CN109543538A - Obtain method, apparatus, computer equipment and the storage medium of the track of alert object - Google Patents
Obtain method, apparatus, computer equipment and the storage medium of the track of alert object Download PDFInfo
- Publication number
- CN109543538A CN109543538A CN201811237079.4A CN201811237079A CN109543538A CN 109543538 A CN109543538 A CN 109543538A CN 201811237079 A CN201811237079 A CN 201811237079A CN 109543538 A CN109543538 A CN 109543538A
- Authority
- CN
- China
- Prior art keywords
- alert
- video
- fixed point
- audio equipment
- point video
- 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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Alarm Systems (AREA)
Abstract
Present invention discloses method, apparatus, computer equipment and the storage mediums of a kind of track for obtaining alert object, the method is carried out based on Intelligent human-face identification and intelligent prediction algorithms, belong to monitoring and early warning technology field, which comprises sound and video are acquired by each fixed point video and audio equipment；Based on collected sound judge whether that alert has occurred；If alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, the alert face information identified in the collected video of fixed point video and audio equipment is reported into central server, to recycle a process at central server, alert object motion trajectory is obtained.The method, device, computer equipment and storage medium can be conducive to be quickly found out alert object with the motion profile of automatic describing alert object.
Description
Technical field
The present invention relates to monitoring and early warning technology fields, method, apparatus, meter more particularly to the track for obtaining alert object
Calculate machine equipment and storage medium.
Background technique
In the prior art, in terms of camera identifies alert, often camera is placed on a position, shoots in the position
The video of shooting is transmitted to central monitor by video, and the people that central monitor goes out monitors the people for for example stealing, plundering, so
After report a case to the security authorities, notify police to arrest.A process is needed with police's responding due to reporting a case to the security authorities, after police rushes to, suspect is early
Spot has been fled from, has been sneaked away.
Summary of the invention
Based on this, spot can be left not to alert object in the time interval of responding to solve alarm in the related technology
The technical issues of easily arresting the present invention provides a kind of method, apparatus of track for obtaining alert object, computer equipment and is deposited
Storage media.
In a first aspect, providing a kind of method of track for obtaining alert object, comprising:
Sound and video are acquired by each fixed point video and audio equipment；
Based on collected sound judge whether that alert has occurred；
If alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, by the fixed point video and audio equipment
The alert face information identified in collected video is reported to central server, to recycle following mistake at central server
Journey: alert information is pushed to positioned at the fixed point video and audio equipment for identifying alert face information with upper one by central server
Distance is other fixed point video and audio equipments within preset distance, so that other fixed point video and audio equipments are periodically by the view of acquisition
The face information identified in frequency reports central server, determines whether for central server for the alert face information, wherein
Identify that the fixed point video and audio equipment of the alert face information by the track that the time sequencing of identification connects into is alert object
Track.
Wherein, the method is used for the video and audio equipment net being formed by connecting by multiple fixed point video and audio equipments.
The position for the multiple fixed point video and audio equipment that the video and audio equipment net includes in one of the embodiments,
It is following to choose:
Position candidate point is chosen according to pre-defined rule on three-dimensional map；
Obtain the unit time flow of the people of position candidate point；
Based on the unit time flow of the people compared with flow of the people threshold value, it is described more that arrangement is chosen from position candidate point
The position of a fixed point video and audio equipment.
The pre-defined rule is by one of following position or a variety of as position candidate in one of the embodiments,
Point:
Crossroad, T-shaped road junction crosspoint；
The entrance of building, outlet；
Cell, square, school playground, park, underground parking entrance；
The lift port of the entrance, civilian every layer of building of every unit of each floor, step ladder way in building；
The entrance of every bottom commerce of building；
The representative location point chosen in the every predetermined number of layers of building；
Bridge, overline bridge, highway entrance；
Every the location point of preset distance setting on highway.
It is described in one of the embodiments, to judge whether that alert, which has occurred, includes: based on collected sound
Text is converted by collected sound；
By the comparison in text language mode corresponding with alert library, judge whether that alert has occurred.
Alert information is pushed to and is located at and upper identification responding by the central server in one of the embodiments,
After the distance of the fixed point video and audio equipment of feelings face information is other fixed point video and audio equipment within preset distance, if pre-
In fixing time, alert face information is not determined from the face information that other fixed point video and audio equipments report, then is executed:
When according to the position of the upper fixed point video and audio equipment for determining alert face information twice and determining twice interval
Between, determine the movement velocity of alert object；
With the speed and the predetermined time, estimate that alert object current location determines that alert face is believed to the last time
The distance of the position of the fixed point video and audio equipment of breath；
The position of the upper fixed point video and audio equipment for determining alert face information twice is linked to be straight line；
By the straight line from last time determine alert face information fixed point video and audio equipment position extend described in away from
From the endpoint after extension is the alert object current location of estimation.
The fixed point video and audio equipment camera is once it is determined that responding feelings face information, knows in one of the embodiments,
Chu not be abnormal, just automatically turn on camera shooting high definition mode.
The fixed point video and audio equipment is once it is determined that responding feelings face information, is switched on and takes the photograph in one of the embodiments,
As wide-angle mode.
The fixed point video and audio equipment is once it is determined that camera described in responding feelings face information in one of the embodiments,
Once identifying exception, then according to the alert face information identified from collected video, the fixed point video and audio is rotated
Equipment identifies the face taken, and with the face rotating camera in picture, makes the fixed point video and audio equipment camera
Face alert face.
The alert face information that the basis is identified from collected video in one of the embodiments, rotation
The fixed point video and audio equipment, comprising:
It determines from the center of the face identified in collected video at a distance from video hub position；
By searching for the face identified in video center at a distance from video hub position, with the center deviation of face
The angle collation table for pinpointing the axis of video and audio equipment determines the angle of the axis of the center deviation fixed point video and audio equipment of face
Degree；
According to the angle, the fixed point video and audio equipment is rotated.
The camera once identifies exception in one of the embodiments, then collects the people's that identification is photographed
Sound, and with the sound rotating camera being collected into, make camera face face.
It is described in one of the embodiments, to judge whether that it includes: that acquire that alert, which has occurred, based on collected sound
Whether the first machine learning model of voice input arrived the judging result of alert is had occurred by the output of the first machine learning model,
Wherein first machine learning model is trained as follows:
By in positive and negative sample set each positive sample or negative sample input the first machine learning model, wherein positive sample is
From the sound of prior known alert collection in worksite, negative sample is from the sound of prior known non-alert collection in worksite, machine
Learning model exports the judging result that alert whether has occurred, if positive sample output does not occur the judging result of alert,
Or the judging result that alert occurs is exported for negative sample, the first machine learning model is adjusted, keeps the first machine learning model defeated
Opposite judging result out.
In one of the embodiments, after based on collected sound judging whether that alert has occurred, the method
Further include:
If it is determined that alert has occurred, the menace level of alert is determined；
According to the menace level of alert, alert information is sent to different objects.
The menace level of the determining alert includes: by collected voice input second in one of the embodiments,
Machine learning model, by the menace level of the second machine learning model output alert, wherein second machine learning model is such as
Lower training:
Each sample sound of sample sound collection is inputted into the second machine learning model, wherein the second machine learning of input
The sample sound of model is from the sample sound of prior known alert collection in worksite, and each sample sound is equipped with various serious etc.
The label of grade, the judging result of the menace level of the second machine learning model output alert, if the judging result and mark
Inconsistent, the second machine learning model of adjustment is signed, the consistent judging result of the second machine learning model output is made.
The language mode library is specific for the place of the fixed point video and audio equipment application in one of the embodiments,
's.
In one of the embodiments, the method also includes: in response to the fixed point video and audio equipment self-test to damage,
Report damage information to central server.
The shooting ginseng that video and audio equipment is pinpointed to one is received in response to central server in one of the embodiments,
Several change instructions, the bat that central server adjustment passes through the adjustable fixed point video and audio equipment camera of central server
Take the photograph parameter.
Second aspect provides a kind of device of track for obtaining alert object, comprising:
Information acquisition unit, for acquiring sound and video by each fixed point video and audio equipment；
Alert judging unit, for based on collected sound judging whether that alert has occurred；
Alert reporting unit, if alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one,
The alert face information identified in the collected video of fixed point video and audio equipment is reported into central server, in center
Following procedure is recycled at server: alert information is pushed to be located at by central server identifies alert face information with upper one
The distance of fixed point video and audio equipment be other fixed point video and audio equipments within preset distance so that this other fixed point video and audios
The face information identified in the video of acquisition is periodically reported central server by equipment, is determined whether for central server for this
Alert face information, wherein identifying what the fixed point video and audio equipment of the alert face information was connected by the time sequencing of identification
Track is the track of alert object.
The third aspect provides a kind of computer equipment, including memory and processor, is stored with meter in the memory
Calculation machine readable instruction, when the computer-readable instruction is executed by the processor, so that processor execution is described above
The step of obtaining the method for the track of alert object.
Fourth aspect provides a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction
When being executed by one or more processors, so that one or more processors execute the track described above for obtaining alert object
The step of method.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Method, apparatus, computer equipment and the storage medium of the track of above-mentioned acquisition alert object, by passing through each fixed point
Video and audio equipment acquires sound and video；Based on collected sound judge whether that alert has occurred；If based on a fixed point
Alert has occurred in the sound judgement of video and audio equipment acquisition, the police that will be identified in the collected video of fixed point video and audio equipment
Sweet heart's face information reporting is to central server, to recycle following procedure at central server: central server is by alert information
It is pushed at a distance from the fixed point video and audio equipment for being located at and identifying alert face information with upper one as its within preset distance
He pinpoints video and audio equipment, so that other fixed point video and audio equipments periodically will be in the face information that identified in the video of acquisition
Central server is reported, is determined whether for central server for the alert face information, wherein identifying the alert face information
Fixed point video and audio equipment is the track of alert object by the track that the time sequencing of identification connects into.It is alert to reach automatic describing
The motion profile of feelings object is conducive to be quickly found out alert object.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Fig. 1 is the implementation environment figure of the method for the track of the acquisition alert object provided in one embodiment.
Fig. 2 is a kind of flow chart of the method for track for obtaining alert object shown according to an exemplary embodiment.
Fig. 3 is respectively to pinpoint video and audio in the method for the track of the acquisition alert object shown in corresponding embodiment according to fig. 2 to set
The flow chart of the selection step of the position of back-up cloth.
Fig. 4 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S120 it is specific
The flow chart of realization.
Fig. 5 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S130 supplement
The flow chart of the specific implementation of scheme.
Fig. 6 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S130 it is specific
The flow chart of realization.
Fig. 7 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S120 it is specific
The another flow chart realized.
Fig. 8 is a kind of block diagram of the device of track for obtaining alert object shown according to an exemplary embodiment.
Fig. 9 schematically shows the electronic equipment example frame of a kind of method of track for realizing above-mentioned acquisition alert object
Figure.
The computer-readable of method that Figure 10 schematically shows a kind of track for realizing above-mentioned acquisition alert object is deposited
Storage media.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the implementation environment figure of the method for the track of the acquisition alert object provided in one embodiment, such as Fig. 1 institute
Show, in the implementation environment, is set including central server 100 and the whole distributed fixed point video and audio for being distributed in each location point
Standby 200.
Each fixed point video and audio equipment 200 acquires sound and video；Based on collected sound judge whether that alert has occurred；
If alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, and the fixed point video and audio equipment is collected
The alert face information identified in video is reported to central server, to recycle following procedure at central server: center
Alert information is pushed at a distance from the fixed point video and audio equipment for being located at and identifying alert face information with upper one by server
Other fixed point video and audio equipments within preset distance, so that other fixed point video and audio equipments will periodically be known in the video of acquisition
Not Chu face information report central server, determine whether for central server for the alert face information, wherein identifying
The fixed point video and audio equipment of the alert face information is the track of alert object by the track that the time sequencing of identification connects into.
It should be noted that the central server 100 can be desktop computer server, huge computer servers, cloud
Server and server cluster etc., however, it is not limited to this.The fixed point video and audio equipment 200 can be monitoring camera, intelligence
The one or more of energy video camera, electronic eyes, electronic peephole viewer etc., however, it is not limited to this.Central server 100 and each fixed point
Video and audio equipment 200 can pass through bluetooth, USB (Universal Serial Bus, universal serial bus) or other communications
Connection type is attached, and the present invention is herein with no restrictions.
As shown in Fig. 2, in one embodiment it is proposed that a kind of method for the track for obtaining alert object, the acquisition
The method of the track of alert object can be applied to the video and audio equipment net that above-mentioned each fixed point video and audio equipment 200 is formed by connecting
In, it can specifically include following steps:
Step S110 acquires sound and video by each fixed point video and audio equipment；
Step S120 based on collected sound judges whether that alert has occurred；
Step S130, if alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, by the fixed point
The alert face information identified in the collected video of video and audio equipment is reported to central server, at central server
Circulation following procedure: alert information is pushed to be located at by central server identifies that the fixed point of alert face information regards with upper one
The distance of audio frequency apparatus is other fixed point video and audio equipments within preset distance, so that other fixed point video and audio equipments are regular
The face information identified in the video of acquisition is reported into central server, is determined whether for central server for the alert face
Information, wherein identifying that the fixed point video and audio equipment of the alert face information by the track that the time sequencing of identification connects into is police
The track of feelings object.
In this way, according to the track of alert object, so that it may be quickly found out alert object.
Optionally, Fig. 3 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in respectively fixed point view
The datail description of the selection step of the position of audio frequency apparatus distribution, in the method for the track of the acquisition alert object, each fixed point is regarded
The selection step of audio frequency apparatus distributed point may comprise steps of:
Step S210 chooses position candidate point according to pre-defined rule on three-dimensional map；
Step S220 obtains the unit time flow of the people of position candidate point；
Step S230 is chosen from position candidate point based on the unit time flow of the people compared with flow of the people threshold value
Arrange the position of the multiple fixed point video and audio equipment.
Wherein, the position of each fixed point video and audio equipment distribution refers to the distributed in three dimensions of fixed point video and audio equipment, i.e.,
Certain point on two-dimensional map increases the height coordinate of fixed point video and audio distribution apparatus arrangement.For example, two-dimensional map certain
A bit, it is possible to inside building, require one fixed point video and audio equipment of arrangement in different floors.The acquisition position candidate
The flow of the people of the unit time of point can crawl the position candidate point from traffic control department website or map application server
Unit time flow of the people, method of determination can be according to satellite sounding result, vehicle drivers, pedestrian's terminal report and it is existing
There is the detection of the existing video and audio equipment of building, road to determine.For example, traffic control department can more depend on satellite and view
The detection of audio frequency apparatus, map application server are reported by vehicle drivers, the automatic of pedestrian's terminal.The map is answered
It is, for example, Amap, Google Maps, Baidu map and Tencent's map etc. with server, the unit time is, for example, small half
When, a hour, two hours etc..
Optionally, in the corresponding embodiment of Fig. 3, the pre-defined rule in step S210 is by one of following position
Or it is a variety of as position candidate point:
Crossroad, T-shaped road junction crosspoint；
The entrance of building, outlet；
Cell, square, school playground, park, underground parking entrance；
The lift port of the entrance, civilian every layer of building of every unit of each floor, step ladder way in building；
The entrance of every bottom commerce of building；
The representative location point chosen in the every predetermined number of layers of building；
Bridge, overline bridge, highway entrance；
Every the location point of preset distance setting on highway.
Optionally, Fig. 4 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S120
Datail description, step S120 may comprise steps of:
Collected sound is converted text by step S121；
Step S122 by the comparison in text language mode corresponding with alert library judges whether that alert has occurred.
Corresponding early warning language is placed in the language mode library, the early warning language is, for example, " messenger ", " has small
Steathily ", " robbery ", " help " etc..
Optionally, Fig. 5 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S130
Further describe, alert information is pushed to be located at by the central server in step s 130 with upper one identifies alert
After the distance of the fixed point video and audio equipment of face information is other fixed point video and audio equipment within preset distance, if predetermined
In time, alert face information is not determined from the face information that other fixed point video and audio equipments report, then is executed as follows
Step:
Step S140, according to it is upper determine twice alert face information fixed point video and audio equipment position and twice really
Fixed interval time determines the movement velocity of alert object；
Step S150, with the speed and the predetermined time, estimation alert object current location to last time is determined
The distance of the position of the fixed point video and audio equipment of alert face information；
The position of the upper fixed point video and audio equipment for determining alert face information twice is linked to be straight line by step S160；
The straight line is determined the position extension of the fixed point video and audio equipment of alert face information by step S170 from the last time
The distance out, the endpoint after extension are the alert object current location of estimation.
In this way, can also depict the fortune of alert object under other fixed point video and audio equipments for a long time not corresponding situation
Dynamic rail mark, quickly and easily to find alert object.
Optionally, in the corresponding embodiment of Fig. 2, in step s 130, the fixed point video and audio equipment is once it is determined that responding
Feelings face information is switched on camera shooting high definition mode.
In this way, the face information of the offender taken is apparent, comparison is improved when in order to compare face information
Accuracy is avoided non-alert Object identifying being alert object, more accurately be arrested to realize.
Optionally, in the corresponding embodiment of Fig. 2, in step s 130, the fixed point video and audio equipment is once it is determined that responding
Feelings face information is switched on camera shooting wide-angle mode.
In this way, can make the image of shooting has the deeper depth of field and wider array of visual angle, to take more contents, more
Alert object is captured on a large scale, avoids shooting blind angle amount.
Optionally, in the corresponding embodiment of Fig. 2, in step s 130, the fixed point video and audio equipment is once it is determined that responding
Feelings face information rotates the fixed point video and audio equipment then according to the alert face information identified from collected video,
Make the fixed point video and audio equipment face alert face.
Optionally, Fig. 6 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S130
Further describe, in step s 130, the alert face information that the basis is identified from collected video, rotate institute
State fixed point video and audio equipment specific steps include:
Step S310 is determined from the center of the face identified in collected video at a distance from video hub position；
Step S320, by searching for the face identified in video center at a distance from video hub position and face
Center deviation fixed point video and audio equipment axis angle collation table, determine the center deviation fixed point video and audio equipment of face
The angle of axis；
Step S330 rotates the fixed point video and audio equipment according to the angle.
Since the fixed point video and audio equipment can be rotated with the face in picture, the face information of shooting can be more clear
It is clear, the accuracy of comparison is improved when comparing face information in order to central server, avoids non-alert Object identifying being alert
Object is more accurately arrested to realize.
Optionally, in the method for the track of the acquisition alert object shown in Fig. 2 corresponding embodiment, step S120 can be with
The following steps are included:
By collected the first machine learning model of voice input, whether police is had occurred by the output of the first machine learning model
The judging result of feelings, wherein first machine learning model is trained as follows:
By in positive and negative sample set each positive sample or negative sample input the first machine learning model, wherein positive sample is
From the sound of prior known alert collection in worksite, negative sample is from the sound of prior known non-alert collection in worksite, machine
Learning model exports the judging result that alert whether has occurred, if positive sample output does not occur the judging result of alert,
Or the judging result that alert occurs is exported for negative sample, the first machine learning model is adjusted, keeps the first machine learning model defeated
Opposite judging result out.
Due to positive sample and negative sample be it is known, these samples are inputted into the first machine learning model one by one, by machine
Learning model export its whether be abnormal conditions judgement as a result, and whether be abnormal conditions be it is known, therefore, once machine
The judgement result and truth of learning model are inconsistent, with regard to the connection weight in regularized learning algorithm model, make its export result with
It is expected consistent.Study is exactly constantly to change the connection weight of network under the stimulation of extraneous input sample.The essence of study is
Dynamic adjustment is carried out to each connection weight.The thought of neural network algorithm is: error i.e. reality output and phase after utilizing output
Hope the error of the direct preceding conducting shell of the estimation error output layer of output, then with the error of this estimation error more preceding layer, so
Anti-pass in layer is gone down, and the estimation error of every other each layer is just obtained.BP neural network model topology structure includes
Input layer, hidden layer and output layer.After training machine learning model, any recording is inputted into the machine learning model, machine
Learning model can export the recording that the recording is abnormal conditions.By the method for machine learning, it is different that identification can be improved
The accuracy rate of ordinary affair part.
Optionally, Fig. 7 be according to fig. 2 shown in corresponding embodiment acquisition alert object track method in step S120
Datail description, based on collected sound judge whether that alert has occurred after step S120 may comprise steps of:
Step S125 determines the menace level of alert if it is determined that alert has occurred；
Step S126 sends alert information to different objects according to the menace level of alert.
For example, menace level can be divided into general exception and severely subnormal.In the case where general exception, it can incite somebody to action
Corresponding warning information is sent to corresponding property or safety and protection monitoring room；In the case where advanced exception, then by corresponding alarm
Information is sent to public security control and command center.Realize the flexible reply of different severity anomalous events.
Optionally, in the method for the track of the acquisition alert object shown in Fig. 7 corresponding embodiment, step S125 can be with
The following steps are included:
By collected the second machine learning model of voice input, by the serious etc. of the second machine learning model output alert
Grade, wherein second machine learning model is trained as follows:
Each sample sound of sample sound collection is inputted into the second machine learning model, wherein the second machine learning of input
The sample sound of model is from the sample sound of prior known alert collection in worksite, and each sample sound is equipped with various serious etc.
The label of grade, the judging result of the menace level of the second machine learning model output alert, if the judging result and mark
Inconsistent, the second machine learning model of adjustment is signed, the consistent judging result of the second machine learning model output is made.
Optionally, in the method for the track of the acquisition alert object shown in Fig. 2 corresponding embodiment, the language mode library
It is specific for the place of the fixed point video and audio equipment application.
Optionally, such as completely different, the language in warehouse of the language rule in the language mode library in warehouse and jeweler's shop
Pattern base has the more language rule about stealing, and then has the more language about robbery in the language mode library of jeweler's shop
Speech rule, to improve the accuracy of identification of anomalous event for individual scene.
Optionally, in the method for the track of the acquisition alert object shown in Fig. 2 corresponding embodiment, the acquisition alert pair
The method of the track of elephant further include:
In response to the fixed point video and audio equipment self-test to damage, report damage information to central server.
Optionally, it in the method for the track of the acquisition alert object shown in Fig. 2 corresponding embodiment, is taken when in response to center
When business device receives the change instruction for the acquisition parameters for pinpointing video and audio equipment to one, central server adjusts the fixed point view
The acquisition parameters of audio frequency apparatus.
As shown in figure 8, in one embodiment, providing a kind of device of track for obtaining alert object, the acquisition
The device of the track of alert object can integrate in above-mentioned distributed fixed point video and audio equipment, can specifically include information and adopts
Collect unit 210, alert judging unit 220, alert reporting unit 230.
Information acquisition unit 210, for acquiring sound and video by each fixed point video and audio equipment；
Alert judging unit 220, for based on collected sound judging whether that alert has occurred；
Alert reporting unit 230, if police has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one
The alert face information identified in the collected video of fixed point video and audio equipment is reported to central server by feelings, with
Following procedure is recycled at central server: alert information is pushed to be located at by central server identifies alert face with upper one
The distance of the fixed point video and audio equipment of information is other fixed point video and audio equipments within preset distance, so that other fixed point views
The face information identified in the video of acquisition is periodically reported central server by audio frequency apparatus, is determined whether for central server
For the alert face information, wherein identifying that the fixed point video and audio equipment of the alert face information is connected by the time sequencing of identification
At track be alert object track.
The function of modules and the realization process of effect are specifically detailed in the rail of above-mentioned acquisition alert object in above-mentioned apparatus
The realization process of step is corresponded in the method for mark, details are not described herein.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Fig. 9.The electronics that Fig. 9 is shown
Equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 9, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in Figure 2, by each
Pinpoint video and audio equipment acquisition sound and video；Step S120 based on collected sound judges whether that alert has occurred；Step
S130 adopts the fixed point video and audio equipment if alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one
The alert face information identified in the video collected is reported to central server, to recycle following mistake at central server
Journey: alert information is pushed to positioned at the fixed point video and audio equipment for identifying alert face information with upper one by central server
Distance is other fixed point video and audio equipments within preset distance, so that other fixed point video and audio equipments are periodically by the view of acquisition
The face information identified in frequency reports central server, determines whether for central server for the alert face information, wherein
Identify that the fixed point video and audio equipment of the alert face information by the track that the time sequencing of identification connects into is alert object
Track.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 500 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 10, describing the program product for realizing the above method of embodiment according to the present invention
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (18)
1. a kind of method for the track for obtaining alert object, which is characterized in that the method by multiple fixed point video and audios for being set
The standby video and audio equipment net being formed by connecting, which comprises
Sound and video are acquired by each fixed point video and audio equipment；
Based on collected sound judge whether that alert has occurred；
If alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, which is acquired
To video in the alert face information that identifies be reported to central server, to recycle following procedure at central server:
Central server by alert information be pushed to upper one identify alert face information fixed point video and audio equipment away from
From for other fixed point video and audio equipments within preset distance, so that this other fixed point video and audio equipments are periodically by the video of acquisition
In the face information that identifies report central server, determine whether for central server for the alert face information, wherein knowing
Not Chu the alert face information the track that connects by the time sequencing of identification of fixed point video and audio equipment be alert object rail
Mark.
2. the method as described in claim 1, which is characterized in that the multiple fixed point that the video and audio equipment net includes regards sound
It chooses as follows the position of frequency equipment:
Position candidate point is chosen according to pre-defined rule on three-dimensional map；
Obtain the unit time flow of the people of position candidate point；
Based on the unit time flow of the people compared with flow of the people threshold value, it is the multiple fixed that arrangement is chosen from position candidate point
The position of point video and audio equipment.
3. method according to claim 2, which is characterized in that the pre-defined rule is by one of following position or a variety of
As position candidate point:
Crossroad, T-shaped road junction crosspoint；
The entrance of building, outlet；
Cell, square, school playground, park, underground parking entrance；
The lift port of the entrance, civilian every layer of building of every unit of each floor, step ladder way in building；
The entrance of every bottom commerce of building；
The representative location point chosen in the every predetermined number of layers of building；
Bridge, overline bridge, highway entrance；
Every the location point of preset distance setting on highway.
4. the method as described in claim 1, which is characterized in that described based on collected sound to judge whether that alert has occurred
Include:
Text is converted by collected sound；
By the comparison in text language mode corresponding with alert library, judge whether that alert has occurred.
5. the method as described in claim 1, which is characterized in that the central server by alert information be pushed to be located at it is upper
One distance for identifying the fixed point video and audio equipment of alert face information is that other fixed point video and audios within preset distance are set
After standby, if in the given time, not determining alert face from the face information that other fixed point video and audio equipments report
Information then executes:
According to the position of the upper fixed point video and audio equipment for determining alert face information twice and interval time determining twice,
Determine the movement velocity of alert object；
With the speed and the predetermined time, estimate that alert face information is determined to last in alert object current location
Pinpoint the distance of the position of video and audio equipment；
The position of the upper fixed point video and audio equipment for determining alert face information twice is linked to be straight line；
The straight line is extended into the distance from the position of the last fixed point video and audio equipment for determining alert face information, is prolonged
Endpoint after stretching is the alert object current location of estimation.
6. the method as described in claim 1, which is characterized in that the fixed point video and audio equipment is once it is determined that responding sweet heart's face is believed
Breath is switched on camera shooting high definition mode.
7. the method as described in claim 1, which is characterized in that the fixed point video and audio equipment is once it is determined that responding sweet heart's face is believed
Breath is switched on camera shooting wide-angle mode.
8. the method as described in claim 1, which is characterized in that the fixed point video and audio equipment is once it is determined that responding sweet heart's face is believed
Breath rotates the fixed point video and audio equipment, it is described fixed to make then according to the alert face information identified from collected video
Point video and audio equipment face alert face.
9. method according to claim 8, which is characterized in that the alert people that the basis is identified from collected video
Face information rotates the fixed point video and audio equipment, comprising:
It determines from the center of the face identified in collected video at a distance from video hub position；
It is pinpointed at a distance from video hub position with the center deviation of face by searching for the center of the face identified in video
The angle collation table of the axis of video and audio equipment determines the angle of the axis of the center deviation fixed point video and audio equipment of face；
According to the angle, the fixed point video and audio equipment is rotated.
10. the method as described in claim 1, which is characterized in that described based on collected sound to judge whether that police has occurred
Feelings include: whether collected the first machine learning model of voice input is had occurred police by the output of the first machine learning model
The judging result of feelings, wherein first machine learning model is trained as follows:
By each positive sample or negative sample the first machine learning model of input in positive and negative sample set, wherein positive sample is to be engaged in
The sound of alert collection in worksite known to elder generation, negative sample are from the sound of prior known non-alert collection in worksite, machine learning
Model exports the judging result that alert whether has occurred, if exporting the judging result that alert does not occur or right for positive sample
The judging result that alert occurs is exported in negative sample, is adjusted the first machine learning model, is made the first machine learning model output phase
Anti- judging result.
11. the method as described in claim 1, which is characterized in that based on collected sound judge whether that alert has occurred
Later, the method also includes:
If it is determined that alert has occurred, the menace level of alert is determined；
According to the menace level of alert, alert information is sent to different objects.
12. method as claimed in claim 11, which is characterized in that the menace level of the determining alert includes: that will collect
The second machine learning model of voice input, by the second machine learning model output alert menace level, wherein described second
Machine learning model is trained as follows:
Each sample sound of sample sound collection is inputted into the second machine learning model, wherein the second machine learning model of input
Sample sound be from the sample sound of prior known alert collection in worksite, each sample sound is equipped with various menace levels
Label, the judging result of the menace level of the second machine learning model output alert, if the judging result and label are not
Unanimously, the second machine learning model is adjusted, the second machine learning model is made to export consistent judging result.
13. method as claimed in claim 4, which is characterized in that the language mode library is specific for the fixed point video and audio
The place of equipment application.
14. the method as described in claim 1, which is characterized in that the method also includes: it is set in response to the fixed point video and audio
Standby self-test reports damage information to central server to damage.
15. the method as described in claim 1, which is characterized in that received in response to central server and regard sound to a fixed point
The change of the acquisition parameters of frequency equipment instructs, and central server adjusts the acquisition parameters of the fixed point video and audio equipment.
16. a kind of device for the track for obtaining alert object, which is characterized in that described device includes:
Information acquisition unit, for acquiring sound and video by each fixed point video and audio equipment；
Alert judging unit, for based on collected sound judging whether that alert has occurred；
Alert reporting unit, if alert has occurred in the sound judgement for pinpointing video and audio equipment acquisition based on one, by this
The alert face information identified in the fixed point collected video of video and audio equipment is reported to central server, in central service
Following procedure is recycled at device: alert information is pushed to be located at by central server identifies determining for alert face information with upper one
The distance of point video and audio equipment is other fixed point video and audio equipments within preset distance, so that other fixed point video and audio equipments
The face information identified in the video of acquisition is periodically reported into central server, is determined whether for central server for the alert
Face information, wherein identifying the track that the fixed point video and audio equipment of the alert face information is connected by the time sequencing of identification
For the track of alert object.
17. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, institute
When stating computer-readable instruction and being executed by the processor, so that the processor executes such as any one of claims 1 to 13
The method.
18. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the method as described in any one of claims 1 to 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811237079.4A CN109543538A (en) | 2018-10-23 | 2018-10-23 | Obtain method, apparatus, computer equipment and the storage medium of the track of alert object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811237079.4A CN109543538A (en) | 2018-10-23 | 2018-10-23 | Obtain method, apparatus, computer equipment and the storage medium of the track of alert object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543538A true CN109543538A (en) | 2019-03-29 |
Family
ID=65844987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811237079.4A Pending CN109543538A (en) | 2018-10-23 | 2018-10-23 | Obtain method, apparatus, computer equipment and the storage medium of the track of alert object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543538A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671234A (en) * | 2019-01-04 | 2019-04-23 | 北京中星微人工智能芯片技术有限公司 | A kind of alarm method and device of monitoring device |
| 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 |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101501564A (en) * | 2006-08-03 | 2009-08-05 | 国际商业机器公司 | Video surveillance system and method with combined video and audio recognition |
| 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 |
-
2018
- 2018-10-23 CN CN201811237079.4A patent/CN109543538A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101501564A (en) * | 2006-08-03 | 2009-08-05 | 国际商业机器公司 | Video surveillance system and method with combined video and audio recognition |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 梁鹏;刘晓勇;郝刚;肖思源;何显康;: "基于人脸识别和无线射频识别的行人移动轨迹监控系统及实现", 广东技术师范学院学报, no. 11 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109671234A (en) * | 2019-01-04 | 2019-04-23 | 北京中星微人工智能芯片技术有限公司 | A kind of alarm method and device of monitoring device |
| 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 |
| WO2021159604A1 (en) * | 2020-02-12 | 2021-08-19 | 中车唐山机车车辆有限公司 | Monitoring system, monitoring method, and monitoring device for railway train |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11941887B2 (en) | Scenario recreation through object detection and 3D visualization in a multi-sensor environment | |
| US12431024B2 (en) | Providing autonomous vehicle assistance | |
| US11854136B2 (en) | Monitoring a scene to analyze an event using a plurality of image streams | |
| US11748896B2 (en) | Object tracking method and apparatus, storage medium, and electronic device | |
| CN112955900B (en) | Intelligent Video Surveillance System and Method | |
| US10997430B1 (en) | Dangerous driver detection and response system | |
| US10848719B2 (en) | System and method for gate monitoring during departure or arrival of an autonomous vehicle | |
| CN105913559B (en) | A kind of ATM in bank intelligent control method based on body-sensing technology | |
| US10997832B1 (en) | Augmented reality based dynamic guidance | |
| JP2018173914A (en) | Image processing system, imaging apparatus, learning model creation method, information processing apparatus | |
| WO2021095351A1 (en) | Monitoring device, monitoring method, and program | |
| US20220292941A1 (en) | Asset tracking and protection | |
| CN109543538A (en) | Obtain method, apparatus, computer equipment and the storage medium of the track of alert object | |
| CN106294724A (en) | A kind of night watching track acquisition methods and device | |
| EP4071728B1 (en) | Artificial intelligence model integration and deployment for providing a service | |
| WO2020024552A1 (en) | Road safety monitoring method and system, and computer-readable storage medium | |
| US11500396B2 (en) | Systems and methods for electronic monitoring and protection | |
| JP7479496B2 (en) | System and method for identifying obstacles and hazards along a route - Patents.com | |
| KR102043922B1 (en) | A cctv divided management system and method it | |
| CN114677848B (en) | Perception warning system, method, device and computer program product | |
| Atzori et al. | Heimdall: an AI-based infrastructure for traffic monitoring and anomalies detection | |
| JP2021124633A (en) | Map generation system and map generation program | |
| CN116630888A (en) | Unmanned aerial vehicle monitoring method, unmanned aerial vehicle monitoring device, electronic equipment and storage medium | |
| KR102501084B1 (en) | Method of managing safety through tracking movement paths based on artificial intelligence and apparatus thereof | |
| CN114677605B (en) | Lost property detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI) Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI) |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240621 |
|
| AD01 | Patent right deemed abandoned |