CN111723741A - Temporary fence movement detection alarm system based on visual analysis - Google Patents
Temporary fence movement detection alarm system based on visual analysis Download PDFInfo
- Publication number
- CN111723741A CN111723741A CN202010567581.2A CN202010567581A CN111723741A CN 111723741 A CN111723741 A CN 111723741A CN 202010567581 A CN202010567581 A CN 202010567581A CN 111723741 A CN111723741 A CN 111723741A
- Authority
- CN
- China
- Prior art keywords
- alarm
- temporary fence
- module
- constructor
- model
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 230000000007 visual effect Effects 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000010276 construction Methods 0.000 claims description 16
- 210000000988 bone and bone Anatomy 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 4
- 101000878595 Arabidopsis thaliana Squalene synthase 1 Proteins 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 3
- XOOUIPVCVHRTMJ-UHFFFAOYSA-L zinc stearate Chemical compound [Zn+2].CCCCCCCCCCCCCCCCCC([O-])=O.CCCCCCCCCCCCCCCCCC([O-])=O XOOUIPVCVHRTMJ-UHFFFAOYSA-L 0.000 claims description 3
- 238000002955 isolation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a temporary fence movement detection alarm system based on visual analysis, which is used for solving the problem that in the prior art, the temporary fence movement condition cannot be known in time and further deviates from the original position because constructors do not detect the temporary fence movement through the visual analysis, and comprises a model establishing module, a data acquisition module, a server, an action recognition module and an alarm module; the method utilizes a fast-rcnn target detector to train constructors and a model for detecting the temporary fence, and uses a space-time graph convolution network to train the constructors to move the temporary fence action recognition model; and deploying the two models to a server, and when detecting that intersection exists between the constructor and the temporary fence in the current frame image, judging whether the constructor has the violation behavior of moving the temporary fence by using the action recognition model so as to give an alarm.
Description
Technical Field
The invention relates to the technical field of temporary fence movement detection, in particular to a temporary fence movement detection alarm system based on visual analysis.
Background
The temporary fence can also be called as a movable fence, a temporary isolation fence and a movable safety fence net. The temporary guardrail net is suitable for temporary isolation, temporary partition and temporary enclosure, and is a product with strong flexibility;
can all gather the rail at the job site and keep apart, constructor can appear in current interim rail carries out the problem of removing, among the prior art, does not have through visual analysis to constructor to the detection of interim rail removal, leads to unable timely understanding interim rail removal situation, and then makes the skew primary position of interim rail.
Disclosure of Invention
The invention aims to solve the problems that the movement condition of a temporary fence cannot be known in time and the temporary fence deviates from the original position due to the fact that the movement of a constructor is not detected by visual analysis in the prior art, and provides a temporary fence movement detection alarm system based on visual analysis; deploying the two models to a server, and judging whether the constructor has the violation behavior of moving the temporary fence or not by using the action recognition model when the intersection of the constructor and the temporary fence in the current frame image is detected, so as to give an alarm; the method comprises the steps of alarming a mobile temporary fence and analyzing an alarm coincidence value of a manager, selecting a site checking person to check the mobile temporary fence according to the alarm coincidence value, and managing the constructor;
the purpose of the invention can be realized by the following technical scheme: a temporary fence movement detection alarm system based on visual analysis comprises a model building module, a data acquisition module, a server, an action identification module and an alarm module;
the model building module is used for training a model MdAnd model MaAnd will train good model MdAnd model MaSending the data to a server for storage;
wherein, the model MdThe training process comprises the following steps: collecting construction site temporary fence and constructor sample pictures, marking the positions of the fence and constructors in the pictures by using a rectangular frame, and training the constructors and the temporary fence by using a fast-rcnn target detector to obtain a model Md；
Model MaThe training steps are as follows:
s1: collecting a video sequence of a temporary fence moved by a constructor as a training sample, and extracting human skeleton key points by using a human posture estimation algorithm aiming at each frame of image of the video;
s2: constructing a multi-layer bone space-time graph G (V, E) by using a space-time convolution graph, wherein a node matrix set V (V) isti1, …, T, i 1, …, N }, where T is the number of video frames, N is the number of skeleton key points, the feature vector F (v) of the T-th frame and the i-th key point on a key pointti) The method is characterized by comprising the following steps of (1) forming key point coordinates;
s3 edge E in the multi-level bone space-time diagram G is composed of two subsets, E1＝{vtivtj|(i,j)∈H}，E2＝{vtiv(t+1)j}，E2Represents the trajectory of a particular keypoint over time; wherein H represents a human skeleton point set;
s4: training is carried out through a Softmax cross entropy loss function and a random gradient descent algorithm to obtain a model Ma；
The camera is used for acquiring video data of temporary fences and constructors on a construction site in real time and sending the video data to the action recognition module;
the action recognition module is used for detecting video data, and the specific detection steps are as follows:
SS 1: reading video frame in video data, calling model MdWhen the constructor and the temporary fence are detected, the step SS2 is executed, and if not, the step SS1 is continuously executed;
SS 2: calculating a constructor detection rectangular frame and a temporary fence detection rectangular frame, and executing the step SS3 when the constructor detection rectangular frame and the temporary fence detection rectangular frame have intersection, and continuing to execute the step SS1 if the constructor detection rectangular frame and the temporary fence detection rectangular frame do not have intersection;
SS 3: using current frame as first frame, inputting continuous M frames of images into model MaObtaining an action recognition result, generating an alarm instruction and sending the alarm instruction to an alarm module when the recognition result is that the constructor moves the temporary fence, and receiving the alarm instruction by the alarm module and giving an alarm; the recognition completion continues to step SS 1.
Preferably, the specific steps of receiving the alarm instruction and alarming by the alarm module are as follows:
the method comprises the following steps: acquiring a camera shot by an image corresponding to the alarm instruction, and acquiring the position of the camera according to the serial number of the camera;
step two: acquiring an alarm at the position according to the position of the camera, sending an alarm signal to the alarm, and carrying out alarm reminding through sound and light after the alarm receives the alarm signal;
step three: the method comprises the following steps that an alarm module sends a position acquisition instruction to a mobile phone terminal of a manager on a construction site, and the manager receives the position acquisition instruction through the mobile phone terminal and then sends the current real-time position to the alarm module;
step four: the alarm module marks the manager receiving the current real-time position as a primary selection person;
step five: calculating the distance difference between the current real-time position of the primarily selected person and the position of the camera to obtain a person spacing mark M1;
step six: setting the total selection times of the primary selection personnel as M2;
step seven: obtaining an alarm coincidence value M of the initially selected person by using a formula M of M1 × d1+ M2 × d 2; wherein d1 and d2 are preset proportionality coefficients;
step eight: selecting the primary selection personnel with the maximum alarm coincidence value as field checking personnel, and increasing the total selection times of the primary selection personnel by one;
step nine: sending the position of the camera and the recognition result as an image of the temporary fence moved by the constructor to a mobile phone terminal of the site observer; and the site checking personnel check the moving temporary fence according to the position of the camera and manage the constructor.
Preferably, the server further comprises a storage module, and the storage module is used for storing the number and the position of the camera and the number and the position of the alarm.
Preferably, the system further comprises a registration login module; the registration login module is used for a manager on a construction site to submit registration information through a mobile phone terminal for registration and send the registration information which is successfully registered to the server for storage; the registration information includes the name, the mobile phone number, and the job name of the manager.
Compared with the prior art, the invention has the beneficial effects that:
1. the method utilizes a fast-rcnn target detector to train constructors and a model for detecting the temporary fence, and uses a space-time graph convolution network to train the constructors to move the temporary fence action recognition model; deploying the two models to a server, and judging whether the constructor has the violation behavior of moving the temporary fence or not by using the action recognition model when the intersection of the constructor and the temporary fence in the current frame image is detected, so as to give an alarm;
2. the alarm module receives an alarm instruction and gives an alarm, acquires a camera corresponding to the alarm instruction and shooting images, acquires the position of the camera according to the serial number of the camera, acquires an alarm at the position according to the position of the camera, and sends an alarm signal to the alarm; the method comprises the following steps that an alarm module sends a position acquisition instruction to a mobile phone terminal of a manager on a construction site, and the manager receives the position acquisition instruction through the mobile phone terminal and then sends the current real-time position to the alarm module; calculating the distance difference between the current real-time position of the primary selected person and the position of the camera to obtain the distance between the persons, and obtaining the alarm coincidence value of the primary selected person by using a formula; selecting the primary selected person with the largest alarm coincidence value as a site checking person, and sending the image of the temporary fence moved by the constructor, which is the position of the camera and the recognition result, to a mobile phone terminal of the site checking person; the temporary fence is used for alarming the movable temporary fence and analyzing the alarm coincidence value of a manager, and a site checking person is selected according to the alarm coincidence value to check the movable temporary fence and manage the constructor.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
Fig. 1 is a schematic block diagram 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a temporary fence movement detection alarm system based on visual analysis includes a model building module, a data acquisition module, a server, an action recognition module, an alarm module and a registration module;
the model building module is used for training the model MdAnd model MaAnd will train good model MdAnd model MaSending the data to a server for storage;
wherein, the model MdThe training process comprises the following steps: collecting construction site temporary fence and constructor sample pictures, marking the positions of the fence and constructors in the pictures by using a rectangular frame, and training the constructors and the temporary fence by using a fast-rcnn target detector to obtain a model Md；
Model MaThe training steps are as follows:
s1: collecting a video sequence of a temporary fence moved by a constructor as a training sample, and extracting human skeleton key points by using a human posture estimation algorithm aiming at each frame of image of the video;
s2: constructing a multi-layer bone space-time graph G (V, E) by using a space-time convolution graph, wherein a node matrix set V (V) isti1, …, T, i 1, …, N }, where T is the number of video frames, N is the number of skeleton key points, the feature vector F (v) of the T-th frame and the i-th key point on a key pointti) The method is characterized by comprising the following steps of (1) forming key point coordinates;
s3 side E in the multi-level bone space-time diagram G is composed of two subsets, E1 ═ vtivtj|(i,j)∈H}，E2＝{vtiv(t+1)j}，E2Represents the trajectory of a particular keypoint over time; wherein H represents a human skeleton point set; the specific key point is a certain bone key point;
s4: training is carried out through a Softmax cross entropy loss function and a random gradient descent algorithm to obtain a model Ma；
The camera is used for acquiring video data of the temporary fence and constructors on the construction site in real time and sending the video data to the action recognition module;
the action recognition module is used for detecting video data, and the specific detection steps are as follows:
SS 1: reading video frame in video data, calling model MdWhen the constructor and the temporary fence are detected, the step SS2 is executed, and if not, the step SS1 is continuously executed;
SS 2: calculating a constructor detection rectangular frame and a temporary fence detection rectangular frame, and executing the step SS3 when the constructor detection rectangular frame and the temporary fence detection rectangular frame have intersection, and continuing to execute the step SS1 if the constructor detection rectangular frame and the temporary fence detection rectangular frame do not have intersection;
SS 3: using current frame as first frame, inputting continuous M frames of images into model MaObtaining an action recognition result, generating an alarm instruction and sending the alarm instruction to an alarm module when the recognition result is that the constructor moves the temporary fence, and receiving the alarm instruction by the alarm module and giving an alarm; the recognition completion continues to step SS 1.
The specific steps of receiving the alarm instruction and alarming by the alarm module are as follows:
the method comprises the following steps: acquiring a camera shot by an image corresponding to the alarm instruction, and acquiring the position of the camera according to the serial number of the camera;
step two: acquiring an alarm at the position according to the position of the camera, sending an alarm signal to the alarm, and carrying out alarm reminding through sound and light after the alarm receives the alarm signal;
step three: the method comprises the following steps that an alarm module sends a position acquisition instruction to a mobile phone terminal of a manager on a construction site, and the manager receives the position acquisition instruction through the mobile phone terminal and then sends the current real-time position to the alarm module;
step four: the alarm module marks the manager receiving the current real-time position as a primary selection person;
step five: calculating the distance difference between the current real-time position of the primarily selected person and the position of the camera to obtain a person spacing mark M1;
step six: setting the total selection times of the primary selection personnel as M2;
step seven: obtaining an alarm coincidence value M of the primary selected personnel by using a formula M which is M1 multiplied by d1+ (1/M2) multiplied by d 2; wherein d1 and d2 are preset proportionality coefficients;
step eight: selecting the primary selection personnel with the maximum alarm coincidence value as field checking personnel, and increasing the total selection times of the primary selection personnel by one;
step nine: sending the position of the camera and the recognition result as an image of the temporary fence moved by the constructor to a mobile phone terminal of the site observer; and the site checking personnel check the moving temporary fence according to the position of the camera and manage the constructor.
The server also comprises a storage module, and the storage module is used for storing the serial number and the position of the camera and the serial number and the position of the alarm.
The registration login module is used for a manager on a construction site to submit registration information through a mobile phone terminal for registration and send the registration information which is successfully registered to the server for storage; the registration information comprises the name, the mobile phone number and the position name of the manager;
the working method of the system comprises the following steps:
step 1, collecting construction site temporary fence and constructor sample pictures, and marking the positions of the fence and constructors in the pictures by using rectangular frames;
step 2, training the temporary fence detection and constructor detection model M by adopting a fast-rcnn target detectord；
Step 3, collecting a video sequence of the temporary fence moved by the constructor as a training sample;
step 4, training a mobile temporary fence action recognition model M based on a graph convolution neural networka；
4.1, aiming at each frame of image of the video, extracting key points of a human skeleton by using a human posture estimation algorithm;
4.2 construction of a multi-level bone spatio-temporal graph G ═ (V, E) using a spatio-temporal convolution map, in which the set of node matrices V ═ Vti1, …, T, i 1, …, N }, where T is the number of video frames, N is the number of skeleton key points, the feature vector F (v) of the T-th frame and the i-th key point on a key pointti) The method is characterized by comprising the following steps of (1) forming key point coordinates;
4.3 edge E in space-time graph G consists of two subsets, E1＝{vtivtjL (i, j) ∈ H, H represents the set of human skeleton points, E2＝{vtiv(t+1)jRepresents the trajectory of a particular keypoint over time;
4.4 training by adopting a Softmax cross entropy loss function and a random gradient descent algorithm to obtain a measurement model Md；
Step 5, training the model MdAnd MaDeploying the temporary fence in a server, reading real-time video data of a camera, and alarming when detecting that a constructor moves the temporary fence;
5.1 reading video frames, calling model MdIf the constructor and the fence are detected, executing the step 5.2, otherwise, continuing to execute the step 5.1;
5.2, calculating a constructor detection rectangular frame and a temporary fence detection rectangular frame, if the constructor detection rectangular frame and the temporary fence detection rectangular frame have an intersection, executing the step 5.3, and if the constructor detection rectangular frame and the temporary fence detection rectangular frame have the intersection, continuing to execute the step 5.1;
5.3 taking the current frame as the first frame, inputting the continuous M frames of images into the model MaAnd obtaining an action recognition result, and giving an alarm if the recognition result is that the constructor moves the temporary fence. The recognition is completed and step 5.1 is continued.
When the temporary fence motion recognition system is used, a fast-rcnn target detector is used for training constructors and a temporary fence detection model, and a space-time graph convolution network is used for training the constructors to move the temporary fence motion recognition model; deploying the two models to a server, and judging whether the constructor has the violation behavior of moving the temporary fence or not by using the action recognition model when the intersection of the constructor and the temporary fence in the current frame image is detected, so as to give an alarm; the alarm module receives the alarm instruction and gives an alarm, acquires a camera corresponding to image shooting of the alarm instruction, acquires the position of the camera according to the serial number of the camera, acquires an alarm at the position according to the position of the camera, and sends an alarm signal to the alarm; the method comprises the following steps that an alarm module sends a position acquisition instruction to a mobile phone terminal of a manager on a construction site, and the manager receives the position acquisition instruction through the mobile phone terminal and then sends the current real-time position to the alarm module; the alarm module marks the manager receiving the current real-time position as a primary selection person; calculating the distance difference between the current real-time position of the primary selected person and the position of the camera to obtain the distance between the persons, and obtaining the alarm coincidence value M of the primary selected person by using a formula M (M1 × d1+ (1/M2) × d 2; selecting the primary selected person with the largest alarm coincidence value as a site checking person, and sending the image of the temporary fence moved by the constructor, which is the position of the camera and the recognition result, to a mobile phone terminal of the site checking person; the site checking personnel check the moving temporary fence according to the position of the camera and manage the constructor; the temporary fence is used for alarming the movable temporary fence and analyzing the alarm coincidence value of a manager, and a site checking person is selected according to the alarm coincidence value to check the movable temporary fence and manage the constructor.
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 (4)
1. A temporary fence movement detection alarm system based on visual analysis is characterized by comprising a model building module, a data acquisition module, a server, an action recognition module and an alarm module;
the model building module is used for training a model MdAnd model MaAnd will train good model MdAnd model MaSending the data to a server for storage;
wherein, the model MdThe training process comprises the following steps: collecting construction site temporary fence and constructor sample pictures, marking the positions of the fence and constructors in the pictures by using a rectangular frame, and training the constructors and the temporary fence by using a fast-rcnn target detector to obtain a model Md；
Model MaThe training steps are as follows:
s1: collecting a video sequence of a temporary fence moved by a constructor as a training sample, and extracting human skeleton key points by using a human posture estimation algorithm aiming at each frame of image of the video;
s2: constructing a multi-layer bone space-time graph G (V, E) by using a space-time convolution graph, wherein a node matrix set V (V) isti1, …, T, i 1, …, N }, where T is the number of video frames, N is the number of skeleton key points, the feature vector F (v) of the T-th frame and the i-th key point on a key pointti) The method is characterized by comprising the following steps of (1) forming key point coordinates;
s3 edge E in the multi-level bone space-time diagram G is composed of two subsets, E1＝{vtivtj|(i,j)∈H}，E2＝{vtiv(t+1)j}，E2Represents the trajectory of a particular keypoint over time; wherein H represents a human skeleton point set; the specific key points are skeleton key points;
s4: training is carried out through a Softmax cross entropy loss function and a random gradient descent algorithm to obtain a model Ma；
The camera is used for acquiring video data of temporary fences and constructors on a construction site in real time and sending the video data to the action recognition module;
the action recognition module is used for detecting video data, and the specific detection steps are as follows:
SS 1: reading video frame in video data, calling model MdWhen the constructor and the temporary fence are detected, the step SS2 is executed, and if not, the step SS1 is continuously executed;
SS 2: calculating a constructor detection rectangular frame and a temporary fence detection rectangular frame, and executing the step SS3 when the constructor detection rectangular frame and the temporary fence detection rectangular frame have intersection, and continuing to execute the step SS1 if the constructor detection rectangular frame and the temporary fence detection rectangular frame do not have intersection;
SS 3: using current frame as first frame, inputting continuous M frames of images into model MaObtaining an action recognition result, generating an alarm instruction and sending the alarm instruction to an alarm module when the recognition result is that the constructor moves the temporary fence, and receiving the alarm instruction by the alarm module and giving an alarm; the recognition completion continues to step SS 1.
2. The temporary fence movement detection alarm system based on visual analysis as claimed in claim 1, wherein the specific steps of receiving the alarm instruction and alarming by the alarm module are as follows:
the method comprises the following steps: acquiring a camera shot by an image corresponding to the alarm instruction, and acquiring the position of the camera according to the serial number of the camera;
step two: acquiring an alarm at the position according to the position of the camera, sending an alarm signal to the alarm, and carrying out alarm reminding through sound and light after the alarm receives the alarm signal;
step three: the method comprises the following steps that an alarm module sends a position acquisition instruction to a mobile phone terminal of a manager on a construction site, and the manager receives the position acquisition instruction through the mobile phone terminal and then sends the current real-time position to the alarm module;
step four: the alarm module marks the manager receiving the current real-time position as a primary selection person;
step five: calculating the distance difference between the current real-time position of the primarily selected person and the position of the camera to obtain a person spacing mark M1;
step six: setting the total selection times of the primary selection personnel as M2;
step seven: obtaining an alarm coincidence value M of the primary selected personnel by using a formula M which is M1 multiplied by d1+ (1/M2) multiplied by d 2; wherein d1 and d2 are preset proportionality coefficients;
step eight: selecting the primary selection personnel with the maximum alarm coincidence value as field checking personnel, and increasing the total selection times of the primary selection personnel by one;
step nine: sending the position of the camera and the recognition result as an image of the temporary fence moved by the constructor to a mobile phone terminal of the site observer; and the site checking personnel check the moving temporary fence according to the position of the camera and manage the constructor.
3. The temporary fence movement detection alarm system based on visual analysis as claimed in claim 1, further comprising a storage module in the server, wherein the storage module is used for storing the number and position of the camera and the number and position of the alarm.
4. A temporary fence movement detection alarm system based on visual analysis as claimed in claim 1, further comprising a registration login module; the registration login module is used for a manager on a construction site to submit registration information through a mobile phone terminal for registration and send the registration information which is successfully registered to the server for storage; the registration information includes the name, the mobile phone number, and the job name of the manager.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010567581.2A CN111723741A (en) | 2020-06-19 | 2020-06-19 | Temporary fence movement detection alarm system based on visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010567581.2A CN111723741A (en) | 2020-06-19 | 2020-06-19 | Temporary fence movement detection alarm system based on visual analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111723741A true CN111723741A (en) | 2020-09-29 |
Family
ID=72568181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010567581.2A Pending CN111723741A (en) | 2020-06-19 | 2020-06-19 | Temporary fence movement detection alarm system based on visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723741A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117549330A (en) * | 2024-01-11 | 2024-02-13 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004234429A (en) * | 2003-01-31 | 2004-08-19 | Oki Electric Ind Co Ltd | Parking lot management system and parking lot management method |
| CN204069108U (en) * | 2014-10-17 | 2014-12-31 | 惠州聆韵科技有限公司 | The myopic-preventing mobile phone of a kind of prompting |
| CN106815574A (en) * | 2017-01-20 | 2017-06-09 | 博康智能信息技术有限公司北京海淀分公司 | Set up detection model, detect the method and apparatus for taking mobile phone behavior |
| CN107730428A (en) * | 2017-10-17 | 2018-02-23 | 贾俊力 | Job site intelligent monitoring administration system and its control method |
| CN109492581A (en) * | 2018-11-09 | 2019-03-19 | 中国石油大学(华东) | A kind of human motion recognition method based on TP-STG frame |
| CN109977896A (en) * | 2019-04-03 | 2019-07-05 | 上海海事大学 | A kind of supermarket's intelligence vending system |
| CN110097759A (en) * | 2019-04-28 | 2019-08-06 | 南京师范大学 | A kind of motor vehicle violation behavioral value method based on video geography fence |
| WO2019168323A1 (en) * | 2018-02-27 | 2019-09-06 | 엘지이노텍 주식회사 | Apparatus and method for detecting abnormal object, and photographing device comprising same |
| CN110517429A (en) * | 2019-09-10 | 2019-11-29 | 浙江蓝迪电力科技有限公司 | A kind of Intelligent electronic fence system and processing method |
| US20190370577A1 (en) * | 2018-06-04 | 2019-12-05 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving Management Methods and Systems, Vehicle-Mounted Intelligent Systems, Electronic Devices, and Medium |
| CN110543825A (en) * | 2019-08-01 | 2019-12-06 | 江苏濠汉信息技术有限公司 | Dangerous construction behavior identification method and device based on space-time characteristics |
| CN110837778A (en) * | 2019-10-12 | 2020-02-25 | 南京信息工程大学 | Traffic police command gesture recognition method based on skeleton joint point sequence |
| CN111144232A (en) * | 2019-12-09 | 2020-05-12 | 国网智能科技股份有限公司 | Transformer substation electronic fence monitoring method based on intelligent video monitoring, storage medium and equipment |
| CN111179714A (en) * | 2020-02-27 | 2020-05-19 | 尚熠然 | A physical experiment teaching display device for junior middle school student |
| US20200160682A1 (en) * | 2018-11-20 | 2020-05-21 | Paul Johnson | Proximity-based personnel safety system and method |
| CN111262922A (en) * | 2020-01-13 | 2020-06-09 | 安徽华创环保设备科技有限公司 | Visual environmental protection equipment service management system based on big data |
-
2020
- 2020-06-19 CN CN202010567581.2A patent/CN111723741A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004234429A (en) * | 2003-01-31 | 2004-08-19 | Oki Electric Ind Co Ltd | Parking lot management system and parking lot management method |
| CN204069108U (en) * | 2014-10-17 | 2014-12-31 | 惠州聆韵科技有限公司 | The myopic-preventing mobile phone of a kind of prompting |
| CN106815574A (en) * | 2017-01-20 | 2017-06-09 | 博康智能信息技术有限公司北京海淀分公司 | Set up detection model, detect the method and apparatus for taking mobile phone behavior |
| CN107730428A (en) * | 2017-10-17 | 2018-02-23 | 贾俊力 | Job site intelligent monitoring administration system and its control method |
| WO2019168323A1 (en) * | 2018-02-27 | 2019-09-06 | 엘지이노텍 주식회사 | Apparatus and method for detecting abnormal object, and photographing device comprising same |
| US20190370577A1 (en) * | 2018-06-04 | 2019-12-05 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving Management Methods and Systems, Vehicle-Mounted Intelligent Systems, Electronic Devices, and Medium |
| CN109492581A (en) * | 2018-11-09 | 2019-03-19 | 中国石油大学(华东) | A kind of human motion recognition method based on TP-STG frame |
| US20200160682A1 (en) * | 2018-11-20 | 2020-05-21 | Paul Johnson | Proximity-based personnel safety system and method |
| CN109977896A (en) * | 2019-04-03 | 2019-07-05 | 上海海事大学 | A kind of supermarket's intelligence vending system |
| CN110097759A (en) * | 2019-04-28 | 2019-08-06 | 南京师范大学 | A kind of motor vehicle violation behavioral value method based on video geography fence |
| CN110543825A (en) * | 2019-08-01 | 2019-12-06 | 江苏濠汉信息技术有限公司 | Dangerous construction behavior identification method and device based on space-time characteristics |
| CN110517429A (en) * | 2019-09-10 | 2019-11-29 | 浙江蓝迪电力科技有限公司 | A kind of Intelligent electronic fence system and processing method |
| CN110837778A (en) * | 2019-10-12 | 2020-02-25 | 南京信息工程大学 | Traffic police command gesture recognition method based on skeleton joint point sequence |
| CN111144232A (en) * | 2019-12-09 | 2020-05-12 | 国网智能科技股份有限公司 | Transformer substation electronic fence monitoring method based on intelligent video monitoring, storage medium and equipment |
| CN111262922A (en) * | 2020-01-13 | 2020-06-09 | 安徽华创环保设备科技有限公司 | Visual environmental protection equipment service management system based on big data |
| CN111179714A (en) * | 2020-02-27 | 2020-05-19 | 尚熠然 | A physical experiment teaching display device for junior middle school student |
Non-Patent Citations (3)
| Title |
|---|
| SEUNG HYUN KIM 等: "Intelligent intrusion detection system featuring a virtual fence, active intruder detection, classification, tracking, and action recognition", 《ANNALS OF NUCLEAR ENERGY》 * |
| TIANZHENG WANG 等: "Fast recognition of human climbing fences in transformer substations", 《2017 NINTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI)》 * |
| 时俊: "基于GCN人体行为识别系统的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117549330A (en) * | 2024-01-11 | 2024-02-13 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
| CN117549330B (en) * | 2024-01-11 | 2024-03-22 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109819208B (en) | Intensive population security monitoring management method based on artificial intelligence dynamic monitoring | |
| CN109190508B (en) | Multi-camera data fusion method based on space coordinate system | |
| CN111709409B (en) | Face living body detection method, device, equipment and medium | |
| CN104166841B (en) | The quick detection recognition methods of pedestrian or vehicle is specified in a kind of video surveillance network | |
| Sidla et al. | Pedestrian detection and tracking for counting applications in crowded situations | |
| CN110418114B (en) | Object tracking method and device, electronic equipment and storage medium | |
| CN103605971B (en) | Method and device for capturing face images | |
| CN108234927A (en) | Video frequency tracking method and system | |
| JP7292492B2 (en) | Object tracking method and device, storage medium and computer program | |
| CN103632427B (en) | A kind of gate cracking protection method and gate control system | |
| CN109583373B (en) | Pedestrian re-identification implementation method | |
| CN110414400A (en) | A kind of construction site safety cap wearing automatic testing method and system | |
| CN114445780A (en) | Detection method and device for bare soil covering, and training method and device for recognition model | |
| CN112257669A (en) | Pedestrian re-identification method and device and electronic equipment | |
| CN110458198A (en) | Multiresolution target identification method and device | |
| CN114359976A (en) | Intelligent security method and device based on person identification | |
| CN110276379A (en) | A kind of the condition of a disaster information rapid extracting method based on video image analysis | |
| CN111723741A (en) | Temporary fence movement detection alarm system based on visual analysis | |
| CN110580708B (en) | Rapid movement detection method and device and electronic equipment | |
| CN114581990A (en) | Intelligent running test method and device | |
| CN109977796A (en) | Trail current detection method and device | |
| Van Den Hengel et al. | Activity topology estimation for large networks of cameras | |
| CN116976721A (en) | Power distribution operation behavior normalization evaluation method, system and computing equipment | |
| Yang et al. | Deep learning based real-time facial mask detection and crowd monitoring | |
| Mantini et al. | UHCTD: A comprehensive dataset for camera tampering detection |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |