CN107452104A - A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring - Google Patents
A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring Download PDFInfo
- Publication number
- CN107452104A CN107452104A CN201710618714.2A CN201710618714A CN107452104A CN 107452104 A CN107452104 A CN 107452104A CN 201710618714 A CN201710618714 A CN 201710618714A CN 107452104 A CN107452104 A CN 107452104A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- face
- bayonet socket
- image
- license
- 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
Classifications
-
- 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
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
-
- 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
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring, and method includes:Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;According to the license plate image, judge whether car plate is car plate in car plate blacklist;If it is not, then according to the facial image, judge whether face is face in face blacklist;If it is not, then determine whether the vehicle can be by vehicle bayonet socket according to the license plate image and the facial image.The control method for vehicle of vehicle bayonet socket of the invention based on intelligent monitoring can control the vehicle for not meeting the unit entry condition and people can not be by vehicle bayonet socket, so as to the safety of guarantor unit and the peace and quiet of working environment.
Description
Technical field
The present invention relates to technical field of vehicle management, more particularly to a kind of vehicle control of the vehicle bayonet socket based on intelligent monitoring
Method and system processed.
Background technology
With the fast development of economic technology, city size expands constantly, and urban population and vehicle fleet size are also fast
Speed increases.Each unit can have many vehicles to enter daily, to prevent hazard event, and ensure internal work environment
Peace and quiet, some units set up sentry box inquiry on doorway and enter vehicle, to prevent Migrant women and vehicle from entering.
But above-mentioned inquiry is usually that inquiry is checked in artificial inquiry, and the mode preferably at most registered, these modes can not ensure to believe
The authenticity of breath, therefore, its can not the inherently safety of guarantor unit and working environment peace and quiet.
The content of the invention
The present invention provides the vehicle that a kind of at least part solves the vehicle bayonet socket based on intelligent monitoring of above-mentioned technical problem
Control method and system.
In a first aspect, the present invention provides a kind of control method for vehicle of the vehicle bayonet socket based on intelligent monitoring, including:
Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;
According to the license plate image, judge whether car plate is car plate in car plate blacklist;
If it is not, then according to the facial image, judge whether face is face in face blacklist;
If it is not, then determine whether the vehicle can be by vehicle bayonet socket according to the license plate image and the facial image.
Preferably, it is described according to the license plate image, judge whether car plate is car plate in car plate blacklist, including:
According to the license plate image, license board information is obtained;
Judge whether the license board information matches with the license board information in the car plate black list database pre-established;It is described
Car plate black list database is database corresponding with the car plate blacklist;
If mismatch, it is determined that the car plate is not the car plate in car plate blacklist.
Preferably, it is described according to the facial image, judge whether face is face in face blacklist, including:
According to the facial image, the characteristic information of face is obtained;
Calculate the characteristic information of the characteristic information and the face in the face black list database pre-established of the face
Matching degree;The face black list database is database corresponding with the face blacklist;
Judge whether include the matching degree that matching degree is more than or equal to preset value in matching degree;
If do not include, it is determined that the face is not the face in face blacklist.
Preferably, it is described according to the license plate image and the facial image, determine whether the vehicle can pass through vehicle
Bayonet socket, including:
Judge whether the characteristic information of the license board information and the face matches;
According to judged result, determine whether the vehicle can be by vehicle bayonet socket.
Preferably, whether the characteristic information for judging the license board information and the face matches, including:
Whether include the license board information in the man-vehicle interface database for judging to pre-establish;The people's car pre-established
Relational database includes the corresponding relation of the characteristic information of license board information and face;
If including judging whether the characteristic information of the face matches with the characteristic information of target face;The target
The characteristic information of face is the characteristic information of the face corresponding with the license board information in the man-vehicle interface database;
Whether the characteristic information for determining the license board information and the face according to judged result matches.
Preferably, it is described according to judged result, determine the vehicle whether can by vehicle bayonet socket, including:
If judged result is the license board information and the characteristic information mismatch of the face, it is determined that the vehicle can not
Pass through vehicle bayonet socket;
Methods described also includes:
Alarm.
Preferably, the license plate image for obtaining the vehicle into the region to be detected of vehicle bayonet socket, including:
Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;
According to the video data, the license plate image of vehicle is obtained.
Preferably, the facial image corresponding with vehicle for obtaining the region to be detected for entering vehicle bayonet socket, including:
Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;
The human face region in the video data is detected, and image segmentation, acquisition and vehicle are carried out to the human face region
Corresponding facial image.
Preferably, it is described to obtain into the license plate image of vehicle in the region to be detected of vehicle bayonet socket and corresponding with vehicle
Before facial image, methods described includes:
Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;
According to the license plate image, license board information is obtained, and according to the facial image, obtain the characteristic information of face;
The Query Result whether acquisition vehicle and people corresponding with vehicle match;
If judge to know the Query Result as the vehicle and people's matching corresponding with vehicle, according to default rule
The characteristic information of the license board information and face is then stored, to establish man-vehicle interface database.
Second aspect, the present invention also provide a kind of vehicle control system of the vehicle bayonet socket based on intelligent monitoring, including:
Acquiring unit, for obtaining into the license plate image of vehicle in the region to be detected of vehicle bayonet socket and corresponding with vehicle
Facial image;
First judging unit, for according to the license plate image, judging whether car plate is car plate in car plate blacklist;
Second judging unit, for if it is not, then according to the facial image, judging whether face is in face blacklist
Face;
Determining unit, for if it is not, then according to the license plate image and the facial image, determining that the vehicle whether may be used
Pass through vehicle bayonet socket.
As shown from the above technical solution, the control method for vehicle of the vehicle bayonet socket of the invention based on intelligent monitoring can control
The vehicle and people for not meeting the unit entry condition can not be by vehicle bayonet sockets, so as to the safety and working environment of guarantor unit
It is quiet.
Brief description of the drawings
Fig. 1 is the flow of the control method for vehicle for the vehicle bayonet socket based on intelligent monitoring that one embodiment of the invention provides
Figure;
Fig. 2 is the principle frame of the vehicle control system for the vehicle bayonet socket based on intelligent monitoring that one embodiment of the invention provides
Figure;
Fig. 3 is the entity structure schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
Fig. 1 is a kind of stream of the control method for vehicle for vehicle bayonet socket based on intelligent monitoring that one embodiment of the invention provides
Cheng Tu.
A kind of control method for vehicle of vehicle bayonet socket based on intelligent monitoring as shown in Figure 1, including:
The license plate image and face figure corresponding with vehicle of S101, acquisition into the vehicle in the region to be detected of vehicle bayonet socket
Picture;
What deserves to be explained is image can be gathered by image capture device.Because driver is the necessary behaviour of each vehicle
Make personnel, rather than each car has passenger, therefore, the facial image is generally the facial image of driver.The vehicle card
Mouth can be the bayonet socket of the entrance of certain unit.
S102, according to the license plate image, judge whether car plate is car plate in car plate blacklist;
It is understood that the car plate blacklist can be corresponding with car plate black list database, can be public security organ
Car plate black list database, car plate black list database may include that hit-and-run etc. does not meet the car plate letter of the unit entry condition
Breath, such as license plate number.
S103, if it is not, then according to the facial image, judge whether face is face in face blacklist;
It is understood that face blacklist can be corresponding with face black list database, face black list database can
For the face black list database of public security organ, face black list database may include fugitive personnel or other do not meet into should
The characteristic information of the face of unit condition.
S104, if it is not, then according to the license plate image and the facial image, determine whether the vehicle can pass through vehicle
Bayonet socket.
The control method for vehicle of the vehicle bayonet socket based on intelligent monitoring of the invention, which can control, not to be met the unit and enters bar
The vehicle of part and people can not be by vehicle bayonet sockets, so as to the safety of guarantor unit and the peace and quiet of working environment.
As a kind of preferred embodiment, the S102, including:
According to the license plate image, license board information is obtained;
It is understood that the license board information can be license plate number.License plate image can be identified by Car license recognition software
In license plate number.
Judge whether the license board information matches with the license board information in the car plate black list database pre-established;It is described
Car plate black list database is database corresponding with the car plate blacklist;
It is understood that the license board information of car plate in car plate blacklist is stored with the black list database, such as
License plate number.
If mismatch, it is determined that the car plate is not the car plate in car plate blacklist.
It is described to judge in the license board information and the car plate black list database pre-established as a kind of preferred embodiment
License board information whether match after, methods described also includes:
If so, then store the license board information and/or alarm.
It is understood that this method can be inquired about the car plate of car plate blacklist, or inform that staff is carried out
Processing, so as to assist public security to carry out tracing for illegal car with traffic relevant departments.
As a kind of preferred embodiment, the S103, including:
According to the facial image, the characteristic information of face is obtained;
It is understood that the characteristic information of the face can be these characteristic portions such as eyes, nose, face, forehead
Information.
Calculate the characteristic information of the characteristic information and the face in the face black list database pre-established of the face
Matching degree;The face black list database is database corresponding with the face blacklist;
It is understood that the feature letter for the face being stored with the face black list database in face blacklist
Breath, face characteristic information are these features of the information, the eyes enumerated as described above, nose, face, forehead etc. of face characteristic portion
The information at position.
Judge whether include the matching degree that matching degree is more than or equal to preset value in matching degree;
It is understood that preset value may be greater than the value equal to 90%, such as 90%, 95%.
If do not include, it is determined that the face is not the face in face blacklist.
It can be seen from face recognition technology, when the matching degree of the characteristic portion of face is more than or equal to preset value, it is believed that the spy
Levy it is identical, if the matching degree of multiple characteristic portions is all higher than being equal to preset value, then it is assumed that in face and face black list database
The face of storage is identical face.
It is described to judge whether include the matching that matching degree is more than or equal to preset value in matching degree as a kind of preferred embodiment
After degree, methods described also includes:
If including storing characteristic information and/or the alarm of the face.
It is understood that this method can be inquired about the characteristic information of the face in face blacklist, Huo Zhegao
Know that staff is handled, so as to assist public security to carry out tracing for fugitive personnel with traffic relevant departments.
As a kind of preferred embodiment, the S104, including:
Judge whether the characteristic information of the license board information and the face matches;
In a kind of specific embodiment, whether the characteristic information for judging the license board information and the face matches,
Including:
Whether include the license board information in the man-vehicle interface database for judging to pre-establish;The people's car pre-established
Relational database includes the corresponding relation of the characteristic information of license board information and face;
It is understood that a license board information can correspond to the feature letter of several faces in the man-vehicle interface database
Breath, the characteristic information of a face can also correspond to several license board informations.
If including judging whether the characteristic information of the face matches with the characteristic information of target face;The target
The characteristic information of face is the characteristic information of the face corresponding with the license board information in the man-vehicle interface database;According to
Judged result determines whether the characteristic information of the license board information and the face matches.
According to judged result, determine whether the vehicle can be by vehicle bayonet socket.
It is described according to judged result in a kind of specific embodiment, determine whether the vehicle can be wrapped by vehicle bayonet socket
Include:
If judged result is the license board information and the characteristic information mismatch of the face, it is determined that the vehicle can not
Pass through vehicle bayonet socket;
It is understood that this method be it is actually detected to face characteristic information and license board information do not meet people's car
The characteristic information of face in relational database and the corresponding relation of license board information, then it is assumed that unsafe factor be present, do not allow
Vehicle is by vehicle bayonet socket, so as to ensure the safety of the unit.
Methods described also includes:
Alarm.
It is understood that can inform that staff is handled by way of alarm, the vehicle is such as forbidden to enter.
It is described according to judged result in a kind of specific embodiment, determine whether the vehicle can be by vehicle bayonet socket, also
Including:
If judged result is the characteristic information matching of the license board information and the face, it is determined that the vehicle can pass through
Vehicle bayonet socket.
It is understood that this method be it is actually detected to face characteristic information and license board information meet Ren Cheguan
It is the characteristic information of the face in database and the corresponding relation of license board information, then it is assumed that it is safe, vehicle can be allowed to lead to
Cross vehicle bayonet socket.
As a kind of preferred embodiment, the acquisition in the step S101 enters the region to be detected of vehicle bayonet socket
The license plate image of vehicle, including:
Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;
According to the video data, the license plate image of vehicle is obtained.
As a kind of preferred embodiment, the acquisition in the step S101 enters the region to be detected of vehicle bayonet socket
Facial image corresponding with vehicle, including:
Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;
The human face region in the video data is detected, and image segmentation, acquisition and vehicle are carried out to the human face region
Corresponding facial image.
As a kind of preferred embodiment, before the S101, methods described includes:
Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;
What deserves to be explained is image can be gathered by image capture device,
According to the license plate image, license board information is obtained, and according to the facial image, obtain the characteristic information of face;
It is understood that the license board information can be license plate number, the characteristic information of the face can be eyes, nose,
The information of these characteristic portions such as face, forehead.
The Query Result whether acquisition vehicle and people corresponding with vehicle match;
Inquired about what deserves to be explained is can be the mode that staff artificially inquires about herein.It is understood that due to
Driver is the necessary operating personnel of each vehicle, rather than each car has passenger, and therefore, people corresponding with vehicle is generally
Driver.The matching can be that driver is car owner, and driver is that car owner is known people, e.g., relative, friend, colleague etc..
If judge to know the Query Result as the vehicle and people's matching corresponding with vehicle, according to default rule
The characteristic information of the license board information and face is then stored, to establish man-vehicle interface database.
It is understood that the preset rules can be by the corresponding storage of the characteristic information of license board information and face.Due to
Therefore, one may be there may be in man-vehicle interface database by different driver drivings by same car of vehicle bayonet socket
License board information corresponds to the characteristic information of multiple faces, and the characteristic information of same face corresponds to the feelings of multiple license board informations
Condition.
After the Query Result whether people obtained on vehicle and vehicle matches, methods described also includes:
If judging to know that the Query Result mismatches as the people on the vehicle and vehicle, the car plate is stored respectively
The characteristic information of information and face.
If it is understood that judging to know that the Query Result mismatches as the people on the vehicle and vehicle, recognize
Unsafe factor to be present, store the characteristic information of the license board information and face respectively, can in order to later inquiry, so as to
Assist tracing for public security and traffic the relevant departments illegal car of progress or fugitive personnel.
Specifically, the license plate image and facial image are obtained by the video of monitoring, device corresponding to this method includes
VAM Video Access Module and video encoding module, the VAM Video Access Module, can access analog video camera, web camera, DVR,
The video equipments such as NVR, by same LAN optimization video capture device, obtain the video data of analysis.
The video encoding module, using H.264 video compression coding standard, it video signal compression will encode, supply all the way
Intelligent video analysis, face snap, Car license recognition video is analyzed or video in face and car plate detection, crawl.
The intelligent video analysis module, the preset rules of various analyses are done to video using Video Analysis Technology, to regarding
The behavior of moving target and feature carry out analysis judgement in real time in frequency, are then triggered when reaching the threshold value or condition of preset rules pre-
Police simultaneously sends warning information to deep learning module, and deep learning module is done secondary by deep learning algorithm to warning information
Filtering judge, judged result be 1 think this time triggering early warning be truly to alarm, then by the alarm output module
Reach central platform;Think that this time alarm belongs to wrong report, does not do warning output, does not show in platform if judged result is 0.Area
Domain intrusion detection feature utilizes algorithm of target detection, target tracking algorism, tripwire detection by setting detection zone in video
The event that principle enters or left the region to moving target detects.
Line of stumbling invasion, circumference intrusion detection feature are stumbled line by delimiting virtual detection in video, using target detection,
Target tracking algorism, line intrusion detection principle of stumbling detect to the event of moving target across line of stumbling.
Article leave loss detection function be by delimiting detection zone in video, using background contrast's learning method,
Detected to appearing or disappearing that target and duration exceed the event of predetermined threshold value in video suddenly.
Pyrotechnics detection function is using smog, pyrotechnics detection algorithm and deep learning algorithm in global or local video pictures
Smog and flame detected, blue or green cigarette, the diffusion property of dense smoke feature and smog and degree are judged, to fire face
Color, shape, jump frequency etc. judge, draw whether there is pyrotechnics so as to analyze.
Reverse movement detection function utilizes algorithm of target detection, target tracking algorism, tripwire detection algorithm, direction of motion inspection
Survey, with reference to deep learning algorithm to being detected across the people of line and the violation direction of motion that stumbles, car.
Detection function of hovering is to utilize the inspection of algorithm of target detection, target tracking algorism combination deep learning algorithm to setting
Survey region in target hover walking away from discrete time exceed given threshold event carry out detection alarm.
Crowd massing is to utilize algorithm of target detection, people counting algorithm, density analysis algorithm combination deep learning algorithm
The event that quantity and density to moving target in the detection zone of setting have exceeded given threshold detects.
Act of violence detection is that target tracking algorism and Velocity Detection algorithm pair are utilized in locally or globally video pictures
Target is similar, and the violent behavior event such as fight is detected.
Demographics are to entering across the people for line of stumbling using algorithm of target detection tripwire detection algorithm and people counting algorithm
Row quantity statistics.
Parking detection is the setting regions in video pictures utilize algorithm of target detection, background comparison algorithm to video pictures
Interior parking violation phenomenon is analyzed, and target occurs and then triggers alarm more than predetermined parking time.
Detection of leaving post is that target in video pictures (people) is detected using algorithm of target detection, background comparison algorithm,
Target is that target disappears or transfixion and then triggers alarm more than predetermined threshold value in picture background.
Abnormal elevator detection is to utilize target detection, target tracking algorism and walking direction algorithm, velocity analysis algorithm
To in video pictures, multiple mobile object direction changes on staircase and elevator locates object of reference directionization and then triggers alarm end to end, lead to
Cross the reversing of people and elevator object of reference walking direction elevator, jerk phenomenon on elevator.
Wherein, obtaining facial image mainly includes following module:
Face recognition module, according to recognition of face flow chart, including:Face datection, feature extraction, feature recognition,
As a result output, face training, human face data.
Face detection module, deep learning, image or video to Video processing utilize convolutional neural networks technology pair
Face is detected in video, carries out image segmentation to the human face region detected, the facial image obtained after segmentation is used for
Feature extraction and recognition of face are carried out afterwards.A kind of face of the module based on combination classics cascade structure and multilayer neural network
Detection method realizes that its used funnel type cascade structure is detected and designed specifically for multi-pose Face, wherein introducing
By the thick design concept to essence, the balance of speed and precision has been taken into account.
Characteristic extracting module:Feature extraction is carried out to face picture key position.Mainly for glasses, nose, face, volume
First-class region, it is a string of character strings.
Feature recognition module:It is compared with the face characteristic extracted with the faceform in human face data module,
So as to find matching degree highest one or more personage, according to actual demand, using single personage or character sequence as identification
As a result.
Face training module:Face picture in face database is trained, obtains model corresponding to every personage.
Human face data module:The module is used to store face picture storehouse and other relevant informations, such as face database total number of persons, people
Thing is numbered, sex, and the data such as obtained faceform after training.
The matching result of face recognition module has single personage or character sequence, and single personage is characteristic matching highest one
Individual, character sequence are that the people being up to after characteristic matching more than threshold value is arranged by matching degree size order.Final output knot
Fruit is the information such as the personage matched or the pictorial information additional character name of sequence, sex.Recognition of face can realize that white list carries
Wake up, blacklist alarm, the specifically defined recognition rule of self-defined list, meanwhile, by face picture temporally, place etc. it is a plurality of
Part is retrieved, and can check the historical track of retrieval face, and the thermodynamic chart displaying of retrieval face on the electronic map, can be according to heat
Try hard to habits and customs or the permanent residence of the color analysis personage.
Obtaining license plate image mainly includes following module:
The Car license recognition module, can be to the car plate detection in video and candid photograph, and by Video Analysis Technology to vehicle body
Color, type of vehicle are analyzed, and are entered line character processing to the car plate of candid photograph, are obtained license board information transmission platform, add simultaneously
The other information such as vehicle color and car plate color.
Also include:Video diagnostic module;
The video diagnostic module, can be abnormal to camera video loss, video shelter, video blur, luminance video etc.
Video anomaly carries out real-time diagnosis, and in camera exception, grabgraf uploads center.
The deep learning module, the deep learning algorithm are pair compared with one of the deep learning, feature in recognition of face
Substantial amounts of thousands of video is trained, such as pyrotechnics detection utilizes color of the deep learning algorithm to naked light, flare spy
The various features such as sign, jump frequency, the diffusion velocity of smog, white cigarette color, blue or green cigarette color carry out class brain teaching and training, and training is learned
The number of habit is more, and the precision of judgement is higher.Judgement study i.e. to affair character, hoisting machine judges in a large amount of training
Accuracy, reduce error recognition rate.The two of feature are to carry out the early warning picture detected secondary filter, filtering car light, tree
The interference such as leaf rocks, toy, light are reported by mistake.
Deep learning (Face datection) module, the deep learning in the deep learning algorithm relatively intelligent video analysis, feature
One of be detection before face snap, face in video is detected using convolutional neural networks technology, to detecting
Human face region carry out image segmentation, carry out feature extraction and recognition of face after the facial image obtained after segmentation is used for.
The module is based on a kind of realization of the method for detecting human face of combination classics cascade structure and multilayer neural network, its used funnel
Type cascade structure is detected and designed specifically for multi-pose Face, wherein introducing by the thick design concept to essence, has taken into account speed
The balance of degree and precision.Recognition of face based on deep learning, the two of its feature is to grow up online, by the report after processing
Alert result carries out self-teaching and training, and memory filtering is carried out for wrong report, realizes automatic enhancing to correct alarm, system is with 7
It is to carry out self-promotion in the cycle.
13 video analysis functions use the deep learning algorithm based on manikin, example in the intelligent analysis module
As region invasion, line of stumbling cross the border, circumference invasion etc. detection in can effectively filter small animals such as cats and dogs or leaf caused by by mistake
Report.Hover, demographics etc. utilize the target tracking algorism based on deep learning;Demographics can bus in accurate calculation region
Flow demographics and entrance and exit of the passage face statistics.Passenger flow statisticses can realize that form is shown simultaneously, pass through cake chart, bar chart
And the volume of the flow of passengers of the displaying query point of the formal intuition of other a variety of forms;And by the period, day, the moon multi-condition inquiry it is every
The passenger flow analysing data of period, for related management, personnel provide data message.Abnormal elevator detection no matter on elevator whether someone
It can detect its jerk and reversal events.
The present invention integrates video analysis, recognition of face, Car license recognition various video are analyzed, and region can be invaded, stumbled
Line is crossed the border, circumference is invaded, article is left/lost, pyrotechnics detection, reverse movement detection, detection of hovering, crowd massing, violence row
Abnormal behaviour or event are detected in detecting etc. 13 for, demographics, parking detection, detection of leaving post, abnormal elevator;Meanwhile
Face in video can be detected by the form of software, capture, identify, reach blacklist alarm, white list is reminded
Effect;Meanwhile the discriminatory analysis of vehicle color, car plate color, the number-plate number etc. can be carried out to the vehicle of the process in video, and
Prompt.At the same time, the institute of above intelligent monitoring server is functional can be achieved wechat PUSH message.
The present invention provides a kind of intelligent monitoring server based on deep learning algorithm, to realize that machine intelligence is on duty, real
When analysis and early warning, recognition of face, Car license recognition, video diagnosis etc. multiple functions in one intelligent monitoring server.
IPC, DVR, NVR are accessed into this intelligent monitoring server, intelligent monitoring server accesses its video flowing, in intelligent prison
Control and start intelligent video analysis, recognition of face, Car license recognition, the corresponding with service of video diagnosis in server, it is complete to service configuration
Detected rule is set to each road video in software after.Its alarm, early warning letter are triggered to it respectively for 13 kinds of behavioural analyses
Breath can be detected again by deep learning algorithm to it, confirm as true alert, then warning output uploads central platform
Wechat is pushed to related account simultaneously.Invalid alarm or the false alarm as caused by disturbing factor are triggered, can be through deep learning to it
Classification and filtering, wrong report is filtered out, and does not upload central platform and push wechat.
To recognition of face video channel, after effective face enters monitored picture, human face analysis algorithm carries out pre- to image
Processing, the clear face application depth deficiency of blood algorithm in treated video is detected, by the feature of facial key position
Extracted, the characteristic value of extraction is screened with the characteristic value in the human face data deposited, compared, and is up to more than threshold value
Face additional personnel information uploads platform.
Intelligent video diagnosing algorithm can regard to camera video loss, video shelter, video blur, luminance video exception etc.
Frequency anomaly carries out real-time diagnosis, and in camera exception, grabgraf uploads center.
Fig. 2 is the principle frame of the vehicle control system for the vehicle bayonet socket based on intelligent monitoring that one embodiment of the invention provides
Figure.
A kind of vehicle control system of vehicle bayonet socket based on intelligent monitoring as shown in Figure 2, including:
Acquiring unit 201, for obtaining the license plate image and and vehicle of the vehicle into the region to be detected of vehicle bayonet socket
Corresponding facial image;
First judging unit 202, for according to the license plate image, judging whether car plate is car in car plate blacklist
Board;
Second judging unit 203, for if it is not, then according to the facial image, judging whether face is face blacklist
In face;
Determining unit 204, for if it is not, then according to the license plate image and the facial image, determining that the vehicle is
It is no to pass through vehicle bayonet socket.
Fig. 3 shows the entity structure schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.As shown in Figure 3 one
Kind electronic equipment, including:Processor 301, memory 302, bus 303 and it is stored on memory 302 and can be in processor 301
The computer program of upper operation;
Wherein, the processor 301, memory 302 complete mutual communication by the bus 303;
The processor 301 realizes the method that above-mentioned each method embodiment is provided, example when performing the computer program
Such as include:Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;Root
According to the license plate image, judge whether car plate is car plate in car plate blacklist;If it is not, then judged according to the facial image
Whether face is face in face blacklist;If it is not, the car is then determined according to the license plate image and the facial image
Whether can pass through vehicle bayonet socket.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, and calculating is stored with the storage medium
Machine program, the computer program realize the method that above-mentioned each method embodiment is provided when being executed by processor, such as including:Obtain
Take the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;According to the car plate
Image, judge whether car plate is car plate in car plate blacklist;If it is not, then according to the facial image, judge face whether be
Face in face blacklist;If it is not, then determine whether the vehicle can lead to according to the license plate image and the facial image
Cross vehicle bayonet socket.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, apparatus or computer program
Product.Therefore, the application can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application be with reference to according to the method, apparatus of the embodiment of the present application and the flow chart of computer program product and/or
Block diagram describes.It should be understood that can by each flow in computer program instructions implementation process figure and/or block diagram and/or
Square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to arrive
All-purpose computer, special-purpose computer, the processor of Embedded Processor or other programmable data processing devices are to produce one
Machine so that produced by the instruction of computer or the computing device of other programmable data processing devices and flowed for realizing
The device/system for the function of being specified in one flow of journey figure or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.Term " on ", " under " etc. refers to
The orientation or position relationship shown is based on orientation shown in the drawings or position relationship, is for only for ease of the description present invention and simplifies
Description, rather than the device or element of instruction or hint meaning must have specific orientation, with specific azimuth configuration and behaviour
Make, therefore be not considered as limiting the invention.Unless otherwise clearly defined and limited, term " installation ", " connected ",
" connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected;Can be
Mechanically connect or electrically connect;Can be joined directly together, can also be indirectly connected by intermediary, can be two
The connection of element internal.For the ordinary skill in the art, above-mentioned term can be understood at this as the case may be
Concrete meaning in invention.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that embodiments of the invention can
To be put into practice in the case of these no details.In some instances, known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it will be appreciated that disclose in order to simplify the present invention and helps to understand respectively
One or more of individual inventive aspect, in the description to the exemplary embodiment of the present invention above, each spy of the invention
Sign is grouped together into single embodiment, figure or descriptions thereof sometimes.However, should not be by the method solution of the disclosure
Release and be intended in reflection is following:I.e. the present invention for required protection requirement is than the feature that is expressly recited in each claim more
More features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of embodiment are expressly incorporated in the embodiment,
Wherein each claim is in itself as separate embodiments of the invention.It should be noted that in the case where not conflicting, this
The feature in embodiment and embodiment in application can be mutually combined.The invention is not limited in any single aspect,
Any single embodiment is not limited to, is also not limited to any combination and/or the displacement of these aspects and/or embodiment.And
And can be used alone the present invention each aspect and/or embodiment or with other one or more aspects and/or its implementation
Example is used in combination.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations;To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that:Its according to
The technical scheme described in foregoing embodiments can so be modified, either which part or all technical characteristic are entered
Row equivalent substitution;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.
Claims (10)
- A kind of 1. control method for vehicle of the vehicle bayonet socket based on intelligent monitoring based on intelligent monitoring, it is characterised in that including:Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;According to the license plate image, judge whether car plate is car plate in car plate blacklist;If it is not, then according to the facial image, judge whether face is face in face blacklist;If it is not, then determine whether the vehicle can be by vehicle bayonet socket according to the license plate image and the facial image.
- 2. according to the method for claim 1, it is characterised in that it is described according to the license plate image, judge car plate whether be Car plate in car plate blacklist, including:According to the license plate image, license board information is obtained;Judge whether the license board information matches with the license board information in the car plate black list database pre-established;The car plate Black list database is database corresponding with the car plate blacklist;If mismatch, it is determined that the car plate is not the car plate in car plate blacklist.
- 3. according to the method for claim 2, it is characterised in that it is described according to the facial image, judge face whether be Face in face blacklist, including:According to the facial image, the characteristic information of face is obtained;Calculate of the characteristic information and the characteristic information of the face in the face black list database pre-established of the face With degree;The face black list database is database corresponding with the face blacklist;Judge whether include the matching degree that matching degree is more than or equal to preset value in matching degree;If do not include, it is determined that the face is not the face in face blacklist.
- 4. according to the method for claim 3, it is characterised in that it is described according to the license plate image and the facial image, Determine the vehicle whether can by vehicle bayonet socket, including:Judge whether the characteristic information of the license board information and the face matches;According to judged result, determine whether the vehicle can be by vehicle bayonet socket.
- 5. according to the method for claim 4, it is characterised in that described to judge the license board information and the feature of the face Whether information matches, including:Whether include the license board information in the man-vehicle interface database for judging to pre-establish;The man-vehicle interface pre-established Database includes the corresponding relation of the characteristic information of license board information and face;If including judging whether the characteristic information of the face matches with the characteristic information of target face;The target face Characteristic information be the man-vehicle interface database in face corresponding with the license board information characteristic information;Whether the characteristic information for determining the license board information and the face according to judged result matches.
- 6. according to the method for claim 4, it is characterised in that it is described according to judged result, determine that the vehicle whether may be used By vehicle bayonet socket, including:If judged result is the license board information and the characteristic information mismatch of the face, it is determined that the vehicle can not pass through Vehicle bayonet socket;Methods described also includes:Alarm.
- 7. according to the method for claim 1, it is characterised in that described to obtain the car into the region to be detected of vehicle bayonet socket License plate image, including:Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;According to the video data, the license plate image of vehicle is obtained.
- 8. according to the method for claim 1, it is characterised in that it is described obtain into vehicle bayonet socket region to be detected with Facial image corresponding to vehicle, including:Obtain the video data in the region to be detected of the vehicle bayonet socket of monitoring;The human face region in the video data is detected, and image segmentation is carried out to the human face region, is obtained corresponding with vehicle Facial image.
- 9. according to the method for claim 1, it is characterised in that described to obtain the car into the region to be detected of vehicle bayonet socket License plate image and facial image corresponding with vehicle before, methods described includes:Obtain the license plate image of the vehicle into the region to be detected of vehicle bayonet socket and facial image corresponding with vehicle;According to the license plate image, license board information is obtained, and according to the facial image, obtain the characteristic information of face;The Query Result whether acquisition vehicle and people corresponding with vehicle match;If judge to know that the Query Result as the vehicle and people's matching corresponding with vehicle, is deposited according to preset rules The characteristic information of the license board information and face is stored up, to establish man-vehicle interface database.
- A kind of 10. vehicle control system of the vehicle bayonet socket based on intelligent monitoring, it is characterised in that including:Acquiring unit, for the license plate image for obtaining the vehicle into the region to be detected of vehicle bayonet socket and people corresponding with vehicle Face image;First judging unit, for according to the license plate image, judging whether car plate is car plate in car plate blacklist;Second judging unit, for if it is not, then according to the facial image, judging whether face is people in face blacklist Face;Determining unit, for if it is not, then according to the license plate image and the facial image, determining whether the vehicle can pass through Vehicle bayonet socket.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710618714.2A CN107452104A (en) | 2017-07-26 | 2017-07-26 | A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710618714.2A CN107452104A (en) | 2017-07-26 | 2017-07-26 | A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107452104A true CN107452104A (en) | 2017-12-08 |
Family
ID=60489025
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710618714.2A Pending CN107452104A (en) | 2017-07-26 | 2017-07-26 | A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107452104A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108242179A (en) * | 2018-03-01 | 2018-07-03 | 苏州科技大学 | A kind of monitoring of the intelligent garage door based on Car license recognition and warning device and method |
CN108269336A (en) * | 2018-01-18 | 2018-07-10 | 西安艾润物联网技术服务有限责任公司 | A kind of vehicle and authorization management method of occupant, device and storage medium |
CN108647627A (en) * | 2018-05-07 | 2018-10-12 | 沈阳安丰电子工程有限公司 | A kind of safety inspection method and safe examination system of vehicle |
CN108710857A (en) * | 2018-05-22 | 2018-10-26 | 深圳前海华夏智信数据科技有限公司 | People's vehicle recognition methods based on infrared light filling and device |
CN108710858A (en) * | 2018-05-22 | 2018-10-26 | 中国计量大学 | A kind of city Happiness Index dynamic thermodynamic chart generation method based on Expression Recognition |
CN108986282A (en) * | 2018-07-24 | 2018-12-11 | 上海小蚁科技有限公司 | A kind of automated vehicle clearance management method and device, storage medium, terminal |
CN109147336A (en) * | 2018-08-01 | 2019-01-04 | 武汉云易虹科技有限公司 | Personnel's method for early warning and system are driven in a kind of traffic mistake |
CN109726714A (en) * | 2018-12-14 | 2019-05-07 | 广东安居宝数码科技股份有限公司 | Recognition methods, device, equipment and the storage medium of member's vehicle |
CN109918151A (en) * | 2019-03-14 | 2019-06-21 | 佳都新太科技股份有限公司 | Workflow implementing method, device, equipment and storage medium |
CN109960993A (en) * | 2017-12-26 | 2019-07-02 | 同方威视科技江苏有限公司 | Vehicle safety detection system and method, electronic equipment, storage medium |
CN110110587A (en) * | 2019-03-21 | 2019-08-09 | 南京领胜科技有限公司 | Intelligent cloud portrait verification platform |
CN110517500A (en) * | 2018-05-21 | 2019-11-29 | 上海大唐移动通信设备有限公司 | A kind of people's vehicle association process method and device |
CN110660226A (en) * | 2019-10-30 | 2020-01-07 | 浙江大华技术股份有限公司 | Method, system and equipment for detecting vehicle safety standard and storage device |
CN110689725A (en) * | 2019-09-03 | 2020-01-14 | 北京理工大学 | Security robot system for crossing comprehensive inspection and processing method thereof |
CN110717352A (en) * | 2018-07-11 | 2020-01-21 | 杭州海康威视系统技术有限公司 | Platform passenger flow volume statistical method, server and image acquisition equipment |
CN110781748A (en) * | 2019-09-24 | 2020-02-11 | 上海商米科技集团股份有限公司 | IPC-based image processing method and camera |
CN110909567A (en) * | 2018-09-17 | 2020-03-24 | 杭州海康威视系统技术有限公司 | Method and device for capturing lost driving personnel |
WO2020088199A1 (en) * | 2018-10-30 | 2020-05-07 | 南京杰迈视讯科技有限公司 | Intelligent entrance and exit system based on association features of human faces and vehicles |
CN111814644A (en) * | 2020-07-01 | 2020-10-23 | 重庆邮电大学 | Video abnormal event detection method based on disturbance visual interpretation |
CN112651004A (en) * | 2020-11-07 | 2021-04-13 | 深圳市思拓通信系统有限公司 | Vehicle management and control method and system based on in-vehicle personnel, storage medium and equipment |
CN113408465A (en) * | 2021-06-30 | 2021-09-17 | 平安国际智慧城市科技股份有限公司 | Identity recognition method and device and related equipment |
CN113688670A (en) * | 2021-07-14 | 2021-11-23 | 南京四维向量科技有限公司 | Method for monitoring street lamp brightness based on image recognition technology |
CN114333126A (en) * | 2020-03-09 | 2022-04-12 | 中通服公众信息产业股份有限公司 | Intelligent human-vehicle checking system and method for inspection station |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105160738A (en) * | 2015-09-07 | 2015-12-16 | 成都杰迈科技有限责任公司 | Antitheft system for parking log |
CN106097499A (en) * | 2016-06-12 | 2016-11-09 | 南宁思飞电子科技有限公司 | It is applied to the vehicle management gate control system of community |
CN106297307A (en) * | 2016-09-30 | 2017-01-04 | 防城港市港口区高光信息技术有限公司 | A kind of community parking course management system |
-
2017
- 2017-07-26 CN CN201710618714.2A patent/CN107452104A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105160738A (en) * | 2015-09-07 | 2015-12-16 | 成都杰迈科技有限责任公司 | Antitheft system for parking log |
CN106097499A (en) * | 2016-06-12 | 2016-11-09 | 南宁思飞电子科技有限公司 | It is applied to the vehicle management gate control system of community |
CN106297307A (en) * | 2016-09-30 | 2017-01-04 | 防城港市港口区高光信息技术有限公司 | A kind of community parking course management system |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109960993A (en) * | 2017-12-26 | 2019-07-02 | 同方威视科技江苏有限公司 | Vehicle safety detection system and method, electronic equipment, storage medium |
CN108269336A (en) * | 2018-01-18 | 2018-07-10 | 西安艾润物联网技术服务有限责任公司 | A kind of vehicle and authorization management method of occupant, device and storage medium |
CN108242179A (en) * | 2018-03-01 | 2018-07-03 | 苏州科技大学 | A kind of monitoring of the intelligent garage door based on Car license recognition and warning device and method |
CN108647627A (en) * | 2018-05-07 | 2018-10-12 | 沈阳安丰电子工程有限公司 | A kind of safety inspection method and safe examination system of vehicle |
CN110517500A (en) * | 2018-05-21 | 2019-11-29 | 上海大唐移动通信设备有限公司 | A kind of people's vehicle association process method and device |
CN108710858A (en) * | 2018-05-22 | 2018-10-26 | 中国计量大学 | A kind of city Happiness Index dynamic thermodynamic chart generation method based on Expression Recognition |
CN108710857A (en) * | 2018-05-22 | 2018-10-26 | 深圳前海华夏智信数据科技有限公司 | People's vehicle recognition methods based on infrared light filling and device |
CN110717352B (en) * | 2018-07-11 | 2022-05-31 | 杭州海康威视系统技术有限公司 | Platform passenger flow volume statistical method, server and image acquisition equipment |
CN110717352A (en) * | 2018-07-11 | 2020-01-21 | 杭州海康威视系统技术有限公司 | Platform passenger flow volume statistical method, server and image acquisition equipment |
CN108986282A (en) * | 2018-07-24 | 2018-12-11 | 上海小蚁科技有限公司 | A kind of automated vehicle clearance management method and device, storage medium, terminal |
CN109147336A (en) * | 2018-08-01 | 2019-01-04 | 武汉云易虹科技有限公司 | Personnel's method for early warning and system are driven in a kind of traffic mistake |
CN110909567A (en) * | 2018-09-17 | 2020-03-24 | 杭州海康威视系统技术有限公司 | Method and device for capturing lost driving personnel |
WO2020088199A1 (en) * | 2018-10-30 | 2020-05-07 | 南京杰迈视讯科技有限公司 | Intelligent entrance and exit system based on association features of human faces and vehicles |
CN109726714A (en) * | 2018-12-14 | 2019-05-07 | 广东安居宝数码科技股份有限公司 | Recognition methods, device, equipment and the storage medium of member's vehicle |
CN109918151A (en) * | 2019-03-14 | 2019-06-21 | 佳都新太科技股份有限公司 | Workflow implementing method, device, equipment and storage medium |
CN110110587A (en) * | 2019-03-21 | 2019-08-09 | 南京领胜科技有限公司 | Intelligent cloud portrait verification platform |
CN110689725A (en) * | 2019-09-03 | 2020-01-14 | 北京理工大学 | Security robot system for crossing comprehensive inspection and processing method thereof |
CN110781748A (en) * | 2019-09-24 | 2020-02-11 | 上海商米科技集团股份有限公司 | IPC-based image processing method and camera |
CN110660226A (en) * | 2019-10-30 | 2020-01-07 | 浙江大华技术股份有限公司 | Method, system and equipment for detecting vehicle safety standard and storage device |
CN114333126A (en) * | 2020-03-09 | 2022-04-12 | 中通服公众信息产业股份有限公司 | Intelligent human-vehicle checking system and method for inspection station |
CN111814644B (en) * | 2020-07-01 | 2022-05-03 | 重庆邮电大学 | Video abnormal event detection method based on disturbance visual interpretation |
CN111814644A (en) * | 2020-07-01 | 2020-10-23 | 重庆邮电大学 | Video abnormal event detection method based on disturbance visual interpretation |
CN112651004A (en) * | 2020-11-07 | 2021-04-13 | 深圳市思拓通信系统有限公司 | Vehicle management and control method and system based on in-vehicle personnel, storage medium and equipment |
CN113408465A (en) * | 2021-06-30 | 2021-09-17 | 平安国际智慧城市科技股份有限公司 | Identity recognition method and device and related equipment |
CN113688670A (en) * | 2021-07-14 | 2021-11-23 | 南京四维向量科技有限公司 | Method for monitoring street lamp brightness based on image recognition technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107452104A (en) | A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring | |
CN110390262B (en) | Video analysis method, device, server and storage medium | |
CN104680555B (en) | Cross the border detection method and out-of-range monitoring system based on video monitoring | |
CN109002744A (en) | Image-recognizing method, device and video monitoring equipment | |
CN110446015A (en) | A kind of abnormal behaviour monitoring method based on computer vision and system | |
CN108875466A (en) | Monitoring method, monitoring system and storage medium based on recognition of face | |
CN110188807A (en) | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN | |
CN110298278A (en) | A kind of underground parking garage Pedestrians and vehicles monitoring method based on artificial intelligence | |
CN112085010A (en) | Mask detection and deployment system and method based on image recognition | |
CN106845342A (en) | A kind of intelligence community monitoring system and method | |
CN106534779A (en) | Intelligent monitoring system for early warning of security of scenic spot | |
CN107220633A (en) | A kind of intelligent mobile enforcement system and method | |
CN107527012A (en) | Make a dash across the red light monitoring method, device and monitoring processing equipment | |
CN109389794A (en) | A kind of Intellectualized Video Monitoring method and system | |
CN108805008A (en) | A kind of community's vehicle security system based on deep learning | |
CN112241696A (en) | Image processing method and device, electronic device and storage medium | |
CN109460744A (en) | A kind of video monitoring system based on deep learning | |
CN110047272A (en) | A kind of intelligent transportation pedestrian behavior monitoring and alarming system based on big data | |
CN109492548A (en) | The preparation method of region mask picture based on video analysis | |
CN114358980A (en) | Intelligent community property management system and method based on Internet of things | |
JP2022003499A (en) | Program and system for discriminating the degree of risk | |
CN110188617A (en) | A kind of machine room intelligent monitoring method and system | |
Wang et al. | Vision-based highway traffic accident detection | |
CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
CN115913998A (en) | PCTSE intelligent park state evaluation method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171208 |
|
RJ01 | Rejection of invention patent application after publication |