CN110110657A - Method for early warning, device, equipment and the storage medium of visual identity danger - Google Patents
Method for early warning, device, equipment and the storage medium of visual identity danger Download PDFInfo
- Publication number
- CN110110657A CN110110657A CN201910375065.7A CN201910375065A CN110110657A CN 110110657 A CN110110657 A CN 110110657A CN 201910375065 A CN201910375065 A CN 201910375065A CN 110110657 A CN110110657 A CN 110110657A
- Authority
- CN
- China
- Prior art keywords
- personnel
- danger
- monitor video
- danger zone
- location information
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 9
- 238000009434 installation Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000001699 lower leg Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The present invention provides method for early warning, device, equipment and the storage medium of a kind of visual identity danger, this method comprises: delimiting the danger zone in monitor video according to the current monitoring scene of photographic device;Convolutional neural networks based on deep learning identify in the monitor video whether there is personnel's appearance;When there are personnel to occur in the monitor video, the location information of the personnel is obtained;Compare the location information of the personnel and the position range of the danger zone;If the location information in the danger zone, issues the warning information for invading danger zone about personnel.By using in the identification monitoring of intelligent vision identification technology whether someone and when someone whether offend delimitation danger zone range, can monitor the danger zone specified for 24 hours, prevent personnel to be strayed into and cause safety accident;Realize that intelligent monitoring, intelligent decision, relatively traditional artificial monitoring reduce the workload of artificial early warning, improve the accuracy of monitoring.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of method for early warning of visual identity danger, device,
Equipment and storage medium.
Background technique
With popularizing for security monitoring camera, the identification demand under various different scenes is also come into being, especially needle
To the identification demand in terms of personnel safety.For building site, factory and other specific occasions, do not allow people specifically there are some
" danger zone " that member enters needs 24 hours monitor in real time to such region by security monitoring camera, if
Someone enters the region, then reminds or issue in time alarm signal.
Existing security protection video monitoring means be using manually distinguishing large batch of monitor video, however, using
Artificial monitor video carries out early warning, on the one hand, heavy workload needs continuous monitoring in staff 24 hours;On the other hand, it needs
The long-term attention of staff is concentrated, and same staff can not monitor multiple monitor videos, is otherwise easy to happen leakage and is seen, is wrong
The situation seen causes safety accident.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of early warning of visual identity danger
Method, apparatus, equipment and storage medium, when for solving to use artificial monitoring and early warning in safety monitoring in the prior art, efficiency
It is low and with operating time increase influence early warning precision the problem of.
In order to achieve the above objects and other related objects, the application's in a first aspect, present invention provides a kind of visual identity
Dangerous method for early warning, comprising:
The danger zone in monitor video delimited according to the current monitoring scene of photographic device;
Convolutional neural networks based on deep learning identify in the monitor video whether there is personnel's appearance;
When there are personnel to occur in the monitor video, the location information of the personnel is obtained;
Compare the location information of the personnel and the position range of the danger zone;If the location information is described
In danger zone, then the warning information that danger zone is invaded about personnel is issued.
The second aspect of the application provides a kind of prior-warning device of visual identity danger, comprising:
Module delimited, for delimiting the danger zone in monitor video according to the current monitoring scene of photographic device;
Identification module identifies in the monitor video whether have personnel to go out for the convolutional neural networks based on deep learning
It is existing;
Position information acquisition module, for obtaining the position of the personnel when thering are personnel to occur in the monitor video
Information;
Warning module, for the location information of the personnel and the position range of the danger zone;If described
Location information then issues the warning information that danger zone is invaded about personnel in the danger zone.
The third aspect of the application, provides a kind of electronic equipment, comprising:
One or more processors;
Memory;And
One or more programs, wherein one or more of programs be stored in the memory and be configured as by
One or more of processors execute instruction, and execute instruction described in one or more of processors execution so that the electronics
Equipment executes the method for early warning of above-mentioned visual identity danger.
The fourth aspect of the application provides a kind of storage medium, comprising: and the storage medium includes the program of storage,
In, described program realizes the method for early warning of above-mentioned visual identity danger in called execute.
As described above, method for early warning, device, equipment and the storage medium of visual identity danger of the invention, have following
The utility model has the advantages that
By using in the identification monitoring of intelligent vision identification technology, whether someone and when someone offend the danger of delimitation
The range in danger zone domain can monitor specified danger zone for 24 hours, prevent personnel to be strayed into and cause safety accident;Realize intelligence prison
Control, intelligent decision, relatively traditional artificial monitoring reduce the workload of artificial early warning, improve the accuracy of monitoring.
Detailed description of the invention
Fig. 1 is shown as a kind of method for early warning flow chart of visual identity danger provided by the invention;
Fig. 2 is shown as an a kind of embodiment flow chart of the method for early warning of visual identity danger provided by the invention;
Fig. 3 is shown as a kind of prior-warning device structural block diagram of visual identity danger provided by the invention;
Fig. 4 is shown as an a kind of example structure block diagram of the prior-warning device of visual identity danger provided by the invention;
Fig. 5 is shown as a kind of early warning electronic devices structure block diagram of visual identity danger provided by the invention.
Specific embodiment
Presently filed embodiment is illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book understands other advantages and effect of the application easily.
In described below, with reference to attached drawing, attached drawing describes several embodiments of the application.It should be appreciated that also can be used
Other embodiments, and can be carried out without departing substantially from spirit and scope of the present disclosure mechanical composition, structure, electrically with
And the operational detailed description changed below should not be considered limiting, and the range of embodiments herein
Only the limited of claims of the patent by announcing term used herein is merely to describe specific embodiment, and be not
It is intended to limit the application.The term of space correlation, for example, "upper", "lower", "left", "right", " following ", " lower section ", " lower part ",
" top ", " top " etc. can be used in the text in order to an elements or features and another element or spy shown in explanatory diagram
The relationship of sign.
Although term first, second etc. are used to describe various elements herein in some instances, these elements
It should not be limited by these terms.These terms are only used to distinguish an element with another element.For example, first is pre-
If threshold value can be referred to as the second preset threshold, and similarly, the second preset threshold can be referred to as the first preset threshold, and
The range of various described embodiments is not departed from.First preset threshold and preset threshold are to describe a threshold value, still
Unless context otherwise explicitly points out, otherwise they are not the same preset thresholds.Similar situation further includes first
Volume and the second volume.
Furthermore as used in herein, singular " one ", "one" and "the" are intended to also include plural number shape
Formula, unless having opposite instruction in context it will be further understood that term "comprising", " comprising " show that there are the spies
Sign, step, operation, element, component, project, type, and/or group, but it is not excluded for one or more other features, step, behaviour
Work, element, component, project, the presence of type, and/or group, appearance or addition term "or" used herein and "and/or" quilt
Be construed to inclusive, or mean any one or any combination therefore, " A, B or C " or " A, B and/or C " mean " with
Descend any one: A;B;C;A and B;A and C;B and C;A, B and C " is only when element, function, step or the combination of operation are in certain modes
Under it is inherently mutually exclusive when, just will appear the exception of this definition.
With popularizing for security monitoring camera, the identification demand under various different scenes is also come into being, especially needle
To the identification demand in terms of personnel safety.For building site, factory and other specific occasions, do not allow people specifically there are some
" danger zone " that member enters needs 24 hours monitor in real time to such region by security monitoring camera, if
There are personnel to enter the region and then reminds or issue in time alarm signal.Existing security protection video monitoring means are by full-time people
Member distinguishes large batch of monitor video with human eye, it is difficult to 24 continuous throughout the twenty-four hour24s, and when such security protection video content is long
Between do not change, be responsible for distinguish full-time staff be difficult to for a long time focus on, be easy to happen the case where leakage is seen.Therefore it needs to adopt
With the intelligent vision identification technology that can carry out discriminance analysis for 24 hours to safety monitoring video incessantly, for video image
In " danger zone ", instead of manually carry out intellectual analysis handle and in real time issue alarm model.
Referring to Fig. 1, being a kind of method for early warning flow chart of visual identity danger provided by the invention, comprising:
Step S1 delimit the danger zone in monitor video according to the current monitoring scene of photographic device;
Wherein, the monitor video of current scene is acquired according to the installation site of photographic device, and in the monitor video
Delimit danger zone to be detected, wherein photographic device includes the photographing modules such as camera, video camera, for acquiring current prison
Control the monitor video of scene.In addition, expressing the setting range of the danger zone in a manner of polygon and being stored in a point set S
={ p1, p2, p3 ..., pn };For example, being connected to form the polygonal region of closure two-by-two in order in the point set, that is, delimit
Danger zone.
Step S2, the convolutional neural networks based on deep learning identify in the monitor video whether there is personnel's appearance;
Wherein, by the intelligent vision identification technology of the convolutional neural networks based on deep learning, identify in video whether
There is personnel's appearance.
Step S3 obtains the location information of the personnel when having personnel to occur in the monitor video;
Wherein, monitor video is identified by the identification model of trained convolutional neural networks, when the monitoring
When there are personnel to occur in video, location information of the personnel in monitor video is obtained;Wherein, with human body boundary rectangle frame
The form of upper left angular coordinate, rectangle width of frame and height is rendered as { x, y, w, h };Or, with the upper left of human body boundary rectangle frame
The form of angular coordinate and bottom right angular coordinate is rendered as { x1, y1, x2, y2 }.
Step S4, the position range of the location information of the personnel and the danger zone;If the position letter
Breath then issues the warning information that danger zone is invaded about personnel in the danger zone.
Wherein, due to foot part left foot, the right crus of diaphragm of people, the personnel foot is being extracted corresponding to the location information
Coordinate points, left foot, right crus of diaphragm are respectively (x, y+h) and (x+w, y+h), or, left foot, right crus of diaphragm are respectively (x1, y1) and (x2, y2);
The position range for comparing point set in coordinate points corresponding to the personnel foot and danger zone, when wherein any one
When a coordinate points are located in the danger zone inside point set, then the warning information that danger zone is invaded about personnel is issued.
In the present embodiment, the coordinate points of the foot corresponding to the personnel any one drop into danger zone point set inside
When, then issue the warning information that danger zone is invaded about personnel;Wherein, the coordinate points of the foot corresponding to the personnel and danger area
It when domain inner edge boundary line is overlapped, and drops into inside the point set of danger zone, issues the early warning for invading danger zone about personnel
Information.
In addition, comparing the location information of personnel not in the position range of the danger zone, that is, the foot corresponding to the personnel
The coordinate points in portion any one outside the point set of danger zone when, without taking any movement, continue monitoring.
By using in the identification monitoring of intelligent vision identification technology, whether someone and when someone offend the danger of delimitation
The range in danger zone domain can monitor specified danger zone for 24 hours, prevent personnel to be strayed into and cause safety accident;Realize intelligence prison
Control, intelligent decision, relatively traditional artificial monitoring reduce the workload of artificial early warning, improve the accuracy of monitoring.
Referring to Fig. 2, being an a kind of embodiment flow chart of the method for early warning of visual identity danger provided by the invention, in detail
It states as follows:
To there are personnel to occur and the monitor video in calibration sample set occur without personnel;
Using monitor video in the convolutional neural networks training sample set based on deep learning, obtain to identify monitoring view
Frequency whether someone occur identification model.
In the present embodiment, for monitor video to be detected, firstly, video image in interception monitor video (video flowing)
(video frame), then change into unified leveldb format, by the way of manually demarcating by above-mentioned image according to have personnel occur with
The label that no personnel occur is demarcated, and by the video frame composing training collection of calibration, utilizes convolutional neural networks
(Convolutional Neural Network, CNN) model carries out feature extraction to the video frame in the training set.
Specifically, the network architectures such as classical CNN model such as AlexNet, VGGNet or Inception can be selected, obtain
The feature vector statement for obtaining video frame, for example, VGGNet (Visual Geometry Group Network) is using VGG16's
Convolutional neural networks comprising 1 data input layer, 13 convolutional layers, 3 full articulamentums.The convolution kernel of 13 convolutional layers
Number is respectively 64,64,128,128,256,256,256,512,512,512,512,512,512.2nd convolutional layer and the 3rd
Between convolutional layer, between the 4th convolutional layer and the 5th convolutional layer, the 13rd between the 7th convolutional layer and the 8th convolutional layer ...
Between a convolutional layer and the 1st full articulamentum, it is all connected with a pond layer, above-mentioned 13 convolutional layers and 3 full articulamentums are equal
It is handled with ReLU (nonlinear activation function).The identification model the last layer of VGG-16 network is removed into re -training, most
There are personnel to occur using the output of softmax function afterwards, occur the probability value of class label without personnel, output valve is most probable value pair
The class label answered.One K dimensional vector z containing any real number can be tieed up reality vector σ (z) " compressed " to another K by softmax function
In so that the range of each element is between (0,1), and all elements and be 1.For example, input vector [has personnel
Occurring, no personnel occur] value of corresponding Softmax function is [0.2,0.8], then possessing weight limit in output vector
Item corresponds to the maximum value " no personnel occur " in input vector.
Specifically, it is not limited to VGG16 using convolutional neural networks, the nerve net of other convolutional layer table structures can also be used
Network will not repeat them here.
Referring to Fig. 3, being a kind of prior-warning device structural block diagram of visual identity danger provided by the invention, comprising:
Module 1 delimited, for delimiting the danger zone in monitor video according to the current monitoring scene of photographic device;
Wherein, the delimitation module further comprises:
The monitor video of current scene is acquired according to the installation site of photographic device, and danger delimited in the monitor video
Danger zone domain, wherein the setting range of the danger zone is expressed in a manner of polygon and be stored in a point set S=p1, p2,
P3 ..., pn }.
Identification module 2 identifies in the monitor video whether there is personnel for the convolutional neural networks based on deep learning
Occur;
Wherein, intelligent vision identification technology of the identification module 2 by the convolutional neural networks based on deep learning, identification view
Whether personnel appearance is had in frequency.
Position information acquisition module 3, for obtaining the position of the personnel when thering are personnel to occur in the monitor video
Information;
Wherein, the position information acquisition module further comprises:
When there are personnel to occur in the monitor video, location information of the personnel in monitor video is obtained;Wherein,
{ x, y, w, h } is rendered as in the form of the upper left angular coordinate (x, y), rectangle width of frame w and height h of human body boundary rectangle frame;
Or, be rendered as in the form of the top left co-ordinate (x1, y1) of human body boundary rectangle frame and bottom right angular coordinate (x2, y2) x1, y1,
x2,y2}。
Warning module 4, for the location information of the personnel and the position range of the danger zone;If described
Location information then issues the warning information that danger zone is invaded about personnel in the danger zone.
The warning module further comprises:
Extract personnel foot coordinate points corresponding to the location information, respectively (x, y+h) and (x+w, y+
H), or, (x1, y1) and (x2, y2);
The position range for comparing point set in coordinate points corresponding to the personnel foot and danger zone, when wherein any one
When a coordinate points are located in the danger zone inside point set, then the warning information that danger zone is invaded about personnel is issued.
Referring to Fig. 4, be an a kind of example structure block diagram of the prior-warning device of visual identity danger provided by the invention,
Details are as follows:
Module 1 delimited, for delimiting the danger zone in monitor video according to the current monitoring scene of photographic device;
Training identification model 5, for there are personnel to occur and the monitor video in calibration sample set occur without personnel;Using
Monitor video in convolutional neural networks training sample set based on deep learning obtains to identify whether someone goes out monitor video
Existing identification model;
Identification module 2 identifies in the monitor video whether there is personnel for the convolutional neural networks based on deep learning
Occur;
Position information acquisition module 3, for obtaining the position of the personnel when thering are personnel to occur in the monitor video
Information;
Warning module 4, for the location information of the personnel and the position range of the danger zone;If described
Location information then issues the warning information that danger zone is invaded about personnel in the danger zone.
In the present embodiment, since the method for early warning of visual identity danger and the prior-warning device of visual identity danger are one by one
Corresponding relationship, technical detail and technical effect involved in the two are all the same, do not repeat one by one secondary.
Referring to Fig. 5, providing a kind of battery capacity status estimation electronic equipment for the present invention, comprising:
One or more processors 51;
Memory 52;And
One or more programs, wherein one or more of programs are stored in the memory 52 and are configured as
It is executed instruction by one or more of processors 51, is executed instruction described in one or more of processors execution so that described
Electronic equipment executes the method for early warning such as above-mentioned visual identity danger.
The processor 51 is operationally coupled with memory and/or non-volatile memory device.More specifically, processor
51 can be performed the instruction stored in memory and/or non-volatile memory device to execute operation in calculating equipment, such as
It generates image data and/or image data is transferred to electronic console.In this way, processor may include one or more general micro-
Processor, one or more application specific processor (ASIC), one or more Field Programmable Logic Array (FPGA) or they
Any combination.
The application provides a kind of early warning storage medium of visual identity danger, and the storage medium includes the program of storage,
Wherein, equipment where controlling the storage medium when described program is run executes battery capacity status estimation side described in upper item
Method storage medium.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
In embodiment provided by the present application, the computer-readable storage medium of writing may include read-only memory
(ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), EEPROM, CD-ROM or
Other optical disk storage apparatus, disk storage device or other magnetic storage apparatus, flash memory, USB flash disk, mobile hard disk or it can be used in
Store any other Jie that there is the desired program code of instruction or data structure form and can be accessed by computer
Matter.In addition, any connection can be properly termed as computer-readable medium.For example, if instruction is using coaxial cable, light
The wireless technology of fine optical cable, twisted pair, digital subscriber line (DSL) or such as infrared ray, radio and microwave etc, from net
Stand, server or other remote sources send, then the coaxial cable, optical fiber cable, twisted pair, DSL or such as infrared ray,
The wireless technology of radio and microwave etc includes in the definition of the medium.
In conclusion the present invention by using in the identification monitoring of intelligent vision identification technology whether someone and when someone
Whether offence delimit danger zone range, can monitor for 24 hours specify danger zone, prevent personnel to be strayed into and cause to pacify
Full accident;Realize that intelligent monitoring, intelligent decision, relatively traditional artificial monitoring reduce the workload of artificial early warning, improve
The accuracy of monitoring.So the present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (12)
1. a kind of method for early warning of visual identity danger characterized by comprising
The danger zone in monitor video delimited according to the current monitoring scene of photographic device;
Convolutional neural networks based on deep learning identify in the monitor video whether there is personnel's appearance;
When there are personnel to occur in the monitor video, the location information of the personnel is obtained;
Compare the location information of the personnel and the position range of the danger zone;If the location information is in the danger
In region, then the warning information that danger zone is invaded about personnel is issued.
2. the method for early warning of visual identity danger according to claim 1, which is characterized in that described to be worked as according to photographic device
Preceding monitoring scene delimit the step of danger zone in monitor video, comprising:
The monitor video of current scene is acquired according to the installation site of photographic device, and delimits danger area in the monitor video
Domain, wherein express the setting range of the danger zone in a manner of polygon and be stored in a point set S={ p1, p2, p3...,
pn}。
3. the method for early warning of visual identity danger according to claim 1, which is characterized in that described based on deep learning
Convolutional neural networks identify before whether having the step of personnel occur in the monitor video, comprising:
To there are personnel to occur and the monitor video in calibration sample set occur without personnel;
Using monitor video in the convolutional neural networks training sample set based on deep learning, obtain to identify that monitor video is
The identification model that no someone occurs.
4. the method for early warning of visual identity danger according to claim 1, which is characterized in that described to work as the monitor video
In when thering are personnel to occur, the step of obtaining the location information of the personnel, comprising:
When there are personnel to occur in the monitor video, location information of the personnel in monitor video is obtained;Wherein, with people
The form of the external upper left angular coordinate for connecing rectangle frame, rectangle width of frame and height is rendered as { x, y, w, h };Or, outside with human body
The form of the top left co-ordinate and bottom right angular coordinate that connect rectangle frame is rendered as { x1,y1,x2,y2}。
5. the method for early warning of visual identity danger according to claim 1, which is characterized in that the personnel's
The position range of location information and the danger zone, if the location information in the danger zone, issue about
Personnel invade the step of warning information of danger zone, comprising:
Personnel foot coordinate points corresponding to the location information, respectively (x, y+h) and (x+w, y+h) are extracted, or,
(x1,y1) and (x2,y2);
The position range for comparing point set in coordinate points corresponding to the personnel foot and danger zone, when wherein any one is sat
When punctuate is located in the danger zone inside point set, then the warning information that danger zone is invaded about personnel is issued.
6. a kind of prior-warning device of visual identity danger characterized by comprising
Module delimited, for delimiting the danger zone in monitor video according to the current monitoring scene of photographic device;
Identification module identifies in the monitor video whether there is personnel's appearance for the convolutional neural networks based on deep learning;
Position information acquisition module, for obtaining the location information of the personnel when thering are personnel to occur in the monitor video;
Warning module, for the location information of the personnel and the position range of the danger zone;If the position
Information then issues the warning information that danger zone is invaded about personnel in the danger zone.
7. a kind of prior-warning device of visual identity danger according to claim 6, which is characterized in that the delimitation module packet
It includes:
The monitor video of current scene is acquired according to the installation site of photographic device, and delimits danger area in the monitor video
Domain, wherein express the setting range of the danger zone in a manner of polygon and be stored in a point set S={ p1, p2, p3...,
pn}。
8. a kind of prior-warning device of visual identity danger according to claim 6, which is characterized in that the identification module it
Before, comprising:
Training identification model, for there are personnel to occur and the monitor video in calibration sample set occur without personnel;Using being based on
Monitor video in the convolutional neural networks training sample set of deep learning obtains capable of identifying whether someone monitor video occurs
Identification model.
9. a kind of prior-warning device of visual identity danger according to claim 6, which is characterized in that the location information obtains
Modulus block, comprising:
When there are personnel to occur in the monitor video, location information of the personnel in monitor video is obtained;Wherein, with people
The form of the external upper left angular coordinate for connecing rectangle frame, rectangle width of frame and height is rendered as { x, y, w, h };Or, outside with human body
The form of the top left co-ordinate and bottom right angular coordinate that connect rectangle frame is rendered as { x1,y1,x2,y2}。
10. a kind of prior-warning device of visual identity danger according to claim 6, which is characterized in that the warning module,
Include:
Personnel foot coordinate points corresponding to the location information, respectively (x, y+h) and (x+w, y+h) are extracted, or,
(x1,y1) and (x2,y2);
The position range for comparing point set in coordinate points corresponding to the personnel foot and danger zone, when wherein any one is sat
When punctuate is located in the danger zone inside point set, then the warning information that danger zone is invaded about personnel is issued.
11. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors;
Memory;
And one or more programs, wherein one or more of programs be stored in the memory and be configured as by
One or more of processors execute instruction, and execute instruction described in one or more of processors execution so that the electronics
Equipment executes the method for early warning of visual identity danger as claimed in any one of claims 1 to 5.
12. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program is being adjusted
With the method for early warning realized when executing such as visual identity danger as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910375065.7A CN110110657A (en) | 2019-05-07 | 2019-05-07 | Method for early warning, device, equipment and the storage medium of visual identity danger |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910375065.7A CN110110657A (en) | 2019-05-07 | 2019-05-07 | Method for early warning, device, equipment and the storage medium of visual identity danger |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110657A true CN110110657A (en) | 2019-08-09 |
Family
ID=67488498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910375065.7A Pending CN110110657A (en) | 2019-05-07 | 2019-05-07 | Method for early warning, device, equipment and the storage medium of visual identity danger |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110657A (en) |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110733983A (en) * | 2019-12-20 | 2020-01-31 | 广东博智林机器人有限公司 | tower crane safety control system and control method thereof |
CN110796032A (en) * | 2019-10-11 | 2020-02-14 | 深圳市誉托科技有限公司 | Video fence based on human body posture assessment and early warning method |
CN110889339A (en) * | 2019-11-12 | 2020-03-17 | 南京甄视智能科技有限公司 | Head and shoulder detection-based dangerous area grading early warning method and system |
CN110995808A (en) * | 2019-11-25 | 2020-04-10 | 国网安徽省电力有限公司建设分公司 | Power grid infrastructure site safety dynamic management and control system based on ubiquitous power Internet of things |
CN111028480A (en) * | 2019-12-06 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Drowning detection and alarm system |
CN111104856A (en) * | 2019-11-18 | 2020-05-05 | 中冶赛迪技术研究中心有限公司 | Converter smelting splash monitoring method, system, storage medium and equipment |
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 |
CN111209814A (en) * | 2019-12-27 | 2020-05-29 | 广东德融汇科技有限公司 | Face recognition campus area early warning method and system for K12 education stage |
CN111341068A (en) * | 2020-03-02 | 2020-06-26 | 北京四利通控制技术股份有限公司 | Drilling site dangerous area early warning system and method based on deep learning |
CN111339901A (en) * | 2020-02-21 | 2020-06-26 | 北京容联易通信息技术有限公司 | Intrusion detection method and device based on image, electronic equipment and storage medium |
CN111524112A (en) * | 2020-04-17 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Steel chasing identification method, system, equipment and medium |
CN111593891A (en) * | 2020-04-26 | 2020-08-28 | 中联重科股份有限公司 | Safety early warning method and device for engineering mechanical arm frame equipment and engineering machine |
CN111968104A (en) * | 2020-08-27 | 2020-11-20 | 中冶赛迪重庆信息技术有限公司 | Machine vision-based steel coil abnormity identification method, system, equipment and medium |
CN112053526A (en) * | 2020-09-29 | 2020-12-08 | 上海振华重工(集团)股份有限公司 | Monitoring system and monitoring method |
CN112087604A (en) * | 2020-09-18 | 2020-12-15 | 浪潮天元通信信息***有限公司 | Intelligent monitoring video management and control method based on image recognition |
CN112130504A (en) * | 2020-09-25 | 2020-12-25 | 重庆天智慧启科技有限公司 | Online monitoring and alarming system for preventing personnel from entering dangerous area |
CN112165610A (en) * | 2020-09-29 | 2021-01-01 | 北京法之运科技有限公司 | Video positioning method, video positioning device and storage device |
CN112395921A (en) * | 2019-08-16 | 2021-02-23 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior detection method, device and system |
CN112597950A (en) * | 2020-12-29 | 2021-04-02 | 三一海洋重工有限公司 | Safety monitoring method and device for mechanical equipment |
CN112800947A (en) * | 2021-01-27 | 2021-05-14 | 上海电气集团股份有限公司 | Video monitoring method, system, electronic equipment and storage medium |
CN112885014A (en) * | 2021-01-15 | 2021-06-01 | 广州穗能通能源科技有限责任公司 | Early warning method, device, system and computer readable storage medium |
CN113160510A (en) * | 2021-05-31 | 2021-07-23 | 西南石油大学 | Visual early warning method for construction dangerous area |
CN113393703A (en) * | 2020-03-11 | 2021-09-14 | 中国石油化工股份有限公司 | Forklift operation risk early warning method and system |
CN113610072A (en) * | 2021-10-11 | 2021-11-05 | 精英数智科技股份有限公司 | Method and system for identifying person crossing belt based on computer vision |
CN113688713A (en) * | 2021-08-18 | 2021-11-23 | 广东电网有限责任公司 | Cable protection method, device, system and medium based on dangerous behavior recognition |
CN113808354A (en) * | 2021-11-16 | 2021-12-17 | 深圳市思拓通信***有限公司 | Method, device and medium for early warning of construction site dangerous area |
CN113936248A (en) * | 2021-10-12 | 2022-01-14 | 河海大学 | Beach personnel risk early warning method based on image recognition |
CN113971868A (en) * | 2020-07-23 | 2022-01-25 | 易程融创信息科技有限公司 | Alarm method and system based on infant behavior statistics |
CN114241737A (en) * | 2021-11-30 | 2022-03-25 | 慧之安信息技术股份有限公司 | Iron tower climbing monitoring method and device based on deep learning |
CN115050125A (en) * | 2022-05-20 | 2022-09-13 | 劢微机器人科技(深圳)有限公司 | Safety early warning method, device, equipment and storage medium based on 2d camera |
CN115082865A (en) * | 2022-07-27 | 2022-09-20 | 国能大渡河检修安装有限公司 | Bridge crane intrusion dangerous behavior early warning method and system based on visual image recognition |
CN116206255A (en) * | 2023-01-06 | 2023-06-02 | 广州纬纶信息科技有限公司 | Dangerous area personnel monitoring method and device based on machine vision |
CN116740821A (en) * | 2023-08-16 | 2023-09-12 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006287884A (en) * | 2005-03-31 | 2006-10-19 | Ara Software:Kk | Intelligent video monitoring system |
CN109034124A (en) * | 2018-08-30 | 2018-12-18 | 成都考拉悠然科技有限公司 | A kind of intelligent control method and system |
-
2019
- 2019-05-07 CN CN201910375065.7A patent/CN110110657A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006287884A (en) * | 2005-03-31 | 2006-10-19 | Ara Software:Kk | Intelligent video monitoring system |
CN109034124A (en) * | 2018-08-30 | 2018-12-18 | 成都考拉悠然科技有限公司 | A kind of intelligent control method and system |
Non-Patent Citations (2)
Title |
---|
刘宇刚等: "监控图像中的人体识别", 《河南工程学院学报(自然科学版)》 * |
刘志斌等: "基于实时定位技术的变电站智能安全管理***", 《电力***及其自动化学报》 * |
Cited By (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112395921A (en) * | 2019-08-16 | 2021-02-23 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior detection method, device and system |
CN110796032A (en) * | 2019-10-11 | 2020-02-14 | 深圳市誉托科技有限公司 | Video fence based on human body posture assessment and early warning method |
CN110889339A (en) * | 2019-11-12 | 2020-03-17 | 南京甄视智能科技有限公司 | Head and shoulder detection-based dangerous area grading early warning method and system |
CN111104856A (en) * | 2019-11-18 | 2020-05-05 | 中冶赛迪技术研究中心有限公司 | Converter smelting splash monitoring method, system, storage medium and equipment |
CN110995808A (en) * | 2019-11-25 | 2020-04-10 | 国网安徽省电力有限公司建设分公司 | Power grid infrastructure site safety dynamic management and control system based on ubiquitous power Internet of things |
CN110995808B (en) * | 2019-11-25 | 2024-04-02 | 国网安徽省电力有限公司建设分公司 | Power grid infrastructure site safety dynamic management and control system based on ubiquitous power Internet of things |
CN111028480A (en) * | 2019-12-06 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Drowning detection and alarm system |
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 |
CN110733983A (en) * | 2019-12-20 | 2020-01-31 | 广东博智林机器人有限公司 | tower crane safety control system and control method thereof |
CN111209814B (en) * | 2019-12-27 | 2023-05-19 | 广东德融汇科技有限公司 | Face recognition campus area early warning method and system for K12 education stage |
CN111209814A (en) * | 2019-12-27 | 2020-05-29 | 广东德融汇科技有限公司 | Face recognition campus area early warning method and system for K12 education stage |
CN111339901A (en) * | 2020-02-21 | 2020-06-26 | 北京容联易通信息技术有限公司 | Intrusion detection method and device based on image, electronic equipment and storage medium |
CN111341068A (en) * | 2020-03-02 | 2020-06-26 | 北京四利通控制技术股份有限公司 | Drilling site dangerous area early warning system and method based on deep learning |
CN111341068B (en) * | 2020-03-02 | 2022-04-08 | 北京四利通控制技术股份有限公司 | Construction method of drilling site dangerous area early warning system based on deep learning |
CN113393703A (en) * | 2020-03-11 | 2021-09-14 | 中国石油化工股份有限公司 | Forklift operation risk early warning method and system |
CN111524112B (en) * | 2020-04-17 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Steel chasing identification method, system, equipment and medium |
CN111524112A (en) * | 2020-04-17 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Steel chasing identification method, system, equipment and medium |
CN111593891A (en) * | 2020-04-26 | 2020-08-28 | 中联重科股份有限公司 | Safety early warning method and device for engineering mechanical arm frame equipment and engineering machine |
CN113971868A (en) * | 2020-07-23 | 2022-01-25 | 易程融创信息科技有限公司 | Alarm method and system based on infant behavior statistics |
CN111968104A (en) * | 2020-08-27 | 2020-11-20 | 中冶赛迪重庆信息技术有限公司 | Machine vision-based steel coil abnormity identification method, system, equipment and medium |
CN112087604A (en) * | 2020-09-18 | 2020-12-15 | 浪潮天元通信信息***有限公司 | Intelligent monitoring video management and control method based on image recognition |
CN112130504A (en) * | 2020-09-25 | 2020-12-25 | 重庆天智慧启科技有限公司 | Online monitoring and alarming system for preventing personnel from entering dangerous area |
CN112165610A (en) * | 2020-09-29 | 2021-01-01 | 北京法之运科技有限公司 | Video positioning method, video positioning device and storage device |
CN112053526A (en) * | 2020-09-29 | 2020-12-08 | 上海振华重工(集团)股份有限公司 | Monitoring system and monitoring method |
CN112597950A (en) * | 2020-12-29 | 2021-04-02 | 三一海洋重工有限公司 | Safety monitoring method and device for mechanical equipment |
CN112885014A (en) * | 2021-01-15 | 2021-06-01 | 广州穗能通能源科技有限责任公司 | Early warning method, device, system and computer readable storage medium |
CN112800947A (en) * | 2021-01-27 | 2021-05-14 | 上海电气集团股份有限公司 | Video monitoring method, system, electronic equipment and storage medium |
CN113160510A (en) * | 2021-05-31 | 2021-07-23 | 西南石油大学 | Visual early warning method for construction dangerous area |
CN113688713A (en) * | 2021-08-18 | 2021-11-23 | 广东电网有限责任公司 | Cable protection method, device, system and medium based on dangerous behavior recognition |
CN113610072A (en) * | 2021-10-11 | 2021-11-05 | 精英数智科技股份有限公司 | Method and system for identifying person crossing belt based on computer vision |
CN113936248A (en) * | 2021-10-12 | 2022-01-14 | 河海大学 | Beach personnel risk early warning method based on image recognition |
CN113936248B (en) * | 2021-10-12 | 2023-10-03 | 河海大学 | Beach personnel risk early warning method based on image recognition |
CN113808354A (en) * | 2021-11-16 | 2021-12-17 | 深圳市思拓通信***有限公司 | Method, device and medium for early warning of construction site dangerous area |
CN114241737A (en) * | 2021-11-30 | 2022-03-25 | 慧之安信息技术股份有限公司 | Iron tower climbing monitoring method and device based on deep learning |
CN115050125A (en) * | 2022-05-20 | 2022-09-13 | 劢微机器人科技(深圳)有限公司 | Safety early warning method, device, equipment and storage medium based on 2d camera |
CN115050125B (en) * | 2022-05-20 | 2023-08-29 | 劢微机器人科技(深圳)有限公司 | 2d camera-based safety early warning method, device, equipment and storage medium |
CN115082865A (en) * | 2022-07-27 | 2022-09-20 | 国能大渡河检修安装有限公司 | Bridge crane intrusion dangerous behavior early warning method and system based on visual image recognition |
CN116206255A (en) * | 2023-01-06 | 2023-06-02 | 广州纬纶信息科技有限公司 | Dangerous area personnel monitoring method and device based on machine vision |
CN116206255B (en) * | 2023-01-06 | 2024-02-20 | 广州纬纶信息科技有限公司 | Dangerous area personnel monitoring method and device based on machine vision |
CN116740821A (en) * | 2023-08-16 | 2023-09-12 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
CN116740821B (en) * | 2023-08-16 | 2023-10-24 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110110657A (en) | Method for early warning, device, equipment and the storage medium of visual identity danger | |
US10184787B2 (en) | Apparatus and methods for distance estimation using multiple image sensors | |
CN110569772B (en) | Method for detecting state of personnel in swimming pool | |
US20190034712A1 (en) | Methods and systems for drowning detection | |
WO2018025831A1 (en) | People flow estimation device, display control device, people flow estimation method, and recording medium | |
CN105405150B (en) | Anomaly detection method and device based on fusion feature | |
KR20180135898A (en) | Systems and methods for training object classifiers by machine learning | |
KR101983684B1 (en) | A People Counting Method on Embedded Platform by using Convolutional Neural Network | |
CN111833340A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
Choi et al. | Human body orientation estimation using convolutional neural network | |
Pramada et al. | Intelligent sign language recognition using image processing | |
CN109492575A (en) | A kind of staircase safety monitoring method based on YOLOv3 | |
CN103049747B (en) | The human body image utilizing the colour of skin knows method for distinguishing again | |
Lamer et al. | Computer vision based object recognition principles in education | |
CN109740527A (en) | Image processing method in a kind of video frame | |
CN109684990A (en) | A kind of behavioral value method of making a phone call based on video | |
JP7099809B2 (en) | Image monitoring system | |
CN109241952A (en) | Personage's method of counting and device under crowd scene | |
Hai et al. | An efficient star skeleton extraction for human action recognition using hidden Markov models | |
CN102867214A (en) | Counting management method for people within area range | |
KR102564300B1 (en) | System for Preventing Violence School Using Body Temperature and Behavior Pattern | |
CN110796008A (en) | Early fire detection method based on video image | |
Pairo et al. | Person following by mobile robots: analysis of visual and range tracking methods and technologies |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: 401122 No. 11 Huijin Road, North New District of Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |