CN116645782B - Safety helmet belt detection method based on image recognition - Google Patents
Safety helmet belt detection method based on image recognition Download PDFInfo
- Publication number
- CN116645782B CN116645782B CN202310883398.7A CN202310883398A CN116645782B CN 116645782 B CN116645782 B CN 116645782B CN 202310883398 A CN202310883398 A CN 202310883398A CN 116645782 B CN116645782 B CN 116645782B
- Authority
- CN
- China
- Prior art keywords
- worker
- helmet
- safety helmet
- safety
- head
- 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 38
- 230000001502 supplementing effect Effects 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 19
- 230000009471 action Effects 0.000 claims description 13
- 239000013589 supplement Substances 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
- G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Helmets And Other Head Coverings (AREA)
Abstract
The invention relates to the technical field of image recognition. The invention relates to a safety helmet belt detection method based on image recognition. Which comprises the following steps: when a worker needs to enter a construction site, acquiring worker image information shot by a safety gate; identifying the posture of the safety helmet of the worker according to the acquired image information, extracting the wearing path of the safety helmet belt on the head of the worker according to the identification passing result, shielding and detecting the wearing path, positioning the position shielded by the path, and transmitting the position to a safety gate to carry out image supplementing acquisition reminding on the worker; according to the safety helmet, the distance warning threshold value is set, and the chin position of a worker is combined with the position of the helmet belt of the safety helmet to carry out comparison, so that whether the safety helmet is in a fastened state is judged, the safety helmet is prevented from being hung on the head of the worker only, the helmet belt is not fastened, and when the safety helmet is impacted, the safety helmet is directly separated from the head of the worker, so that the head of the worker cannot be well protected, and the detection effect is improved.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a safety helmet belt detection method based on image recognition.
Background
Wearing the safety helmet is one of effective methods for preventing or relieving injury of workers on construction sites, at present, when the safety helmet is worn and detected by workers, some workers only hang the safety helmet on the head and do not tie the helmet belt, when the safety helmet is impacted and directly separated from the head of the workers, good protection cannot be formed on the heads of the workers, but the safety helmet is still displayed in a wearing state when the safety helmet is detected through a gate, so that when a construction accident occurs, the protection effect of the safety helmet is tiny, meanwhile, the safety helmet is damaged when the safety helmet is detected, the safety helmet is held by hands, so that the wearing state of the safety helmet is achieved, and the detection of false information is caused, so that supervision and examination are not in place.
Disclosure of Invention
The invention aims to provide a safety helmet belt detection method based on image recognition, which aims to solve the problems in the background technology.
In order to achieve the above purpose, the method for detecting the helmet belt based on image recognition comprises the following steps:
s1, when a worker needs to enter a construction site, acquiring worker image information shot by a safety gate;
s2, identifying the posture of the safety helmet of the worker according to the image information acquired in the S1, extracting the wearing path of the safety helmet belt on the head of the worker according to the identification result, carrying out shielding detection on the wearing path, positioning the position shielded by the path, and transmitting the position to a safety gate to carry out image supplement acquisition reminding on the worker;
s3, setting a warning threshold value of the attaching distance between the safety helmet belt and the chin of the worker, comparing the chin of the worker with the warning threshold value of the distance between the safety helmet belt and the chin of the worker in the image information after the supplement of S2, and sending the comparison result to a safety gate to warn the worker.
As a further improvement of the technical scheme, the S1 is connected with the safety gate through OpenCV, and the worker image information shot by the safety gate is acquired in real time.
As a further improvement of the technical scheme, the step of S2 for identifying the posture of the safety helmet of the worker is as follows:
s2.1, collecting worker identity data;
s2.2, carrying out gesture simulation on the worker identity data acquired in the step S2.1 in combination with the safety helmet, acquiring a correct wearing gesture of the safety helmet, carrying out recognition detection on the worker image information acquired in the step S1 according to the correct wearing gesture of the safety helmet, carrying out the step S2.3 if the recognition detection is passed, and controlling the safety brake to send out an alarm if the recognition detection is not passed.
As a further improvement of the technical scheme, the S2.1 collects face data of workers through the camera, and inputs the collected face data into corresponding worker identity data in the safety gate.
As a further improvement of the technical scheme, the step of S2 for carrying out image supplement acquisition reminding on workers is as follows:
s2.3, extracting a helmet belt path in the corresponding correct helmet wearing posture according to the worker image information which is identified and detected by the S2.2;
s2.4, carrying out shielding detection on the hat band path extracted in the S2.3 and the worker image information, and outputting a signal which needs to be supplemented by the current image information if the shielding value reaches five percent;
s2.5, receiving signals which are required to be supplemented by the current image information output by the S2.4, determining the position of the blocked face, outputting the signals to a safety gate to remind the direction of workers, and supplementing the collected image data.
As a further improvement of the technical scheme, the S2.5 is used for respectively left and right faces of the face of the worker; if the shielding position is at the left side of the image information, a prompt for supplementing the left face image information is sent; if the shielding position is on the right side of the image information, a prompt for supplementing the right face image information is sent out, and the side with the large shielding area ratio is sent out preferentially.
As a further improvement of the technical scheme, the step of sending the comparison result to the safety gate to give a warning to workers by the S3 is as follows:
s3.1, setting a warning threshold value of the attaching distance between the helmet belt and the chin of a worker to be two centimeters;
s3.2, detecting the distance between the helmet belt and the chin of the worker according to the image data supplemented by the S2.5; comparing the detected distance with a distance warning threshold of S3.1, outputting a signal that the current safety helmet is unqualified to wear if the distance is greater than two centimeters, and controlling the safety brake to release interception to workers if the distance is less than two centimeters;
and S3.3, receiving the signal sent by the step S3.2, sending the signal to the safety gate, and controlling the safety gate to send out sound to warn the worker.
As a further improvement of the technical scheme, the S3.2 stores the image data of the workers in the comparison and extracts the face data to upload to the S2.1 for updating the identity data of the workers.
As a further improvement of the technical scheme, the S3 identifies the actions of the workers in the image data supplemented by the S2.5, judges whether the workers hold the safety helmet lacing according to the identification result, and sends a signal that the safety helmet is unqualified to the S3.3.
Compared with the prior art, the invention has the beneficial effects that:
according to the safety helmet belt detection method based on image recognition, the distance warning threshold is set, the chin position of a worker is combined to the position of the safety helmet belt to be compared, whether the safety helmet is in a fastened state is judged, the fact that the worker only hangs the safety helmet on the head and does not fasten the helmet belt is avoided, when the safety helmet is impacted, the head of the worker is directly separated from the impact, good protection cannot be formed on the head of the worker, the detection effect is improved, meanwhile, the limb action of the worker is detected, the worker is prevented from holding the safety helmet to achieve the wearing state of the safety helmet, false information detection occurs through a security check gate, and supervision and examination are not in place.
Drawings
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a flow chart diagram of the invention for image replenishment acquisition reminding;
fig. 3 is a block flow diagram of the present invention for alerting workers.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Referring to fig. 1-3, the present embodiment is aimed at providing a method for detecting a helmet belt based on image recognition, which includes the steps of:
s1, when a worker needs to enter a construction site, acquiring worker image information shot by a safety gate;
s1 is connected with a safety gate through OpenCV, and worker image information shot by the safety gate is obtained in real time. The method comprises the following steps:
installing an OpenCV library: installing an OpenCV library, which is an open-source computer vision library, providing various image processing and computer vision functions;
connect the camera: connecting a camera of the safety gate with a computer;
real-time video stream processing: using a video capturing function of OpenCV to read an image frame of a camera;
interaction with the gate: according to specific requirements, transmitting the image result processed by OpenCV to a gate to execute corresponding operation;
treatment results: and allowing or refusing to enter according to the response of the gate, and sending out an audible warning.
S2, identifying the posture of the safety helmet of the worker according to the image information acquired in the S1, extracting the wearing path of the safety helmet belt on the head of the worker according to the identification result, carrying out shielding detection on the wearing path, positioning the position shielded by the path, and transmitting the position to a safety gate to carry out image supplement acquisition reminding on the worker;
the step of S2 for identifying the posture of the safety helmet of the worker is as follows:
s2.1, collecting worker identity data;
and S2.1, acquiring face data of a worker through a camera, and inputting the acquired face data into corresponding worker identity data in a safety gate.
S2.2, carrying out posture simulation on the worker identity data acquired in the S2.1 in combination with the safety helmet, and acquiring a correct wearing posture of the safety helmet, wherein the expression is as follows:
extracting the characteristics related to the head and the posture of the safety helmet from the worker identity data, wherein the characteristics comprise the rotation angle and the inclination angle of the head, the position and the rotation angle of the safety helmet and the like;
according to the posture data of the worker and the position information of the safety helmet, the correct posture of the worker wearing the safety helmet is simulated by using an Euler angle posture simulation representation method, and the formula is as follows:
the euler angle uses 3 angle components to represent the rotation of the head. There are different combinations of euler angles depending on the rotation order:
ZYX order The angle indicates the rotation about the X-axis, +.>The angle indicates rotation about the Y-axis, +.>The angle represents rotation about the Z axis;
XYZ order The angle indicates the rotation about the Z axis, +.>The angle represents a rotation about the Y-axis,the angle represents rotation about the X-axis.
And (3) carrying out identification detection on the worker image information acquired in the step (S1) according to the correct wearing posture of the safety helmet, carrying out the step (S2.3) if the identification detection is passed, and controlling the safety gate to send out an alarm if the identification detection is not passed. The method comprises the following steps:
judging whether the safety helmet is at the top or behind the head of the worker or not can be judged by comparing the position of the safety helmet with the position of the head, and the formula is as follows:
wherein ,is the position of the safety helmet>For head position->Is a height position, when->Less than->The safety helmet is positioned at the head of the worker, otherwise, the safety helmet is not positioned at the head of the worker, and the wearing is unqualified;
judging whether the safety helmet shields the important area of the head of the worker or not, the overlapping degree of the safety helmet and the head can be calculated, and the formula is as follows:
wherein ,indicating the degree of overlap of the helmet and the head of the worker, < + >>For the area of the overlapping area of the helmet and the head, < >>Is the area of the helmet, when +.>And 0.9 indicates that the wearing is qualified, otherwise, the wearing is unqualified.
S2.3, extracting a helmet belt path in the corresponding correct helmet wearing posture according to the worker image information which is identified and detected by the S2.2; the method comprises the following steps:
and (3) detecting a safety helmet: detecting a position of the helmet in the image using a target detection algorithm, identifying the position of the helmet by a marker or bounding box;
dividing the safety helmet: and (3) performing image segmentation on the detected helmet region, and separating the helmet from other objects or backgrounds. This may be achieved using an image segmentation algorithm;
extracting a hat band path: and extracting the path of the hat band from the segmented helmet image by using contour detection. This can be extracted based on the color, texture and shape characteristics of the hat band;
path optimization and adjustment: and optimizing and adjusting the extracted hat band path. The use of curve fitting allows the path to more closely conform to the shape and trajectory of the actual hat band.
S2.4, carrying out shielding detection on the hat band path extracted in the S2.3 and the worker image information, and outputting a signal which needs to be supplemented by the current image information if the shielding value reaches five percent; the expression poems are as follows: an appropriate threshold, for example 0.05, is set to determine if the masking level of the hat band path reaches five percent, equation:
wherein ,for the proportion of the hat band path area, +.>Display area ratio for image hat band path, +.>For the ratio of the shielding area, when->If the shielding degree of the path of the cap belt exceeds a limit value, the shielding degree is considered to be more than or equal to 0.05, and a supplementary signal is required to be output.
S2.5, receiving signals which are required to be supplemented by the current image information output by the S2.4, determining the position of the blocked face, outputting the signals to a safety gate to remind the direction of workers, and supplementing the collected image data.
S2.5, the face of the worker is left and right; if the shielding position is at the left side of the image information, a prompt for supplementing the left face image information is sent; if the shielding position is on the right side of the image information, a prompt for supplementing the right face image information is sent out, and the side with the large shielding area ratio is sent out preferentially.
S3, setting a warning threshold value of the attaching distance between the safety helmet belt and the chin of the worker, comparing the chin of the worker with the warning threshold value of the distance between the safety helmet belt and the chin of the worker in the image information after the supplement of S2, and sending the comparison result to a safety gate to warn the worker.
The step of sending the comparison result to the safety gate to give a warning to workers is as follows:
s3.1, setting a warning threshold value of the attaching distance between the helmet belt and the chin of a worker to be two centimeters;
s3.2, detecting the distance between the helmet belt and the chin of the worker according to the image data supplemented by the S2.5; comparing the detected distance with a distance warning threshold of S3.1, outputting a signal that the current safety helmet is unqualified to wear if the distance is greater than two centimeters, and controlling the safety brake to release interception to workers if the distance is less than two centimeters; the method comprises the following steps:
face detection: a face position in the worker image is detected using a face detection algorithm. This can be achieved by a target detection algorithm or a face key point detection algorithm;
and (3) detecting a safety helmet: the position of the helmet in the worker's image is detected using a target detection algorithm or other technique. This may be by marking or bounding boxes to determine the position of the helmet;
extraction of the cap band and chin position: extracting position information of a hat band and chin according to the detection result of the face and the safety helmet;
calculate the cap to chin distance: the distance between the cap strap and the chin is calculated based on the position of the cap strap and the position of the chin. This may use euclidean distance; the formula is:
assume that the position of the hat band isThe position of the chin is +.>The distance from the cap belt to the chinIt can be calculated as:
wherein For distance (I)>。
Distance judgment and output control signals: comparing the calculated distance from the cap belt to the chin with a set threshold (such as 2 cm), judging according to the distance, and outputting a corresponding signal. For example:
if the distance is more than 2 cm, outputting a signal that the current safety helmet is unqualified to wear;
if the distance is less than 2 cm, the safety gate is controlled to release interception of workers;
and S3.2, meanwhile, saving the image data of workers with qualified comparison, extracting the face data, and uploading the face data to S2.1 to update the identity data of the workers. The method comprises the following steps:
determining qualified worker images and face data: and extracting face data in the image for the worker image passing the qualification detection. The method can acquire the position and the characteristics of the human face through the human face detection and the human face key point positioning technology;
saving qualified worker images and face data: saving the extracted qualified worker image and corresponding face data;
updating the worker identity data: and correlating the stored face data with the original identity data of the worker. This may include updating a face feature representation, face image, or other relevant information of the worker;
uploading updated data: and uploading the updated worker identity data to a safety gate so as to ensure that the worker identity information is updated and maintained.
And S3.3, receiving the signal sent by the step S3.2, sending the signal to the safety gate, and controlling the safety gate to send out sound to warn the worker.
And S3, identifying the actions of the workers in the image data supplemented by the S2.5, judging whether the workers hold the safety helmet laces according to the identification result, and sending a signal of unqualified wearing of the safety helmet to the S3.3. The expression is as follows:
assume that the action label of a worker isThe associated action tag of the hand-held helmet harness may be expressed asIf the identification result contains the related actions of the hand-held safety helmet lacing, judging that the hand-held safety helmet lacing exists;
the specific judgment formula can be expressed as:outputting a signal of the existence of a hand-held safety helmet lace; wherein->: representing the current action tag of the worker obtained from the action recognition model. />: indicating an action tag associated with a harness strap. These action tags are the actions for the hand helmet tie, which are set to the relevant actions during training of the model, < +.>Representing the matching process.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. The utility model provides a safety helmet area detection method based on image recognition which characterized in that: the method comprises the following steps:
s1, when a worker needs to enter a construction site, acquiring worker image information shot by a safety gate;
s2, identifying the posture of the safety helmet of the worker according to the image information acquired in the S1, extracting the wearing path of the safety helmet belt on the head of the worker according to the identification result, carrying out shielding detection on the wearing path, positioning the position shielded by the path, and transmitting the position to a safety gate to carry out image supplement acquisition reminding on the worker;
the step of S2 for identifying the posture of the safety helmet of the worker is as follows:
s2.1, collecting worker identity data;
s2.2, carrying out gesture simulation on the worker identity data acquired in the step S2.1 in combination with the safety helmet, acquiring a correct wearing gesture of the safety helmet, carrying out recognition detection on the worker image information acquired in the step S1 according to the correct wearing gesture of the safety helmet, carrying out the step S2.3 if the recognition detection is passed, and controlling the safety brake to send out an alarm if the recognition detection is not passed;
extracting the characteristics related to the head and the posture of the safety helmet from the worker identity data, wherein the characteristics comprise the rotation angle and the inclination angle of the head, and the position and the rotation angle of the safety helmet;
simulating the correct posture of the worker wearing the safety helmet by using an Euler angle posture simulation representation method according to the posture data of the worker and the position information of the safety helmet;
euler angles represent the rotation of the head with 3 angular components, there are different Euler angle combinations depending on the rotation order:
ZYX order The angle indicates the rotation about the X-axis, +.>The angle indicates rotation about the Y-axis, +.>The angle represents rotation about the Z axis;
XYZ order The angle indicates the rotation about the Z axis, +.>The angle indicates rotation about the Y-axis, +.>The angle represents rotation about the X axis;
judging whether the safety helmet is at the top or behind the head of the worker or not, and judging by comparing the position of the safety helmet with the position of the head, wherein the formula is as follows:
;
wherein ,is the position of the safety helmet>For head position->Is a height position, when->Less than->The safety helmet is positioned at the head of the worker, otherwise, the safety helmet is not positioned at the head of the worker, and the wearing is unqualified;
judging whether the safety helmet shields the important area of the head of the worker or not, the overlapping degree of the safety helmet and the head can be calculated, and the formula is as follows:
;
wherein ,indicating the degree of overlap of the helmet and the head of the worker, < + >>For the area of the overlapping area of the helmet and the head, < >>Is the area of the helmet, when +.>0.9, indicating that the wearing is qualified, otherwise, the wearing is unqualified;
s2.3, extracting a helmet belt path in the corresponding correct helmet wearing posture according to the worker image information which is identified and detected by the S2.2;
and (3) detecting a safety helmet: detecting a position of the helmet in the image using a target detection algorithm, identifying the position of the helmet by a marker or bounding box;
dividing the safety helmet: image segmentation is carried out on the detected safety helmet area, and the safety helmet is separated from other objects or backgrounds;
extracting a hat band path: extracting paths of the hat bands from the segmented helmet images by using contour detection, and extracting according to the color, texture and shape characteristics of the hat bands;
path optimization and adjustment: optimizing and adjusting the extracted hat band path, and using curve fitting to enable the path to be more in line with the shape and track of an actual hat band;
s2.4, carrying out shielding detection on the hat band path extracted in the S2.3 and the worker image information, and outputting a signal which needs to be supplemented by the current image information if the shielding value reaches five percent;
setting a threshold value to judge whether the shielding degree of the hat band path reaches five percent, and adopting the formula:
;
wherein ,for the proportion of the hat band path area, +.>Display area ratio for image hat band path, +.>For the ratio of the shielding area, when->If the shielding degree of the path of the cap belt exceeds the limit value, outputting a supplementary signal;
s2.5, receiving signals which are required to be supplemented by the current image information output by the S2.4, determining the position of the blocked face, outputting the signals to a safety gate to remind the direction of workers, and supplementing the collected image data;
s2.5, the face of the worker is left and right; if the shielding position is at the left side of the image information, a prompt for supplementing the left face image information is sent; if the shielding position is on the right side of the image information, a prompt for supplementing the right face image information is sent out, and the side with the large shielding area is preferentially sent out;
s3, setting a warning threshold value of the attaching distance between the safety helmet belt and the chin of the worker, comparing the chin of the worker with the warning threshold value of the distance between the safety helmet belt and the chin of the worker in the image information after the supplement of S2, and sending the comparison result to a safety gate to warn the worker.
2. The method for detecting the helmet belt based on the image recognition according to claim 1, wherein: s1 is connected with a safety gate through OpenCV, and worker image information shot by the safety gate is obtained in real time.
3. The method for detecting the helmet belt based on the image recognition according to claim 1, wherein: and S2.1, acquiring face data of a worker through a camera, and inputting the acquired face data into corresponding worker identity data in a safety gate.
4. The method for detecting the helmet belt based on the image recognition according to claim 1, wherein: the step of sending the comparison result to the safety gate to give a warning to workers is as follows:
s3.1, setting a warning threshold value of the attaching distance between the helmet belt and the chin of a worker to be two centimeters;
s3.2, detecting the distance between the helmet belt and the chin of the worker according to the image data supplemented by the S2.5; comparing the detected distance with a distance warning threshold of S3.1, outputting a signal that the current safety helmet is unqualified to wear if the distance is greater than two centimeters, and controlling the safety brake to release interception to workers if the distance is less than two centimeters;
and S3.3, receiving the signal sent by the step S3.2, sending the signal to the safety gate, and controlling the safety gate to send out sound to warn the worker.
5. The method for detecting the helmet belt based on the image recognition according to claim 4, wherein: and S3.2, meanwhile, saving the image data of workers with qualified comparison, extracting the face data, and uploading the face data to S2.1 to update the identity data of the workers.
6. The method for detecting the helmet belt based on the image recognition according to claim 4, wherein: and S3, identifying the actions of the workers in the image data supplemented by the S2.5, judging whether the workers hold the safety helmet laces according to the identification result, and sending a signal of unqualified wearing of the safety helmet to the S3.3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310883398.7A CN116645782B (en) | 2023-07-19 | 2023-07-19 | Safety helmet belt detection method based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310883398.7A CN116645782B (en) | 2023-07-19 | 2023-07-19 | Safety helmet belt detection method based on image recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116645782A CN116645782A (en) | 2023-08-25 |
CN116645782B true CN116645782B (en) | 2023-10-13 |
Family
ID=87623260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310883398.7A Active CN116645782B (en) | 2023-07-19 | 2023-07-19 | Safety helmet belt detection method based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116645782B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108402570A (en) * | 2018-02-25 | 2018-08-17 | 中国电信股份有限公司盐城分公司 | A kind of intelligent safety helmet based on NB-IOT |
CN110533811A (en) * | 2019-08-28 | 2019-12-03 | 深圳市万睿智能科技有限公司 | The method and device and system and storage medium of safety cap inspection are realized based on SSD |
CN110705389A (en) * | 2019-09-16 | 2020-01-17 | 全球能源互联网研究院有限公司 | Power grid operation behavior identification method and system |
CN112949354A (en) * | 2019-12-10 | 2021-06-11 | 顺丰科技有限公司 | Method and device for detecting wearing of safety helmet, electronic equipment and computer-readable storage medium |
CN113158851A (en) * | 2021-04-07 | 2021-07-23 | 浙江大华技术股份有限公司 | Wearing safety helmet detection method and device and computer storage medium |
CN113570327A (en) * | 2021-07-06 | 2021-10-29 | 廖妹远 | Construction supervision intelligent management system and supervision method |
CN113963162A (en) * | 2021-11-12 | 2022-01-21 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Helmet wearing identification method and device, computer equipment and storage medium |
CN113971829A (en) * | 2021-10-28 | 2022-01-25 | 广东律诚工程咨询有限公司 | Intelligent detection method, device, equipment and storage medium for wearing condition of safety helmet |
CN215642791U (en) * | 2021-07-06 | 2022-01-25 | 国网浙江省电力有限公司温州供电公司 | Remote control system for safety production risk |
CN115346244A (en) * | 2022-08-19 | 2022-11-15 | 南京晓庄学院 | Worker safety helmet wearing identification system |
CN116092228A (en) * | 2023-01-05 | 2023-05-09 | 厦门科拓通讯技术股份有限公司 | Access control processing method and device for face shielding, access control equipment and medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113553938B (en) * | 2021-07-19 | 2024-05-14 | 黑芝麻智能科技(上海)有限公司 | Seat belt detection method, apparatus, computer device, and storage medium |
-
2023
- 2023-07-19 CN CN202310883398.7A patent/CN116645782B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108402570A (en) * | 2018-02-25 | 2018-08-17 | 中国电信股份有限公司盐城分公司 | A kind of intelligent safety helmet based on NB-IOT |
CN110533811A (en) * | 2019-08-28 | 2019-12-03 | 深圳市万睿智能科技有限公司 | The method and device and system and storage medium of safety cap inspection are realized based on SSD |
CN110705389A (en) * | 2019-09-16 | 2020-01-17 | 全球能源互联网研究院有限公司 | Power grid operation behavior identification method and system |
CN112949354A (en) * | 2019-12-10 | 2021-06-11 | 顺丰科技有限公司 | Method and device for detecting wearing of safety helmet, electronic equipment and computer-readable storage medium |
CN113158851A (en) * | 2021-04-07 | 2021-07-23 | 浙江大华技术股份有限公司 | Wearing safety helmet detection method and device and computer storage medium |
CN113570327A (en) * | 2021-07-06 | 2021-10-29 | 廖妹远 | Construction supervision intelligent management system and supervision method |
CN215642791U (en) * | 2021-07-06 | 2022-01-25 | 国网浙江省电力有限公司温州供电公司 | Remote control system for safety production risk |
CN113971829A (en) * | 2021-10-28 | 2022-01-25 | 广东律诚工程咨询有限公司 | Intelligent detection method, device, equipment and storage medium for wearing condition of safety helmet |
CN113963162A (en) * | 2021-11-12 | 2022-01-21 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Helmet wearing identification method and device, computer equipment and storage medium |
CN115346244A (en) * | 2022-08-19 | 2022-11-15 | 南京晓庄学院 | Worker safety helmet wearing identification system |
CN116092228A (en) * | 2023-01-05 | 2023-05-09 | 厦门科拓通讯技术股份有限公司 | Access control processing method and device for face shielding, access control equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN116645782A (en) | 2023-08-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110889376A (en) | Safety helmet wearing detection system and method based on deep learning | |
CN111144263A (en) | Construction worker high-fall accident early warning method and device | |
CN104616438A (en) | Yawning action detection method for detecting fatigue driving | |
JP6655727B2 (en) | Monitoring system | |
WO2015165365A1 (en) | Facial recognition method and system | |
CN109002801B (en) | Face shielding detection method and system based on video monitoring | |
CN109165685B (en) | Expression and action-based method and system for monitoring potential risks of prisoners | |
CN111914636B (en) | Method and device for detecting whether pedestrian wears safety helmet | |
RU2724785C1 (en) | System and method of identifying personal protective equipment on a person | |
CN112149761A (en) | Electric power intelligent construction site violation detection method based on YOLOv4 improved algorithm | |
CN110991315A (en) | Method for detecting wearing state of safety helmet in real time based on deep learning | |
CN109389040B (en) | Inspection method and device for safety dressing of personnel in operation field | |
CN115294533B (en) | Building construction state monitoring method based on data processing | |
CN112613449A (en) | Safety helmet wearing detection and identification method and system based on video face image | |
CN111931652A (en) | Dressing detection method and device and monitoring terminal | |
CN111325133A (en) | Image processing system based on artificial intelligence recognition | |
CN111597910A (en) | Face recognition method, face recognition device, terminal equipment and medium | |
CN115512304B (en) | Subway station safety monitoring system based on image recognition | |
CN116259002A (en) | Human body dangerous behavior analysis method based on video | |
CN114187543A (en) | Safety belt detection method and system in high-altitude power operation scene | |
CN111695432A (en) | Artificial intelligent face abnormity detection system and method under video monitoring scene | |
CN116645782B (en) | Safety helmet belt detection method based on image recognition | |
CN114359712A (en) | Safety violation analysis system based on unmanned aerial vehicle inspection | |
CN114092875A (en) | Operation site safety supervision method and device based on machine learning | |
CN112149527A (en) | Wearable device detection method and device, electronic device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |