CN112885013A - Monitoring and early warning method and device and readable storage medium - Google Patents
Monitoring and early warning method and device and readable storage medium Download PDFInfo
- Publication number
- CN112885013A CN112885013A CN202110040669.3A CN202110040669A CN112885013A CN 112885013 A CN112885013 A CN 112885013A CN 202110040669 A CN202110040669 A CN 202110040669A CN 112885013 A CN112885013 A CN 112885013A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- image
- electronic fence
- early warning
- face recognition
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004519 manufacturing process Methods 0.000 claims abstract description 90
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000013135 deep learning Methods 0.000 claims description 24
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013479 data entry Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
-
- 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
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- 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)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a monitoring and early warning method, a monitoring and early warning device and a readable storage medium. The monitoring and early warning method comprises the following steps: acquiring images in the electronic fence through a monitoring camera, wherein the images comprise an inlet image, an outlet image and an internal image; carrying out face recognition on the inlet image and the outlet image to obtain the number of authorized personnel in the electronic fence; detecting the human body of the internal image to acquire the number of people in the electronic fence; and early warning is carried out based on the fact that the number of the personnel is larger than the number of authorized personnel. According to the technical scheme, an access control system does not need to be additionally arranged, illegal intrusion alarm monitoring in a monitoring area is realized through a monitoring camera, face recognition and human body detection, the monitoring accuracy and real-time performance are guaranteed, material transportation in the monitoring area is not influenced, normal production of a production line is not interfered, and the cost is not greatly increased.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a monitoring early warning method, a monitoring early warning device and a readable storage medium.
Background
The unmanned production line in the lighthouse factory occupies a large area, and inspection personnel cannot monitor the unmanned production line for 24 hours without dead angles; if the outside personnel break in, life and property loss is possibly caused, an alarm is needed to be given to unauthorized personnel, and the production line operation is stopped immediately when the condition is serious. Conventionally, an access control system is not installed at an entrance of a production line, and unauthorized persons cannot enter a dangerous area. The disadvantage of this method is that the additional addition of an access control system may affect the transportation of materials in the lighthouse plant and interfere with normal production.
Disclosure of Invention
The present invention is directed to solving at least one of the above problems.
Therefore, the first objective of the present invention is to provide a monitoring and early warning method.
The second purpose of the invention is to provide a monitoring and early warning device.
A third object of the present invention is to provide a readable storage medium.
In order to achieve the first object of the present invention, the technical solution of the present invention provides a monitoring and early warning method, including: acquiring images in the electronic fence through a monitoring camera, wherein the images comprise an inlet image, an outlet image and an internal image; carrying out face recognition on the inlet image and the outlet image to obtain the number of authorized personnel in the electronic fence; detecting the human body of the internal image to acquire the number of people in the electronic fence; and early warning is carried out based on the fact that the number of the personnel is larger than the number of authorized personnel.
The technical scheme is used for monitoring unmanned/unmanned workshop production lines (called unmanned production lines or unmanned production lines of lighthouse factories for short) of lighthouse factories (or other highly automated factories). This technical scheme need not add access control system, realizes the control that unmanned production line of lighthouse mill illegally intruded the warning through surveillance camera head, face identification and human body detection, guarantees the accuracy and the real-time of control, can not influence the material transport in the lighthouse mill, disturbs the normal production of production line.
In addition, the technical scheme provided by the invention can also have the following additional technical characteristics:
among the above-mentioned technical scheme, before carrying out the image of gathering in the fence through the camera, still include: collecting an entrance image through an entrance camera arranged at an entrance of the electronic fence; acquiring an exit image through an exit camera arranged at an exit of the electronic fence; and internal images are collected through side wall cameras arranged on two sides of the electronic fence.
Among this technical scheme, entrance and exit do not install access control system, both increased face identification's flexibility, also avoided installing additional access control system and bring the cost-push to the influence of the material transport in the lighthouse mill.
In any one of the above technical solutions, before the execution acquires the image in the electronic fence through the camera, the method further includes: face data of authorized persons is collected.
In the technical scheme, the face data of authorized personnel are collected aiming at the authorized personnel of the unmanned production line of the lighthouse factory, and the face data of the authorized personnel are collected to provide data support for subsequent face recognition, so that a deep learning algorithm of the face recognition can be applied, and the safety of the unmanned production line of the lighthouse factory is further improved.
In any one of the above technical solutions, face recognition is performed on the entrance image and the exit image, and the number of authorized persons in the electronic fence is obtained, which specifically includes: performing face recognition on the entrance image based on the entrance image, and increasing the number of authorized persons by one based on the face recognition result as authorized persons; and performing face recognition on the exit image based on the exit image, and reducing the number of authorized personnel by one based on the face recognition result.
According to the technical scheme, the entrance and the exit of the electronic fence are identified, the entering and exiting authorized personnel and unauthorized personnel can be effectively identified, the number of the authorized personnel and the number of the unauthorized personnel in the electronic fence are accurately acquired, the identification mode is simple, and the accuracy is high.
In any of the above technical solutions, the face recognition specifically includes: performing face detection and face alignment by adopting a convolutional neural network based on deep learning; and (4) performing feature extraction and face comparison by adopting a deep network model.
In the technical scheme, face recognition is executed through a face database of authorized personnel, wherein the face recognition comprises face detection, face alignment, feature extraction and face comparison, and the face detection and the face alignment are realized by using a convolutional neural network based on deep learning; and the feature extraction and the face comparison are realized by adopting a deep network model. The face recognition is carried out through the steps, the accuracy of the face recognition result is high, and the real-time monitoring can be effectively carried out.
In any of the above technical solutions, the early warning specifically includes: carrying out voice alarm of a field alarm; and/or the monitoring platform alarms; and/or to perform remote alarms.
This technical scheme reports to the police according to the circumstances, and furthest reports to the police to the dangerous condition, guarantees the safety of unmanned production line of lighthouse mill to provide multiple alarm mode, under the circumstances that unauthorized person got into, can be better carry out omnidirectional and report to the police, furthest guarantees the safety of unmanned production line of lighthouse mill.
In any of the above technical solutions, the monitoring and early warning method further includes: and based on early warning, capturing face data of unauthorized persons at the entrance and the exit of the electronic fence, and/or recording the movement video of the persons in the electronic fence.
In the technical scheme, the evidence is timely saved under the condition of alarming, and effective support is provided for subsequent matters such as processing of unauthorized personnel.
In any of the above technical solutions, the monitoring and early warning method further includes: based on the fact that production line equipment is arranged in the electronic fence, when the distance between unauthorized people and the production line equipment is smaller than a distance threshold value or the intrusion time of the unauthorized people exceeds a time threshold value, the production line equipment is controlled to stop.
In the technical scheme, if the unauthorized person is very close to the production line equipment, namely the distance between the unauthorized person and the production line equipment is smaller than a distance threshold, or the intrusion time of the unauthorized person exceeds a time threshold, and the personal safety is possibly endangered, the production line equipment is controlled to stop, and casualty accidents are avoided.
In order to achieve the second object of the present invention, the technical solution of the present invention provides a monitoring and early warning device, including: the device comprises a memory and a processor, wherein the memory stores programs or instructions, and the processor executes the programs or instructions; wherein, the processor implements the steps of the monitoring and early warning method according to any technical scheme of the invention when executing the program or the instruction.
The monitoring and early warning device provided by the technical scheme realizes the steps of the monitoring and early warning method according to any technical scheme of the invention, so that the monitoring and early warning device has all the beneficial effects of the monitoring and early warning method according to any technical scheme of the invention, and is not repeated herein.
In order to achieve the third object of the present invention, the technical solution of the present invention provides a readable storage medium, where a program or an instruction is stored, and when the program or the instruction is executed, the steps of the monitoring and early warning method according to any one of the above technical solutions are implemented.
The readable storage medium provided in the technical solution implements the steps of the monitoring and early warning method according to any technical solution of the present invention, so that the readable storage medium has all the beneficial effects of the monitoring and early warning method according to any technical solution of the present invention, and is not described herein again.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a monitoring and early warning method according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a monitoring and warning method according to an embodiment of the present invention;
FIG. 3 is a third schematic flow chart of a monitoring and warning method according to an embodiment of the present invention;
FIG. 4 is a fourth flowchart illustrating a monitoring and warning method according to an embodiment of the present invention;
FIG. 5 is a fifth flowchart illustrating a monitoring and warning method according to an embodiment of the present invention;
FIG. 6 is a sixth flowchart illustrating a monitoring and warning method according to an embodiment of the present invention;
FIG. 7 is a seventh schematic flow chart illustrating a monitoring and warning method according to an embodiment of the present invention;
FIG. 8 is a block diagram of a monitoring and warning device according to an embodiment of the present invention;
FIG. 9 is an eighth schematic flow chart illustrating a monitoring and warning method according to an embodiment of the present invention;
fig. 10 is a flow chart illustrating the process of defining an electronic fence according to an embodiment of the present invention;
FIG. 11 is a schematic view of an authorized face data entry process according to an embodiment of the present invention;
FIG. 12 is a schematic view of a monitoring camera in accordance with one embodiment of the present invention;
fig. 13 is a schematic view illustrating an unauthorized person intrusion alert process according to an embodiment of the present invention.
Wherein, the correspondence between the reference numbers and the part names in fig. 8 and 12 is:
100: side wall camera, 102: entrance and exit camera, 200: monitoring and early warning device, 210: memory, 220: a processor.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
A monitoring and early-warning method, a monitoring and early-warning apparatus 200, and a readable storage medium according to some embodiments of the present invention are described below with reference to fig. 1 to 13.
Example 1:
as shown in fig. 1, the embodiment provides a monitoring and early warning method, which includes the following steps:
s102, collecting images in the electronic fence through a monitoring camera, wherein the images comprise an entrance image, an exit image and an internal image;
step S104, carrying out face recognition on the entrance image and the exit image to obtain the number of authorized personnel in the electronic fence;
step S106, carrying out human body detection on the internal image to obtain the number of people in the electronic fence;
and S108, early warning is carried out based on the fact that the number of the personnel is larger than the number of authorized personnel.
A plurality of common cameras, a pan-tilt camera, a zooming wide-angle multi-target tracking system, a PC type hard disk video recorder, a control system and a display are used, a traditional image processing algorithm is adopted, scenes with high safety production requirements are monitored and alarmed, the system is mainly used for monitoring factories, tunnels, warehouses, airports and the like, a background difference method is adopted as an identification method, the method is easy to interfere, and the false detection rate is high.
The embodiment is used for monitoring unmanned/few workshop production lines (called unmanned production lines or unmanned production lines of lighthouse factories for short) of lighthouse factories (or other highly automated factories), and the false detection rate is low by adopting a deep learning algorithm.
The unmanned production line in the lighthouse factory occupies a large area, and inspection personnel cannot monitor the unmanned production line for 24 hours without dead angles; if the outside personnel break in, life and property loss is possibly caused, an alarm is needed to be given to unauthorized personnel, and the production line operation is stopped immediately when the condition is serious. Conventionally, an access control system is not installed at an entrance of a production line, and unauthorized persons cannot enter a dangerous area. The disadvantage of this method is that the additional addition of an access control system may affect the transportation of materials in the lighthouse plant and interfere with normal production.
In the embodiment, firstly, the images in the electronic fence are collected through the monitoring camera, then the images are identified, if the images are the inlet images and the outlet images, a depth learning algorithm is adopted, the images are subjected to face identification, the number of authorized persons in the electronic fence is further obtained, if the images are the internal images, the depth learning algorithm is adopted, the images are subjected to human body detection, the number of persons in the electronic fence is further obtained, finally, the number of persons in the electronic fence is compared with the number of authorized persons in the electronic fence through the number of persons in the electronic fence, and when the number of persons is larger than the number of authorized persons, early warning is carried out. The embodiment does not need to add an access control system, realizes illegal intrusion alarm monitoring of the unmanned production line of the lighthouse factory through a common camera and a deep learning algorithm, ensures the accuracy and the real-time performance of monitoring, does not influence material transportation in the lighthouse factory, interferes with normal production of the production line, and does not increase the cost greatly. In the embodiment, the face recognition and the human body detection are performed by adopting the deep learning algorithm, the accuracy of the algorithm is high, and further, the false detection rate is reduced.
In this embodiment, according to actual needs, a position to be monitored is set as an electronic fence, for example, a boundary between an unmanned production line and a small number of extension areas may be set as the electronic fence, a dangerous area to be monitored is inside the electronic fence, and data of the electronic fence may be stored in a database.
In the embodiment, when the face recognition is performed on the inlet image and the outlet image, unauthorized persons can be recognized, and early warning can be performed for the entrance and the exit of the unauthorized persons, so that the safety of the unmanned production line of the lighthouse factory is improved.
In this embodiment, for the internal image, a deep learning algorithm is adopted to perform human body detection to obtain the number of people in the electronic fence, the deep learning algorithm may be a deep learning algorithm such as a fast Convolutional Neural Network (fast Convolutional Neural Network), a Single Shot multi-box Detector (SSD), a YOLO (You Only need to see Once) series, and the accuracy of algorithm identification is high, and the false detection rate can be effectively reduced.
In this embodiment, a server is added in the background, the monitoring camera collects images in the electronic fence and stores the images in the electronic fence in the server, and the server runs a deep learning algorithm to process video monitoring data in real time, and deep learning algorithm processes such as face recognition and human body detection are all implemented on the server. The surveillance camera head of this embodiment adopts ordinary camera head, realizes full flow, the all-round control of unmanned production line of lighthouse mill through ordinary camera head and server, guarantees the safety in production of unmanned production line, effective reduce cost.
Example 2:
as shown in fig. 2, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
before the image in the electronic fence is collected through the camera, the method further comprises the following steps:
step S202, collecting an entrance image through an entrance camera arranged at an entrance of the electronic fence;
step S204, acquiring an exit image through an exit camera arranged at an exit of the electronic fence;
and S206, acquiring internal images through side wall cameras arranged on two sides of the electronic fence.
In this embodiment, a plurality of common cameras, called side wall cameras, are installed on the walls on the two sides of the unmanned production line, so that it is ensured that all dangerous areas inside the electronic fence of the unmanned production line can be monitored. In addition, common cameras are additionally arranged at all inlets and outlets of the unmanned production line, the common cameras at the inlets are called inlet cameras, the common cameras at the outlets are called outlet cameras, and images collected by the inlet cameras and the outlet cameras are used for recognizing human faces. In this embodiment, entrance and exit do not install access control system, both increased face identification's flexibility, also avoided installing additional access control system and brought the cost-push to reach the influence of the material transport in the lighthouse mill.
In this embodiment, through setting up ordinary camera, need not install access control system additional, only use ordinary camera and degree of depth learning algorithm to realize the monitored control system that the warning was illegally rushed into to unmanned production line of lighthouse mill, can guarantee the accuracy and the real-time of control, can not disturb normal operation yet, can not increase the cost in a large number simultaneously.
Example 3:
as shown in fig. 3, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
before the image in the electronic fence is collected through the camera, the method further comprises the following steps:
step S302, face data of authorized personnel is collected.
In the embodiment, the face data of authorized personnel are collected aiming at the authorized personnel of the unmanned production line of the lighthouse factory, the data are formed into the database, the database is stored in the server, the data of the database are called when the face recognition is carried out, and the data support is provided for the follow-up face recognition by collecting the face data of the authorized personnel, so that the deep learning algorithm of the face recognition can be applied, and the safety of the unmanned production line of the lighthouse factory is further improved.
The authorized personnel in the embodiment can be set according to actual conditions, for example, the authorized personnel can be unmanned production line inspection personnel and the like.
Example 4:
as shown in fig. 4, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
carry out face identification to entry image and export image, obtain the authorized personnel number in the fence, specifically include the following steps:
step S402, based on the image as an entrance image, carrying out face recognition on the entrance image, and based on the face recognition result as authorized personnel, increasing the number of the authorized personnel by one;
and S404, performing face recognition on the exit image based on the exit image as the image, and reducing the number of authorized personnel by one based on the face recognition result as the authorized personnel.
In this embodiment, if the acquired image is an entry image, face recognition is performed based on a face database of authorized persons, the number of authorized persons is increased by one if the face recognition is the authorized person, and the number of unauthorized persons is increased by one if the face recognition is the unauthorized person. And if the acquired image is an exit image, performing face recognition based on a face database of authorized personnel, reducing the number of the authorized personnel by one if the face recognition is the authorized personnel, and reducing the number of the unauthorized personnel by one if the face recognition is the unauthorized personnel. For the same authorized person, if the entrance image is detected twice or more and the exit image is not detected, the number of authorized persons is increased by only one, for example, the entrance image and the exit image are collected, face recognition is respectively performed on the entrance image and the exit image, and if the entrance detects an authorized person twice and the exit does not detect the face of the authorized person, the number of authorized persons is increased by only one. When the entering person falls down and the face recognition cannot be carried out, voice prompt is carried out to enable the entering person to be in head-up cooperation, and if the entering person is not in head-up cooperation, the entering person is determined to be an unauthorized person. Through the process, the number of authorized personnel and the number of unauthorized personnel in the electronic fence can be obtained, and early warning can be performed under the condition that the unauthorized personnel exist. The embodiment can effectively identify the authorized personnel and the unauthorized personnel entering and exiting through identifying the images of the inlet and the outlet, so as to obtain the number of the authorized personnel and the number of the unauthorized personnel in the accurate electronic fence, and the identification method is simple and has high accuracy.
Example 5:
as shown in fig. 5, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
the face recognition is carried out, and the method specifically comprises the following steps:
step S502, adopting a convolutional neural network based on deep learning to carry out face detection and face alignment;
and step S504, performing feature extraction and face comparison by adopting a deep network model.
In this embodiment, face recognition is performed through a face database of authorized personnel, where the face recognition includes face detection, face alignment, feature extraction, and face comparison, where the face detection and the face alignment are implemented using a Convolutional Neural Network based on deep learning, and the Convolutional Neural Network may adopt MTCNN (Multi-task Convolutional Neural Network) or the like; the feature extraction and the Face comparison are realized by adopting a Deep network model, and the Deep network model can adopt Deep Identification (Deep ID), Deep Face (Deep Face), and the like. The face recognition is carried out through the steps, the accuracy of the face recognition result is high, and the real-time monitoring can be effectively carried out.
Example 6:
in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
carrying out early warning, specifically comprising: carrying out voice alarm of a field alarm; and/or the monitoring platform alarms; and/or to perform remote alarms.
In this embodiment, when the unmanned production line is working, the alarm can be given as long as someone is in the electronic fence. When the unmanned production line stops working, if the number of the personnel in the electronic fence is less than or equal to the number of the authorized personnel, no alarm is given, otherwise, an alarm is given. This embodiment is reported to the police according to the condition, and furthest reports to the police to the dangerous condition, guarantees the safety of unmanned production line of beacon factory.
In this embodiment, the warning can adopt multiple mode, firstly, on-the-spot alarm audio alert, can install a plurality of alarms on unmanned production line both sides wall, carry out on-the-spot alarm audio alert, be used for warning illegal intruder (unauthorized personnel get into), secondly, monitor platform reports to the police, can report to the police at background monitor platform, be used for promoting backstage monitor personnel, thirdly, carry out remote alarm, can carry out long-range propelling movement to alarm information, for example, can carry out SMS warning etc. for relevant leading cell-phone.
This embodiment provides multiple alarm mode, and under the condition that unauthorized person got into, the security of the unmanned production line of beacon factory is guaranteed to furthest in the warning that can be better carries out the omnidirectional.
Example 7:
as shown in fig. 6, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
the monitoring and early warning method further comprises the following steps:
and step S602, capturing face data of unauthorized persons at the entrance and the exit of the electronic fence based on early warning, and/or recording the movement video of the persons in the electronic fence.
In this embodiment, based on the early warning, the evidence that unauthorized people entered may also be saved, and the method may include: the method comprises the steps of snapshotting face data information of unauthorized persons at an entrance and an exit, recording moving videos of the persons in a dangerous area (electronic fence), and the like. Under the condition of alarming, the evidence is stored in time, and effective support is provided for subsequent matters such as processing of unauthorized personnel.
Example 8:
as shown in fig. 7, in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:
the monitoring and early warning method further comprises the following steps:
step S702, based on the fact that production line equipment is arranged in the electronic fence, when the distance between unauthorized people and the production line equipment is smaller than a distance threshold or the intrusion time of unauthorized people exceeds a time threshold, the production line equipment is controlled to stop.
In this embodiment, if an unauthorized person is very close to the production line device, that is, the distance between the unauthorized person and the production line device is less than a distance threshold, or the intrusion time of the unauthorized person exceeds a time threshold (for example, 5 minutes), which may endanger the personal safety, the production line device is controlled to stop, so as to avoid casualty accidents.
Example 9:
as shown in fig. 8, the present embodiment provides a monitoring and early warning apparatus 200, including: a memory 210 and a processor 220, the memory 210 storing programs or instructions, the processor 220 executing the programs or instructions; wherein, the processor 220, when executing the program or the instructions, implements the steps of the monitoring and warning method according to any embodiment of the present invention.
Example 10:
the embodiment provides a readable storage medium, which stores a program or instructions, and when the program or instructions are executed by the processor 220, the steps of the monitoring and early warning method of any of the above embodiments are implemented.
The specific embodiment is as follows:
the embodiment provides an entrance guard system which is not additionally provided, and only uses a common camera and a deep learning algorithm to realize illegal intrusion alarm of an unmanned production line of a lighthouse factory, namely a monitoring and early warning method, so that the monitoring accuracy and the real-time performance can be ensured, the normal operation can not be interfered, and the cost can not be greatly increased.
In order to achieve the technical purpose, a plurality of common cameras (called side wall cameras) are mounted on the walls on the two sides of the unmanned production line, so that the dangerous areas inside the electronic fence of the unmanned production line can be monitored completely. In addition, all the entrances and exits of the unmanned production line are additionally provided with pillars for mounting common cameras (called entrance cameras and exit cameras) for recognizing human faces. In addition, a plurality of alarms are mounted on the walls on the two sides of the unmanned production line and used for warning illegal intruders, and a processing server is added in the background to run a deep learning algorithm to process video monitoring data in real time.
The specific steps are shown in fig. 9, and include the following steps:
step S802, defining an electronic fence;
as shown in fig. 10, includes:
step S8022, setting an electronic fence;
setting the boundary of the unmanned production line with a small number of extension areas as an electronic fence, wherein the inside of the electronic fence is a dangerous area needing to be monitored;
step S8024, storing the data in a database;
saving the electronic fence area to a database;
step S804, authorizing the input of face data;
as shown in fig. 11, includes:
step S8042, collecting human faces;
collecting a face image of an unmanned production line inspection tour worker;
step S8044, storing the data in a database;
storing face data of authorized personnel in a database;
step S806, installing a monitoring camera;
as shown in fig. 12, a plurality of common cameras, called as side wall cameras 100, are installed on the walls on both sides of the unmanned production line, so as to ensure that all dangerous areas inside the electronic fence of the unmanned production line can be monitored; the method comprises the steps that pillars are additionally arranged at all inlets and outlets of an unmanned production line, common cameras, namely the inlet and outlet cameras 102, are arranged and used for recognizing human faces, the inlet and outlet cameras 102 are arranged by additionally arranging one pillar at the inlet and outlet, and the pillars do not influence the safety of the production line and the inlet and outlet of inspection personnel;
step S808, an unauthorized person gives an alarm when entering;
the method for acquiring the images in the electronic fence by using the camera comprises the following steps of:
step S8082, collecting images in the electronic fence;
if the image is the entrance image, the process goes to step S8084, and if the image is the image of the dangerous area (inside the electronic fence), the process goes to step S8094;
step S8084, face recognition;
if the entrance and exit cameras collect entrance and exit images (entrance images and exit images), face recognition is performed by means of the face database collected in step S804. The face recognition comprises several links of face detection, face alignment, feature extraction and face comparison, and the face detection and the face alignment are realized by using a convolutional neural network (such as MTCNN) based on deep learning; and the feature extraction and the face comparison are realized by adopting a deep network model (such as deep ID, deep face and the like). If the person enters the intelligent terminal and falls down, the person cannot recognize the face, the voice prompts the person to lift the head to match, and if the person does not match, the person is determined to be an unauthorized person.
Step S8086, judging whether the person is an authorized person;
judging whether the person is an authorized person or not according to the face recognition result, if so, entering a step S8088, and otherwise, entering a step S8090;
step S8088, judging whether the program is to enter;
if the authorized person enters, adding 1 to the authorized person number in the electronic fence, and if the authorized person exits, subtracting 1 from the authorized person number in the electronic fence;
step S8090, judging whether the program is to enter;
if the unauthorized person enters the electronic fence, adding 1 to the unauthorized person in the electronic fence, and if the unauthorized person exits, subtracting 1 from the unauthorized person in the electronic fence;
step S8092, counting the authorized number of people;
step S8094, detecting a human body;
if the images of the dangerous areas in the electronic fence (the images inside the electronic fence) acquired by the side wall cameras are used, human body detection is executed and can be completed by means of deep learning algorithms such as Faster CNN, SSD, YOLO series and the like;
step S8096, counting the number of people in the dangerous area;
counting the number of people in the dangerous area according to the detection result;
step S810, alarming for illegal intrusion;
as shown in fig. 13, includes:
step S8100, judging whether the number of people in the area is more than the authorized number of people;
when the unmanned production line is working, people can give an alarm as long as people are in a dangerous area. When the unmanned production line stops working, if the number of people in the dangerous area (electronic fence) is more than the authorized number of people, the step S8104 is carried out, otherwise, the step S8102 is carried out.
Step S8102, alarm is cancelled;
entering step S8082;
step S8104, alarming and storing evidence;
carrying out illegal intrusion alarm and storing evidence, wherein the alarm mode comprises the following steps: a site alarm gives an alarm by voice, a background monitoring platform gives an alarm and a related leader short message alarm; the evidence saving mode comprises the following steps: capturing face information of unauthorized people at an entrance and an exit, and recording a movement video of people in a dangerous area;
step S812, stopping production line equipment;
as shown in fig. 13, includes:
step S8120, judging whether personal safety is endangered;
if yes, go to step S8122, otherwise, go to step S8082.
Step S8122, equipment is shut down;
if the unauthorized person is very close to the production line equipment (the distance between the unauthorized person and the production line equipment is less than the distance threshold) or the break-in time exceeds a specified time (the break-in time of the unauthorized person exceeds the time threshold), for example, 5 minutes, the system controls the production line equipment to stop, and casualty accidents are avoided.
The monitoring method of the unmanned production line of the lighthouse factory based on the common vision camera and the deep learning algorithm does not need to be additionally provided with an access control system, only uses the access camera to complete face recognition, uses the side wall camera to complete human body detection, judges whether the number of people in a dangerous area is larger than the authorized number of people, and decides whether to alarm or even stop the equipment.
The embodiment uses the common camera and the server to realize the full-flow and all-around monitoring of the unmanned production line of the lighthouse factory, and can ensure the safe production of the unmanned production line.
For example, the embodiment can also be implemented by a method of additionally installing an access control system at an entrance or using a hawk-eye camera to shoot a human face. However, the method of using a physical access control system increases the cost and may affect the production line, and the eagle-eye camera capture scheme can also achieve the purpose, but the cost is higher.
In summary, the embodiment of the invention has the following beneficial effects:
1. the embodiment does not need to add an access control system, realizes illegal intrusion alarm monitoring of the unmanned production line of the lighthouse factory through a common camera and a deep learning algorithm, ensures the accuracy and the real-time performance of monitoring, does not influence material transportation in the lighthouse factory, interferes with normal production of the production line, and does not increase the cost greatly. In the embodiment, the face recognition and the human body detection are performed by adopting the deep learning algorithm, the accuracy of the algorithm is high, and further, the false detection rate is reduced.
2. In the embodiment, when the face recognition is performed on the inlet image and the outlet image, unauthorized persons can be recognized, and early warning can be performed for the entrance and the exit of the unauthorized persons, so that the safety of the unmanned production line of the lighthouse factory is improved.
3. In this embodiment, a server is added in the background, the monitoring camera collects images in the electronic fence and stores the images in the electronic fence in the server, and the server runs a deep learning algorithm to process video monitoring data in real time, and deep learning algorithm processes such as face recognition and human body detection are all implemented on the server. The surveillance camera head of this embodiment adopts ordinary camera head, realizes full flow, the all-round control of unmanned production line of lighthouse mill through ordinary camera head and server, guarantees the safety in production of unmanned production line, effective reduce cost.
In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; the term "plurality" means two or more unless expressly limited otherwise. The terms "mounted," "connected," "fixed," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection; "coupled" may be direct or indirect through an intermediary. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", "front", "rear", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or unit must have a specific direction, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
In the description herein, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A monitoring and early warning method is characterized by comprising the following steps:
acquiring images in the electronic fence through a monitoring camera, wherein the images comprise an inlet image, an outlet image and an internal image;
carrying out face recognition on the entrance image and the exit image to obtain the number of authorized personnel in the electronic fence;
carrying out human body detection on the internal image to obtain the number of people in the electronic fence;
and early warning is carried out based on the fact that the number of the personnel is larger than the number of the authorized personnel.
2. The monitoring and early warning method according to claim 1, wherein before the capturing of the image in the electronic fence by the camera is executed, the method further comprises:
acquiring an entrance image through an entrance camera arranged at an entrance of the electronic fence;
collecting an exit image through an exit camera arranged at an exit of the electronic fence;
and acquiring the internal images through side wall cameras arranged on two sides of the electronic fence.
3. The monitoring and early warning method according to claim 2, wherein before the capturing of the image in the electronic fence by the camera is executed, the method further comprises:
and acquiring the face data of the authorized person.
4. The monitoring and early warning method according to any one of claims 1 to 3, wherein the face recognition is performed on the entrance image and the exit image to obtain the number of authorized persons in the electronic fence, specifically comprising:
performing face recognition on the entrance image based on the image as the entrance image, and increasing the number of authorized persons by one based on the face recognition result as the authorized persons;
and performing face recognition on the exit image based on the exit image, and reducing the number of authorized personnel by one based on the face recognition result as authorized personnel.
5. The monitoring and early warning method according to claim 4, wherein the face recognition specifically comprises:
performing face detection and face alignment by adopting a convolutional neural network based on deep learning;
and (4) performing feature extraction and face comparison by adopting a deep network model.
6. The monitoring and early-warning method according to any one of claims 1 to 3, wherein the early warning specifically comprises:
carrying out voice alarm of a field alarm; and/or
The monitoring platform gives an alarm; and/or
And carrying out remote alarm.
7. The monitoring and pre-warning method according to claim 6, further comprising:
and based on early warning, capturing the face data of unauthorized persons at the entrance and the exit of the electronic fence, and/or recording the movement video of the persons in the electronic fence.
8. The monitoring and early-warning method according to any one of claims 1 to 3, further comprising:
and based on the fact that production line equipment is arranged in the electronic fence, when the distance between unauthorized people and the production line equipment is smaller than a distance threshold value or the intrusion time of unauthorized people exceeds a time threshold value, the production line equipment is controlled to stop.
9. A monitoring and early warning device (200), comprising:
a memory (210) storing programs or instructions;
a processor (220) that executes the program or instructions;
wherein the processor (220), when executing the program or instructions, carries out the steps of the monitoring and pre-warning method according to any one of claims 1 to 8.
10. A readable storage medium, on which a program or instructions are stored, which when executed by a processor, implement the steps of the monitoring and warning method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040669.3A CN112885013A (en) | 2021-01-13 | 2021-01-13 | Monitoring and early warning method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040669.3A CN112885013A (en) | 2021-01-13 | 2021-01-13 | Monitoring and early warning method and device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112885013A true CN112885013A (en) | 2021-06-01 |
Family
ID=76045161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110040669.3A Pending CN112885013A (en) | 2021-01-13 | 2021-01-13 | Monitoring and early warning method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112885013A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113985796A (en) * | 2021-12-02 | 2022-01-28 | 东莞市君正塑胶电子有限公司 | Security protection intelligence siren |
| CN114040173A (en) * | 2021-11-26 | 2022-02-11 | 广东鉴面智能科技有限公司 | A method and system for supervising sand mining ships in a watershed |
| CN114495011A (en) * | 2022-02-15 | 2022-05-13 | 辽宁奥普泰通信股份有限公司 | Non-motor vehicle and pedestrian illegal intrusion identification method, storage medium and computer equipment based on target detection |
| 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 (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102099839A (en) * | 2008-06-03 | 2011-06-15 | 赛德斯安全与自动化公司 | Safety apparatus and method for monitoring a monitoring area |
| CN104867205A (en) * | 2014-11-22 | 2015-08-26 | 重庆市行安电子科技有限公司 | Secure identification monitoring system |
| CN105046874A (en) * | 2015-07-07 | 2015-11-11 | 合肥指南针电子科技有限责任公司 | Police prison intelligent video monitoring system |
| WO2017134323A1 (en) * | 2016-02-05 | 2017-08-10 | Viabox Company, S.A. | System for controlling attendance on premises with access control |
| CN107452116A (en) * | 2017-08-21 | 2017-12-08 | 哈尔滨海邻科信息技术有限公司 | A kind of method of personnel identity and quantity in identification specific region |
| CN108737791A (en) * | 2018-06-19 | 2018-11-02 | 河南孚点电子科技有限公司 | A kind of intelligent video monitoring system based on simulation with number |
| CN110491009A (en) * | 2019-09-03 | 2019-11-22 | 北京华捷艾米科技有限公司 | Home security method and system based on intelligent recognition camera |
| CN110969743A (en) * | 2018-09-26 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Person retention detection method and device, electronic device and readable storage medium |
| DE102018220754A1 (en) * | 2018-11-30 | 2020-06-04 | Volkswagen Aktiengesellschaft | Access control system and method for controlling access of at least one person to a building area |
| CN112073689A (en) * | 2020-09-03 | 2020-12-11 | 国网北京市电力公司 | Limited space operation personnel business turn over management and control device |
-
2021
- 2021-01-13 CN CN202110040669.3A patent/CN112885013A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102099839A (en) * | 2008-06-03 | 2011-06-15 | 赛德斯安全与自动化公司 | Safety apparatus and method for monitoring a monitoring area |
| CN104867205A (en) * | 2014-11-22 | 2015-08-26 | 重庆市行安电子科技有限公司 | Secure identification monitoring system |
| CN105046874A (en) * | 2015-07-07 | 2015-11-11 | 合肥指南针电子科技有限责任公司 | Police prison intelligent video monitoring system |
| WO2017134323A1 (en) * | 2016-02-05 | 2017-08-10 | Viabox Company, S.A. | System for controlling attendance on premises with access control |
| CN107452116A (en) * | 2017-08-21 | 2017-12-08 | 哈尔滨海邻科信息技术有限公司 | A kind of method of personnel identity and quantity in identification specific region |
| CN108737791A (en) * | 2018-06-19 | 2018-11-02 | 河南孚点电子科技有限公司 | A kind of intelligent video monitoring system based on simulation with number |
| CN110969743A (en) * | 2018-09-26 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Person retention detection method and device, electronic device and readable storage medium |
| DE102018220754A1 (en) * | 2018-11-30 | 2020-06-04 | Volkswagen Aktiengesellschaft | Access control system and method for controlling access of at least one person to a building area |
| CN110491009A (en) * | 2019-09-03 | 2019-11-22 | 北京华捷艾米科技有限公司 | Home security method and system based on intelligent recognition camera |
| CN112073689A (en) * | 2020-09-03 | 2020-12-11 | 国网北京市电力公司 | Limited space operation personnel business turn over management and control device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114040173A (en) * | 2021-11-26 | 2022-02-11 | 广东鉴面智能科技有限公司 | A method and system for supervising sand mining ships in a watershed |
| CN113985796A (en) * | 2021-12-02 | 2022-01-28 | 东莞市君正塑胶电子有限公司 | Security protection intelligence siren |
| CN114495011A (en) * | 2022-02-15 | 2022-05-13 | 辽宁奥普泰通信股份有限公司 | Non-motor vehicle and pedestrian illegal intrusion identification method, storage medium and computer equipment based on target detection |
| 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 |
|---|---|---|
| CN112885013A (en) | Monitoring and early warning method and device and readable storage medium | |
| CN112132045B (en) | Community personnel abnormal behavior monitoring scheme based on computer vision | |
| CN105654647B (en) | A kind of real-time judge someone invades indoor recognition methods | |
| CN111144291B (en) | Video monitoring area personnel intrusion discrimination method and device based on target detection | |
| CN201278180Y (en) | Automatic tracking recognition system | |
| CN110675586A (en) | Airport enclosure intrusion monitoring method based on video analysis and deep learning | |
| CN1401112A (en) | Intruder detection through trajectory analysis in monitoring and surveillance systems | |
| CN101609588A (en) | Full-automatic anti-intrusion intelligent video monitoring alarm system for unattended villa | |
| KR101036947B1 (en) | Automated security system for crime and accident prevention using computer image analysis technology | |
| CN112738468A (en) | A smart park security early warning method and system | |
| CN117912186A (en) | Intelligent security linkage early warning system based on big data service | |
| CN118918669B (en) | Optical fiber fence intrusion alarm system | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| CN118155363A (en) | Remote monitoring system for community building linkage alarm | |
| CN119360518A (en) | A safety distance alarm system and method for combined electronic blocking | |
| CN115019463A (en) | Water area supervision system based on artificial intelligence technology | |
| CN117173847B (en) | Intelligent door and window anti-theft alarm system and working method thereof | |
| CN117789128B (en) | Digital management method and system for security equipment based on Internet of Things | |
| CN117456471B (en) | Perimeter security method, perimeter security system, terminal equipment and storage medium | |
| CN118942159A (en) | A park visitor safety warning method, system and medium based on digital twin | |
| CN118675277A (en) | Network security equipment integrated system of intelligent building | |
| CN118736743A (en) | Smart manhole cover anti-theft monitoring system | |
| CN117994734A (en) | Target risk level assessment method based on robot | |
| CN116757422A (en) | Building engineering safety supervision early warning method and monitoring system | |
| CN115841727A (en) | Airport enclosure intrusion alarm system and method |
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 |