CN117315575B - Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions - Google Patents
Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions Download PDFInfo
- Publication number
- CN117315575B CN117315575B CN202311225600.3A CN202311225600A CN117315575B CN 117315575 B CN117315575 B CN 117315575B CN 202311225600 A CN202311225600 A CN 202311225600A CN 117315575 B CN117315575 B CN 117315575B
- Authority
- CN
- China
- Prior art keywords
- main control
- control circuit
- circuit board
- helmet
- personnel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 101
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 230000001681 protective effect Effects 0.000 claims abstract description 67
- 210000001061 forehead Anatomy 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 85
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 33
- 229910052760 oxygen Inorganic materials 0.000 claims description 33
- 239000001301 oxygen Substances 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 30
- 230000036760 body temperature Effects 0.000 claims description 20
- 239000008280 blood Substances 0.000 claims description 19
- 210000004369 blood Anatomy 0.000 claims description 19
- 230000003321 amplification Effects 0.000 claims description 14
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 6
- 239000003990 capacitor Substances 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A42—HEADWEAR
- A42B—HATS; HEAD COVERINGS
- A42B3/00—Helmets; Helmet covers ; Other protective head coverings
- A42B3/04—Parts, details or accessories of helmets
- A42B3/0406—Accessories for helmets
- A42B3/0433—Detecting, signalling or lighting devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6803—Head-worn items, e.g. helmets, masks, headphones or goggles
-
- 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
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Cardiology (AREA)
- Multimedia (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Optics & Photonics (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Pulmonology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computational Linguistics (AREA)
- Alarm Systems (AREA)
Abstract
The utility model provides a take safety protection clothes to dress intelligent cloud helmet that detects and vital sign monitor function, is provided with cloud helmet main part, is used for detecting vital sign's sign sensor module and main control circuit board, sign sensor module with main control circuit board assemble respectively in cloud helmet main part, just sign sensor module is located user's forehead position when intelligent cloud helmet wears, sign sensor module with main control circuit board is connected. This intelligence cloud helmet still carries out safety protection clothes and dresses the detection. The intelligent cloud helmet with the functions of wearing detection and vital sign monitoring of the safety protective clothing can effectively reduce the wearing missing rate of the safety protective clothing while carrying out vital signs, improves the identification precision of various environments, and has stronger generalization capability and robustness in practical operation field application.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to an intelligent helmet with functions of wearing detection and vital sign monitoring of safety protective clothing.
Background
Because the operators in the construction operation site area are more, the continuous operation time is long, and typical violation phenomena such as wearing safety helmets, personal protection articles and the like by the site operators are easy to occur. The supervision personnel performs dressing supervision by simply relying on manpower, the workload is large, human factor errors such as supervision concentration failure easily occur, huge personal safety hidden dangers are caused for safety production, and how to guarantee the safety production in the high-speed construction process becomes an important subject.
In order to ensure the life safety of the constructors, the constructors must be required to correctly wear safety protection equipment, however, the traditional manual inspection mode is difficult to comprehensively monitor the dressing condition of each constructor. Therefore, the machine vision technology is used for assisting in safety supervision, whether the constructor wears or not is automatically judged, the wearing illegal behaviors of the constructor can be timely restrained, and the operation risk can be greatly reduced. Has important significance for improving the safety management level in the construction operation process and ensuring the construction quality.
At present, the scheme for judging the wearing of the personnel mainly adopts a method for training a target detection model to identify by directly constructing personnel image data of wearing or not wearing safety protective clothing, and has some limitations. Firstly, the safety protective clothing has various types, construction environments are changed in a lot, and image data of various safety protective clothing under different scenes is difficult to collect, so that a training data set cannot well represent actual conditions, and the generalization capability of a model is weak; secondly, due to the limitation of the training set, the recognition accuracy of the model is not high enough, and the conditions of missing report and false report are easy to occur; third, different lighting conditions, occlusions, etc. can have a large impact on recognition. Therefore, it is difficult to accurately identify whether a person wears the safety protective clothing only by means of the target detection model trained by the image data, and the requirement of actual operation cannot be met.
Moreover, the existing helmets and helmets cannot monitor physical signs of users, and accidents caused by discomfort and abnormal physical signs of the users in the working process cannot be found in time.
Therefore, aiming at the defects of the prior art, it is necessary to provide an intelligent helmet with the functions of wearing detection and vital sign monitoring of safety protection clothing so as to solve the defects of the prior art.
Disclosure of Invention
The invention aims to avoid the defects of the prior art and provides an intelligent cloud helmet with functions of wearing detection and vital sign monitoring of safety protection clothing. The intelligent cloud helmet with the functions of wearing detection and vital sign monitoring of the safety protective clothing can effectively reduce the wearing missing rate of the safety protective clothing while carrying out vital signs, improves the identification precision of various environments, and has stronger generalization capability and robustness in practical operation field application.
The above object of the present invention is achieved by the following technical measures:
the utility model provides a take intelligent cloud helmet of safety protection clothes dress detection and vital sign monitoring function is provided with cloud helmet main part, is used for detecting vital sign's sign sensor module and main control circuit board, sign sensor module with main control circuit board assemble respectively in cloud helmet main part, just sign sensor module is located user's forehead position when intelligent cloud helmet wears, sign sensor module with main control circuit board connects.
The intelligent cloud helmet also carries out wearing detection of safety protection clothing, and specifically comprises the following steps:
s1, inputting an image to be detected into an optimal model to obtain an output result of personnel and safety protective clothing in the image to be detected; the output result is a personnel detection frame of all personnel and a safety protection suit detection frame of all safety protection suit in the image to be detected;
s2, obtaining an intersection ratio matrix according to the personnel detection frame and the safety protective clothing detection frame of the S1;
s3, identifying the cross ratio matrix of the S2 through a Hungary algorithm to obtain an identification result;
and S4, drawing the image to be detected according to the identification result of the S3, and obtaining a wearing judgment result.
Preferably, the step S1 is specifically performed by:
s1.1, establishing a coordinate system by taking the upper left corner of the image to be detected as an origin, defining the direction from the origin to the right as the positive direction of an X axis, and defining the direction from the origin to the lower as the positive direction of a Y axis;
s1.2, inputting the image to be detected into an optimal model to obtain the output result, wherein the output result is expressed in the form of (x 1, y1, x2, y2, class), class is a distinguishing code of personnel or safety protective clothing, x1 and y1 are the coordinates of the upper left corner point of the detection frame in the coordinate system, and x2 and y2 are the coordinates of the lower right corner point of the detection frame in the coordinate system.
Preferably, the step S2 is specifically performed by:
s2.1, respectively calculating the intersection area area_overlap of each personnel detection frame and each safety protective clothing detection frame in the coordinate system, defining the number of the personnel detection frames as M, and defining the number of the safety protective clothing detection frames as N;
s2.2, respectively calculating the union area of each personnel detection frame and each safety protection suit detection frame;
s2.3, obtaining an intersection ratio IoU according to the intersection area area_overlap of the S2.1 and the corresponding union area area_unit of the S2.2;
s2.4, constructing an intersection ratio matrix of all people and each piece of safety protective clothing according to the intersection ratio IoU of S2.3, wherein the intersection ratio matrix is an M multiplied by N matrix, and each row in the intersection ratio matrix is the intersection ratio of the same person and each piece of safety protective clothing.
Preferably, the step S3 is specifically performed by:
s3.1, subtracting the cross ratio of each item in the cross ratio matrix through a numerical value 1 to obtain a processed cross ratio matrix;
s3.2, filling the processing cross ratio matrix of S3.1 through zero padding operation to obtain an MxM matrix;
s3.3, subtracting the minimum value in the same column from the M X M matrix according to the column to obtain a processed M X M matrix;
s3.4, covering all zero values of the processed MxM matrix by using a minimum row and column to obtain a coverage matrix, wherein the coverage matrix is an MxN matrix;
s3.5, obtaining subscripts of rows or columns with values of 0 in the coverage matrix values, and recording positions to obtain an optimal solution of the Hungary algorithm;
s3.6, reconstructing a detection matrix of all the personnel according to the optimal solution and x1, y1, x2 and y2 in all the personnel detection frames in the S1, and adding a column of identification value for identifying whether the personnel wear the safety protective clothing in the detection matrix.
Preferably, the step S4 is specifically to draw the image to be measured according to the personnel detection matrix of step S3.6, and finally obtain the wearing judgment result.
Preferably, the optimal model is obtained by the following steps:
a1, acquiring a plurality of safety protective clothing images and a plurality of personnel images, respectively marking rectangular frames and rectangular frame positions on the safety protective clothing images and the personnel images, and dividing the safety protective clothing images and the personnel images into a training set and a verification set;
a2, setting training parameters of a network model, wherein the training parameters are the classification number and the maximum training times, the training times are defined as alpha, and alpha=0 is led to enter A3;
a3, inputting the safety protective clothing image and the personnel image in the training set into a network model, and processing the images through a loss function to obtain a primary model and model parameters;
a4, inputting the safety protective clothing image and the personnel image in the verification set into the primary model obtained in the A3, and then adjusting model parameters through an error back propagation algorithm;
a5, judging the value of alpha, and when alpha is the maximum training times, judging A7; if not, then enter A6;
a6, let α=α+1 return to A3;
a7, defining the current primary model as an optimal model.
Preferably, the network model is yolo8 network model.
Preferably, the safety protection suit image is crawled on the internet through a crawler script.
Preferably, the personnel image is obtained from an open source coco data set.
The intelligent helmet is further provided with a loudspeaker, a power signal switching board, an audio amplifying board and a battery, wherein the loudspeaker, the power signal switching board and the battery are respectively assembled on the helmet main body, the power signal switching board and the audio amplifying board are respectively connected with the main control circuit board, the audio amplifying board is connected with the loudspeaker, and the power signal switching board is connected with the battery.
Preferably, the physical sign sensor module is connected with the i2c4_sda end, the i2c4_scl end, the INT end, the GPIO end, the VBAT end and the GND end of the main control circuit board respectively, the INN end of the audio amplification board is connected with the cdc_hph_r end of the main control circuit board, the INP end of the audio amplification board is connected with the cdc_hph_ref end of the main control circuit board, the VOP end of the audio amplification board is connected with the positive electrode of the speaker, the VON end of the audio amplification board is connected with the negative electrode of the speaker, the VBAT end of the power signal switching board is connected with the VBAT end of the main control circuit board, the VCC end of the power signal switching board is connected with the VCC end of the main control circuit board, the GND end of the power signal switching board is connected with the positive electrode of the battery, and the GND end of the power signal switching board is connected with the negative electrode of the battery.
Preferably, the physical sign sensor module is provided with an oxygen heart rate sensor U3, a body temperature sensor U1, a capacitor C1 and a resistor R1, a pin 2 of the oxygen heart rate sensor U3 is connected with an i2c4_scl end of the main control circuit board, a pin 3 of the oxygen heart rate sensor U3 is connected with an i2c4_sda end of the main control circuit board, a pin 13 of the oxygen heart rate sensor U3 is connected with an INT end of the main control circuit board, a pin 9, a pin 10 and a pin 11 of the oxygen heart rate sensor U3 are respectively connected with a VBAT end of the main control circuit board, a pin 4 and a pin 12 of the oxygen heart rate sensor U3 are respectively connected with a GND end of the main control circuit board, a pin 1 of the body temperature sensor U1 is also connected with a VBAT end of the main control circuit board, a pin 1 of the body temperature sensor U1 is also connected with a GND end of the main control circuit board, a pin 9, a pin 10 and a pin 11 of the oxygen heart rate sensor U3 are respectively connected with a VBAT end of the main control circuit board, and a pin 1 of the main control circuit board is also connected in series with a body temperature sensor 1.
Preferably, the blood oxygen heart rate sensor U3 is MAX30102, the body temperature sensor U1 is CT1711, the main control circuit board is SLM758, and the audio amplifying board is AW8736.
The intelligent helmet with the functions of wearing detection and vital sign monitoring for the safety protective clothing is provided with a helmet main body, a vital sign sensor module and a main control circuit board, wherein the vital sign sensor module and the main control circuit board are respectively assembled on the helmet main body, the vital sign sensor module is positioned at the forehead position of a user when the intelligent helmet is worn, and the vital sign sensor module is connected with the main control circuit board. This intelligence cloud helmet still carries out safety protection clothes and dresses the detection. Compared with the prior art, the invention has the beneficial effects that: (1) The wearing judgment is carried out according to the overlapping degree of the person and the safety protective clothing, so that the construction of training data is more flexible, and a detection model with higher generalization capability can be trained only by collecting the picture data related to the person and the safety protective clothing. (2) The problem of incorrect wearing judgment caused by overlapping of the personnel detection frame and the safety protection clothing can be solved. Therefore, the invention can effectively reduce the false alarm rate, improve the recognition precision of various environments, and has stronger generalization capability and robustness in the practical operation field application. (3) And the vital signs of the user can be detected in real time, so that the monitoring coverage is improved.
Drawings
The invention is further illustrated by the accompanying drawings, which are not to be construed as limiting the invention in any way.
Fig. 1 is a flowchart of a method for detecting wear of a safety suit.
Fig. 2 is a screenshot of a plurality of safety suit images and a plurality of personnel images.
Fig. 3 is a schematic diagram of intersection of the personnel detection frame and the safety protection suit detection frame in S2.
Fig. 4 is a schematic diagram of the output result of example 2.
Fig. 5 is a schematic diagram of an m×n matrix as the coverage matrix in embodiment 2.
Fig. 6 is a schematic diagram of the optimal solution of example 2.
Fig. 7 is a schematic block circuit diagram of embodiment 4.
Fig. 8 is a circuit diagram of the sign sensor module of embodiment 4.
Detailed Description
The technical scheme of the invention is further described with reference to the following examples.
Example 1
A wearing detection method of safety protection clothing is carried out by the following steps as shown in fig. 1:
s1, inputting an image to be detected into an optimal model to obtain output results of personnel and safety protective clothing in the image to be detected; the output results are the personnel detection frames of all personnel and the safety protection clothing detection frames of all safety protection clothing in the image to be detected;
s2, obtaining an intersection ratio matrix according to the personnel detection frame and the safety protective clothing detection frame of the S1;
s3, identifying the cross ratio matrix of the S2 through a Hungary algorithm to obtain an identification result;
and S4, drawing the image to be detected according to the identification result of the S3 to obtain a wearing judgment result.
In the actual operation, the invention inputs the image to be detected into the optimal model to obtain the rectangular frame coordinate position matrix of personnel consisting of personnel detection frames of all personnel and the rectangular frame coordinate position matrix of safety protective clothing consisting of the safety protective clothing detection frames of all safety protective clothing.
The S1 of the invention is specifically carried out by the following steps:
s1.1, establishing a coordinate system by taking the upper left corner of an image to be detected as an origin, defining the direction from the origin to the right as the positive direction of an X axis, and defining the direction from the origin to the lower as the positive direction of a Y axis;
s1.2, inputting an image to be detected into an optimal model to obtain an output result, wherein the output result is expressed in the form of (x 1, y1, x2, y2 and class), class is a distinguishing code of personnel or safety protective clothing, x1 and y1 are coordinates of an upper left corner point of a detection frame in a coordinate system, and x2 and y2 are coordinates of a lower right corner point of the detection frame in the coordinate system, as shown in FIG. 3.
The S2 of the invention is specifically carried out by the following steps:
s2.1, in a coordinate system, calculating the intersection area area_overlap of each personnel detection frame and each safety protection suit detection frame respectively, wherein the number of the personnel detection frames is defined as M, and the number of the safety protection suit detection frames is defined as N;
s2.2, respectively calculating the union area of each personnel detection frame and each safety protection suit detection frame;
s2.3, obtaining an intersection ratio IoU according to the intersection area area_overlap of the S2.1 and the corresponding union area area_unit of the S2.2;
s2.4, constructing an intersection ratio matrix of all people and each piece of safety protective clothing according to the intersection ratio IoU of S2.3, wherein the intersection ratio matrix is an MxN matrix, and each row in the intersection ratio matrix is the intersection ratio of the same person and each piece of safety protective clothing.
Note that, the overlap ratio (IntersectionofUnion, ioU) is used to describe the overlap ratio between two frames. The cross-over ratio is derived from a mathematical set, and is used to describe the relationship between two sets a and B, and is equal to the number of elements contained in the intersection of the two sets divided by the number of elements contained in the union of the two sets, and the specific calculation formula is as follows:。
in this embodiment, S2 is explained by taking fig. 3 as an example, and two rectangular frames in fig. 3; wherein the coordinates of the upper left corner and the coordinates of the lower right corner of the box1 are (x 1, y 1) and (x 2, y 2), respectively, and the coordinates of the box2 are (a 1, b 1) and (a 2, b 2), respectively.
In the calculation IoU, it is necessary to obtain the upper left and lower right corner coordinates of the overlapped portion of the two rectangular frames, that is, (x_inter 1, y_inter 1) and (x_inter 2, y_inter 2) in the figure.
When solving the area of the overlapping portion of the two rectangular frames, the coordinates of the upper left corner of the overlapping portion need to be solved, and the coordinates of the upper left corners of the two rectangular frames are compared, it can be found that the position of x_inter1 should be as far as possible to the right, the position of y_inter1 should be as far as possible to the bottom, and the right and the bottom simultaneously mean that the x value and the y value should be as large as possible relative to the coordinate system, namely:
x_inter1=max(x1,a1)
y_inter1=max(y1,b1)。
when solving the lower right corner coordinates of the overlapping portion, the lower right corner coordinates of the two boundingboxes are compared, and at this time, the x_inter2 should be as far to the left as possible, and the y_inter2 should be as far as possible, which means that the x value and the y value should be as small as possible, namely:
x_inter2=min(x2,a2)
y_inter2=min(y2,b2)
the area of the overlapping portion of the two rectangles can be obtained according to the two coordinate points (x_inter 1, y_inter 1) and (x_inter 2, y_inter 2), and the area of the overlap portion can be solved as follows:
width=(x_inter2-x_inter1)
height=(y_inter2-y_inter1)
area_overlap=width*height。
( Note that: if the two rectangles do not intersect, at least one of the width and height is calculated to be negative, the negative value is set to 0 by means of interception, and the intersection area is necessarily 0. )
The area of the union part of each personnel detection frame and each safety protection suit detection frame is obtained by the following formula:
area_box1=(x2-x1)*(y2-y1)
area_box2=(a2-a1)*(b2-b1)
area_union=area_box1+area_box2-area_overlap。
the respective intersection ratio of each personnel detection frame and each safety protection suit detection frame is obtained by the following formula: ioU = (area_overlap/area_unit).
The S3 of the invention is specifically carried out by the following steps:
s3.1, subtracting the cross ratio of each item in the cross ratio matrix through a numerical value 1 to obtain a processed cross ratio matrix;
s3.2, filling the processing cross ratio matrix of the S3.1 through zero padding operation to obtain an M multiplied by M matrix;
s3.3, subtracting the minimum value in the same column from the M X M matrix according to the column to obtain a processed M X M matrix;
s3.4, covering all zero values of the processed MxM matrix by using the minimum row and column to obtain a coverage matrix, wherein the coverage matrix is an MxN matrix;
s3.5, obtaining subscripts of rows or columns with values of 0 in the coverage matrix values, and recording positions to obtain an optimal solution of the Hungary algorithm;
s3.6, reconstructing a detection matrix of all the personnel according to the optimal solution and x1, y1, x2 and y2 in the detection frame of all the personnel in the S1, and adding a column of identification value for identifying whether the personnel wear the safety protective clothing into the detection matrix.
The step S4 of the invention is to draw the image to be detected according to the personnel detection matrix of the step S3.6, and finally obtain the wearing judgment result.
The optimal model is obtained through the following steps:
a1, acquiring a plurality of safety protective clothing images and a plurality of personnel images, respectively marking rectangular frames and rectangular frame positions on the safety protective clothing images and the personnel images, and dividing the safety protective clothing images and the personnel images into a training set and a verification set;
a2, setting training parameters of a network model, wherein the training parameters are the classification number and the maximum training times, the training times are defined as alpha, alpha=0 is enabled to enter A3, the classification number is 2, the personnel is 0, and the safety protective clothing is 1; the maximum training frequency is 30;
a3, inputting the safety protective clothing image and the personnel image in the training set into a network model, and processing the images through a loss function to obtain a primary model and model parameters;
a4, inputting the security protective clothing image and the personnel image in the verification set into the primary model obtained in the A3, and then adjusting model parameters through an error back propagation algorithm;
a5, judging the value of alpha, and when alpha is the maximum training times, judging A7; if not, then enter A6;
a6, let α=α+1 return to A3;
a7, defining the current primary model as an optimal model.
It should be noted that, the network model of the present invention may be a yolo8 network model, or other network models may be used, and when other network models are used, only the format of the corresponding data set is converted.
Those skilled in the art can correspondingly select the loss function in A3 according to the actual situation, and the loss function and the error back propagation algorithm are conventional techniques in the training of the network model, and those skilled in the art should appreciate that the training of the neural network model is also a common technique. The network model type and the loss function type are not the key points of the invention, and only the optimal model which can identify the personnel detection frame and the safety protective clothing detection frame based on the safety protective clothing image and the personnel image can be obtained, and the optimal model can be used as the optimal model of the application, and the detailed description is omitted.
Taking a yolo8 network model as an example for illustration, respectively obtaining a rectangular box of a safety protective clothing image and a rectangular box of a personnel image after marking in A1, marking the rectangular box as a data set in yolo format, and respectively storing each safety protective clothing image and each personnel image in a specified marking directory by corresponding one marking file xxx.txt with xxx.jpg; yolo labeling format is as follows: the meaning of the data for each row is the position coordinates of the category classid + rectangle xyxy: 10.5035160.38750.02890630.0527778;00.5429690.4972220.0281250.05.
the image of the safety protective clothing is crawled on the internet through a crawler script, as shown in fig. 2; the personnel image is obtained from an open source coco dataset.
Compared with the prior art, the wearing detection method for the safety protective clothing has the beneficial effects that: (1) The wearing judgment is carried out according to the overlapping degree of the person and the safety protective clothing, so that the construction of training data is more flexible, and a detection model with higher generalization capability can be trained only by collecting the picture data related to the person and the safety protective clothing. (2) The problem of incorrect wearing judgment caused by overlapping of the personnel detection frame and the safety protection clothing can be solved. Therefore, the invention can effectively reduce the false alarm rate, improve the recognition precision of various environments, and has stronger generalization capability and robustness in the practical operation field application.
Example 2
According to the wearing detection method of the safety protection suit of the embodiment 1, 2735 pictures of the safety protection suit are obtained by climbing on the net through a crawler script, 8 class personnel images are obtained through an open-source coco data set, and finally an optimal model is obtained according to A1-A7 of the embodiment 1. The safety protective clothing of the embodiment is specifically a reflective clothing.
S1, inputting an image to be detected into an optimal model to obtain output results of personnel and safety protective clothing in the image to be detected; the output results are the personnel detection frames of all personnel and the safety protection clothing detection frames of all safety protection clothing in the image to be detected; as shown in fig. 4;
s2, according to the personnel detection frame and the safety protection suit detection frame of the S1, the cross-ratio matrix shown as follows is obtained:
s3 is specifically performed by the following steps:
s3.1, respectively subtracting the cross ratio of each item in the cross ratio matrix through a value 1 to obtain a processing cross ratio matrix as follows;
s3.2, filling the processing cross ratio matrix of the S3.1 through zero padding operation to obtain the following M multiplied by M matrix;
s3.3, subtracting the minimum value in the same column from the M X M matrix according to the column to obtain the M X M matrix after the following treatment;
s3.4, covering all zero values on the processed MxM matrix by using the minimum line, so as to obtain a coverage matrix, wherein the coverage matrix is an MxN matrix, as shown in FIG. 5, the numerical value of the minimum line which can cover all the zero values is calculated to be 7, and the numerical value is equivalent to the number of lines of 7 of the matrix;
s3.5, obtaining subscripts of rows or columns with values of 0 in the coverage matrix values, and recording positions to obtain an optimal solution of the Hungary algorithm, as shown in FIG. 6;
s3.6, reconstructing a detection matrix of all the personnel according to the optimal solution and x1, y1, x2 and y2 in the detection frame of all the personnel in the S1, wherein a column of identification values for identifying whether the personnel wear the safety protective clothing is added into the detection matrix.
。
And S4, drawing the image to be detected according to the personnel detection matrix of the step S3.6, and finally obtaining the wearing judgment result.
It should be noted that in S3.5 this coverage matrix value is the minimum cost match obtained by the hungarian algorithm, and in fig. 6 the matching result of the personnel to the safety suit is composed of a7 x2 matrix, the 7 rows representing 7 personnel and the 2 columns representing 2 safety suits, wherein a matrix value of 0 is the row and column subscript of interest. The software and hardware of the computer are calculated from 0 instead of 1, so the numbers of the personnel are respectively 0, 1, 2, 3, 4, 5 and 6, and the numbers of the safety protection clothing are 0 and 1; so the column and row subscript of the first 0 in the matrix is row 1, column 0, and the column and row subscript of the second 0 is row 5, column 1. The second screenshot in FIG. 6 represents the rank position of the 0 value subscript in the matrix.
Example 3
An intelligent cloud helmet with functions of wearing detection and vital sign monitoring of safety protection clothing adopts the wearing detection method of the safety protection clothing according to the embodiment 1 or 2.
The intelligent cloud helmet disclosed by the invention is provided with a cloud helmet main body, a vital sign sensor module and a main control circuit board, wherein the vital sign sensor module and the main control circuit board are respectively assembled on the cloud helmet main body, the vital sign sensor module is positioned at the forehead position of a user when the intelligent cloud helmet is worn, and the vital sign sensor module is connected with the main control circuit board.
The intelligent helmet is further provided with a loudspeaker, a power signal switching board, an audio amplifying board and a battery, wherein the loudspeaker, the power signal switching board and the battery are respectively assembled on the helmet main body, the power signal switching board and the audio amplifying board are respectively connected with the main control circuit board, the audio amplifying board is connected with the loudspeaker, and the power signal switching board is connected with the battery.
The intelligent cloud helmets of the present invention may also be referred to as helmets, helmets.
Compared with the prior art, the intelligent cloud helmet has the beneficial effects that: (1) The wearing judgment is carried out according to the overlapping degree of the person and the safety protective clothing, so that the construction of training data is more flexible, and a detection model with higher generalization capability can be trained only by collecting the picture data related to the person and the safety protective clothing. (2) The problem of incorrect wearing judgment caused by overlapping of the personnel detection frame and the safety protection clothing can be solved. Therefore, the invention can effectively reduce the false alarm rate, improve the recognition precision of various environments, and has stronger generalization capability and robustness in the practical operation field application. (3) And the vital signs of the user can be detected in real time, so that the monitoring coverage is improved.
Example 4
An intelligent helmet with functions of wearing detection and vital sign monitoring of safety protection clothing, as shown in fig. 7 and 8, has the specific features same as those of embodiment 3, and further has the following features: the sign sensor module is respectively connected with an I2C4_SDA end, an I2C4_SCL end, an INT end, a GPIO end, a VBAT end and a GND end of the main control circuit board, an INN end of the audio amplification board is connected with a CDC_HPH_R end of the main control circuit board, an INP end of the audio amplification board is connected with a CDC_HPH_REF end of the main control circuit board, a VOP end of the audio amplification board is connected with a positive electrode of the loudspeaker, a VON end of the audio amplification board is connected with a negative electrode of the loudspeaker, a VBAT end of the power signal switching board is connected with a VBAT end of the main control circuit board, a VCC end of the power signal switching board is connected with a VCC end of the main control circuit board, a GND end of the power signal switching board is connected with a GND end of the main control circuit board, a VBAT end of the power signal switching board is connected with a positive electrode of the battery, and a GND end of the power signal switching board is connected with a negative electrode of the battery.
The vital sign sensor module is provided with an blood oxygen heart rate sensor U3, a body temperature sensor U1, a capacitor C1 and a resistor R1, a2 pin of the blood oxygen heart rate sensor U3 is connected with an I2C4_SCL end of a main control circuit board, a3 pin of the blood oxygen heart rate sensor U3 is connected with an I2C4_SDA end of the main control circuit board, a 13 pin of the blood oxygen heart rate sensor U3 is connected with an INT end of the main control circuit board, a 9 pin, a 10 pin and a 11 pin of the blood oxygen heart rate sensor U3 are respectively connected with a VBAT end of the main control circuit board, a4 pin and a 12 pin of the blood oxygen heart rate sensor U3 are respectively connected with a GND end of the main control circuit board, a1 pin of the body temperature sensor U1 is connected with a GND end of the main control circuit board in series, a3 pin of the body temperature sensor U1 is connected with a GPIO end of the main control circuit board in series, and a resistor R1 is connected with a GPIO end of the main control circuit board.
The model of the blood oxygen heart rate sensor U3 is MAX30102, the model of the body temperature sensor U1 is CT1711, the model of the main control circuit board is SLM758, and the model of the audio amplification board is AW8736.
According to the intelligent cloud helmet, the physical sign sensor module is added to the intelligent cloud helmet, and the optical measuring technology is adopted to enable a user to be in contact with the optical sensor on the intelligent cloud helmet, so that blood oxygen and heart rate physical signs of the user can be measured.
The SLM758 master board of this embodiment is an 8 core, high performance motherboard with a main frequency of 2G, capable of running an android system. The main control board integrates functional interfaces such as 4G communication, an I2C bus controller, audio output and the like.
When the device is powered on, SLM758 master control board reads the register values of the blood oxygen, heart rate sensors through the I2C interface. When a user wears the intelligent cloud helmet, the main control circuit board can read that the data of the proximity register corresponding to the blood oxygen heart rate sensor is 0x0000. When the data FIFO of the blood oxygen heart rate sensor has data, the interrupt signal INT is used for informing the main control board to read the data, and after the main control circuit board reads the data, the measured blood oxygen and heart rate data can be obtained through an algorithm of blood oxygen and heart rate. Meanwhile, the body temperature sensor U1 can also detect the body temperature of a user, and the main control circuit board can also read the body temperature data.
The main control circuit board transmits the calculated blood oxygen, heart rate data and body temperature data to the background server through 4G communication for storage, analysis and processing. Meanwhile, the main control board can also locally analyze blood oxygen, heart rate data and body temperature data. If the data is judged to be abnormal, the user is prompted to pay attention to the physical condition through voice.
Compared with the embodiment 2, the physical sign monitoring function of blood oxygen, heart rate and body temperature of a person wearing the safety helmet is realized by adding the physical sign sensor module on the intelligent cloud helmet, and abnormal conditions of the body of the person can be timely found through physical sign data monitoring in the working process of the person, so that voice prompt can be carried out to remind the person to take notice of rest, and the discomfort of the body of the person is avoided, so that accidents occur. Compared with the traditional safety helmet, the safety helmet has the advantages of perfecting monitoring of blood oxygen, heart rate and body temperature physical signs of personnel, perfecting functions and being more intelligent.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted equally without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. Intelligent helmet with safety protection clothing wearing detection and vital sign monitoring functions, and is characterized in that: the intelligent helmet comprises a helmet main body, a vital sign sensor module and a main control circuit board, wherein the vital sign sensor module and the main control circuit board are respectively assembled on the helmet main body, the vital sign sensor module is positioned at the forehead position of a user when the intelligent helmet is worn, and the vital sign sensor module is connected with the main control circuit board;
and the wearing detection of the safety protection suit is also carried out, and the method specifically comprises the following steps of:
s1, inputting an image to be detected into an optimal model to obtain an output result of personnel and safety protective clothing in the image to be detected; the output result is a personnel detection frame of all personnel and a safety protection suit detection frame of all safety protection suit in the image to be detected;
s2, obtaining an intersection ratio matrix according to the personnel detection frame and the safety protective clothing detection frame of the S1;
s3, identifying the cross ratio matrix of the S2 through a Hungary algorithm to obtain an identification result;
s4, drawing the image to be detected according to the identification result of the S3 to obtain a wearing judgment result;
the step S2 is specifically performed by the following steps:
s2.1, respectively calculating the intersection area area_overlap of each personnel detection frame and each safety protective clothing detection frame in a coordinate system, wherein the number of the personnel detection frames is defined as M, and the number of the safety protective clothing detection frames is defined as N;
s2.2, respectively calculating the union area of each personnel detection frame and each safety protection suit detection frame;
s2.3, obtaining an intersection ratio IoU according to the intersection area area_overlap of the S2.1 and the corresponding union area area_unit of the S2.2;
s2.4, constructing an intersection ratio matrix of all people and each piece of safety protective clothing according to the intersection ratio IoU of S2.3, wherein the intersection ratio matrix is an M multiplied by N matrix, and each row in the intersection ratio matrix is the intersection ratio of the same person and each piece of safety protective clothing;
the step S3 is specifically performed by the following steps:
s3.1, subtracting the cross ratio of each item in the cross ratio matrix through a numerical value 1 to obtain a processed cross ratio matrix;
s3.2, filling the processing cross ratio matrix of S3.1 through zero padding operation to obtain an MxM matrix;
s3.3, subtracting the minimum value in the same column from the M X M matrix according to the column to obtain a processed M X M matrix;
s3.4, covering all zero values of the processed MxM matrix by using a minimum row and column to obtain a coverage matrix, wherein the coverage matrix is an MxN matrix;
s3.5, obtaining subscripts of rows or columns with values of 0 in the coverage matrix values, and recording positions to obtain an optimal solution of the Hungary algorithm;
s3.6, reconstructing a detection matrix of all the personnel according to the optimal solution and x1, y1, x2 and y2 in all the personnel detection frames in the S1, and adding a column of identification value for identifying whether the personnel wear the safety protective clothing in the detection matrix.
2. The intelligent cloud helmet with the functions of wearing detection and vital sign monitoring of safety protection clothing according to claim 1, wherein the step S1 is specifically performed by:
s1.1, establishing a coordinate system by taking the upper left corner of the image to be detected as an origin, defining the direction from the origin to the right as the positive direction of an X axis, and defining the direction from the origin to the lower as the positive direction of a Y axis;
s1.2, inputting the image to be detected into an optimal model to obtain the output result, wherein the output result is expressed in the form of (x 1, y1, x2, y2, class), class is a distinguishing code of personnel or safety protective clothing, x1 and y1 are the coordinates of the upper left corner point of the detection frame in the coordinate system, and x2 and y2 are the coordinates of the lower right corner point of the detection frame in the coordinate system.
3. The intelligent cloud helmet with safety suit wearing detection and vital sign monitoring functions according to claim 1, wherein: and S4, drawing the image to be detected according to the personnel detection matrix of S3.6, and finally obtaining the wearing judgment result.
4. An intelligent cloud helmet with safety suit wear detection and vital sign monitoring functions according to any one of claims 1 to 3, wherein the optimal model is obtained by:
a1, acquiring a plurality of safety protective clothing images and a plurality of personnel images, respectively marking rectangular frames and rectangular frame positions on the safety protective clothing images and the personnel images, and dividing the safety protective clothing images and the personnel images into a training set and a verification set;
a2, setting training parameters of a network model, wherein the training parameters are the classification number and the maximum training times, the training times are defined as alpha, and alpha=0 is led to enter A3;
a3, inputting the safety protective clothing image and the personnel image in the training set into a network model, and processing the images through a loss function to obtain a primary model and model parameters;
a4, inputting the safety protective clothing image and the personnel image in the verification set into the primary model obtained in the A3, and then adjusting model parameters through an error back propagation algorithm;
a5, judging the value of alpha, and when alpha is the maximum training times, judging A7; if not, then enter A6;
a6, let α=α+1 return to A3;
a7, defining the current primary model as an optimal model.
5. The intelligent cloud helmet with safety suit wear detection and vital sign monitoring functions of claim 4, wherein: the network model is a yolo8 network model;
the safety protective clothing image is crawled on the internet through a crawler script;
the personnel image is obtained from an open source coco dataset.
6. The intelligent cloud helmet with safety suit wear detection and vital sign monitoring functions according to any one of claims 1 to 3, wherein: the helmet is characterized by further comprising a loudspeaker, a power signal adapter plate, an audio amplifying plate and a battery, wherein the loudspeaker, the power signal adapter plate and the battery are assembled on the helmet body respectively, the power signal adapter plate and the audio amplifying plate are connected with the main control circuit board respectively, the audio amplifying plate is connected with the loudspeaker, and the power signal adapter plate is connected with the battery.
7. The intelligent cloud helmet with safety suit wear detection and vital sign monitoring functions of claim 6, wherein: the physical sign sensor module is respectively connected with an I2C4_SDA end, an I2C4_SCL end, an INT end, a GPIO end, a VBAT end and a GND end of the main control circuit board, an INN end of the audio amplification board is connected with a CDC_HPH_R end of the main control circuit board, an INP end of the audio amplification board is connected with a CDC_HPH_REF end of the main control circuit board, a VOP end of the audio amplification board is connected with an anode of the loudspeaker, a VON end of the audio amplification board is connected with a cathode of the loudspeaker, the VBAT end of the power supply signal switching board is connected with the VBAT end of the main control circuit board, the VCC end of the power supply signal switching board is connected with the VCC end of the main control circuit board, the GND end of the power supply signal switching board is connected with the GND end of the main control circuit board, the VBAT end of the power supply signal switching board is connected with the positive electrode of the battery, and the GND end of the power supply signal switching board is connected with the negative electrode of the battery.
8. The intelligent cloud helmet with safety suit wear detection and vital sign monitoring functions of claim 7, wherein: the physical sign sensor module is provided with an oxygen heart rate sensor U3, a body temperature sensor U1, a capacitor C1 and a resistor R1, wherein a pin 2 of the oxygen heart rate sensor U3 is connected with an I2C4_SCL end of the main control circuit board, a pin 3 of the oxygen heart rate sensor U3 is connected with an I2C4_SDA end of the main control circuit board, a pin 13 of the oxygen heart rate sensor U3 is connected with an INT end of the main control circuit board, a pin 9, a pin 10 and a pin 11 of the oxygen heart rate sensor U3 are respectively connected with a VBAT end of the main control circuit board, a pin 4 and a pin 12 of the oxygen heart rate sensor U3 are respectively connected with a GND end of the main control circuit board, a pin 1 of the body temperature sensor U1 is connected with a VBAT end of the main control circuit board, a pin 1 of the body temperature sensor U1 is also connected with a GND end of the main control circuit board, a pin 9, a pin 10 and a pin 11 of the oxygen heart rate sensor U3 are respectively connected with a VBAT end of the main control circuit board, and a GPIO end of the main control circuit board is connected in series with the GPIO end 1;
the model of the blood oxygen heart rate sensor U3 is MAX30102, the model of the body temperature sensor U1 is CT1711, the model of the main control circuit board is SLM758, and the model of the audio amplification board is AW8736.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311225600.3A CN117315575B (en) | 2023-09-21 | 2023-09-21 | Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311225600.3A CN117315575B (en) | 2023-09-21 | 2023-09-21 | Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117315575A CN117315575A (en) | 2023-12-29 |
CN117315575B true CN117315575B (en) | 2024-02-20 |
Family
ID=89249181
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311225600.3A Active CN117315575B (en) | 2023-09-21 | 2023-09-21 | Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117315575B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2020100705A4 (en) * | 2020-05-05 | 2020-06-18 | Chang, Jiaying Miss | A helmet detection method with lightweight backbone based on yolov3 network |
CN111598066A (en) * | 2020-07-24 | 2020-08-28 | 之江实验室 | Helmet wearing identification method based on cascade prediction |
CN113807240A (en) * | 2021-09-15 | 2021-12-17 | 国网河北省电力有限公司衡水供电分公司 | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition |
-
2023
- 2023-09-21 CN CN202311225600.3A patent/CN117315575B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2020100705A4 (en) * | 2020-05-05 | 2020-06-18 | Chang, Jiaying Miss | A helmet detection method with lightweight backbone based on yolov3 network |
CN111598066A (en) * | 2020-07-24 | 2020-08-28 | 之江实验室 | Helmet wearing identification method based on cascade prediction |
CN113807240A (en) * | 2021-09-15 | 2021-12-17 | 国网河北省电力有限公司衡水供电分公司 | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition |
Non-Patent Citations (1)
Title |
---|
夏鄂 ; 刘啸宇 ; 颜龙飞 ; 宋其津 ; 张赛尧 ; .实时监测骑行信息的智能头盔安全系统设计.单片机与嵌入式系统应用.2020,(第07期),第76-78页. * |
Also Published As
Publication number | Publication date |
---|---|
CN117315575A (en) | 2023-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110210302B (en) | Multi-target tracking method, device, computer equipment and storage medium | |
CN109670441B (en) | Method, system, terminal and computer readable storage medium for realizing wearing recognition of safety helmet | |
CN107704805B (en) | Method for detecting fatigue driving, automobile data recorder and storage device | |
CN105758450B (en) | Met an urgent need based on multisensor the fire-fighting early warning sensory perceptual system construction method of robot | |
CN111539276B (en) | Method for detecting safety helmet in real time in power scene | |
CN107330386A (en) | A kind of people flow rate statistical method and terminal device | |
CN112633111B (en) | Method and device for detecting wearing of safety helmet and storage medium | |
CN112818901A (en) | Wearing mask face recognition method based on eye attention mechanism | |
CN109145812A (en) | Squatter building monitoring method and device | |
CN111738132A (en) | Method and device for measuring human body temperature, electronic equipment and readable storage medium | |
CN117315575B (en) | Intelligent cloud helmet with safety protection clothing wearing detection and vital sign monitoring functions | |
TW202201275A (en) | Device and method for scoring hand work motion and storage medium | |
CN111931573A (en) | Helmet detection and early warning method based on YOLO evolution deep learning model | |
CN113314230A (en) | Intelligent epidemic prevention method, device, equipment and storage medium based on big data | |
CN116965781B (en) | Method and system for monitoring vital signs and driving behaviors of driver | |
CN109975312A (en) | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique | |
CN113762221B (en) | Human body detection method and device | |
WO2022121886A1 (en) | Method and apparatus for identifying dress code for electric power operations | |
CN115620340A (en) | Intelligent unsafe behavior identification method based on YOLO | |
CN115631169A (en) | Product detection method and device, electronic equipment and storage medium | |
CN112188156B (en) | Fire control room personnel monitored control system on duty based on big data | |
CN112287758A (en) | Climbing identification method based on key point detection | |
CN209388335U (en) | A kind of inductive arrangement based on bio-identification | |
CN117333929B (en) | Method and system for identifying abnormal personnel under road construction based on deep learning | |
CN112418140B (en) | Electric shock prevention alarm method and system for power distribution construction site |
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 |