CN106033530A - Identification method and apparatus for suspected person - Google Patents
Identification method and apparatus for suspected person Download PDFInfo
- Publication number
- CN106033530A CN106033530A CN201510106082.2A CN201510106082A CN106033530A CN 106033530 A CN106033530 A CN 106033530A CN 201510106082 A CN201510106082 A CN 201510106082A CN 106033530 A CN106033530 A CN 106033530A
- Authority
- CN
- China
- Prior art keywords
- trace information
- event trace
- suspect
- video data
- people
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012800 visualization Methods 0.000 claims description 14
- 230000005021 gait Effects 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000008878 coupling Effects 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 5
- 238000005859 coupling reaction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 8
- 238000013480 data collection Methods 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 16
- 230000001815 facial effect Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010000210 abortion Diseases 0.000 description 1
- 231100000176 abortion Toxicity 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000700 radioactive tracer Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides an identification method and apparatus for a suspected person. The method comprises: video data are collected; according to the video data and position information of the video data collection, moving track information of a person in the video data is recorded; comparison and analysis are carried out on the moving track information and preset moving track information; and according to a comparison and analysis result, dubiety of the person corresponding to the moving track information is determined. With the method and apparatus, problems that a suspected person can not be screened and identified automatically and the checking efficiency is low in the prior art can be solved. Therefore, a suspected person can be screened and identified automatically without any extra device; and the checking efficiency is improved.
Description
Technical field
The present invention relates to big data technique field, one utilizes big data technique on airport, station, bank,
In the public place of the densely populated place such as market, the method automatically identifying a suspect.
Background technology
Along with the density of urban population increases so that in public places, such as my airport, station and bank et al.
The safety check protected working of the intensive public place of member requires to improve constantly.The management method of public place is main at present
For installing monitoring camera and safety check machine, accredit police and patrolman, mainly utilize manpower to arrange
Look into a suspect.But in city as high in population density Beijing, Shanghai, and meet on and off duty, joint
Period population peak phase of holiday etc., the public place such as AT STATION, it may appear that large-scale artificial abortion, pass through people
Work investigation suspicion personnel, not only inefficiency, and be easily caused a large amount of personnel and be detained.
Due to being widely used of Video Supervision Technique, the face in video can be carried out by computer technology
Identify and followed the trail of, but its can not help safety law enforcement personnel in densely populated public place from
Dynamic identification a suspect, thus a suspect automatically identified is given " special care ", the criminal of reduction
The probability that crime molecule is succeeded, the generation of the criminal activity of preventing damage public safety.
For cannot automatic screening identification a suspect and investigate inefficient present in correlation technique
Problem, the most not yet proposes the scheme effectively solved.
Summary of the invention
The present invention provides a kind of a suspect's recognition methods and device, at least to solve present in prior art
Cannot automatic screening identification a suspect and investigate inefficient problem.
According to an aspect of the invention, it is provided a kind of a suspect's recognition methods, including
Gather video data;
According to described video data and the positional information of the described video data of collection, record described video data
The event trace information of middle people;
Described event trace information is compared with default event trace information;
The result analyzed according to comparison, it is judged that the dubiety of the people that described event trace information is corresponding.
Preferably, it is characterised in that the result analyzed according to comparison, it is judged that described event trace information is corresponding
The dubiety of people includes:
In the feelings that result is described event trace information and described default event trace information matches that comparison is analyzed
Under condition, determine the artificial normal personnel that described event trace information is corresponding;
The result analyzed in comparison is that described event trace information is unmatched with described default event trace information
In the case of, determine the artificial a suspect that described event trace information is corresponding.
Preferably, in the case of judging the artificial a suspect that described event trace information is corresponding, described side
Method also includes: is shown by monitoring device visualization and is followed the trail of described a suspect.
Preferably, in the case of judging the artificial a suspect that described event trace information is corresponding, described side
Method also includes: the information of described a suspect with the online wanted criminal in public security system is identified comparison.
Preferably, according to described data and the positional information of the described video data of collection, described video counts is recorded
After the event trace information of middle people, described method also includes: according to the active rail of the people of the magnanimity recorded
Mark information, determines described default event trace information.
Preferably, described event trace information and/or described default event trace information include at least one of:
The course of action of the people that the positional information calculation according to face tracking technology and the described video data of collection goes out;
The gait of march of people;The time of staying of people.
According to a further aspect in the invention, also provide for a kind of a suspect and identify device, it is characterised in that including:
Acquisition module, is used for gathering video data;
Logging modle, for according to described video data and the positional information of the described video data of collection, recording institute
State the event trace information of people in video data;
Contrast module, for comparing described event trace information with default event trace information;
Judge module, for the result analyzed according to comparison, it is judged that the people's that described event trace information is corresponding can
Doubt property.
Preferably, described judge module includes:
First determines unit, and the result for analyzing in comparison is described event trace information and described default activity
In the case of trace information coupling, determine the artificial normal personnel that described event trace information is corresponding;
Second determines unit, and the result for analyzing in comparison is described event trace information and described default activity
In the case of trace information is unmatched, determine the artificial a suspect that described event trace information is corresponding.
Preferably, described device also includes: tracing module, for judging that described event trace information is corresponding
Artificial a suspect in the case of, by monitoring device visualization display and follow the trail of described a suspect.
Preferably, described device also includes: identification module, for judging that described event trace information is corresponding
Artificial a suspect in the case of, by the information of the online wanted criminal in described a suspect and public security system
It is identified comparison.
Preferably, described device also comprises determining that module, for the event trace of the people of the magnanimity according to record
Information, determines described default event trace information.
By the present invention, use and gather video data;According to described video data and the described video data of collection
Positional information, records the event trace information of people in described video data;By described event trace information with pre-
If event trace information compares;The result analyzed according to comparison, it is judged that described event trace information
The dubiety of corresponding people, solve that prior art exists cannot automatic screening identification a suspect and row
Look into inefficient problem, use the technical solution of the present invention can automatic screening identification a suspect, it is not necessary to
Increase extras, improve the efficiency of investigation.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application,
The schematic description and description of the present invention is used for explaining the present invention, is not intended that the improper limit to the present invention
Fixed.In the accompanying drawings:
Fig. 1 is the flow chart of a kind of a suspect's recognition methods according to embodiments of the present invention;
Fig. 2 is the preferred flow charts of a kind of a suspect's recognition methods according to embodiments of the present invention;
Fig. 3 is the structured flowchart that a kind of a suspect according to embodiments of the present invention identifies device;
Fig. 4 is the preferred structure block diagram that a kind of a suspect according to embodiments of the present invention identifies device;
Fig. 5 is the structured flowchart that another kind of a suspect according to embodiments of the present invention identifies device;
Fig. 6 is the schematic diagram that a kind of a suspect according to its preferred embodiment of the present invention identifies system;
Detailed description of the invention
Below with reference to accompanying drawing and describe the present invention in detail in conjunction with the embodiments.It should be noted that not
In the case of conflict, the embodiment in the application and the feature in embodiment can be mutually combined.
Providing a kind of a suspect's recognition methods in the present embodiment, Fig. 1 is according to embodiments of the present invention
The flow chart of a kind of a suspect's recognition methods, as it is shown in figure 1, the method comprises the steps:
S102: gather video data;
S104: according to described video data and the positional information of the described video data of collection, record described video counts
Event trace information according to middle people;
S106: described event trace information is compared with default event trace information;
S108: the result analyzed according to comparison, it is judged that the dubiety of the people that described event trace information is corresponding.
According to above-mentioned steps, the video counts of this public place monitoring camera shooting of the present invention first Real-time Collection
According to, by video, image processing techniques, the facial feature data about people is carried from the video data of magnanimity
Take out, utilize face tracking technology everyone according to the time sequencing occurred in video, further according to often
The position at individual monitor video place can record everyone event trace, then by the activity of above-mentioned individual
The information of track compares with the event trace information of the normal person preset, and judges according to analysis result
The dubiety of the event trace of described corresponding people.The present invention can automatic screening identification a suspect, it is not necessary to
Increase extras, improve the efficiency of investigation.
In a preferred embodiment, the result analyzed according to comparison, it is judged that described event trace information pair
The dubiety of the people answered includes: the result analyzed in comparison is described event trace information and described default activity
In the case of trace information coupling, determine the artificial normal personnel that described event trace information is corresponding;In comparison
The result analyzed is in the case of to be described event trace information unmatched with described default event trace information, really
The artificial a suspect that fixed described event trace information is corresponding.Compare according to similarity analysis result, as
Really analysis result be more similar so this person be not suspect, be otherwise suspect.
In a preferred embodiment, the artificial a suspect judging that described event trace information is corresponding
In the case of, described method also includes: is shown by monitoring device visualization and is followed the trail of described a suspect.
The structure of this public place known and the position of each monitoring camera, when having analyzed a suspect and having occurred,
Can according to monitoring interface or the deviation situation judging a suspect and normal trace on visualization interface,
Thus carry out law enforcement behavior.
In a preferred embodiment, the artificial a suspect judging that described event trace information is corresponding
In the case of, described method also includes: by the letter of described a suspect with the online wanted criminal in public security system
Breath is identified comparison.The high-risk individuals identified, respectively with public security system in pursuing and capturing an escaped prisoner online
The criminal ordered to arrest is identified comparison, if similar, using these individualities as the high-risk molecule of highest level,
Prompting needs to take action at once.
In a preferred embodiment, Fig. 2 is a kind of a suspect's recognition methods of the embodiment of the present invention
Preferred flow charts, as in figure 2 it is shown, in the confidence breath according to described data and the described video data of collection, note
After recording the event trace information of people in described video data, described method also includes: S105, according to record
The event trace information of people of magnanimity, determine described default event trace information.Gather this public place
Historical data, obtained about facial characteristics proprietary in this public place after over cleaning, filtration treatment
Video data.The position of known each monitor video, so the video data collected utilizes face with
Track technology everyone according to the time sequencing occurred in video, further according to the position at each monitor video place
Put the event trace that can depict everyone, through calculating the event trace that can preset normal person.
In a preferred embodiment, event trace information described in said method and/or described default work
Dynamic trace information includes at least one of: according to face tracking technology and the position of the described video data of collection
The course of action of the people that information calculates;The gait of march of people;The time of staying of people.
Additionally providing a kind of a suspect in the present embodiment and identify device, this device is used for realizing above-mentioned enforcement
Example and preferred implementation, carried out repeating no more of explanation.As used below, term " mould
Block " software of predetermined function and/or the combination of hardware can be realized.Although the dress described by following example
Put and preferably realize with software, but hardware, or the realization of the combination of software and hardware is also also possible
It is contemplated.
Fig. 3 is the structure chart that a kind of a suspect according to embodiments of the present invention identifies device, as it is shown on figure 3,
This device includes acquisition module 32, logging modle 34, contrast module 36 and judge module 38.Below to this
Device illustrates.
Acquisition module 32, is used for gathering video data;Logging modle 34, is connected to above-mentioned acquisition module 32,
For according to described video data and the positional information of the described video data of collection, recording in described video data
The event trace information of people;Contrast module 36, is connected to above-mentioned logging modle 34, for by described activity
Trace information compares with default event trace information;Judge module 38, is connected to above-mentioned contrast
Module 36, for the result analyzed according to comparison, it is judged that the people's that described event trace information is corresponding is suspicious
Property.
In a preferred embodiment, Fig. 4 is that a kind of a suspect according to embodiments of the present invention identifies dress
The preferred structure figure put, as shown in Figure 4, the described judge module 38 in device includes: first determines list
Unit 381, the result for analyzing in comparison is described event trace information and described default event trace information
In the case of coupling, determine the artificial normal personnel that described event trace information is corresponding;Second determines unit
382, the result for analyzing in comparison is described event trace information with described default event trace information not
In the case of coupling, determine the artificial a suspect that described event trace information is corresponding.
In a preferred embodiment, said apparatus also includes: tracing module 40, connects above-mentioned judgement mould
Block 38, in the case of judging the artificial a suspect that described event trace information is corresponding, passes through
Monitoring device visualization shows and follows the trail of described a suspect.
In a preferred embodiment, said apparatus also includes: identification module 42, connects above-mentioned judgement mould
Block 38, in the case of judging the artificial a suspect that described event trace information is corresponding, by institute
The information stating the online wanted criminal in a suspect and public security system is identified comparison.
In a preferred embodiment, Fig. 5 is that another kind of a suspect according to embodiments of the present invention identifies
The structured flowchart of device, as it is shown in figure 5, described device also comprises determining that module 35, connects described note
Record module, for the event trace information of the people of the magnanimity according to record, determines that described default event trace is believed
Breath.
For the problems referred to above in the presence of correlation technique, illustrating below in conjunction with preferred embodiment, this is excellent
Embodiment is selected to combine above-described embodiment and preferred implementation thereof.Fig. 6 is that it is preferable to carry out according to the present invention
A kind of a suspect of example identifies the schematic diagram of system, as shown in Figure 6:
Step 601, the scope determining public place and the position of each monitoring camera, specify this public field
The position of each monitoring camera, the distance between each monitoring camera, and be each monitoring camera
Head arranges labelling.The method can apply as railway station, subway station, airport, financial institution, hospital,
In the multiple public place that personnel's comparatively denses such as market, scope are bigger, it is also possible to by the whole subway system in city
System is considered a public place.
Step 602, gather the video data of this public place monitoring camera shooting.First, these public affairs are gathered
All video datas that in region, place, all monitoring cameras photograph altogether;Then, these video datas
It is carried out, filters and integrates, the most so-called data cleansing, filter and integrate and utilize video, figure exactly
As treatment technology extracts the facial feature data about people from the video data of magnanimity, and preserve
Getting off, after processing, we just obtain regarding about facial characteristics proprietary in this public place
Frequency evidence.
Step 603, records everyone event trace, gait of march and the time of staying, and concrete operations are exactly,
First, it is known that the position of each monitor video, so the video data collected utilizes face tracking skill
Art is everyone according to the time sequencing occurred in video, and the position further according to each monitor video place can
To depict everyone event trace, it addition, since it is known everyone occurs from a video, again
In the time interval that another one video occurs, so, may finally depict and regard so that this public place is all
Frequently position is everyone event trace of basic point, and can mark the time between each basic point
, namely there is the time needed to next one monitoring place, can calculate from a monitoring place in interval
Everyone gait of march, further, asks the interval between basic point each in everyone event trace
With, can be calculated everyone in this public place residence time.
Step 604, describe and the event trace of normal person's (not having criminal tendency) of benchmark of setting out in advance,
Gait of march and the time of staying.Concrete operations are exactly, and gather nearest 6 months~the going through of 1 year this public place
History data, obtained regarding about facial characteristics proprietary in this public place after over cleaning, filtration treatment
Frequency evidence.The position of known each monitor video, so utilizing face tracking in the video data collected
Technology everyone according to the time sequencing occurred in video, further according to the position at each monitor video place
Everyone event trace can be depicted, it addition, since it is known everyone occurs from a video, then
The secondary time interval occurred at another one video, namely occurs to the next one monitoring from a monitoring place
The time that place needs, everyone gait of march can be calculated, further, everyone activity
In track, sue for peace in the interval between each basic point, can calculate everyone in this public place residence time.
Finally, we just can obtain everyone event trace of magnanimity, and in event trace each basic point it
Between time interval, after the process to history mass data, we can obtain the active rail of normal person
Mark, the speed of service of normal person and normal person are in the time of staying of this public place, further, normal
The speed of service and the normal person of people averaged in the time of staying of this public place, had obtained the activity of benchmark
Track, gait of march and in this public place stay time.Owing to this step operation consuming time is longer, institute
It is a timed task with this step, is usually and runs once weekly, and be to bring into operation morning, run
The result that latest result after success calculates before automatically replacing it.Remarks: the danger actually occurred according to China
Evil public safety criminal information, thus it is speculated that do in public places threaten public safety offender relative to
Normal person or very little, from big data from the point of view of, the track of these offenders is not enough to just affect
Event trace, gait of march and the time of staying of ordinary person's (not having criminal tendency).
Step 605, the identification of suspect and tracking.Real-time everyone's that step 603 is acquired
Event trace, gait of march and the normal person (criminal of not having of the benchmark of acquisition in the time of staying, with step 604
Crime tendency) event trace, gait of march and the time of staying carry out similarity analysis, root according to mathematical algorithm
Carry out the identification of suspect according to similarity analysis result, if namely analysis result be more similar so this
People is not suspect, is otherwise suspect, after identifying suspect, further, utilizes people
Face tracer technique, is tracked suspect.
Step 606, a suspect is followed the trail of in visualization display a suspect and visualization.This public place known
Structure and the position of each monitoring camera, thus can make visualization interface, in this visualization circle
Track and the time situation of the normal person of benchmark is indicated, when there being a suspect to occur, occurring partially on face
Track from personnel is also indicated on this visualization interface, and so, law enfrocement official can be according to visualization interface
On i.e. can determine whether the deviation situation of a suspect and normal trace, thus carry out law enforcement behavior.
Step 607, the high-risk individuals identified, respectively with public security system in pursuing and capturing an escaped prisoner online logical
The criminal seized is identified comparison, if similar these individualities are as the high-risk molecule of highest level, points out
Need to take action at once, it addition, in order to avoid erroneous judgement, such as patrol personnel are mistaken for high-risk molecule,
Can be by advance patrol personnel's information input system, filtering out patrolman in the high-risk individuals identified
Member, it is to avoid erroneous judgement.
The method that this enforcement row provide can identify questionable person, by suspicious people in the boundless and indistinct sea of faces automatically
After member's " emphasis care ", remove a hidden danger, it is to avoid the further generation of the criminal behavior endangered public security,
Thus the safety of man of protectorate people's lives and properties, it addition, the method need not to dispose extra, complicated,
Accurate, expensive equipment, it is not necessary to change any layout of public place, just with existing monitoring
Photographic head, disposes a set of software system, and cost performance is the highest, and also the method can provide visualization circle
Face, it is not necessary to the advantages such as any manual operation.
The above, the only preferred embodiments of the present invention, it is not intended to limit protection scope of the present invention, right
For those skilled in the art, the present invention can have various modifications and variations.All spirit in the present invention
Within principle, any modification, equivalent substitution and improvement etc. done, should be included in the protection of the present invention
Within the scope of.
Claims (11)
1. a suspect's recognition methods, it is characterised in that including:
Gather video data;
According to described video data and the positional information of the described video data of collection, record people in described video data
Event trace information;
Described event trace information is compared with default event trace information;
The result analyzed according to comparison, it is judged that the dubiety of the people that described event trace information is corresponding.
Method the most according to claim 1, it is characterised in that the result analyzed according to comparison, it is judged that institute
The dubiety stating people corresponding to event trace information includes:
In the feelings that result is described event trace information and described default event trace information matches that comparison is analyzed
Under condition, determine the artificial normal personnel that described event trace information is corresponding;
The result analyzed in comparison is that described event trace information is unmatched with described default event trace information
In the case of, determine the artificial a suspect that described event trace information is corresponding.
Method the most according to claim 2, it is characterised in that judging described event trace information pair
In the case of the artificial a suspect answered, described method also includes:
Show by monitoring device visualization and follow the trail of described a suspect.
Method the most according to claim 2, it is characterised in that judging described event trace information pair
In the case of the artificial a suspect answered, described method also includes:
The information of described a suspect with the online wanted criminal in public security system is identified comparison.
Method the most according to claim 1, it is characterised in that regarding according to described data and collection
The positional information of frequency evidence, after recording the event trace information of people in described video data, described method is also
Including:
The event trace information of the people of the magnanimity according to record, determines described default event trace information.
Method the most according to any one of claim 1 to 5, it is characterised in that described event trace is believed
Breath and/or described default event trace information include at least one of:
The course of action of the people that the positional information calculation according to face tracking technology and the described video data of collection goes out;
The gait of march of people;
The time of staying of people.
7. an a suspect identifies device, it is characterised in that including:
Acquisition module, is used for gathering video data;
Logging modle, for according to described video data and the positional information of the described video data of collection, recording institute
State the event trace information of people in video data;
Contrast module, for comparing described event trace information with default event trace information;
Judge module, for the result analyzed according to comparison, it is judged that the people's that described event trace information is corresponding can
Doubt property.
Device the most according to claim 7, it is characterised in that described judge module includes:
First determines unit, and the result for analyzing in comparison is described event trace information and described default activity
In the case of trace information coupling, determine the artificial normal personnel that described event trace information is corresponding;
Second determines unit, and the result for analyzing in comparison is described event trace information and described default activity
In the case of trace information is unmatched, determine the artificial a suspect that described event trace information is corresponding.
Device the most according to claim 8, it is characterised in that described device also includes:
Tracing module, is used in the case of judging the artificial a suspect that described event trace information is corresponding,
Show by monitoring device visualization and follow the trail of described a suspect.
Device the most according to claim 8, it is characterised in that described device also includes:
Identification module, is used in the case of judging the artificial a suspect that described event trace information is corresponding,
The information of described a suspect with the online wanted criminal in public security system is identified comparison.
11. devices according to claim 7, it is characterised in that described device also includes:
Determine module, for the event trace information of the people of the magnanimity according to record, determine described default event trace
Information.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510106082.2A CN106033530A (en) | 2015-03-11 | 2015-03-11 | Identification method and apparatus for suspected person |
PCT/CN2015/081579 WO2016141641A1 (en) | 2015-03-11 | 2015-06-16 | Method and device for recognizing suspicious person |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510106082.2A CN106033530A (en) | 2015-03-11 | 2015-03-11 | Identification method and apparatus for suspected person |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106033530A true CN106033530A (en) | 2016-10-19 |
Family
ID=56879873
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510106082.2A Withdrawn CN106033530A (en) | 2015-03-11 | 2015-03-11 | Identification method and apparatus for suspected person |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106033530A (en) |
WO (1) | WO2016141641A1 (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106791636A (en) * | 2016-12-15 | 2017-05-31 | 重庆凯泽科技股份有限公司 | A kind of key population monitoring system and method |
CN107045537A (en) * | 2017-02-07 | 2017-08-15 | 上海众恒信息产业股份有限公司 | Towards the feature location System and method for of individual |
CN107330584A (en) * | 2017-06-12 | 2017-11-07 | 中国联合网络通信集团有限公司 | A suspect's recognition methods and device |
CN107437075A (en) * | 2017-07-29 | 2017-12-05 | 安徽博威康信息技术有限公司 | A kind of risk alarm system based on daily behavior track |
CN107452027A (en) * | 2017-07-29 | 2017-12-08 | 安徽博威康信息技术有限公司 | A kind of target person method for security protection based on multi-cam monitoring |
CN108364438A (en) * | 2017-12-28 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Method for early warning based on front end perception data and device |
CN108563985A (en) * | 2018-03-02 | 2018-09-21 | 海尔优家智能科技(北京)有限公司 | Identify method, monitoring center, public transport equipment and the storage medium stolen |
CN108629721A (en) * | 2018-04-02 | 2018-10-09 | 杭州孚立计算机软件有限公司 | A kind of comprehensive improvement brain processing method |
CN108629322A (en) * | 2018-05-11 | 2018-10-09 | 中国联合网络通信集团有限公司 | Monitoring method, device and the computer readable storage medium of a suspect |
CN108664608A (en) * | 2018-05-11 | 2018-10-16 | 中国联合网络通信集团有限公司 | Recognition methods, device and the computer readable storage medium of a suspect |
CN109308780A (en) * | 2018-10-19 | 2019-02-05 | 杭州虹晟信息科技有限公司 | Smart home security monitoring system based on Internet of Things |
CN109472731A (en) * | 2018-11-07 | 2019-03-15 | 武汉烽火众智数字技术有限责任公司 | A kind of suspicious object determines method and device |
CN109858346A (en) * | 2018-12-25 | 2019-06-07 | 深圳市天彦通信股份有限公司 | Target person determines method and relevant apparatus |
CN109886236A (en) * | 2019-03-01 | 2019-06-14 | 苏州星奥达科技有限公司 | A kind of video analysis method based on magnanimity crowd behaviour |
CN109886196A (en) * | 2019-02-21 | 2019-06-14 | 中水北方勘测设计研究有限责任公司 | Personnel track traceability system and method based on BIM plus GIS video monitoring |
CN110070687A (en) * | 2019-03-18 | 2019-07-30 | 苏州凸现信息科技有限公司 | A kind of intelligent safety defense monitoring system and its working method based on motion analysis |
CN111325056A (en) * | 2018-12-14 | 2020-06-23 | 成都云天励飞技术有限公司 | Floating population analysis method and related product |
CN111613013A (en) * | 2020-06-03 | 2020-09-01 | 克拉玛依市格恩赛电子科技有限公司 | Security positioning analysis early warning system, storage medium and method |
CN112347151A (en) * | 2019-08-08 | 2021-02-09 | 浙江宇视科技有限公司 | Suspicion degree determination method and data analysis equipment |
CN114072861A (en) * | 2019-07-02 | 2022-02-18 | C-T-I株式会社 | Guard device and guard system |
CN114360185A (en) * | 2022-01-14 | 2022-04-15 | 上海星杰装饰有限公司 | Villa intelligent system |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107358146B (en) * | 2017-05-22 | 2018-05-22 | 深圳云天励飞技术有限公司 | Method for processing video frequency, device and storage medium |
CN112182055A (en) * | 2019-07-02 | 2021-01-05 | 中国移动通信集团贵州有限公司 | Suspect determination method, apparatus, device and storage medium |
CN111553225A (en) * | 2020-04-21 | 2020-08-18 | 上海上实龙创智慧能源科技股份有限公司 | System and method for generating personnel movement track based on video analysis |
CN111611894A (en) * | 2020-05-14 | 2020-09-01 | 深圳中科慧据科技有限公司 | Personnel trajectory prediction method and device, computer equipment and storage medium |
CN111639689B (en) * | 2020-05-20 | 2023-07-25 | 杭州海康威视系统技术有限公司 | Face data processing method and device and computer readable storage medium |
CN111552007A (en) * | 2020-05-26 | 2020-08-18 | 上海量卿科技有限公司 | Inspection system and method |
CN114422760B (en) * | 2022-03-29 | 2022-06-07 | 深圳市迈科思腾科技有限公司 | Video monitoring method and device based on multiplexing |
CN114973567B (en) * | 2022-04-06 | 2024-01-16 | 福建长盛亿信息科技有限公司 | Automatic alarm method and terminal based on face recognition |
CN115512304B (en) * | 2022-11-10 | 2023-03-03 | 成都大学 | Subway station safety monitoring system based on image recognition |
CN116347036A (en) * | 2023-03-14 | 2023-06-27 | 电子科技大学 | Security monitoring communication server based on Internet of things and artificial intelligence |
CN116596650B (en) * | 2023-07-17 | 2023-09-22 | 上海银行股份有限公司 | Bank physical management system based on intelligent recognition technology |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101542549A (en) * | 2007-03-06 | 2009-09-23 | 株式会社东芝 | Suspicious behavior detection system and method |
CN102905122A (en) * | 2012-11-13 | 2013-01-30 | 北京航天福道高技术股份有限公司 | Auxiliary method for tracking suspicious people by monitoring system |
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 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100531373C (en) * | 2007-06-05 | 2009-08-19 | 西安理工大学 | Video frequency motion target close-up trace monitoring method based on double-camera head linkage structure |
CN101770648B (en) * | 2009-01-06 | 2013-04-17 | 贵阳中星电子有限公司 | Video monitoring based loitering system and method thereof |
US20110026770A1 (en) * | 2009-07-31 | 2011-02-03 | Jonathan David Brookshire | Person Following Using Histograms of Oriented Gradients |
CN102810206A (en) * | 2011-06-03 | 2012-12-05 | 南京理工大学 | Real-time loitering detection method based on dynamic programming |
-
2015
- 2015-03-11 CN CN201510106082.2A patent/CN106033530A/en not_active Withdrawn
- 2015-06-16 WO PCT/CN2015/081579 patent/WO2016141641A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101542549A (en) * | 2007-03-06 | 2009-09-23 | 株式会社东芝 | Suspicious behavior detection system and method |
CN102905122A (en) * | 2012-11-13 | 2013-01-30 | 北京航天福道高技术股份有限公司 | Auxiliary method for tracking suspicious people by monitoring system |
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 |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106791636A (en) * | 2016-12-15 | 2017-05-31 | 重庆凯泽科技股份有限公司 | A kind of key population monitoring system and method |
CN107045537A (en) * | 2017-02-07 | 2017-08-15 | 上海众恒信息产业股份有限公司 | Towards the feature location System and method for of individual |
CN107330584A (en) * | 2017-06-12 | 2017-11-07 | 中国联合网络通信集团有限公司 | A suspect's recognition methods and device |
CN107437075A (en) * | 2017-07-29 | 2017-12-05 | 安徽博威康信息技术有限公司 | A kind of risk alarm system based on daily behavior track |
CN107452027A (en) * | 2017-07-29 | 2017-12-08 | 安徽博威康信息技术有限公司 | A kind of target person method for security protection based on multi-cam monitoring |
CN108364438A (en) * | 2017-12-28 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Method for early warning based on front end perception data and device |
CN108563985A (en) * | 2018-03-02 | 2018-09-21 | 海尔优家智能科技(北京)有限公司 | Identify method, monitoring center, public transport equipment and the storage medium stolen |
CN108563985B (en) * | 2018-03-02 | 2022-08-26 | 海尔优家智能科技(北京)有限公司 | Method for identifying pickpocket, monitoring center, public transport equipment and storage medium |
CN108629721A (en) * | 2018-04-02 | 2018-10-09 | 杭州孚立计算机软件有限公司 | A kind of comprehensive improvement brain processing method |
CN108629322A (en) * | 2018-05-11 | 2018-10-09 | 中国联合网络通信集团有限公司 | Monitoring method, device and the computer readable storage medium of a suspect |
CN108664608A (en) * | 2018-05-11 | 2018-10-16 | 中国联合网络通信集团有限公司 | Recognition methods, device and the computer readable storage medium of a suspect |
CN109308780A (en) * | 2018-10-19 | 2019-02-05 | 杭州虹晟信息科技有限公司 | Smart home security monitoring system based on Internet of Things |
CN109472731A (en) * | 2018-11-07 | 2019-03-15 | 武汉烽火众智数字技术有限责任公司 | A kind of suspicious object determines method and device |
CN111325056A (en) * | 2018-12-14 | 2020-06-23 | 成都云天励飞技术有限公司 | Floating population analysis method and related product |
CN111325056B (en) * | 2018-12-14 | 2023-06-09 | 成都云天励飞技术有限公司 | Method and device for analyzing floating population |
CN109858346A (en) * | 2018-12-25 | 2019-06-07 | 深圳市天彦通信股份有限公司 | Target person determines method and relevant apparatus |
CN109858346B (en) * | 2018-12-25 | 2020-11-27 | 深圳市天彦通信股份有限公司 | Target person determination method and related device |
CN109886196A (en) * | 2019-02-21 | 2019-06-14 | 中水北方勘测设计研究有限责任公司 | Personnel track traceability system and method based on BIM plus GIS video monitoring |
CN109886236A (en) * | 2019-03-01 | 2019-06-14 | 苏州星奥达科技有限公司 | A kind of video analysis method based on magnanimity crowd behaviour |
CN110070687A (en) * | 2019-03-18 | 2019-07-30 | 苏州凸现信息科技有限公司 | A kind of intelligent safety defense monitoring system and its working method based on motion analysis |
CN114072861A (en) * | 2019-07-02 | 2022-02-18 | C-T-I株式会社 | Guard device and guard system |
CN114072861B (en) * | 2019-07-02 | 2024-02-06 | Do创新株式会社 | Guard device and guard system |
CN112347151A (en) * | 2019-08-08 | 2021-02-09 | 浙江宇视科技有限公司 | Suspicion degree determination method and data analysis equipment |
CN111613013A (en) * | 2020-06-03 | 2020-09-01 | 克拉玛依市格恩赛电子科技有限公司 | Security positioning analysis early warning system, storage medium and method |
CN114360185A (en) * | 2022-01-14 | 2022-04-15 | 上海星杰装饰有限公司 | Villa intelligent system |
Also Published As
Publication number | Publication date |
---|---|
WO2016141641A1 (en) | 2016-09-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106033530A (en) | Identification method and apparatus for suspected person | |
CN109886204A (en) | A kind of Multidimensional Awareness system based on the application of big data police service | |
CN102201061B (en) | Intelligent safety monitoring system and method based on multilevel filtering face recognition | |
TWI776796B (en) | Financial terminal security system and financial terminal security method | |
WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
CN102306304B (en) | Face occluder identification method and device | |
CN109461106A (en) | A kind of multidimensional information perception processing method | |
CN111414854A (en) | Target crowd trajectory tracking method and device | |
CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
CN101794481A (en) | ATM (Automatic teller machine) self-service bank monitoring system and method | |
CN103514694A (en) | Intrusion detection monitoring system | |
CN108777703A (en) | A kind of abnormal behaviour processing method and system based on block chain | |
CN106326835A (en) | Human face data collection statistical system and method for gas station convenience store | |
CN108091140A (en) | A kind of method and apparatus of definite fake license plate vehicle | |
CN110660472A (en) | Hospital management early warning system and method based on face recognition technology | |
CN108540750A (en) | Based on monitor video and the associated method, apparatus of electronic device identification and system | |
CN108710827A (en) | A kind of micro- police service inspection in community and information automatic analysis system and method | |
CN109086829A (en) | A kind of method and device that social population administers | |
CN107944371A (en) | A kind of public security video monitoring image processing method based on data mining | |
CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
CN113343913A (en) | Target determination method, target determination device, storage medium and computer equipment | |
CN110096606A (en) | A kind of expatriate's management method, device and electronic equipment | |
CN113764107A (en) | Early warning method for airborne infectious diseases based on facial recognition technology | |
CN115100572A (en) | System and method for analyzing abnormal behaviors of campus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20161019 |