CN113296427B - Building site safety monitoring system based on thing networking - Google Patents
Building site safety monitoring system based on thing networking Download PDFInfo
- Publication number
- CN113296427B CN113296427B CN202110565348.5A CN202110565348A CN113296427B CN 113296427 B CN113296427 B CN 113296427B CN 202110565348 A CN202110565348 A CN 202110565348A CN 113296427 B CN113296427 B CN 113296427B
- Authority
- CN
- China
- Prior art keywords
- environment
- safety
- data
- action
- state
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a building site safety monitoring system based on the Internet of things, and relates to the technical field of building safety monitoring; the system comprises an environment analysis module, a database, an environment safety evaluation module and a behavior analysis module; the environment analysis module is used for analyzing the environment parameter data to obtain a first safety state; the environment safety evaluation module is used for acquiring the current environment video information of the construction workers in real time; evaluating the environmental security by combining the working environment security state data in the database to obtain a second security state; the behavior analysis module is used for identifying the actions or the movement behaviors of the construction workers to obtain the identification result of the illegal actions or movements; and performing security analysis according to the recognition result; obtaining a third safety state; the environment of the construction worker is analyzed in combination with the first safety state, the second safety state and the third safety state, and the construction worker is reminded according to the analysis result, so that the consumption of human resources is saved; the safety is improved.
Description
Technical Field
The invention relates to the technical field of building safety monitoring, in particular to a building site safety monitoring system based on the Internet of things.
Background
The intelligent building is a product of the information era, is the integration of high-tech and modern buildings, has become the embodiment of comprehensive national force, is an important development direction of modern buildings in future, and the intellectualization of the building is developed from the initial stage of intellectualization to high-level intellectualization. The safety protection system and the building equipment monitoring system are more and more important because of the problems related to building safety, and are valued by society and people. The technical development of the class is also fast, and new products and new control systems are developed in a large number of days and months.
In these constantly developing in-process, there are various hidden dangers often, for example when the building site, putting of various apparatus, need carry out standard processing, avoid causing the damage to the workman, also there are some potential safety hazards easily in depositing and the building process of various building materials etc. to lead to building site construction progress slow, current safety protection only sets for artificial prison in the building site, and install the camera, through artificial supervision, consume a large amount of manpower resources, and the safety judgement effect is not good.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a building site safety monitoring system based on the Internet of things. The environment of the construction worker is analyzed by combining the first safety state, the second safety state and the third safety state, and the construction worker is reminded according to the analysis result, so that the human resource consumption of real-time supervision of the worker is saved; meanwhile, the monitored related data are analyzed and judged, so that the data analysis time is saved, and the safety is improved.
The purpose of the invention can be realized by the following technical scheme:
a building site safety monitoring system based on the Internet of things comprises an environment monitoring module, an environment analysis module, a controller, a database, an intelligent safety helmet, an environment safety evaluation module, a video acquisition module and a behavior analysis module;
the environment monitoring module is used for monitoring the environment parameters of the construction site and transmitting the monitored environment parameter data to the environment analysis module for analysis; the environment monitoring module takes wind power as a strong acquisition index and drives acquisition of other environment parameters according to the acquisition result of the wind power;
the environment analysis module analyzes the environment parameter data; obtaining a first safety state;
the environment safety evaluation module is used for acquiring the current environment video information of construction workers in real time; evaluating the environmental security by combining the current environmental video information with the working environment security state data in the database to obtain a second security state;
the video acquisition module is used for acquiring the action or motion condition of a construction worker and compressing the action or motion condition; sending the compressed code stream to a behavior analysis module, sorting out the characteristic video by the behavior analysis module, and analyzing and detecting the action or the movement behavior in the characteristic video in real time;
the behavior analysis module comprises an action recognition unit and a violation analysis unit; the action recognition unit is used for recognizing the action or the movement behavior of the construction worker and comparing the recognized action or the movement behavior with the illegal action or the movement data stored in the database to obtain the recognition result of the illegal action or the movement; the violation analysis unit is used for acquiring the recognition result of the violation action or movement and carrying out safety analysis; obtaining a third safety state;
further, the specific monitoring process of the environment monitoring module is as follows:
s1: collecting wind power data in response to a preset first environment parameter collecting instruction;
responding to a second environmental parameter acquisition instruction if the wind power data is within a legal threshold range; collecting dust data, temperature data, noise data and humidity data; the issuing frequency of the first environmental parameter acquisition instruction is higher than that of the second environmental parameter acquisition instruction;
s2: if the wind power data is out of the legal threshold range, a wind power monitoring object is created in an environment monitoring module, and the wind power monitoring object comprises a wind power element queue and a timing driver; the timing driver is used for issuing a wind power acquisition command at intervals of preset time so as to acquire wind power data and store the wind power data into the wind power element queue;
s3: if the last element in the current state in the wind element queue is located in a legal threshold range or the number of the elements in the wind element queue reaches a preset first threshold, the wind monitoring object reports the elements in the wind element queue to an environment analysis module, and the wind monitoring object is destroyed in the environment monitoring module;
s4: if the number of the elements in the wind element queue exceeds a preset second threshold value, the environment monitoring module collects dust data, temperature data, noise data and humidity data and transmits characteristic values of the elements in the wind element queue, the dust data, the temperature data, the noise data and the humidity data to the environment analysis module; the environment analysis module acquires a first safety state according to the characteristic values of the elements in the wind element queue, dust data, temperature data, noise data and humidity data;
the characteristic value of the elements in the wind element queue can be a statistical value such as an average value, a weighted average value and the like of the elements in the wind element queue;
further, the environmental parameter data includes dust data, temperature data, noise data, humidity data, and wind data; the database stores working environment safety state data and violation action or movement data; the working environment safety state data is used for comprehensively evaluating the safety state of the current working environment of the construction worker; the working environment safety state data comprises characteristic information of materials or instruments commonly found in a construction site and a machine model for identifying the materials or the instruments, and the machine model identifies each material or instrument in the current environment based on the characteristic information so as to evaluate the safety condition of the current environment where a construction worker is located;
further, the specific analysis steps of the environment analysis module are as follows:
the method comprises the following steps: obtaining elements in the wind power element queue, and if the number of the elements outside a legal threshold range reaches a preset third threshold or reaches a preset proportion within a preset time interval, determining that strong wind exists on a construction site at the moment, and generating an environment abnormal signal; at the moment, the first safe state is a non-safe state;
step two: obtaining characteristic values, dust data, temperature data, noise data and humidity data of elements in the wind element queue; and labeled C1, C2, C3, C4, C5 in sequence;
calculating an environment monitoring coefficient GX of the construction site by using a formula GX which is C1 × a1+ C2 × a2+ C3 × a3+ C4 × a4+ C5 × a5, wherein a1, a2, a3, a4 and a5 are proportional coefficients;
step three: comparing the environment monitoring coefficient GX with a preset coefficient threshold:
if the environment monitoring coefficient GX is larger than or equal to a preset coefficient threshold value, generating an environment abnormal signal; at the moment, the first safe state is a non-safe state; the environment analysis module is used for issuing a first safety state to an intelligent safety helmet worn by a construction worker through a controller, and the intelligent safety helmet carries out first safety reminding on the construction worker according to the first safety state;
further, the environment security evaluation module specifically comprises the following working steps:
SS 1: extracting a picture of a current environment from current environment video information, dividing the picture of the current environment into at least one interval to be identified, wherein only one object to be identified exists in each interval to be identified; the object to be identified is a building material or a building instrument;
SS 2: segmenting the current environment picture according to the interval to be identified to obtain at least one target image, wherein each target image corresponds to one interval to be identified; identifying each target image based on a dynamically updated machine learning model to obtain an identification result corresponding to each target image, wherein the machine learning model is used for outputting at least one label corresponding to the target image;
SS 3: acquiring a second safety state according to the label pointed by each target image; the method comprises the following steps:
SS 31: acquiring a first sensitive label set according to the working environment safety state data; in particular, for construction workers, if broken glass or rivets scattered on the ground, a lifting appliance or crane in operation, and other improperly placed instruments or materials appear in the moving range, potential safety hazards exist; accordingly, tags corresponding to such items can be included in the first set of sensible tags;
SS 32: extracting the tags hit by the first sensitive tag set from the tags corresponding to the target images and marking the tags as target tags;
SS 33: if the number of the target tags is larger than or equal to the preset number threshold or the number ratio of the target tags is larger than or equal to the preset number ratio threshold, judging that the second safety state is a non-safety state at the moment; generating reminding data of a second safety state according to the target label; the reminding data is the range affected by the abnormity generated by the target label; the environment safety evaluation module is used for transmitting the reminding data of the second safety state to the intelligent safety helmet through the controller so as to carry out second safety reminding on construction workers;
further, the specific analysis steps of the behavior analysis module are as follows:
v1: the action recognition unit is used for recognizing the action or movement of a construction worker, and when illegal action or movement is recognized, the recognition result of the illegal action or movement is recorded, wherein the recognition result comprises the type, the action starting time and the action ending time of the illegal action or movement;
v2: calculating the time difference between the action starting time and the action ending time in the recognition result to obtain the violation action duration WT;
setting each illegal action or movement to have a corresponding influence value, matching the illegal action or movement with all the illegal actions or movements to obtain a corresponding influence value, and marking the corresponding influence value as RE;
calculating a single-risk value DS by using a formula DS (WT × b1+ RE × b 2), wherein b1 and b2 are coefficient factors;
v3: within a preset time interval, summing all the single-risk values DS to obtain a violation total value DZ;
if the total violation value DZ is larger than a preset violation threshold, potential safety hazards exist in the actions or movements of the construction workers at the moment, and the third safety state is a non-safety state; and the behavior analysis module transmits the third safety state to the intelligent safety helmet through the controller so as to carry out third safety reminding on the construction workers.
Compared with the prior art, the invention has the beneficial effects that: the environment parameter data is analyzed through an environment analysis module; obtaining a first safety state; acquiring current environment video information of construction workers in real time through an environment safety evaluation module; evaluating the environmental safety according to the current environmental video information and the working environment safety state data in the database to obtain a second safety state, identifying the actions or movement behaviors of construction workers by combining a behavior analysis module, and performing safety analysis according to the identification result of illegal actions or movement; obtaining a third safety state; the environment of the construction worker is analyzed in combination with the first safety state, the second safety state and the third safety state, and the construction worker is reminded according to the analysis result, so that the human resource consumption of real-time supervision of the worker is saved; and by analyzing and judging the monitored related data, the data analysis time is saved, and the safety is improved.
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 some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of the system of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in fig. 1, a building site safety monitoring system based on the internet of things comprises an environment monitoring module, an environment analysis module, a controller, a database, an intelligent safety helmet, an environment safety evaluation module, a video acquisition module and a behavior analysis module;
considering that building materials are continuously carried and lifted during construction of a building site, if strong wind exists during construction, the probability of falling objects or material collapse is high, and meanwhile, for the convenience of collection, the environmental parameters take wind power as a strong collection index, and collection of other environmental parameters is driven according to the collection result of the wind power;
the environment monitoring module is used for monitoring the environment parameters of the construction site and transmitting the monitored environment parameter data to the environment analysis module for analysis; the environmental parameter data comprises dust data, temperature data, noise data, humidity data and wind data; the specific monitoring process of the environment monitoring module is as follows:
s1: collecting wind power data in response to a preset first environmental parameter collection instruction;
responding to a second environment parameter acquisition instruction if the wind power data is within the legal threshold range; collecting dust data, temperature data, noise data and humidity data; the issuing frequency of the first environmental parameter acquisition instruction is higher than that of the second environmental parameter acquisition instruction;
s2: if the wind power data is out of the legal threshold range, a wind power monitoring object is created in the environment monitoring module, and the wind power monitoring object comprises a wind power element queue and a timing driver; the timing driver is used for issuing a wind power acquisition command at intervals of preset time so as to acquire wind power data and store the wind power data into a wind power element queue;
s3: if the last element in the current state in the wind element queue is located in a legal threshold range or the number of the elements in the wind element queue reaches a preset first threshold, the wind monitoring object reports the elements in the wind element queue to an environment analysis module, and the wind monitoring object is destroyed in the environment monitoring module;
s4: if the number of the elements in the wind element queue exceeds a preset second threshold value, the environment monitoring module collects dust data, temperature data, noise data and humidity data, and transmits characteristic values of the elements in the wind element queue, the dust data, the temperature data, the noise data and the humidity data to the environment analysis module; so that the environment analysis module acquires a first safety state according to the characteristic values of the elements in the wind element queue, the dust data, the temperature data, the noise data and the humidity data; the characteristic value of the elements in the wind element queue can be a statistical value such as an average value, a weighted average value and the like of the elements in the wind element queue;
the specific analysis steps of the environment analysis module are as follows:
the method comprises the following steps: obtaining elements in the wind force element queue, and if the number of the elements outside a legal threshold range reaches a preset third threshold or reaches a preset proportion in a preset time interval, determining that strong wind exists on a construction site at the moment, and generating an environment abnormal signal; at the moment, the first safe state is a non-safe state;
step two: acquiring characteristic values, dust data, temperature data, noise data and humidity data of elements in a wind element queue; and labeled C1, C2, C3, C4, C5 in sequence;
calculating an environment monitoring coefficient GX of the construction site by using a formula GX which is C1 × a1+ C2 × a2+ C3 × a3+ C4 × a4+ C5 × a5, wherein a1, a2, a3, a4 and a5 are proportional coefficients;
step three: comparing the environment monitoring coefficient GX with a preset coefficient threshold:
if the environment monitoring coefficient GX is larger than or equal to a preset coefficient threshold value, generating an environment abnormal signal; at the moment, the first safe state is a non-safe state;
the environment analysis module is used for issuing the first safety state to an intelligent safety helmet worn by a construction worker through the controller, so that the intelligent safety helmet can carry out first safety reminding on the construction worker according to the first safety state; the invention monitors the real-time environment of the construction site through the environment monitoring module; meanwhile, wind power is used as a strong collection index, collection of other environmental parameters is driven according to a collection result of the wind power, data collection is more convenient, the first safety state is analyzed according to environmental parameter data, workers are reminded in time, and safety is improved;
the database stores working environment safety state data and violation action or movement data; the working environment safety state data is used for comprehensively evaluating the safety state of the current working environment of the construction worker; the working environment safety state data comprises characteristic information of materials or instruments commonly found in a construction site and a machine model for identifying the materials or the instruments, and the machine model identifies each material or instrument in the current environment based on the characteristic information so as to evaluate the safety condition of the current environment of a construction worker;
the environment safety evaluation module is used for acquiring the current environment video information of the construction workers in real time; evaluating the environmental security according to the current environmental video information and the working environment security state data in the database to obtain a second security state; if the second safety state is a non-safety state, transmitting the reminding data of the second safety state to an intelligent safety helmet worn by the construction worker through a controller so that the intelligent safety helmet can carry out second safety reminding on the construction worker according to the reminding data; the environment safety evaluation module comprises the following specific working steps:
SS 1: extracting a picture of a current environment from current environment video information, dividing the picture of the current environment into at least one interval to be identified, wherein each interval to be identified only has one object to be identified; the object to be identified is a building material or a building instrument;
SS 2: segmenting the current environment picture according to the interval to be identified to obtain at least one target image, wherein each target image corresponds to one interval to be identified; identifying each target image based on a dynamically updated machine learning model to obtain an identification result corresponding to each target image, wherein the machine learning model is used for outputting at least one label corresponding to the target image;
SS 3: acquiring a second safety state according to the label pointed by each target image; the method comprises the following steps:
SS 31: acquiring a first sensitive label set according to the working environment safety state data; in particular, for construction workers, if broken glass or rivets scattered on the ground, a lifting appliance or crane in operation, and other improperly placed instruments or materials appear in the moving range, potential safety hazards exist; accordingly, tags corresponding to such items can be included in the first set of sensible tags;
SS 32: extracting the tags hit by the first sensitive tag set from the tags corresponding to the target images and marking the tags as target tags;
SS 33: if the number of the target tags is larger than or equal to the preset number threshold or the number ratio of the target tags is larger than or equal to the preset number ratio threshold, judging that the second safety state is a non-safety state at the moment; generating reminding data of a second safety state according to the target label; the reminding data is the range where the abnormity generated by the target label is spread;
the video acquisition module is used for acquiring the action or motion condition of a construction worker and compressing the action or motion condition; sending the compressed code stream to a behavior analysis module, sorting out the characteristic video by the behavior analysis module, and analyzing and detecting the action or the movement behavior in the characteristic video in real time;
the behavior analysis module comprises an action recognition unit and an illegal analysis unit; the action recognition unit is used for recognizing the action or the movement behavior of the construction worker and comparing the recognized action or the movement behavior with the illegal action or the movement data stored in the database to obtain the recognition result of the illegal action or the movement; the violation analysis unit is used for acquiring the recognition result of the violation action or the movement and carrying out safety analysis; obtaining a third safety state; the specific analysis steps are as follows:
v1: the action recognition unit is used for recognizing the action or movement of a construction worker, and when illegal action or movement is recognized, the recognition result of the illegal action or movement is recorded, wherein the recognition result comprises the type, the action starting time and the action ending time of the illegal action or movement;
v2: calculating the time difference between the action starting time and the action ending time in the recognition result to obtain the violation action duration WT;
setting each illegal action or movement to have a corresponding influence value, matching the illegal action or movement with all the illegal actions or movements to obtain a corresponding influence value, and marking the corresponding influence value as RE;
calculating a single-risk value DS by using a formula DS (WT × b1+ RE × b 2), wherein b1 and b2 are coefficient factors;
v3: within a preset time interval, summing all the single-risk values DS to obtain a violation total value DZ;
if the violation total value DZ is larger than a preset violation threshold, potential safety hazards exist in the action or movement of the construction worker at the moment, and the third safety state is a non-safety state;
the behavior analysis module transmits the third safety state to an intelligent safety helmet worn by the construction worker through the controller, so that the intelligent safety helmet can carry out third safety reminding on the construction worker according to the third safety state.
The method comprises the steps that the current environment video information of construction workers is obtained in real time through an environment safety evaluation module; evaluating the environmental safety according to the current environmental video information and the working environment safety state data in the database to obtain a second safety state, identifying the actions or movement behaviors of construction workers by combining a behavior analysis module, and performing safety analysis according to the identification result of illegal actions or movement; obtaining a third safety state; the environment of the construction worker is analyzed, and the construction worker is reminded according to the analysis result, so that the human resource consumption of real-time supervision of the worker is saved; by analyzing and judging the monitored related data, the data analysis time is saved, and the safety is improved.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
The working principle of the invention is as follows:
when the building site safety monitoring system based on the Internet of things works, an environment monitoring module is used for monitoring environment parameters of a building site, and firstly, wind power data are collected in response to a preset first environment parameter collecting instruction; responding to a second environmental parameter acquisition instruction if the wind power data is within a legal threshold range; collecting dust data, temperature data, noise data and humidity data; if the wind power data are outside the legal threshold range, issuing a wind power acquisition instruction at intervals of preset time so as to acquire the wind power data and store the wind power data into a wind power element queue; if the last element in the current state in the wind element queue is located in a legal threshold range or the number of the elements in the wind element queue reaches a preset first threshold, reporting the elements in the wind element queue to an environment analysis module; so that the environment analysis module acquires a first safety state according to the characteristic values of the elements in the wind element queue, the dust data, the temperature data, the noise data and the humidity data; if the first safe state is the unsafe state; the first safety state is issued to an intelligent safety helmet worn by a construction worker through a controller, and first safety reminding is carried out on the construction worker; the safety is improved;
the environment safety evaluation module is used for acquiring the current environment video information of the construction workers in real time; evaluating the safety state of the current working environment of the construction worker according to the current environment video information and the working environment safety state data in the database, extracting the picture of the current environment from the current environment video information, and dividing the picture of the current environment into at least one interval to be identified; segmenting a current environment picture according to a to-be-identified interval to obtain at least one target image, identifying each target image based on a dynamically updated machine learning model to obtain an identification result corresponding to each target image, and outputting at least one label corresponding to the target image; acquiring a second safety state according to the label pointed by each target image; if the second safety state is a non-safety state, carrying out second safety reminding on the construction worker through the intelligent safety helmet;
the video acquisition module is used for acquiring the action or motion condition of a construction worker and compressing the action or motion condition; sending the compressed code stream to a behavior analysis module, sorting out the characteristic video by the behavior analysis module, and analyzing and detecting the action or the movement behavior in the characteristic video in real time; comparing the identified action or movement behavior with the illegal action or movement data stored in the database to obtain an identification result of the illegal action or movement; and safety analysis is carried out according to the identification result of the illegal action or movement; obtaining a third safety state; so that the intelligent safety helmet can carry out third safety reminding on the construction worker according to the third safety state;
the environment of the construction worker is analyzed by combining the first safety state, the second safety state and the third safety state, and the construction worker is reminded according to the analysis result, so that the human resource consumption of real-time supervision of the worker is saved; meanwhile, the monitored related data are analyzed and judged, so that the data analysis time is saved, and the safety is improved.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (2)
1. A building site safety monitoring system based on the Internet of things is characterized by comprising an environment monitoring module, an environment analysis module, a controller, a database, an environment safety evaluation module, a video acquisition module and a behavior analysis module;
the environment monitoring module is used for monitoring the environment parameters of the construction site and transmitting the monitored environment parameter data to the environment analysis module; the environment analysis module is used for analyzing the environment parameter data to obtain a first safety state; the specific analysis steps are as follows:
the method comprises the following steps: obtaining elements in the wind power element queue, and if the elements are in a legal threshold in a preset time interval
When the number of the elements outside the value range reaches a preset third threshold value or reaches a preset proportion, determining that strong wind exists on the construction site at the moment, and generating an environment abnormal signal; at the moment, the first safe state is a non-safe state;
step two: acquiring characteristic values, dust data, temperature data, noise data and humidity data of elements in a wind element queue; and labeled C1, C2, C3, C4, C5 in sequence;
calculating an environment monitoring coefficient GX of the construction site by using a formula GX = C1 × a1+ C2 × a2+ C3 × a3+ C4 × a4+ C5 × a5, wherein a1, a2, a3, a4 and a5 are proportional coefficients;
step three: comparing the environmental monitoring coefficient GX with a preset coefficient threshold: if the environment monitoring coefficient GX is larger than or equal to a preset coefficient threshold value, generating an environment abnormal signal; at the moment, the first safe state is a non-safe state; the environment analysis module is used for issuing the first safety state to an intelligent safety helmet worn by a construction worker through a controller, and the intelligent safety helmet carries out first safety reminding on the construction worker according to the first safety state;
the environment safety evaluation module is used for acquiring the current environment video information of construction workers in real time; evaluating the environmental security by combining the current environmental video information with the working environment security state data in the database to obtain a second security state; the specific evaluation steps are as follows:
SS 1: extracting a picture of a current environment from current environment video information, dividing the picture of the current environment into at least one interval to be identified, wherein only one object to be identified exists in each interval to be identified;
SS 2: segmenting a current environment picture according to a to-be-identified interval to obtain at least one target image, wherein each target image corresponds to one to-be-identified interval; identifying each target image based on a dynamically updated machine learning model to obtain an identification result corresponding to each target image, wherein the machine learning model is used for outputting at least one label corresponding to the target image;
SS 3: acquiring a second safety state according to the label pointed by each target image; the method comprises the following steps:
SS 31: acquiring a first sensitive label set according to the safety state data of the working environment; the first sensitive label set comprises ground broken glass or rivets, a running lifting appliance or crane and other improperly placed instruments or materials;
SS 32: extracting the tags hit by the first sensitive tag set from the tags corresponding to the target images and marking the tags as target tags;
SS 33: if the number of the target labels is larger than or equal to the preset number threshold or the number ratio of the target labels is larger than or equal to the preset number ratio
When the number ratio threshold is set, the second safety state is judged to be a non-safety state at the moment; generating reminding data of a second safety state according to the target label, wherein the reminding data are the range affected by the abnormity generated by the target label;
the environment safety evaluation module is used for transmitting the reminding data of the second safety state to the intelligent safety helmet through the controller so as to carry out second safety reminding on construction workers;
the video acquisition module is used for acquiring the action or motion condition of a construction worker and compressing the action or motion condition; sending the compressed code stream to a behavior analysis module, sorting out the characteristic video by the behavior analysis module, and analyzing and detecting the action or the movement behavior in the characteristic video in real time;
the behavior analysis module comprises an action recognition unit and a violation analysis unit; the action recognition unit is used for recognizing the action or the movement behavior of the construction worker and comparing the recognized action or the movement behavior with the illegal action or the movement data stored in the database to obtain a recognition result of the illegal action or the movement; the violation analysis unit is used for acquiring the recognition result of the violation action or movement and carrying out safety analysis to obtain a third safety state; the specific analysis steps are as follows:
acquiring an identification result of the illegal action or movement; calculating the time difference between the action starting time and the action ending time in the recognition result to obtain the violation action duration WT;
setting each illegal action or movement to have a corresponding influence value, matching the illegal action or movement with all the illegal actions or movements to obtain a corresponding influence value, and marking the corresponding influence value as RE;
calculating a single-risk value DS by using a formula DS = WT × b1+ RE × b2, wherein b1 and b2 are coefficient factors; within a preset time interval, summing all the single-risk values DS to obtain a violation total value DZ;
if the violation total value DZ is larger than the preset violation threshold, the third safety state is a non-safety state at the moment; and the behavior analysis module transmits the third safety state to the intelligent safety helmet through the controller so as to carry out third safety reminding on the construction workers.
2. The internet of things-based construction site safety monitoring system of claim 1, wherein the environmental parameter data comprises dust data, temperature data, noise data, humidity data, and wind data; the environment monitoring module takes wind power as a strong acquisition index, and drives acquisition of other environment parameters according to an acquisition result of the wind power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565348.5A CN113296427B (en) | 2021-05-24 | 2021-05-24 | Building site safety monitoring system based on thing networking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565348.5A CN113296427B (en) | 2021-05-24 | 2021-05-24 | Building site safety monitoring system based on thing networking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113296427A CN113296427A (en) | 2021-08-24 |
| CN113296427B true CN113296427B (en) | 2022-06-17 |
Family
ID=77324264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110565348.5A Active CN113296427B (en) | 2021-05-24 | 2021-05-24 | Building site safety monitoring system based on thing networking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113296427B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114048953B (en) * | 2021-10-14 | 2023-09-29 | 上海翼方键数科技有限公司 | Intelligent wind control evaluation method based on multidimensional sensing and enterprise data quantification |
| CN114035466B (en) * | 2021-11-05 | 2022-05-31 | 肇庆高峰机械科技有限公司 | Control system of duplex position magnetic sheet arrangement machine |
| CN115035458B (en) * | 2022-07-06 | 2023-02-03 | 中国安全生产科学研究院 | Safety risk evaluation method and system |
| CN115389385B (en) * | 2022-09-20 | 2023-05-09 | 复旦大学 | Dust intelligent monitoring and early warning system based on operation environment and human occupational health |
| CN115511367B (en) * | 2022-10-21 | 2023-07-25 | 上海数瞳信息科技有限公司 | Intelligent quality management system of production line |
| CN117048113B (en) * | 2023-10-13 | 2023-12-22 | 江苏爱箔乐铝箔制品有限公司 | Dynamic precision detection method and system for stamping aluminum foil cutlery box |
| CN117909678A (en) * | 2023-12-21 | 2024-04-19 | 传质(江苏)科技有限公司 | Block chain-based environment monitoring system |
| CN118192375A (en) * | 2024-04-16 | 2024-06-14 | 甘肃省建设设计咨询集团有限公司 | Building construction safety monitoring system |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007114992A (en) * | 2005-10-20 | 2007-05-10 | Fuji Electric Holdings Co Ltd | Site workers monitoring system and its program |
| CN103676838A (en) * | 2013-10-25 | 2014-03-26 | 国家电网公司 | Electric power line basic construction intelligent safety monitoring system and monitoring method |
| US9466038B2 (en) * | 2014-02-21 | 2016-10-11 | Safety Key Solutions FZ-LLC | Worksite monitoring and management systems and platforms |
| CN105607561A (en) * | 2016-03-11 | 2016-05-25 | 中建二局第二建筑工程有限公司 | Constructional engineering environment monitoring device |
| CN206258706U (en) * | 2016-10-20 | 2017-06-16 | 安徽天枢信息科技有限公司 | A kind of management and control of civil air defense constructions and installations safe construction and real time monitoring system |
| CN106774195A (en) * | 2016-11-29 | 2017-05-31 | 广西理工职业技术学院 | Construction safety production supervision management control system |
| CN106593534B (en) * | 2016-12-18 | 2019-11-05 | 河北科技大学 | A kind of intelligent tunnel construction safety monitoring system |
| CN107544326A (en) * | 2017-08-30 | 2018-01-05 | 深圳市易联智道科技有限公司 | Ensure the multifunction monitoring system of construction site security |
| CN208027114U (en) * | 2017-11-08 | 2018-10-30 | 富盛科技股份有限公司 | A kind of comprehensive environment monitoring system for monitoring construction site safety standard |
| CN208172562U (en) * | 2018-04-16 | 2018-11-30 | 广西越知网络股份有限公司 | A kind of multifunctional intellectual building site monitoring collection system |
| CN111144776A (en) * | 2019-12-30 | 2020-05-12 | 广州途威慧信息科技有限公司 | Construction safety supervisory systems based on BIM model |
| CN213152103U (en) * | 2020-09-01 | 2021-05-07 | 河南天朗生态科技有限公司 | Intelligent building site integrated management system based on intelligent analysis |
| KR20200107912A (en) * | 2020-09-09 | 2020-09-16 | 김춘상 | Construction site safety monitoring system |
-
2021
- 2021-05-24 CN CN202110565348.5A patent/CN113296427B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113296427A (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113296427B (en) | Building site safety monitoring system based on thing networking | |
| CN114003771A (en) | Special operation field abnormity early warning analysis system and method based on Internet of things | |
| CN114973140A (en) | Dangerous area personnel intrusion monitoring method and system based on machine vision | |
| CN114155614B (en) | Method and system for identifying anti-violation behavior of operation site | |
| CN113807240A (en) | Intelligent transformer substation personnel dressing monitoring method based on uncooperative face recognition | |
| CN113542690B (en) | Building construction safety monitoring system and method | |
| CN117035419B (en) | Intelligent management system and method for enterprise project implementation | |
| CN116862244B (en) | Industrial field vision AI analysis and safety pre-warning system and method | |
| CN116185757B (en) | Intelligent monitoring system for energy consumption of machine room | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN114579791A (en) | Construction safety violation identification method and system based on operation ticket | |
| US20210166180A1 (en) | Information processing apparatus, information processing method, and work evaluation system | |
| CN115567690A (en) | Intelligent monitoring system capable of automatically identifying dangerous points of field operation | |
| CN112487935A (en) | Dangerous point source safety management and control system | |
| CN117972687A (en) | Block chain-based intelligent power monitoring system | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| CN113835387A (en) | Operation and maintenance management method, system and medium | |
| CN116582339B (en) | Intelligent building network security monitoring method and monitoring system | |
| CN117373478A (en) | Voiceprint recognition system for transformer | |
| CN112988843A (en) | SMT chip mounter fault management and diagnosis system based on SQL Server database | |
| CN116580514A (en) | Intelligent security method, system, medium and electronic equipment based on Internet of things | |
| CN111310723A (en) | Deep learning technology-based wearing standard analysis method for transformer substation personnel | |
| CN116363751A (en) | Climbing action recognition method, device and equipment for electric power tower climbing operation and storage medium | |
| CN115860979A (en) | Artificial intelligence management system for field operation of power grid | |
| CN114429677A (en) | Coal mine scene operation behavior safety identification and assessment method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |