CN113963252A - Safety helmet wearing early warning method and system based on image recognition - Google Patents
Safety helmet wearing early warning method and system based on image recognition Download PDFInfo
- Publication number
- CN113963252A CN113963252A CN202010702047.8A CN202010702047A CN113963252A CN 113963252 A CN113963252 A CN 113963252A CN 202010702047 A CN202010702047 A CN 202010702047A CN 113963252 A CN113963252 A CN 113963252A
- Authority
- CN
- China
- Prior art keywords
- safety helmet
- early warning
- remote management
- management module
- wearing
- 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.)
- Pending
Links
Images
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
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- 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
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Abstract
The invention discloses a safety helmet wearing early warning method based on image recognition, which comprises the following steps: acquiring a video stream from a monitoring camera in real time, and extracting a video frame in the video stream; filtering the video frame; and identifying whether a safety helmet is worn in the filtered video frame, and if not, generating an early warning signal. According to the invention, the camera is arranged in the operation area and is connected with the remote management module, the camera automatically identifies the wearing condition of the safety helmet of the current operator, when the behavior that the safety helmet is not worn is identified, the camera sends a signal to the remote management module, the remote management operator obtains a prompt, the remote management module sends early warning information to the control module after processing, and the control module is connected with the corresponding voice equipment to directly play early warning voice. Therefore, the wearing identification and early warning of the safety helmet can be automatically realized, the worker can be timely reminded of wearing the safety helmet, and the probability of safety accidents is effectively reduced.
Description
Technical Field
The invention relates to the technical field of remote control, in particular to a safety helmet wearing early warning method and system based on image recognition.
Background
Safety management is always the most important thing in the field of buildings, and safety helmets play an important role as important protective equipment in protecting the life safety of constructors. In the construction process, operators often wear safety helmets according to regulations due to various reasons, and casualties are easily caused when accidents occur due to lack of real-time identification and early warning means.
Disclosure of Invention
The invention mainly aims to solve the problem that an operator cannot find and early warn in real time when not wearing a safety helmet in the prior art, and provides a safety helmet wearing early warning system based on image recognition to realize safety helmet recognition, automatically generate an early warning signal when finding that the safety helmet is not worn, and automatically early warn through voice equipment to remind the operator to wear the safety helmet according to the regulations.
In order to achieve the purpose, the invention provides a safety helmet wearing early warning method based on image recognition, which comprises the following steps:
step S1, acquiring a video stream from a monitoring camera in real time, and extracting a video frame in the video stream;
step S2, filtering the video frame;
and step S3, identifying whether the safety helmet is worn in the filtered video frame, and generating an early warning signal if the safety helmet is not worn.
The safety helmet wearing early warning method based on image recognition provided by the invention further comprises the following steps:
and step S4, sending the early warning signal to a remote management module, and controlling voice equipment to send out early warning sound by the remote management module.
The safety helmet wearing early warning method based on image recognition provided by the invention further comprises the following steps:
step S5: and uploading the captured picture of the unworn safety helmet to the remote management module.
In the image recognition-based helmet wearing warning method provided by the present invention, before step S1, the method further includes:
acquiring a video stream, and creating an algorithm material library;
and training a safety helmet identification algorithm based on the algorithm material library.
The invention also provides a safety helmet wearing early warning system based on image recognition, which comprises a plurality of monitoring cameras and an early warning module integrated in each monitoring camera, wherein each monitoring camera is used for acquiring a field video stream; each early warning module includes:
the extraction unit is used for acquiring the video stream from the monitoring camera in real time and extracting video frames in the video stream;
a processing unit for filtering the video frame;
and the identification unit is used for identifying whether the safety helmet is worn in the filtered video frame or not, and generating an early warning signal if the safety helmet is not worn.
The image recognition-based safety helmet wearing early warning system further comprises a remote management module, wherein the remote management module is in communication connection with the monitoring camera, and the early warning module further comprises an uploading unit which is used for uploading captured pictures of the safety helmet not worn and the early warning signals to the remote management module.
The image recognition-based helmet wearing early warning system further comprises voice equipment and a control module, wherein the voice equipment is electrically connected with the control module, the remote management module is in communication connection with the control module, and the remote management module controls the voice equipment to send out early warning sound according to the early warning signal.
In the image recognition-based safety helmet wearing early warning system provided by the invention, the remote management module comprises a buzzer and a prompting lamp, and is used for sending out a prompt when receiving the early warning signal.
The safety helmet wearing early warning method and system based on image recognition have the following beneficial effects: according to the invention, the camera is arranged in the operation area and is connected with the remote management module, the camera automatically identifies the wearing condition of the safety helmet of the current operator, when the behavior that the safety helmet is not worn is identified, a signal is sent to the remote management module, the remote management personnel is prompted, the camera transmits the captured image information of the personnel to the remote management module, the remote management module sends the early warning information to the control module after processing, and the control module is connected with the corresponding voice equipment to directly play the early warning voice. Therefore, the wearing identification and early warning of the safety helmet can be automatically realized, the worker can be timely reminded of wearing the safety helmet, and the probability of safety accidents is effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts:
FIG. 1 is a flow chart of a method for warning wearing of a safety helmet based on image recognition according to the present invention;
fig. 2 is a schematic diagram of a helmet wearing warning system based on image recognition according to the present invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Exemplary embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
In order to better understand the technical solutions, the technical solutions will be described in detail below with reference to the drawings and the specific embodiments of the specification, and it should be understood that the embodiments and specific features of the embodiments of the present invention are detailed descriptions of the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features of the embodiments and examples of the present invention may be combined with each other without conflict.
Fig. 1 is a flowchart of a helmet wearing warning method based on image recognition according to the present invention. As shown in fig. 1, the method for warning the wearing of a safety helmet based on image recognition provided by the present invention includes the following steps:
step S1, acquiring a video stream from a monitoring camera in real time, and extracting a video frame in the video stream;
specifically, in an embodiment of the present invention, an RTSP format video stream is acquired from a monitoring camera disposed on site in real time, and a video frame in the video is extracted as helmet identification input data.
Step S2, filtering the video frame;
specifically, in an embodiment of the present invention, the obtained video frames are filtered by a human body recognition algorithm, and the video frames with human body patterns are screened out. The method for extracting the video frame with the human body pattern through the human body recognition algorithm may be a method known to those skilled in the art, and the present invention is not limited herein.
Step S3, identifying whether the safety helmet is worn in the filtered video frame, and generating an early warning signal if the safety helmet is not worn;
specifically, in one embodiment of the present invention, a video frame is used as input data, a helmet identification algorithm is invoked to identify whether a helmet is worn, and if not, an early warning signal is generated.
And step S4, sending the early warning signal to a remote management module, and controlling voice equipment to send out early warning sound by the remote management module.
Specifically, in an embodiment of the present invention, after receiving the warning signal, the remote management module sends the warning information to the control module in the construction site, and the control module is connected to the corresponding voice device to directly play the warning voice. Therefore, the wearing identification and early warning of the safety helmet can be automatically realized, the worker can be timely reminded of wearing the safety helmet, and the probability of safety accidents is effectively reduced.
Step S5: and uploading the captured picture of the unworn safety helmet to the remote management module.
Specifically, in an embodiment of the present invention, after the situation that the crash helmet is not worn is recognized on the site, the picture of the crash helmet that is captured on the site and is not worn is uploaded to the remote management module, so that a manager can conveniently know and monitor the situation on the site at the background in time, and the field verification is not required, which is beneficial to providing the work efficiency.
Further, in order to improve the identification efficiency and accuracy of the helmet, before the step S1, the method further includes a step of training a helmet identification algorithm using field materials, and specifically includes:
acquiring a video stream, and creating an algorithm material library;
specifically, in this step, first, an RTSP address of the monitoring device is acquired, and a channel and a code stream type are set; then, reading the video stream of the camera and analyzing the video frame through the RTSP address; and finally, calling a human body recognition algorithm, screening and storing the frame pictures with the human body images, and storing the frame pictures into an algorithm material library.
And training a safety helmet identification algorithm based on the algorithm material library.
Specifically, in the step, firstly, the screened video frame picture is used for carrying out safety helmet position framing treatment, the video frame picture is divided into three labels of a white safety helmet, a red safety helmet and a blue safety helmet, the three labels are stored as an xml format file, and the file is mainly used for recording the specific position of the safety helmet in the picture; and then, the generated label file is imported into a machine algorithm platform for learning training to form a safety helmet algorithm based on image recognition, and the algorithm can be repeatedly trained to improve the recognition rate.
Fig. 2 is a schematic diagram of a helmet wearing warning system based on image recognition according to the present invention. As shown in fig. 2, the image recognition-based helmet wearing warning system provided by the present invention includes a monitoring camera 10, a control module 20, a voice device 30, and a remote management module 40, where the monitoring camera 10, the control module 20, and the voice device 30 are disposed at a construction site, and the remote management module 40 is disposed at a rear management control room. The remote management module is in communication connection with the monitoring camera, the voice device is electrically connected with the control module, and the remote management module is in communication connection with the control module.
Specifically, in an embodiment of the present invention, the monitoring cameras are configured to obtain a live video stream, each monitoring camera is integrated with an early warning module, and each early warning module includes:
the extraction unit is used for acquiring the video stream from the monitoring camera in real time and extracting video frames in the video stream;
specifically, in an embodiment of the present invention, the extraction unit acquires an RTSP format video stream from a monitoring camera disposed on site in real time, and extracts a video frame in the video as helmet identification input data.
A processing unit for filtering the video frame;
specifically, in an embodiment of the present invention, the processing unit filters the acquired video frames by using a human body recognition algorithm, and screens out video frames with human body patterns. The method for extracting the video frame with the human body pattern through the human body recognition algorithm may be a method known to those skilled in the art, and the present invention is not limited herein.
The identification unit is used for identifying whether the safety helmet is worn in the filtered video frame or not, and if the safety helmet is not worn, an early warning signal is generated;
specifically, in an embodiment of the present invention, the recognition unit uses the video frame as input data, invokes a helmet recognition algorithm, recognizes whether a helmet is worn, and generates an early warning signal if the helmet is not worn.
And the uploading unit is used for uploading the captured pictures of the unworn safety helmet and the early warning signals to the remote management module.
Specifically, in an embodiment of the present invention, after the situation that the crash helmet is not worn is identified on the site, the picture of the crash helmet taken on the site and the warning signal are uploaded to the remote management module, so that a manager can conveniently know and monitor the site situation in time at the background, and the field verification is not required, which is beneficial to providing the working efficiency.
Specifically, in an embodiment of the present invention, after receiving the warning signal, the remote management module sends the warning information to the control module in the construction site, and the control module is connected to the corresponding voice device to directly play the warning voice. The remote management module automatically records and identifies the early warning signal and sends the early warning signal to the control module, and the control module controls the voice equipment to send out voice early warning, so that the wearing condition of the safety helmet is automatically monitored and early warned, the workload of managers is reduced, and the safety accident risk of operators is reduced
Further, the remote management module comprises a buzzer and a prompt lamp, and is used for sending out a prompt when the early warning signal is received. The buzzer and the prompting lamp are both electrically connected with an external power supply, and the buzzer and the prompting lamp are controlled through a signal of the video equipment, which is sent out and is not used for wearing the safety helmet. According to the invention, the buzzer and the prompting lamp are arranged, so that when a person does not wear the safety helmet, the buzzer sounds and the prompting lamp is turned on, thereby prompting a manager.
According to the invention, the camera is arranged in the operation area and is connected with the remote management module, the camera automatically identifies the wearing condition of the safety helmet of the current operator, when the behavior that the safety helmet is not worn is identified, a signal is sent to the remote management module, the remote management personnel is prompted, the camera transmits the captured image information of the personnel to the remote management module, the remote management module sends the early warning information to the control module after processing, and the control module is connected with the corresponding voice equipment to directly play the early warning voice. Therefore, the wearing identification and early warning of the safety helmet can be automatically realized, the worker can be timely reminded of wearing the safety helmet, and the probability of safety accidents is effectively reduced.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (8)
1. A safety helmet wearing early warning method based on image recognition is characterized by comprising the following steps:
step S1, acquiring a video stream from a monitoring camera in real time, and extracting a video frame in the video stream;
step S2, filtering the video frame;
and step S3, identifying whether the safety helmet is worn in the filtered video frame, and generating an early warning signal if the safety helmet is not worn.
2. The image recognition-based headgear wearing alert method of claim 1, further comprising:
and step S4, sending the early warning signal to a remote management module, and controlling voice equipment to send out early warning sound by the remote management module.
3. The image recognition-based headgear wearing alert method of claim 1, further comprising:
step S5: and uploading the captured picture of the unworn safety helmet to the remote management module.
4. The image recognition-based headgear wearing alert method of claim 1, prior to the step S1, further comprising:
acquiring a video stream, and creating an algorithm material library;
and training a safety helmet identification algorithm based on the algorithm material library.
5. A safety helmet wearing early warning system based on image recognition is characterized by comprising a plurality of monitoring cameras and an early warning module integrated in each monitoring camera, wherein each monitoring camera is used for acquiring a field video stream; each early warning module includes:
the extraction unit is used for acquiring the video stream from the monitoring camera in real time and extracting video frames in the video stream;
a processing unit for filtering the video frame;
and the identification unit is used for identifying whether the safety helmet is worn in the filtered video frame or not, and generating an early warning signal if the safety helmet is not worn.
6. The image recognition-based helmet wearing warning system of claim 5, further comprising a remote management module in communication with the monitoring camera, wherein the warning module further comprises an uploading unit for uploading captured pictures of the unworn helmet and the warning signal to the remote management module.
7. The image recognition-based helmet wearing warning system of claim 6, further comprising a voice device and a control module, wherein the voice device is electrically connected to the control module, the remote management module is communicatively connected to the control module, and the remote management module controls the voice device to emit a warning sound according to the warning signal.
8. The image recognition-based headgear worn warning system of claim 7, wherein the remote management module comprises a buzzer and a warning light for issuing a warning upon receipt of the warning signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010702047.8A CN113963252A (en) | 2020-07-20 | 2020-07-20 | Safety helmet wearing early warning method and system based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010702047.8A CN113963252A (en) | 2020-07-20 | 2020-07-20 | Safety helmet wearing early warning method and system based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113963252A true CN113963252A (en) | 2022-01-21 |
Family
ID=79459715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010702047.8A Pending CN113963252A (en) | 2020-07-20 | 2020-07-20 | Safety helmet wearing early warning method and system based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113963252A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114513681A (en) * | 2022-01-25 | 2022-05-17 | 武汉工程大学 | Video processing system, method, device, electronic equipment and storage medium |
CN115140626A (en) * | 2022-06-21 | 2022-10-04 | 华能承德风力发电有限公司 | Safety detection method, system and device for box type lifting equipment of wind turbine generator |
CN115215177A (en) * | 2022-08-26 | 2022-10-21 | 中建八局发展建设有限公司 | Intelligent identification system and method for elevator lifting |
-
2020
- 2020-07-20 CN CN202010702047.8A patent/CN113963252A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114513681A (en) * | 2022-01-25 | 2022-05-17 | 武汉工程大学 | Video processing system, method, device, electronic equipment and storage medium |
CN115140626A (en) * | 2022-06-21 | 2022-10-04 | 华能承德风力发电有限公司 | Safety detection method, system and device for box type lifting equipment of wind turbine generator |
CN115215177A (en) * | 2022-08-26 | 2022-10-21 | 中建八局发展建设有限公司 | Intelligent identification system and method for elevator lifting |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113963252A (en) | Safety helmet wearing early warning method and system based on image recognition | |
CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
WO2019238142A2 (en) | Vehicle monitoring system and vehicle monitoring method | |
CN109448155A (en) | Equipment-patrolling method based on AR technology | |
CN106781284A (en) | Trainman's driver fatigue monitor system based on Multi-information acquisition | |
CN110047272B (en) | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data | |
CN112542027A (en) | Construction site personnel safety warning system based on image recognition | |
CN212208379U (en) | Automatic attendance temperature measuring system | |
KR20080044812A (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
CN211209824U (en) | Intelligent security monitoring system for community | |
CN114078224A (en) | Infrastructure field monitoring system and method based on 5G network architecture | |
CN111652185A (en) | Safety construction method, system, device and storage medium based on violation behavior recognition | |
CN111738115A (en) | Mobile camera automatic identification method and system based on artificial intelligence | |
CN107995471A (en) | A kind of image recognition gate inhibition video camera | |
CN205845110U (en) | A kind of construction team based on RFID technique registers system | |
CN210091231U (en) | Wisdom garden management system | |
CN115331386B (en) | Prevent fishing detection alarm system based on computer vision | |
US20160240057A1 (en) | System and method for providing alerts regarding occupancy conditions | |
KR100926580B1 (en) | System of crime prevention for children and operating method thereof | |
CN114281656A (en) | Intelligent central control system | |
KR20160131678A (en) | Portable device for protecting having camera and method for taking picture | |
CN112102590A (en) | Indoor smoking monitoring device and method | |
JP4220322B2 (en) | Intruder monitoring method and apparatus | |
KR20150031059A (en) | The Development Of CCTV For Security By Pattern Recognition Technology | |
CN217932948U (en) | Multimedia safety training toolbox and training system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |