CN109672853A - Method for early warning, device, equipment and computer storage medium based on video monitoring - Google Patents
Method for early warning, device, equipment and computer storage medium based on video monitoring Download PDFInfo
- Publication number
- CN109672853A CN109672853A CN201811120943.2A CN201811120943A CN109672853A CN 109672853 A CN109672853 A CN 109672853A CN 201811120943 A CN201811120943 A CN 201811120943A CN 109672853 A CN109672853 A CN 109672853A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- camera
- merit
- audio data
- early warning
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
Abstract
The invention discloses a kind of method for early warning based on video monitoring, it include: the audio data for receiving the camera of monitoring site, extract the feature of the audio data, and merit is judged whether there is according to the feature, when being determined with merit generation, the sound source direction of the audio data is determined, the camera of the monitoring site is directed at the sound source direction, to shoot the video in the sound source direction, and generate warning information.The invention also discloses a kind of prior-warning devices based on video monitoring, source of early warning and computer storage medium based on video monitoring.The present invention determines whether there is merit by the feature of the audio data according to monitoring site, the video in the sound source direction that merit occurs is shot when there is merit generation, and generate warning information, due to getting the monitor video that merit is relevant, more accurate in time, the treatment effeciency of on-site supervision video can be improved.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of method for early warning based on video monitoring, video monitoring
Device, video monitoring equipment and computer storage medium.
Background technique
With the development of image processing techniques and network technology, numerous camera has been deployed in pipe by public security system
It has jurisdiction in the street intersections in range, the image data of thecamera head becomes the important sources for evidence obtaining of solving a case.In the prior art,
There is the video to high-definition camera transmission to be monitored in real time and analyzed, to find merit in time and send warning information, but by
In camera Numerous and HD video data volume it is huge, be faced with that treatment effeciency is low, the not high problem of information timeliness.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of method for early warning based on video monitoring, based on the early warning of video monitoring
Device, the source of early warning based on video monitoring and computer storage medium, it is intended to solve high-definition camera scene in the prior art
Monitor the low technical problem for the treatment of effeciency.
To achieve the above object, the present invention provides a kind of method for early warning based on video monitoring, described to be based on video monitoring
Method for early warning include the following steps:
Receive the audio data of the camera of monitoring site;
The feature of the audio data is extracted, and merit is judged whether there is according to the feature;
When being determined with merit generation, the sound source direction of the audio data is determined;
The camera of the monitoring site is directed at the sound source direction, and shoots the view in the sound source direction
Frequently, to generate warning information.
Preferably, the feature for extracting the audio data, and merit generation is judged whether there is according to the feature
Step includes:
Determine the signal-to-noise ratio of the audio data;
When the signal-to-noise ratio of the audio data is more than default snr threshold, the audio data is converted into text letter
Breath;
Whether judge in the text information comprising preset keyword;
When in the text information including the preset keyword, it is determined with merit.
Preferably, the feature for extracting the audio data, and merit generation is judged whether there is according to the feature
Step includes:
Determine the noise power of the audio data;
When the noise power of the audio data is more than default noise power thresholds, it is determined with merit.
Preferably, described when there is merit generation, after the step of determining the sound source direction of the audio data also
Include:
The acquisition parameters of the camera of the monitoring site are adjusted, before the clarity of acquisition parameters adjusted is higher than adjustment
Acquisition parameters clarity.
Preferably, the acquisition parameters of the camera of the adjustment monitoring site, acquisition parameters adjusted it is clear
Degree was higher than after the step of clarity of the acquisition parameters before adjustment further include:
Obtain the net of the neighbouring monitoring camera at a distance from the camera of the monitoring site within the scope of pre-determined distance
Network mark;
Message is sent to the neighbouring monitoring camera according to the network identity, to notify the neighbouring monitoring camera
Adjust acquisition parameters, wherein the clarity of acquisition parameters adjusted is higher than the clarity of the acquisition parameters before adjustment.
Preferably, described that message is sent to the neighbouring monitoring camera according to the network identity, to notify the neighbour
Nearly monitoring camera adjusts acquisition parameters, wherein the clarity of acquisition parameters adjusted is higher than the acquisition parameters before adjustment
After the step of clarity further include:
The time and current time occurred according to merit determines the merit duration;
When the merit duration being greater than default merit duration threshold, restore the monitoring site camera and
The acquisition parameters of the neighbouring monitoring camera.
Preferably, the camera by the monitoring site is directed at the sound source direction, to shoot the sound
The video of source direction, and the step of generating warning information includes:
Obtain the image data of the monitoring site camera;
Face picture is identified from described image data, and extracts face characteristic from the face picture;
Judge whether the face characteristic matches with default face characteristic;
When the face characteristic and default face characteristic match, early warning corresponding with the default face characteristic etc. is obtained
Grade information;
Generate the warning information comprising the warning grade information.
In addition, to achieve the above object, the present invention also provides the prior-warning device based on video monitoring, the device packets
It includes:
Receiving module, the audio data of the camera for receiving monitoring site;
Feature processing block judges whether there is merit for extracting the feature of the audio data, and according to the feature
Occur;
Sound source estimation block, for determining the sound source direction of the audio data when being determined with merit generation;
Warning module for the camera of the monitoring site to be directed at the sound source direction, and shoots the sound
The video of sound source direction, to generate warning information.
In addition, to achieve the above object, the present invention also provides the source of early warning based on video monitoring, the equipment packets
Include: memory, processor and be stored on the memory and can run on the processor based on the pre- of video monitoring
Alert processing routine, realizes when the early warning processing routine based on video monitoring is executed by the processor and is based on as described above
The step of method for early warning of video monitoring.
In addition, to achieve the above object, the present invention also proposes a kind of computer storage medium, which is characterized in that the meter
The early warning processing routine based on video monitoring, the early warning processing routine based on video monitoring are stored on calculation machine storage medium
The step of early-warning processing method based on video monitoring as described above is realized when being executed by processor.
The embodiment of the present invention propose a kind of method for early warning based on video monitoring, the prior-warning device based on video monitoring,
Source of early warning and computer storage medium based on video monitoring receive the audio data of the camera of monitoring site, extract institute
The feature of audio data is stated, and merit is judged whether there is according to the feature, when being determined with merit generation, described in determination
The camera of the monitoring site is directed at the sound source direction by the sound source direction of audio data, and described in shooting
The video in sound source direction, to generate warning information, the present invention is determined by the feature of the audio data according to monitoring site
Whether there is merit, the video in the sound source direction that merit occurs shot when there is merit generation, and generates warning information,
Due to getting the monitor video that merit is relevant, more accurate in time, the treatment effeciency of on-site supervision video can be improved.
Detailed description of the invention
Fig. 1 is the apparatus structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is that the present invention is based on the flow diagrams of the method for early warning first embodiment of video monitoring;
Fig. 3 is that the present invention is based on the flow diagrams of the method for early warning second embodiment of video monitoring;
Fig. 4 is that the present invention is based on the flow diagrams of the method for early warning 3rd embodiment of video monitoring;
Fig. 5 is that the present invention is based on the functional block diagrams of one embodiment of prior-warning device of video monitoring.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the terminal structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
As shown in Figure 1, the server that Fig. 1 is the hardware running environment that the embodiment of the present invention is related to (is called at event
Manage equipment, wherein event handling equipment can be to be made of individual event processing apparatus, is also possible to by other devices and thing
Part processing unit combines to be formed) structural schematic diagram.
Server of the embodiment of the present invention refers to a management resource and provides the computer of service for user, is generally divided into file
Server, database server and apps server.The computer or computer system for running the above software are also referred to as
Server.For common PC (personal computer) personal computer, server is in stability, safety, property
Energy etc. requires higher;As shown in Figure 1, the server may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), network interface 1004, user interface 1003, memory 1005, communication bus
1002, hardware such as chipset, disk system, network etc..Wherein, communication bus 1002 is for realizing the connection between these components
Communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user
Interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include having for standard
Line interface, wireless interface (such as Wireless Fidelity WIreless-FIdelity, WIFI interface).Memory 1005 can be high speed with
Machine accesses memory (random access memory, RAM), is also possible to stable memory (non-volatile
), such as magnetic disk storage memory.Memory 1005 optionally can also be the storage dress independently of aforementioned processor 1001
It sets.
Optionally, server can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, sound
Frequency circuit, WiFi module;Input unit, than display screen, touch screen;Network interface can be blue in blanking wireless interface in addition to WiFi
Tooth, probe, 3G/4G/5G (digital representation of front be cellular mobile communication networks algebra.Which exactly indicate to be generation
Network.English alphabet G indicates generation) internet base station equipment etc..It will be understood by those skilled in the art that showing in Fig. 1
Server architecture out does not constitute the restriction to server, may include than illustrating more or fewer components, or combination
Certain components or different component layouts.
As shown in Figure 1, the computer software product, which is stored in a storage medium, (storage medium: is called computer storage
Medium, computer media, readable medium, readable storage medium storing program for executing, computer readable storage medium are directly medium etc., such as
RAM, magnetic disk, CD) in, including some instructions are used so that a terminal device (can be mobile phone, computer, server, sky
Adjust device or the network equipment etc.) method described in each embodiment of the present invention is executed, as a kind of depositing for computer storage medium
It may include operating system, network communication module, Subscriber Interface Module SIM and computer program in reservoir 1005.
In server shown in Fig. 1, network interface 1004 be mainly used for connect background data base, with background data base into
Row data communication;User interface 1003 is mainly used for connection client, and (client, is called user terminal or terminal, and the present invention is implemented
Example terminal can be also possible to mobile terminal, details are not described herein with fixed terminal), data communication is carried out with client;And it handles
Device 1001 can be used for calling the computer program stored in memory 1005, and execute the thing that following embodiment of the present invention provides
Step in part processing method.
Referring to Fig. 2, first embodiment of the invention provides a kind of method for early warning based on video monitoring, which comprises
Step S10 receives the audio data of the camera of monitoring site.
The camera of monitoring site enters monitoring by the network connecting module of itself or the connection of dedicated networked devices
The dedicated network of system, by the video data real-time Transmission taken to the server of monitoring system.It is taken the photograph when server receives
As head transmit video data when, video data is separated into audio stream compress coding data and view according to the encapsulation format of video
Frequency stream compress coding data, then audio stream compress coding data is further unziped it obtain audio code with decryption processing
Stream, i.e., voice data to be processed.
Step S20 extracts the feature of the audio data, and judges whether there is merit according to the feature.
According to the type and merit scene to be identified in monitoring place, the condition that merit occurs first is determined, then determine judgement
Merit occurs to need the feature of the audio data extracted.
Such as when monitoring place and being street or residential quarter due to being sent out when the more people of vehicle are more, environmental background noise is big
The probability of raw criminal offense is low, and vehicle lacks the probability height that criminal offense occurs when people is few, environmental background noise is small at night,
It can be using such scene as merit scene to be identified.Under such merit scene to be identified, the condition that merit occurs is inspection
The voice comprising merit keyword is measured, the feature of the correspondence audio data to be extracted is voice number included in audio data
According to feature.
Voice data can be identified from audio data with the method for machine learning, wherein voice data, that is, voice number
According to.A variety of voice data are first obtained as model training positive sample data source, while obtaining automobile sound and noise etc. and is inhuman
Sound is as negative sample data source, using the spectrum signature and negative sample for extracting positive sample data source based on Mel-cepstral algorithm
Two kinds of spectrum signatures are all input in neural network model and are trained by the spectrum signature in notebook data source, based on training knot
Fruit generates prediction model.When obtaining the audio data of monitoring place thecamera head, sub-frame processing is carried out to audio data,
Using the spectrum signature for extracting each frame audio data based on Mel-cepstral algorithm, which is input to prediction model
Middle carry out prediction result judges whether each frame audio data includes voice.
The signal-to-noise ratio for calculating the audio data comprising voice data identified, when signal-to-noise ratio is more than default signal-to-noise ratio threshold
When value, text converted thereof into using the identification of acoustic model and language model to audio data, and will be converted to
Text and default merit keyword are matched.When the text and default merit keyword match being converted to,
It is determined with merit.
When monitoring place is the quiet place of warehouse, this kind of comparison of computer room, noise power usually maintains leisure one compared with
Low and stable level, and in the raising for the noise power for often showing as place when occurring and the merits such as stealing, catch fire, institute
It can be to detect that noise level increases with the condition that merit occurs.Specific, monitoring place thecamera head can be calculated
The noise power of audio data is determined with merit when the noise power of audio data is more than default noise power thresholds.
Step S30 determines the sound source direction of the audio data when there is merit generation.
The high sound source direction estimation of accuracy in order to obtain microphone array can be used to carry out sound source direction and estimate
Meter receives voice signal with microphone array and makes one in spatial domain by being analyzed multi-channel sound signal and being handled
A or multi-acoustical plane or space coordinate are to get the position for arriving sound source, to obtain the direction of sound source.Wherein, comprising more
The microphone array of a microphone is mounted on the camera of monitored site, or can place multiple camera shootings in monitoring place
Head forms microphone array by the microphone being located on multiple cameras.
Sound localization method based on microphone array mainly has three classes, is respectively: based on steerable beam formed method,
Method based on High-Resolution Spectral Estimation and the method based on time delay estimation.Method based on time delay estimation is not due to by microphone
The limitation of array structure, calculation amount are also small, it is preferable to use this method.
Method based on time delay estimation includes two steps, and the first step is the time difference for calculating sound source to microphone pair, the
Two steps are the estimations obtained according to the time difference of microphone pair and the position of microphone to sound source position.It can be adopted in the first step
Time difference, such as GCC (Generalized Croos Correlation) algorithm, LMS are calculated with a variety of related algorithms
(Least Mean Square) algorithm, PHAT-GCC (Phase Thransform) algorithm etc. are, it is preferable to use PHAT-GCC is calculated
Method.
The step of calculating time difference of the sound source to each microphone pair using PHAT-GCC algorithm are as follows: by each microphone pair
Received two time-domain signals, at frequency-region signal, are obtained by Fast Fourier Transform (FFT) according to frequency-region signal and PHAT weighting function
Crosspower spectrum function carries out reverse Fast Fourier Transform (FFT) to crosspower spectrum and obtains cross-correlation function, to cross-correlation function into
The time difference is obtained in row peak detection process.
After obtaining multiple time differences of the sound source to multiple microphones pair using PHAT-GCC algorithm, according to each microphone
Pair position, multiple time differences, using weighted least-squares method it is estimated that the position of sound source.In the same coordinate system,
On the basis of the horizontal line where microphone array, using the center of microphone array as origin, sound is determined according to the position of sound source
The direction in source, wherein the direction of sound source can be to indicate with the horizontal angle where microphone array.
The camera of the monitoring site is directed at the sound source direction, and shoots the sound source by step S40
The video in direction, to generate warning information.
The goniometer of the Sounnd source direction calculated according to the current angle of camera and last step calculates camera and waits rotating
Angle, control camera rotated with angle to be rotated, to be directed at Sounnd source direction.
In the present embodiment, these step process are carried out by server and generate warning information, are sent to display terminal.
In the present embodiment, merit is determined whether there is according to the feature of the audio data of monitoring site, when there is merit
The video in the sound source direction that merit occurs is shot when generation, and generates warning information, due to getting merit correlation in time
, more accurate monitor video, the treatment effeciency of on-site supervision video can be improved.
Further, referring to Fig. 3, second embodiment of the invention is provided a kind of based on video monitoring based on first embodiment
Method for early warning, the present embodiment is after step S30 further include:
Step S50, adjusts the acquisition parameters of the camera of the monitoring site, and the clarity of acquisition parameters adjusted is high
The clarity of acquisition parameters before adjustment.
It is laid in server of the video data real-time Transmission to monitoring system of the camera shooting in each monitoring place, when
When the capacity of video data is especially big, storage resource and storage performance to server bring huge pressure, and magnanimity
Video data there are excessive redundancies, it is possible to the acquisition parameters for monitoring the camera in place are arranged to satisfaction one
As clarity require parameter, when the feature by audio data be determined with merit occur when, then adjust generation merit monitoring
The acquisition parameters of the camera in place, the clarity of acquisition parameters adjusted are higher than the clarity of the acquisition parameters before adjustment.
When executing the judgement that merit whether occurs by server, message is sent to camera by network by server
Indicate that it adjusts acquisition parameters.Specifically, the different grades of acquisition parameters of camera can be stored in advance on the server,
In, the clarity of higher grade acquisition parameters is higher, when server judges that there is merit generation in some current monitoring place,
When obtaining the current acquisition parameters grade of the monitoring place camera, the acquisition parameters of greater degree are sent to by message
The camera in the monitoring place, to indicate that it adjusts acquisition parameters;Server can also taking the photograph to the monitoring place that merit occurs
As hair is sent only comprising the message that clarity instruction information is turned up, camera adjust automatically correlation ginseng when receiving the instruction message
Number, keeps the corresponding clarity of acquisition parameters adjusted higher.
Further, the geographical location of the related personnel occurred due to merit may become in merit time-continuing process
Change, in order to obtain more comprehensively and accurately merit clue, needs that the camera that merit proximal site occurs also is opened height in time
Clear screening-mode.Specifically, the neighbouring monitoring at a distance from the available camera with monitoring site within the scope of pre-determined distance
The network identity of camera sends adjustment instruction message to neighbouring monitoring camera according to network identity, to notify neighbouring monitoring
Camera adjusts acquisition parameters, and the clarity of acquisition parameters adjusted is higher than the clarity of the acquisition parameters before adjustment.Adjustment
Instruction message can be sent by server, or be sent by the camera of merit spot.
It should be noted that there are many methods of the location information for the camera for obtaining monitoring place.A kind of method are as follows:
The camera that place installation includes locating module, such as the camera comprising GPS module are monitored, the software run on camera can
To obtain the location information of camera in real time by GPS module and be sent to server by network.Another method are as follows: supervising
It controls place and positioning device is installed, positioning device is connected with the camera in monitoring place, location information is provided for camera, by taking the photograph
As location information is sent to server by network by the software run on head.
After acquisition parameters are adjusted to acquisition parameters high-definition according to instruction by the camera of monitoring site, due to height
Shooting the video data volume of clarity is larger, occupies more network transmission bandwidth and server stores resources, needs in merit
At the end of the acquisition parameters of the camera of monitoring site are restored.It can be true according to the time and current time that merit occurs
The verdict feelings duration, when the merit duration being greater than default merit duration threshold, restore monitoring site camera and
The acquisition parameters of neighbouring monitoring camera.
In the present embodiment, fine definition is adjusted to by the acquisition parameters of the camera in the monitoring place that merit occurs
Corresponding acquisition parameters obtain more accurate video information relevant to merit in time, facilitate the detection of case.
Further, referring to Fig. 4, third embodiment of the invention is based on the first embodiment or the second embodiment and provides a kind of base
In the method for early warning of video monitoring, the present embodiment includes: in step S40
Step S60 obtains the image data of the monitoring site camera.
Include the name for being ordered to arrest people and recent clear pictures in the different grades of order for arrest of Ministry of Public Security's publication, has great
The name of the person released upon the completion of a sentence of criminal record and recent clear pictures are stored in public security system database and in society
The relatives of personnel of wandering away can be wandered away the clear pictures of personnel by Web Publishing, the face picture of these people is all merit grade
It identifies and positions and important reference is provided, so when passing through the text for being converted into the audio data of monitoring site and preset pass
Key word carry out matching be determined with merit occur when, can further obtain the image data of monitoring site camera, with and this
The face picture of a little people matches.
Step S70 identifies face picture from described image data, and face spy is extracted from the face picture
Sign.
The face characteristic in face picture is extracted with face feature recognition algorithms.Face characteristic include the eyes of people, nose,
The relative scale or relative positional relationship of the characteristic information of mouth, eyebrow etc., the specially position of face, shape size, face,
And Skin Color Information or the profile information of face etc..The face characteristic recognizer that can be taken has the side based on geometrical characteristic
Method, extracts local feature method (LBP), histograms of oriented gradients at the face identification method based on principal component analysis (PCA)
(HOG), Gabor wavelet converter technique etc. is not defined the algorithm for extracting face characteristic here.
Step S80, judges whether the face characteristic matches with default face characteristic.
By from the face picture identified in image data face characteristic and preset face characteristic matched when,
The similarity between two face characteristics is specially calculated, is then thought when the similarity being calculated is more than preset threshold
Match.
Step S90 is obtained corresponding with the default face characteristic when the face characteristic and the matching of default face characteristic
Warning grade information.
Different default face characteristics corresponds to different personnel, the social influence for the merit that different personnel may relate to
And the extent of injury is different, so different default face characteristics can correspond to different warning grades.Such as it can will be by public security
The people that system is ordered to arrest corresponds to early warning advanced tiers, and the person released upon the completion of a sentence for having terrible crimes previous conviction is corresponded to early warning Middle grade,
The personnel of wandering away are corresponded into the grades such as early warning is low.
Step S100 generates the warning information comprising the warning grade information.
In the present embodiment, by that will have the face characteristic of the face picture of the monitoring site acquisition of merit generation and preset
Face characteristic matched, the early warning for including in warning information is determined according to the warning grade of default face characteristic when matching
Class information improves early warning efficiency.
Referring to Fig. 5, the present invention also provides a kind of prior-warning devices based on video monitoring, should be filled based on the early warning of video monitoring
It sets and includes:
Receiving module 10, the audio data of the camera for receiving monitoring site;
Feature processing block 20 judges whether there is case for extracting the feature of the audio data, and according to the feature
Feelings occur;
Sound source estimation block 30, for determining the sound source direction of the audio data when being determined with merit generation;
Warning module 40, for the camera of the monitoring site to be directed at the sound source direction, and described in shooting
The video in sound source direction, to generate warning information.
Optionally, the feature processing block 20 includes:
Signal-to-noise ratio computation unit, for determining the signal-to-noise ratio of the audio data;
Voice recognition unit, for when the signal-to-noise ratio of the audio data is more than default snr threshold, by the sound
Frequency evidence is converted into text information;
Whether judging unit wraps comprising preset keyword when in the text information in the text information for judging
When containing the preset keyword, it is determined with merit.
Optionally, the feature processing block 20 includes:
Noise power calculation but due to for determining the noise power of the audio data;
Judging unit, for being determined with case when the noise power of the audio data is more than default noise power thresholds
Feelings occur.
Optionally, the prior-warning device based on video monitoring further include:
Acquisition parameters adjust module, the acquisition parameters of the camera for adjusting the monitoring site, shooting adjusted
The clarity of parameter is higher than the clarity of the acquisition parameters before adjustment.
Optionally, the prior-warning device based on video monitoring further include:
Module is obtained, for obtaining the neighbouring prison at a distance from the camera of the monitoring site within the scope of pre-determined distance
Control the network identity of camera;
Sending module, for sending message to the neighbouring monitoring camera according to the network identity, described in notice
Neighbouring monitoring camera adjusts acquisition parameters, wherein the clarity of acquisition parameters adjusted is higher than the acquisition parameters before adjustment
Clarity.
Optionally, the prior-warning device based on video monitoring further include:
Timing module, time and current time for being occurred according to merit determine the merit duration;
The acquisition parameters adjustment module is also used to be greater than default merit duration threshold when the merit duration
When, restore the acquisition parameters of the monitoring site camera and the neighbouring monitoring camera.
Optionally, the warning module 40 includes:
Acquiring unit, for obtaining the image data of the monitoring site camera;
Face identification unit is mentioned for identifying face picture from described image data, and from the face picture
Take out face characteristic;
The face identification unit is also used to judge whether the face characteristic matches with default face characteristic, as the people
When face feature and default face characteristic match, warning grade information corresponding with the default face characteristic is obtained;
Prewarning unit, for generating the warning information comprising the warning grade information.
The present invention also provides a kind of source of early warning based on video monitoring, being somebody's turn to do the source of early warning based on video monitoring includes:
Memory, processor, camera and be stored on the memory and can run on the processor based on video monitoring
Early warning processing routine, realized when the early warning processing routine based on video monitoring is executed by the processor it is described based on
The step of method for early warning of video monitoring.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with the early warning processing routine based on video monitoring, the early warning processing routine based on video monitoring is executed by processor
The step of method for early warning described in Shi Shixian based on video monitoring.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of method for early warning based on video monitoring, which is characterized in that the method for early warning based on video monitoring include with
Lower step:
Receive the audio data of the camera of monitoring site;
The feature of the audio data is extracted, and merit is judged whether there is according to the feature;
When being determined with merit generation, the sound source direction of the audio data is determined;
The camera of the monitoring site is directed at the sound source direction, and shoots the video in the sound source direction,
To generate warning information.
2. as described in claim 1 based on the method for early warning of video monitoring, which is characterized in that described to extract the audio data
Feature, and according to the feature judge whether there is merit occur the step of include:
Determine the signal-to-noise ratio of the audio data;
When the signal-to-noise ratio of the audio data is more than default snr threshold, the audio data is converted into text information;
Whether judge in the text information comprising preset keyword;
When in the text information including the preset keyword, it is determined with merit.
3. as described in claim 1 based on the method for early warning of video monitoring, which is characterized in that described to extract the audio data
Feature, and according to the feature judge whether there is merit occur the step of include:
Determine the noise power of the audio data;
When the noise power of the audio data is more than default noise power thresholds, it is determined with merit.
4. as described in claim 1 based on the method for early warning of video monitoring, which is characterized in that it is described when there is merit generation,
After the step of determining the sound source direction of the audio data further include:
The acquisition parameters of the camera of the monitoring site are adjusted, the clarity of acquisition parameters adjusted is higher than the bat before adjustment
Take the photograph the clarity of parameter.
5. as claimed in claim 4 based on the method for early warning of video monitoring, which is characterized in that the adjustment monitoring site
Camera acquisition parameters, the step of clarity of acquisition parameters adjusted is higher than the clarity of the acquisition parameters before adjustment
Later further include:
Obtain the network mark of the neighbouring monitoring camera at a distance from the camera of the monitoring site within the scope of pre-determined distance
Know;
Message is sent to the neighbouring monitoring camera according to the network identity, to notify the neighbouring monitoring camera adjustment
Acquisition parameters, wherein the clarity of acquisition parameters adjusted is higher than the clarity of the acquisition parameters before adjustment.
6. as claimed in claim 5 based on the method for early warning of video monitoring, which is characterized in that described according to the network identity
Message is sent to the neighbouring monitoring camera, to notify the neighbouring monitoring camera adjustment acquisition parameters, wherein after adjustment
Acquisition parameters clarity be higher than adjustment before acquisition parameters clarity the step of after further include:
The time and current time occurred according to merit determines the merit duration;
When the merit duration being greater than default merit duration threshold, restore the monitoring site camera and described
The acquisition parameters of neighbouring monitoring camera.
7. such as the method for early warning as claimed in any one of claims 1 to 6 based on video monitoring, which is characterized in that it is described will be described
The camera of monitoring site is directed at the sound source direction, to shoot the video in the sound source direction, and generates pre-
The step of alert information includes:
Obtain the image data of the monitoring site camera;
Face picture is identified from described image data, and extracts face characteristic from the face picture;
Judge whether the face characteristic matches with default face characteristic;
When the face characteristic and default face characteristic match, obtains and the corresponding warning grade of the default face characteristic is believed
Breath;
Generate the warning information comprising the warning grade information.
8. a kind of prior-warning device based on video monitoring, which is characterized in that the prior-warning device based on video monitoring includes:
Receiving module, the audio data of the camera for receiving monitoring site;
Feature processing block judges whether there is merit for extracting the feature of the audio data, and according to the feature;
Sound source estimation block, for determining the sound source direction of the audio data when being determined with merit generation;
Warning module for the camera of the monitoring site to be directed at the sound source direction, and shoots the sound
The video in source direction, to generate warning information.
9. a kind of source of early warning based on video monitoring, which is characterized in that the source of early warning based on video monitoring includes: to deposit
Reservoir, processor, camera and be stored on the memory and can run on the processor based on video monitoring
Early warning processing routine realizes such as claim 1 when the early warning processing routine based on video monitoring is executed by the processor
The step of to method for early warning described in any one of 7 based on video monitoring.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium based on view
The early warning processing routine of frequency monitoring, is realized when the early warning processing routine based on video monitoring is executed by processor as right is wanted
The step of method for early warning described in asking any one of 1 to 7 based on video monitoring.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811120943.2A CN109672853B (en) | 2018-09-25 | 2018-09-25 | Early warning method, device and equipment based on video monitoring and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811120943.2A CN109672853B (en) | 2018-09-25 | 2018-09-25 | Early warning method, device and equipment based on video monitoring and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109672853A true CN109672853A (en) | 2019-04-23 |
CN109672853B CN109672853B (en) | 2022-05-17 |
Family
ID=66142592
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811120943.2A Active CN109672853B (en) | 2018-09-25 | 2018-09-25 | Early warning method, device and equipment based on video monitoring and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109672853B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110211316A (en) * | 2019-06-05 | 2019-09-06 | 深圳市梦网百科信息技术有限公司 | A kind of monitoring and early warning method and system |
CN110706459A (en) * | 2019-10-22 | 2020-01-17 | 山东国惠安创智能物联发展有限公司 | Situation perception cabinet air conditioner system |
CN111757052A (en) * | 2020-05-20 | 2020-10-09 | 中牟县美林包装有限责任公司 | Intelligent cloud management system for packaging workshop |
CN111866454A (en) * | 2020-07-02 | 2020-10-30 | 广州博冠智能科技有限公司 | Sound and image linkage detection early warning method and device |
CN112261365A (en) * | 2020-10-19 | 2021-01-22 | 西北工业大学 | Self-contained underwater acousto-optic monitoring and recording device and recording method |
CN112396801A (en) * | 2020-11-16 | 2021-02-23 | 苏州思必驰信息科技有限公司 | Monitoring alarm method, monitoring alarm device and storage medium |
CN112435423A (en) * | 2019-08-22 | 2021-03-02 | 杭州海康威视数字技术股份有限公司 | Monitoring method and device |
CN112653876A (en) * | 2020-12-14 | 2021-04-13 | 厦门四信通信科技有限公司 | Video monitoring adjustment method, device and equipment |
CN112825553A (en) * | 2019-11-21 | 2021-05-21 | 北京声智科技有限公司 | Monitoring system, method, device, equipment and medium |
CN113055649A (en) * | 2021-03-17 | 2021-06-29 | 杭州公路工程监理咨询有限公司 | Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium |
CN113255406A (en) * | 2020-02-12 | 2021-08-13 | 浙江宇视科技有限公司 | Video alarm parameter adjusting method, device, equipment and storage medium |
CN113536983A (en) * | 2021-06-29 | 2021-10-22 | 辽宁工业大学 | Petroleum pipeline stealing positioning method based on P-RLS adaptive filtering time delay estimation |
CN115761633A (en) * | 2022-11-17 | 2023-03-07 | 深圳市阳光博睿教育技术有限公司 | Monitoring and early warning method based on application scene |
CN117218324A (en) * | 2023-10-17 | 2023-12-12 | 广东迅扬科技股份有限公司 | Camera regulation and control system and method based on artificial intelligence |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
CN102045497A (en) * | 2009-10-26 | 2011-05-04 | 鸿富锦精密工业(深圳)有限公司 | Image videotaping equipment and method for monitoring sound event |
CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
US20150237313A1 (en) * | 2012-10-12 | 2015-08-20 | Zte Corporation | Intelligent monitoring terminal and video monitoring method |
CN105227920A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of method and apparatus being undertaken monitoring by web camera |
CN105554443A (en) * | 2015-12-04 | 2016-05-04 | 浙江宇视科技有限公司 | Method and device for positioning abnormal sound source in video image |
CN105741856A (en) * | 2016-04-08 | 2016-07-06 | 王美金 | Earphone capable of prompting environmental crisis sounds in listening to music state |
JP2017028529A (en) * | 2015-07-23 | 2017-02-02 | パナソニックIpマネジメント株式会社 | Monitoring system and monitoring method |
US9749733B1 (en) * | 2016-04-07 | 2017-08-29 | Harman Intenational Industries, Incorporated | Approach for detecting alert signals in changing environments |
CN108063890A (en) * | 2016-11-09 | 2018-05-22 | 杭州海康威视数字技术股份有限公司 | A kind of monitoring device control method and device |
-
2018
- 2018-09-25 CN CN201811120943.2A patent/CN109672853B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
CN102045497A (en) * | 2009-10-26 | 2011-05-04 | 鸿富锦精密工业(深圳)有限公司 | Image videotaping equipment and method for monitoring sound event |
US20150237313A1 (en) * | 2012-10-12 | 2015-08-20 | Zte Corporation | Intelligent monitoring terminal and video monitoring method |
CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
JP2017028529A (en) * | 2015-07-23 | 2017-02-02 | パナソニックIpマネジメント株式会社 | Monitoring system and monitoring method |
CN105227920A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of method and apparatus being undertaken monitoring by web camera |
CN105554443A (en) * | 2015-12-04 | 2016-05-04 | 浙江宇视科技有限公司 | Method and device for positioning abnormal sound source in video image |
US9749733B1 (en) * | 2016-04-07 | 2017-08-29 | Harman Intenational Industries, Incorporated | Approach for detecting alert signals in changing environments |
CN105741856A (en) * | 2016-04-08 | 2016-07-06 | 王美金 | Earphone capable of prompting environmental crisis sounds in listening to music state |
CN108063890A (en) * | 2016-11-09 | 2018-05-22 | 杭州海康威视数字技术股份有限公司 | A kind of monitoring device control method and device |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110211316B (en) * | 2019-06-05 | 2021-12-21 | 深圳市梦网视讯有限公司 | Monitoring early warning method and system |
CN110211316A (en) * | 2019-06-05 | 2019-09-06 | 深圳市梦网百科信息技术有限公司 | A kind of monitoring and early warning method and system |
CN112435423A (en) * | 2019-08-22 | 2021-03-02 | 杭州海康威视数字技术股份有限公司 | Monitoring method and device |
CN112435423B (en) * | 2019-08-22 | 2022-06-03 | 杭州海康威视数字技术股份有限公司 | Monitoring method and device |
CN110706459A (en) * | 2019-10-22 | 2020-01-17 | 山东国惠安创智能物联发展有限公司 | Situation perception cabinet air conditioner system |
CN112825553A (en) * | 2019-11-21 | 2021-05-21 | 北京声智科技有限公司 | Monitoring system, method, device, equipment and medium |
CN113255406A (en) * | 2020-02-12 | 2021-08-13 | 浙江宇视科技有限公司 | Video alarm parameter adjusting method, device, equipment and storage medium |
CN111757052A (en) * | 2020-05-20 | 2020-10-09 | 中牟县美林包装有限责任公司 | Intelligent cloud management system for packaging workshop |
CN111866454A (en) * | 2020-07-02 | 2020-10-30 | 广州博冠智能科技有限公司 | Sound and image linkage detection early warning method and device |
CN112261365A (en) * | 2020-10-19 | 2021-01-22 | 西北工业大学 | Self-contained underwater acousto-optic monitoring and recording device and recording method |
CN112396801A (en) * | 2020-11-16 | 2021-02-23 | 苏州思必驰信息科技有限公司 | Monitoring alarm method, monitoring alarm device and storage medium |
CN112653876A (en) * | 2020-12-14 | 2021-04-13 | 厦门四信通信科技有限公司 | Video monitoring adjustment method, device and equipment |
CN113055649A (en) * | 2021-03-17 | 2021-06-29 | 杭州公路工程监理咨询有限公司 | Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium |
CN113536983A (en) * | 2021-06-29 | 2021-10-22 | 辽宁工业大学 | Petroleum pipeline stealing positioning method based on P-RLS adaptive filtering time delay estimation |
CN113536983B (en) * | 2021-06-29 | 2023-12-12 | 辽宁工业大学 | Petroleum pipeline stealing positioning method based on P-RLS adaptive filtering time delay estimation |
CN115761633A (en) * | 2022-11-17 | 2023-03-07 | 深圳市阳光博睿教育技术有限公司 | Monitoring and early warning method based on application scene |
CN117218324A (en) * | 2023-10-17 | 2023-12-12 | 广东迅扬科技股份有限公司 | Camera regulation and control system and method based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN109672853B (en) | 2022-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109672853A (en) | Method for early warning, device, equipment and computer storage medium based on video monitoring | |
Crocco et al. | Audio surveillance: A systematic review | |
CN110880172A (en) | Video face tampering detection method and system based on cyclic convolution neural network | |
US9761248B2 (en) | Action analysis device, action analysis method, and action analysis program | |
CN111601074A (en) | Security monitoring method and device, robot and storage medium | |
Hossain et al. | Environment classification for urban big data using deep learning | |
Ghiurcau et al. | Audio based solutions for detecting intruders in wild areas | |
WO2021036672A1 (en) | Intelligent vibration augmented reality test method and related product | |
CN110544491A (en) | Method and device for real-time association of speaker and voice recognition result thereof | |
KR20210020723A (en) | Cctv camera device having assault detection function and method for detecting assault based on cctv image performed | |
CN108898079A (en) | A kind of monitoring method and device, storage medium, camera terminal | |
CN111613240A (en) | Camouflage voice detection method based on attention mechanism and Bi-LSTM | |
CN109960969A (en) | The method, apparatus and system that mobile route generates | |
CN110765874B (en) | Monitoring method based on unmanned aerial vehicle and related product | |
CN114125806B (en) | Wireless camera detection method based on cloud storage mode of wireless network flow | |
CN110800053A (en) | Method and apparatus for obtaining event indications based on audio data | |
Omarov | Applying of audioanalytics for determining contingencies | |
CN112102623A (en) | Traffic violation identification method and device and intelligent wearable device | |
Banerjee et al. | Participatory sensing based traffic condition monitoring using horn detection | |
Spadini et al. | Sound event recognition in a smart city surveillance context | |
CN108694388B (en) | Campus monitoring method and device based on intelligent camera | |
CN110544270A (en) | method and device for predicting human face tracking track in real time by combining voice recognition | |
CN113194281B (en) | Video parsing method, device, computer equipment and storage medium | |
KR101520446B1 (en) | Monitoring system for prevention beating and cruel act | |
KR20160120018A (en) | Abnormal voice detecting method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |