according to claim 1, wherein the step 1: acquiring a flow image of a medical waste treatment area, comprising:
acquiring a monitoring node set of a preset medical and health site;
according to the monitoring area information of each monitoring node in the monitoring node set, determining the monitoring node for monitoring each medical waste treatment area and taking the monitoring node as a target node;
acquiring shooting images and shooting time of a target node corresponding to a medical waste treatment area, sequencing the shooting images according to the shooting time, and acquiring an image sequence;
and integrating all the image sequences to obtain a flow image.
3. The method for detecting the wearing of medical waste disposal personnel protective equipment based on the target detection according to claim 1, wherein the step 2: based on the target detection technology, carry out protection apparatus dress detection to medical waste treatment personnel in the flow image, obtain the testing result, include:
Determining a sub-image of the process personnel belonging to different medical waste treatment personnel according to different facial features of each medical waste treatment personnel in the process image;
acquiring a medical waste treatment area where medical waste treatment personnel in a flow personnel sub-image are located, and taking the medical waste treatment area as a first target area;
acquiring medical waste source information of a first target area;
determining a first medical waste type for the first target area based on the medical waste source information;
determining a first protective tool required by medical waste treatment personnel for medical waste treatment operation of a first target area according to a first medical waste type of medical waste;
constructing a standard protective tool wearing feature matrix of the first protective tool;
according to the standard protective equipment wearing feature matrix of the first target area and the image features of the flow personnel sub-images of the medical waste treatment personnel in the first target area, carrying out protective equipment wearing standardization judgment on the corresponding medical waste treatment personnel to obtain a judgment result;
and integrating all the judging results to obtain a detection result.
4. The method for detecting the wearing of medical waste disposal personnel protective equipment based on the target detection according to claim 3, wherein the step of performing the wearing normalization of the protective equipment on the corresponding medical waste disposal personnel according to the standard wearing feature matrix of the protective equipment of the first target area and the image feature of the flow personnel sub-image of the medical waste disposal personnel of the first target area to obtain the determination result comprises the following steps:
Acquiring different extraction parts of medical waste treatment personnel corresponding to a first target area when extracting image features;
acquiring a corresponding preset wearing part of the first protective tool;
if the extraction part is consistent with the wearing part, the corresponding first protective tool is used as a second protective tool corresponding to the extraction part;
acquiring a standard protective tool wearing feature matrix of the second protective tool and taking the standard protective tool wearing feature matrix as a first matching matrix;
dividing the image features according to the differences of the extracted parts to obtain the part features of each extracted part;
acquiring a preset matrix construction frame and matrix element positions of which the position features correspond to the matrix construction frame;
constructing a second matching matrix according to the part characteristics and the matrix element positions;
calculating matrix distance values of a first matching matrix and a second matching matrix of the same extraction part, and simultaneously, acquiring a preset matrix distance value threshold value corresponding to a second protection tool;
if all the matrix distance values are smaller than or equal to the corresponding matrix distance threshold values, the corresponding medical waste treatment personnel protective appliance wear specifications;
otherwise, the wear is not normal.
5. The method for detecting the wearing of medical waste disposal personnel protective equipment based on the target detection according to claim 3, wherein the constructing the standard protective equipment wearing feature matrix of the first protective equipment comprises:
Acquiring a first wearing record of a plurality of first protective gear;
extracting a template and a first wearing record according to a preset standard evaluation factor, and determining the standard evaluation factor of the first wearing record;
acquiring a preset standard evaluation factor-approval value library, determining approval values corresponding to the standard evaluation factors, correlating the approval values with corresponding first wearing records, and carrying out summation calculation on the approval values corresponding to the first wearing records to obtain approval coefficients;
if the approval coefficient is greater than or equal to a preset approval coefficient threshold, taking the corresponding first wearing record as a second wearing record;
analyzing the second wearing record to obtain a plurality of wearing processes;
according to the difference of the importance degree of the wearing process, a standard protective tool wearing feature matrix of the first protective tool is constructed.
6. The method for detecting the wearing of medical waste disposer protection gear based on the target detection according to claim 5, wherein the constructing the standard protection gear wearing feature matrix of the first protection gear according to the difference of the importance degree of the wearing process comprises:
acquiring a process type of a wearing process;
determining important coefficients of the wearing process of each process type based on a preset process type-important coefficient library;
Determining the feature extraction depth of the wearing process of each process type according to the importance coefficient and a preset importance coefficient-feature extraction depth comparison table;
acquiring a preset feature extraction template to be set;
traversing each wearing process in sequence, setting the feature extraction depth of the feature extraction template to be set corresponding to the wearing process being traversed every time, and obtaining an initialized feature extraction template;
extracting process features of the wearing process being traversed based on the initialized feature extraction template;
integrating all process characteristics to obtain matrix construction characteristics;
based on a preset matrix construction rule, constructing a standard protective tool wearing feature matrix of the first protective tool according to the matrix construction feature.
7. Medical waste treatment personnel protective equipment dresses detecting system based on target detection, its characterized in that includes:
the flow image acquisition module is used for acquiring a flow image of the medical waste treatment area;
the detection result determining module is used for carrying out wearing detection on the protective appliance by medical waste treatment personnel in the flow image based on a target detection technology to obtain a detection result;
the target personnel determining module is used for taking the corresponding medical waste treatment personnel as target personnel if the detection result is that the wearing is not standard;
The target personnel reminding module is used for acquiring the environmental risk factors and the risk exposure degrees corresponding to the environmental risk factors of the first position of the target personnel in the medical waste treatment area and carrying out corresponding reminding on the target personnel according to the environmental risk factors and the risk exposure degrees; the environmental risk factors are: the amount of medical waste corresponding to the medical waste of the different medical waste types; the degree of risk exposure is: the exposure degree of the protection part of the protection tool which is worn by the target personnel and can protect the influence caused by the environmental risk factors;
the target person reminding module performs the following operations:
acquiring nonstandard characteristics of a third nonstandard protective appliance worn by a target person;
acquiring a second target area where target personnel are located, and simultaneously acquiring a preset environment risk factor extraction rule;
according to the environmental risk factor extraction rule and the second target area, attempting to acquire the environmental risk factor;
if the acquisition attempt fails, the corresponding target person is used as a first reminding person, and the first reminding person is reminded according to the nonstandard characteristic;
if the attempt is successful, the corresponding target person is used as a second reminding person, and the dangerous exposure degree of the second reminding person is determined according to the nonstandard characteristics;
Determining the risk of the second reminding personnel according to the environmental risk factors and the risk exposure degree;
according to different dangerous types of the dangerous risks, carrying out second reminding on corresponding second reminding personnel;
according to the different dangerous types of dangerous risks, carrying out second reminding on corresponding second reminding personnel, wherein the method comprises the following steps:
if the dangerous type of the dangerous risk is a preset first dangerous type, the corresponding second reminding personnel are used as third reminding personnel;
obtaining an irregular type of irregular wearing of the protective appliance by a third reminding person, wherein the irregular type comprises the following components: unworn and irregular wear;
if the non-standard type is not worn, the transfer robot is scheduled to take a third protection tool at a preset second position, the transfer robot is controlled to go to the third position of a third reminding person according to the shortest route, and after the transfer robot reaches the third position, the third reminding person is reminded of taking the third protection tool based on a preset protection tool taking reminding rule;
if the irregular type is irregular in wearing, carrying out second reminding according to irregular characteristics of the third reminding personnel;
if the risk type of the risk is a preset second risk type, a corresponding second reminder is used as an emergency diagnosis and treatment person;
And determining an emergency diagnosis and treatment scheme according to the environmental risk factors and the risk exposure degree corresponding to the emergency diagnosis and treatment personnel, and performing emergency diagnosis and treatment.
8. The target detection-based medical waste disposer protection gear wear detection system of claim 7, wherein the flow image acquisition module comprises:
the monitoring node set acquisition sub-module is used for acquiring a monitoring node set of a preset medical and health site;
the target node determining submodule is used for determining the monitoring node for monitoring each medical waste treatment area according to the monitoring area information of each monitoring node in the monitoring node set and taking the monitoring node as a target node;
the image sequence acquisition sub-module is used for acquiring shooting images and shooting time of the target node corresponding to the medical waste treatment area, sequencing the shooting images according to the shooting time and acquiring an image sequence;
and the integration sub-module is used for integrating all the image sequences to obtain a flow image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385669.6A CN116503797B (en) | 2023-04-10 | 2023-04-10 | Medical waste treatment personnel protection tool wearing detection method based on target detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385669.6A CN116503797B (en) | 2023-04-10 | 2023-04-10 | Medical waste treatment personnel protection tool wearing detection method based on target detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116503797A CN116503797A (en) | 2023-07-28 |
| CN116503797B true CN116503797B (en) | 2023-10-27 |
Family
ID=87317555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310385669.6A Active CN116503797B (en) | 2023-04-10 | 2023-04-10 | Medical waste treatment personnel protection tool wearing detection method based on target detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503797B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106463041A (en) * | 2014-04-04 | 2017-02-22 | 金明焕 | Personal protection service system and method |
| CN107506903A (en) * | 2017-08-01 | 2017-12-22 | 深圳市盛路物联通讯技术有限公司 | A kind of method for managing security and device |
| RU2724785C1 (en) * | 2020-02-20 | 2020-06-25 | ООО "Ай Ти Ви групп" | System and method of identifying personal protective equipment on a person |
| CN111387617A (en) * | 2020-02-21 | 2020-07-10 | 中国人民解放军陆军特色医学中心 | Protective suit, medical staff infection behavior monitoring system and method |
| CN112739426A (en) * | 2018-09-25 | 2021-04-30 | 3M创新有限公司 | Dynamically determining security devices for dynamically changing environments |
| CN113113151A (en) * | 2021-03-17 | 2021-07-13 | 中国医科大学附属盛京医院 | New crown pneumonia exposure risk assessment system for medical institution staff |
| CN113392716A (en) * | 2021-05-21 | 2021-09-14 | 浙江大华技术股份有限公司 | Personnel safety detection method, device and system and computer equipment |
| KR20210133071A (en) * | 2020-04-28 | 2021-11-05 | 비앤피 이노베이션 주식회사 | Smart safety costume and control method for the same |
| CN114782988A (en) * | 2022-03-29 | 2022-07-22 | 西安交通大学 | Construction environment-oriented multi-stage safety early warning method |
| CN114937232A (en) * | 2022-07-25 | 2022-08-23 | 浙江大学 | Wearing detection method, system and equipment for medical waste treatment personnel protective appliance |
| CN115171037A (en) * | 2022-06-14 | 2022-10-11 | 江苏润和软件股份有限公司 | Wearing identification device and method for safety operation of hazardous chemical storage chamber based on visual identification |
| CN115880722A (en) * | 2022-12-01 | 2023-03-31 | 广东电网有限责任公司 | Intelligent identification method, system and medium worn by power distribution operating personnel |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9143843B2 (en) * | 2010-12-09 | 2015-09-22 | Sealed Air Corporation | Automated monitoring and control of safety in a production area |
-
2023
- 2023-04-10 CN CN202310385669.6A patent/CN116503797B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106463041A (en) * | 2014-04-04 | 2017-02-22 | 金明焕 | Personal protection service system and method |
| CN107506903A (en) * | 2017-08-01 | 2017-12-22 | 深圳市盛路物联通讯技术有限公司 | A kind of method for managing security and device |
| CN112739426A (en) * | 2018-09-25 | 2021-04-30 | 3M创新有限公司 | Dynamically determining security devices for dynamically changing environments |
| RU2724785C1 (en) * | 2020-02-20 | 2020-06-25 | ООО "Ай Ти Ви групп" | System and method of identifying personal protective equipment on a person |
| CN111387617A (en) * | 2020-02-21 | 2020-07-10 | 中国人民解放军陆军特色医学中心 | Protective suit, medical staff infection behavior monitoring system and method |
| KR20210133071A (en) * | 2020-04-28 | 2021-11-05 | 비앤피 이노베이션 주식회사 | Smart safety costume and control method for the same |
| CN113113151A (en) * | 2021-03-17 | 2021-07-13 | 中国医科大学附属盛京医院 | New crown pneumonia exposure risk assessment system for medical institution staff |
| CN113392716A (en) * | 2021-05-21 | 2021-09-14 | 浙江大华技术股份有限公司 | Personnel safety detection method, device and system and computer equipment |
| CN114782988A (en) * | 2022-03-29 | 2022-07-22 | 西安交通大学 | Construction environment-oriented multi-stage safety early warning method |
| CN115171037A (en) * | 2022-06-14 | 2022-10-11 | 江苏润和软件股份有限公司 | Wearing identification device and method for safety operation of hazardous chemical storage chamber based on visual identification |
| CN114937232A (en) * | 2022-07-25 | 2022-08-23 | 浙江大学 | Wearing detection method, system and equipment for medical waste treatment personnel protective appliance |
| CN115880722A (en) * | 2022-12-01 | 2023-03-31 | 广东电网有限责任公司 | Intelligent identification method, system and medium worn by power distribution operating personnel |
Non-Patent Citations (3)
| Title |
|---|
| Bearing fault diagnosis based on particle swarm optimization fusion convolutional neural network;Xian Liu等;《Frontiers in Neurorobotics》;第1-10页 * |
| Face mask and medical waste disposal during the novel COVID-19 pandemic in Asia;Sarawut Sangkham;《Case Studies in Chemical and Environmental Engineering》;第1-9页 * |
| 基于层次异构混合ＧＮＮ模型的多视角 头盔佩戴鲁棒检测方法;卢建刚等;《广东电力》;第35卷(第9期);第19-26页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116503797A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110477925B (en) | Fall detection and early warning method and system for elderly people in nursing home | |
| CN107103733B (en) | One kind falling down alarm method, device and equipment | |
| CN110838118B (en) | System and method for anomaly detection in medical procedures | |
| JP4813476B2 (en) | System and method for quantifying patient clinical trends and monitoring status progression | |
| CN111898580B (en) | System, method and equipment for acquiring body temperature and respiration data of people wearing masks | |
| RU2724785C1 (en) | System and method of identifying personal protective equipment on a person | |
| CN116503797B (en) | Medical waste treatment personnel protection tool wearing detection method based on target detection | |
| Inoue et al. | Bed-exit prediction applying neural network combining bed position detection and patient posture estimation | |
| CN112466444A (en) | Comprehensive management system for protective articles | |
| CN112466445B (en) | Protective article wearing and taking-off monitoring equipment and isolation ward | |
| CN116844117B (en) | Medical protective clothing wearing monitoring system based on AI video analysis | |
| CN113081013A (en) | Method, device and system for scanning positioning sheet | |
| Basilio et al. | Face mask and face shield detection using image processing with deep learning and thermal scanning for logging system | |
| US20240054248A1 (en) | Method for anonymizing video data | |
| Jaisharma | A Deep Learning Based Approach for Detection of Face Mask Wearing using YOLO V3-tiny Over CNN with Improved Accuracy | |
| WO2023178957A1 (en) | Vital sign monitoring method, related device, and computer-readable storage medium | |
| US20220343676A1 (en) | X-ray imaging system | |
| CN117037027A (en) | Medical equipment putting-on and taking-off interpretable intelligent monitoring method and system | |
| TWI779404B (en) | Protective gear identification system and protective gear identification method | |
| KR102457305B1 (en) | A system and method for preventing industrial accident | |
| US20230343448A1 (en) | System and method for traceability and hygiene compliance management reprocessing of reusable medical devices and environments | |
| WO2023285918A1 (en) | Touch-free seal check systems and methods for respiratory protection devices | |
| CN116152927A (en) | Protective clothing wears to take off action supervisory systems | |
| CN117133422A (en) | Hospital infection irregular behavior early warning system based on artificial intelligence | |
| CN115690093A (en) | Detection system for normative radiation medical treatment process |
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 |