CN108664608A - Recognition methods, device and the computer readable storage medium of a suspect - Google Patents
Recognition methods, device and the computer readable storage medium of a suspect Download PDFInfo
- Publication number
- CN108664608A CN108664608A CN201810448414.9A CN201810448414A CN108664608A CN 108664608 A CN108664608 A CN 108664608A CN 201810448414 A CN201810448414 A CN 201810448414A CN 108664608 A CN108664608 A CN 108664608A
- Authority
- CN
- China
- Prior art keywords
- data
- behavioral data
- event trace
- personnel
- suspect
- 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
Landscapes
- Alarm Systems (AREA)
Abstract
The present invention provides a kind of recognition methods of a suspect, device and computer readable storage mediums.This method includes：Obtain the event trace behavioral data into each personnel of monitoring area；Event trace behavioral data and the characteristic in abnormal behavior library are compared, to judge whether event trace behavioral data includes abnormal behaviour data；If event trace behavioral data includes abnormal behaviour data, it is determined that the affiliated personnel of the event trace behavioral data are a suspect.Due to whether being that a suspect judges to the personnel according to event trace behavioral data, it is no longer dependent on personnel at risk's face database, a suspect can be effectively identified according to behavioural characteristic, improve the accuracy of identification, and it can be identified before criminal offence occurs, the prevention in advance before breaking laws and commit crime can be carried out.
Description
Technical field
The present embodiments relate to video and technical field of image processing more particularly to a kind of identification sides of a suspect
Method, device and computer readable storage medium.
Background technology
In order to ensure the security of the lives and property of the people, at the train station, airport, subway station, square, supermarket, market etc.
Densely populated region is all provided with security means.Wherein, video monitoring is current most common security means.
In existing video surveillance program, including manual video monitoring method and intelligent video monitoring method.Artificial
In video frequency monitoring method, need the monitoring personnel moment that attention is kept to concentrate, close observation.Judge that a suspect relies primarily on prison
The profile of control personnel and experience.And intelligent video monitoring method mainly uses the inspection of face identification method progress a suspect
It surveys.
Existing manual video monitoring method, monitoring personnel, which works long hours, is easy fatigue, causes quality monitoring to decline, supervises
Control system can only often play the role of post-mordem forensics, have resulted in economic loss at this time, can not accomplish to prevent in advance.And show
Some intelligent video monitoring methods depend on personnel at risk's face database, for not on personnel at risk's database list
People, can not provide effective method, and the accuracy of identification can not ensure.
Invention content
The embodiment of the present invention provides a kind of recognition methods of a suspect, device and computer readable storage medium, solves
The technical issues of in the prior art can not accomplishing to prevent to the manual identified method of a suspect in advance, also solves existing skill
In art effective side can not be provided for the people not on personnel at risk's database list to the intelligent identification Method of a suspect
The technical issues of method, the accuracy of identification can not ensure.
The embodiment of the present invention provides a kind of recognition methods of a suspect, including：
Obtain the event trace behavioral data into each personnel of monitoring area；
The event trace behavioral data is compared with the characteristic in abnormal behavior library, described in judgement
Whether event trace behavioral data includes abnormal behaviour data；
If the event trace behavioral data includes abnormal behaviour data, it is determined that the event trace behavioral data it is affiliated
Personnel are a suspect.
Further, method as described above, if the event trace behavioral data includes abnormal behaviour data,
It determines that the affiliated personnel of the event trace behavioral data are a suspect, specifically includes：
If the event trace behavioral data includes abnormal behaviour data, judge different in the event trace behavioral data
Whether the normal behavioral data corresponding abnormal behaviour duration is greater than or equal to preset time threshold；
If the abnormal behaviour duration is greater than or equal to preset time threshold, the event trace behavior number is judged
According to include abnormal behaviour data number whether be greater than or equal to predetermined number threshold value；
If the number of the abnormal behaviour data is greater than or equal to predetermined number threshold value, it is determined that the event trace behavior number
According to affiliated personnel be a suspect.
Further, method as described above, it is described to obtain the event trace behavior into each personnel of monitoring area
Data specifically include：
Acquisition enters the behavioral data of each personnel of monitoring area；
The behavioral data of same personnel is spliced sequentially in time based on face recognition technology, forms each personnel
Event trace behavioral data.
Further, method as described above, it is described to obtain the event trace behavior into each personnel of monitoring area
Before data, further include：
Acquire the video data of a variety of densely populated public places；
Feature extraction is carried out to the video data and is classified, to obtain abnormal behavior data；
Abnormal behaviour database is built according to the abnormal behavior data.
The embodiment of the present invention provides a kind of identification device of a suspect, including：
Acquisition module, for obtaining the event trace behavioral data into each personnel of monitoring area；
Judgment module, for carrying out pair the characteristic in the event trace behavioral data and abnormal behavior library
Than to judge whether the event trace behavioral data includes abnormal behaviour data；
Determining module, if including abnormal behaviour data for the event trace behavioral data, it is determined that the event trace
The affiliated personnel of behavioral data are a suspect.
Further, device as described above, the determining module, is specifically used for：
If the event trace behavioral data includes abnormal behaviour data, judge different in the event trace behavioral data
Whether the normal behavioral data corresponding abnormal behaviour duration is greater than or equal to preset time threshold；If the abnormal behaviour continues
Time is greater than or equal to preset time threshold, then judges that the event trace behavioral data includes the number of abnormal behaviour data
Whether predetermined number threshold value is greater than or equal to；If the number of the abnormal behaviour data is greater than or equal to predetermined number threshold value,
Determine that the affiliated personnel of the event trace behavioral data are a suspect.
Further, device as described above, the acquisition module, is specifically used for：
Acquisition enters the behavioral data of each personnel of monitoring area；Based on face recognition technology by the row of same personnel
Spliced sequentially in time for data, forms the event trace behavioral data of each personnel.
Further, device as described above further includes：
Acquisition module acquires the video data of a variety of densely populated public places；
Characteristic extracting module, for carrying out feature extraction to the video data and classifying, to obtain abnormal behavior
Data；
Module is built, for building abnormal behaviour database according to the abnormal behavior data.
The embodiment of the present invention provides a kind of identification device of a suspect, including：
Memory, processor and computer program；
Wherein, the computer program is stored in the memory, and is configured as being executed with reality by the processor
Existing method as described above.
The embodiment of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the calculating
Machine program is executed by processor to realize method as described above.
The embodiment of the present invention provides a kind of recognition methods of a suspect, device and computer readable storage medium, passes through
Obtain the event trace behavioral data into each personnel of monitoring area；By event trace behavioral data and abnormal behavior
Characteristic in library is compared, to judge whether event trace behavioral data includes abnormal behaviour data；If event trace
Behavioral data includes abnormal behaviour data, it is determined that the affiliated personnel of the event trace behavioral data are a suspect.Due to root
Whether it is that a suspect judges to the personnel according to event trace behavioral data, is no longer dependent on personnel at risk's human face data
Library can effectively identify a suspect according to behavioural characteristic, improve the accuracy of identification, and illegal criminal can occur
Crime is identified before being, can carry out the prevention in advance before breaking laws and commit crime.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without having to pay creative labor, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart of the recognition methods embodiment one of a suspect of the present invention；
Fig. 2 is the flow chart of the recognition methods embodiment two of a suspect of the present invention；
Fig. 3 is the structural schematic diagram of the identification device embodiment one of a suspect of the present invention；
Fig. 4 is the structural schematic diagram of the identification device embodiment two of a suspect of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation of description affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate：Individualism A, exists simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, it is a kind of relationship of "or" to typically represent forward-backward correlation object.
Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination " or " in response to detection ".Similarly, depend on context, phrase " if it is determined that " or " if detection
(condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when the detection (condition of statement
Or event) when " or " in response to detection (condition or event of statement) ".
Fig. 1 is the flow chart of the recognition methods embodiment one of a suspect of the present invention, as shown in Figure 1, the present embodiment is held
Row main body is the identification device of a suspect, and the identification device of a suspect is integrated in computer, platform device or server
Or other have independent calculating in the equipment of processing capacity, and service, then this implementation are provided a user by webpage or client
The recognition methods for a suspect that example provides includes following steps.
Step 101, the event trace behavioral data into each personnel of monitoring area is obtained.
Specifically, in the present embodiment, multiple monitoring devices, monitoring device pair are installed in densely populated public place in advance
Behavioral data into each personnel of monitoring area stores.The behavior number of each personnel is obtained from multiple monitoring devices
According to, and the behavioral data of same person is spliced sequentially in time, form the event trace behavioral data of each personnel.
The event trace behavioral data of each personnel can indicate concrete behavior of each personnel in each zone of action.
In the present embodiment, to the event trace behavioral data of certain personnel illustrate for：8 points of Zhang morning into
Enter supermarket, pushes shopping cart, go to prepared food area from fruit area returns to fruit area again, but does not do shopping, and finally goes to payment area,
After the pocket of previous purchaser is greater than or equal to 2 minutes, 9 points are left from Non-Purchase Exit.
Step 102, event trace behavioral data and the characteristic in abnormal behavior library are compared, to judge
Whether event trace behavioral data includes abnormal behaviour data.
In the present embodiment, abnormal behavior library is built in advance, a large amount of exception is stored in abnormal behavior library
The characteristic of behavior.Wherein, abnormal behaviour is that have very maximum probability that delinquent suspicious actions will occur.Will such as it occur
Suspicious actions before stealing or robbery etc. are delinquent.
In the present embodiment, to the characteristic of super incity abnormal behaviour by taking densely populated public place is supermarket as an example
Illustrate for：It does not do shopping into supermarket, pushes empty wagons and gyrate；Push empty wagons or the empty-handedly yield outside supermarket
It patrols；Specially stare at the shopping cart after others pays the bill or wallet, handbag etc..
It is understood that abnormal behavior data can be added or correct according to actual conditions.
Step 103, if event trace behavioral data includes abnormal behaviour data, it is determined that the event trace behavioral data
Affiliated personnel are a suspect.
It specifically, can be at interval of preset time period by event trace behavioral data and abnormal behavior in the present embodiment
Whether the characteristic in library is compared, judge in event trace behavioral data to include abnormal behaviour data, if event trace
Behavioral data includes abnormal behaviour data, it is determined that the affiliated personnel of the event trace behavioral data are a suspect, if living
Do not include abnormal behaviour data in dynamic rail mark behavioral data, then continues the event trace behavior number for obtaining next preset time period
According to, and whether the event trace behavioral data is judged including abnormal behaviour data again, until the personnel leave the people
The intensive public place of mouth.
The recognition methods of a suspect provided in this embodiment enters the activity of each personnel of monitoring area by acquisition
Track behavioral data；Event trace behavioral data and the characteristic in abnormal behavior library are compared, to judge to live
Whether dynamic rail mark behavioral data includes abnormal behaviour data；If event trace behavioral data includes abnormal behaviour data, it is determined that
The affiliated personnel of the event trace behavioral data are a suspect.Due to according to event trace behavioral data to the personnel whether be
A suspect judges, is no longer dependent on personnel at risk's face database, can effectively be identified according to behavioural characteristic suspicious
Personnel improve the accuracy of identification, and can be identified before criminal offence occurs, and can break laws and commit crime
Preceding prevention in advance.
Fig. 2 is the flow chart of the recognition methods embodiment two of a suspect of the present invention, as shown in Fig. 2, the present embodiment provides
A suspect recognition methods, be on the basis of the recognition methods embodiment one of a suspect of the present invention, to step 101,
The further refinement of step 103, and the step of further comprising structure abnormal behaviour database, then it is provided in this embodiment suspicious
The recognition methods of personnel includes the following steps.
Step 201, the video data of a variety of densely populated public places is acquired.
Wherein, densely populated public place includes at least：Railway station, airport, subway station, square, supermarket, market, may be used also
To include other densely populated public places, this is not limited in the present embodiment.
Wherein, include the behavioral data of a large amount of personnel in the video data of acquisition.
Step 202, feature extraction is carried out to video data and classified, to obtain abnormal behavior data.
Specifically, in the present embodiment, feature extraction is carried out to video data using feature extraction algorithm, and use engineering
It practises algorithm to classify, obtains the characteristic for abnormal class in class categories, the characteristic of the abnormal class is abnormal
Behavioural characteristic data.
Wherein, in the present embodiment, the classification of the algorithm of feature extraction is not limited, to the classification of machine learning bob
It does not limit.
Step 203, abnormal behaviour database is built according to abnormal behavior data.
Abnormal behavior data are stored and build abnormal behaviour database into database.Wherein, type of database
It does not limit, such as can be MySQL database, oracle database etc..
It is understood that if abnormal behaviour database has built completion, subsequently when the identification of progress a suspect not
Step 201- steps 203 are executed again.
Step 204, the event trace behavioral data into each personnel of monitoring area is obtained.
Further, the event trace behavioral data obtained into each personnel of monitoring area specifically includes：
First, acquisition enters the behavioral data of each personnel of monitoring area.
Specifically, it due to being provided with multiple monitoring devices in densely populated public place, is corresponded to from multiple monitoring devices
Storage region acquisition enter monitoring area each personnel behavioral data.
Then, the behavioral data of same personnel is spliced sequentially in time based on face recognition technology, is formed every
The event trace behavioral data of a personnel.
Specifically, all behavioral datas that face recognition technology obtains same personnel are first passed through, and according in behavioral data
Temporal information, behavioral data is spliced sequentially in time, forms the event trace behavioral data of the personnel.
Wherein, face recognition technology can be any one in existing face recognition technology.
Step 205, event trace behavioral data and the characteristic in abnormal behavior library are compared, judges to live
Whether dynamic rail mark behavioral data includes abnormal behaviour data, if so, 206 are thened follow the steps, it is no to then follow the steps 204.
Step 206, judge in event trace behavioral data whether is the abnormal behaviour data corresponding abnormal behaviour duration
More than or equal to preset time threshold, if so, 207 are thened follow the steps, it is no to then follow the steps 204.
Step 207, judge that event trace behavioral data includes whether the number of abnormal behaviour data is greater than or equal in advance
If number threshold value, if so, 208 are thened follow the steps, it is no to then follow the steps 204.
Step 208, determine that the affiliated personnel of the event trace behavioral data are a suspect.
It is illustrated in conjunction with step 205- steps 208.Further, in this embodiment by event trace behavioral data with
Characteristic in abnormal behavior library is compared, and judges whether event trace behavioral data includes abnormal behaviour data,
If event trace behavioral data includes abnormal behaviour data, illustrates that the personnel have motivation to carry out criminal offence, then sentence
Whether the abnormal behaviour data corresponding abnormal behaviour duration is greater than or equal to preset time in disconnected event trace behavioral data
It is delinquent to illustrate that the personnel will carry out if the abnormal behaviour duration is greater than or equal to preset time threshold for threshold value
Suspicion improves, and then judges that event trace behavioral data includes whether the number of abnormal behaviour data is greater than or equal to default
Number threshold value illustrates that the personnel will carry out illegal criminal if the number of abnormal behaviour data is greater than or equal to predetermined number threshold value
The suspicion of crime further increases, and the abnormal behaviour duration is greater than or equal to preset time threshold and abnormal behaviour data
The affiliated personnel that number is greater than or equal to the event trace behavioral data of predetermined number threshold value are determined as a suspect.If abnormal row
The number for being less than preset time threshold or abnormal behaviour data for the duration is less than predetermined number threshold value, then continues to obtain the people
The event trace behavioral data of member, further to be judged.
Wherein, preset time threshold and predetermined number threshold value are preset.As preset time threshold can be 2 minutes, or
Other suitable times, predetermined number threshold value can be 2 times, 3 times or other suitable for number.
The recognition methods of a suspect provided in this embodiment, by the video counts for acquiring a variety of densely populated public places
According to video data feature extraction and classify, to obtain abnormal behavior data, according to abnormal behavior data structure
Abnormal behaviour database is built, the event trace behavioral data into each personnel of monitoring area is obtained, by event trace behavior
Data are compared with the characteristic in abnormal behavior library, judge whether event trace behavioral data includes abnormal behaviour
Data, if so, judging whether the abnormal behaviour data corresponding abnormal behaviour duration is more than in event trace behavioral data
Or be equal to preset time threshold, if so, judge event trace behavioral data include abnormal behaviour data number it is whether big
In or be equal to predetermined number threshold value, if so, determine the event trace behavioral data affiliated personnel be a suspect, otherwise,
Continue to obtain the event trace behavioral data into the personnel of monitoring area, subsequently to be judged.It can not only occur
It is identified before criminal offence, the prevention in advance before breaking laws and commit crime can be carried out, and further improve the standard of identification
Exactness reduces the generation of incident.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a read/write memory medium.The program is being held
When row, execution includes the steps that above-mentioned each method embodiment；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or CD
Etc. the various media that can store program code.
Fig. 3 is the structural schematic diagram of the identification device embodiment one of a suspect of the present invention, as shown in figure 3, the present embodiment
The identification device of a suspect of offer includes：Acquisition module 31, judgment module 32, determining module 33.
Wherein, acquisition module 31, for obtaining the event trace behavioral data into each personnel of monitoring area.Judge
Module 32 is connect with acquisition module 31.For by the characteristic in event trace behavioral data and abnormal behavior library into
Row comparison, to judge whether event trace behavioral data includes abnormal behaviour data.Determining module 33 connects with judgment module 32
It connects.If including abnormal behaviour data for event trace behavioral data, it is determined that the affiliated personnel of the event trace behavioral data
For a suspect.
The identification device of a suspect provided in this embodiment can execute the technical solution of embodiment of the method shown in Fig. 1,
Its implementing principle and technical effect is similar, and details are not described herein again.
Fig. 4 is the structural schematic diagram of the identification device embodiment two of a suspect of the present invention, as shown in figure 4, the present embodiment
The identification device of a suspect of offer is on the basis of the identification device embodiment one of a suspect of the present invention, further,
Further include：Acquisition module 41, characteristic extracting module 42 and structure module 43.
Further, it is determined that module 33, is specifically used for：
If event trace behavioral data includes abnormal behaviour data, abnormal behaviour number in event trace behavioral data is judged
Whether it is greater than or equal to preset time threshold according to the corresponding abnormal behaviour duration；If the abnormal behaviour duration is more than or waits
In preset time threshold, then judge that event trace behavioral data includes whether the number of abnormal behaviour data is greater than or equal in advance
If number threshold value；If the number of abnormal behaviour data is greater than or equal to predetermined number threshold value, it is determined that the event trace behavior number
According to affiliated personnel be a suspect.
Further, acquisition module 31 are specifically used for：
Acquisition enters the behavioral data of each personnel of monitoring area；Based on face recognition technology by the row of same personnel
Spliced sequentially in time for data, forms the event trace behavioral data of each personnel.
Further, acquisition module 41 acquire the video data of a variety of densely populated public places.Characteristic extracting module
42, it is connect with acquisition module 41.For carrying out feature extraction to video data and classifying, to obtain abnormal behavior data.
Module 43 is built, is connect with characteristic extracting module 42.For building abnormal behaviour database according to abnormal behavior data.
The identification device of a suspect provided in this embodiment can execute the technical solution of embodiment of the method shown in Fig. 2,
Its implementing principle and technical effect is similar, and details are not described herein again.
The embodiment of the present invention also provides a kind of identification device of a suspect, including：Memory, processor and computer
Program.
Wherein, computer program stores in memory, and is configured as being executed by processor to realize that the present invention is suspicious
Method in the recognition methods embodiment one of personnel or the recognition methods embodiment two of a suspect of the present invention.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored thereon with computer program, computer
Program is executed by processor with the identification of the recognition methods embodiment one or a suspect of the present invention of realizing a suspect of the present invention
Method in embodiment of the method two.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of recognition methods of a suspect, which is characterized in that including：
Obtain the event trace behavioral data into each personnel of monitoring area；
The event trace behavioral data is compared with the characteristic in abnormal behavior library, to judge the activity
Whether track behavioral data includes abnormal behaviour data；
If the event trace behavioral data includes abnormal behaviour data, it is determined that the affiliated personnel of the event trace behavioral data
For a suspect.
2. if according to the method described in claim 1, it is characterized in that, the event trace behavioral data includes abnormal row
For data, it is determined that the affiliated personnel of the event trace behavioral data are a suspect, are specifically included：
If the event trace behavioral data includes abnormal behaviour data, abnormal row in the event trace behavioral data is judged
Whether it is greater than or equal to preset time threshold for the data corresponding abnormal behaviour duration；
If the abnormal behaviour duration is greater than or equal to preset time threshold, judge in the event trace behavioral data
Whether the number including abnormal behaviour data is greater than or equal to predetermined number threshold value；
If the number of the abnormal behaviour data is greater than or equal to predetermined number threshold value, it is determined that the event trace behavioral data
Affiliated personnel are a suspect.
3. method according to claim 1 or 2, which is characterized in that described to obtain into each personnel's of monitoring area
Event trace behavioral data, specifically includes：
Acquisition enters the behavioral data of each personnel of monitoring area；
The behavioral data of same personnel is spliced sequentially in time based on face recognition technology, forms the work of each personnel
Dynamic rail mark behavioral data.
4. according to the method described in claim 3, it is characterized in that, described obtain the activity into each personnel of monitoring area
Before the behavioral data of track, further include：
Acquire the video data of a variety of densely populated public places；
Feature extraction is carried out to the video data and is classified, to obtain abnormal behavior data；
Abnormal behaviour database is built according to the abnormal behavior data.
5. a kind of identification device of a suspect, which is characterized in that including：
Acquisition module, for obtaining the event trace behavioral data into each personnel of monitoring area；
Judgment module, for the event trace behavioral data to be compared with the characteristic in abnormal behavior library,
To judge whether the event trace behavioral data includes abnormal behaviour data；
Determining module, if including abnormal behaviour data for the event trace behavioral data, it is determined that the event trace behavior
The affiliated personnel of data are a suspect.
6. device according to claim 5, which is characterized in that the determining module is specifically used for：
If the event trace behavioral data includes abnormal behaviour data, abnormal row in the event trace behavioral data is judged
Whether it is greater than or equal to preset time threshold for the data corresponding abnormal behaviour duration；If the abnormal behaviour duration
More than or equal to preset time threshold, then judge the event trace behavioral data include abnormal behaviour data number whether
More than or equal to predetermined number threshold value；If the number of the abnormal behaviour data is greater than or equal to predetermined number threshold value, it is determined that
The affiliated personnel of the event trace behavioral data are a suspect.
7. device according to claim 5 or 6, which is characterized in that the acquisition module is specifically used for：
Acquisition enters the behavioral data of each personnel of monitoring area；Based on face recognition technology by the behavior number of same personnel
According to being spliced sequentially in time, the event trace behavioral data of each personnel is formed.
8. device according to claim 7, which is characterized in that further include：
Acquisition module acquires the video data of a variety of densely populated public places；
Characteristic extracting module, for carrying out feature extraction to the video data and classifying, to obtain abnormal behavior data；
Module is built, for building abnormal behaviour database according to the abnormal behavior data.
9. a kind of identification device of a suspect, which is characterized in that including：
Memory, processor and computer program；
Wherein, the computer program is stored in the memory, and is configured as being executed to realize such as by the processor
Method described in any one of claim 1-4.
10. a kind of computer readable storage medium, which is characterized in that be stored thereon with computer program, the computer program
It is executed by processor to realize the method as described in any one of claim 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810448414.9A CN108664608A (en) | 2018-05-11 | 2018-05-11 | Recognition methods, device and the computer readable storage medium of a suspect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810448414.9A CN108664608A (en) | 2018-05-11 | 2018-05-11 | Recognition methods, device and the computer readable storage medium of a suspect |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108664608A true CN108664608A (en) | 2018-10-16 |
Family
ID=63778481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810448414.9A Pending CN108664608A (en) | 2018-05-11 | 2018-05-11 | Recognition methods, device and the computer readable storage medium of a suspect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108664608A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784175A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Abnormal behaviour people recognition methods, equipment and storage medium based on micro- Expression Recognition |
| CN109815820A (en) * | 2018-12-26 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Object localization method and relevant apparatus |
| CN110298254A (en) * | 2019-05-30 | 2019-10-01 | 罗普特科技集团股份有限公司 | A kind of analysis method and system for personnel's abnormal behaviour |
| CN110321582A (en) * | 2019-03-22 | 2019-10-11 | 贵阳博烁科技有限公司 | A kind of pyramid schemes analysis method and device |
| CN111309954A (en) * | 2020-02-24 | 2020-06-19 | 浙江力石科技股份有限公司 | Scenic spot shopping guide behavior recognition system |
| CN111353426A (en) * | 2020-02-28 | 2020-06-30 | 山东浪潮通软信息科技有限公司 | Abnormal behavior detection method and device |
| CN111353414A (en) * | 2020-02-25 | 2020-06-30 | 重庆中科云从科技有限公司 | Identity recognition method, system, machine readable medium and equipment |
| CN111552007A (en) * | 2020-05-26 | 2020-08-18 | 上海量卿科技有限公司 | Inspection system and method |
| CN111553192A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Hierarchical authority unlocking method and device and storage medium |
| CN111694854A (en) * | 2020-06-05 | 2020-09-22 | 北京百度网讯科技有限公司 | Method and device for monitoring entrance and exit of area, electronic equipment and storage medium |
| CN112016363A (en) * | 2019-05-30 | 2020-12-01 | 富泰华工业（深圳）有限公司 | Personnel monitoring method and device, computer device and readable storage medium |
| CN112507772A (en) * | 2020-09-03 | 2021-03-16 | 广州市标准化研究院 | Face recognition security system and suspicious person detection and early warning method |
| CN113343743A (en) * | 2020-03-03 | 2021-09-03 | 杭州海康威视系统技术有限公司 | Target person identification method and device, electronic equipment and storage medium |
| WO2022165685A1 (en) * | 2021-02-03 | 2022-08-11 | 京东方科技集团股份有限公司 | Method for determining dangerousness of person, apparatus, system and storage medium |
| CN114898516A (en) * | 2022-04-13 | 2022-08-12 | 深圳市鸿普森科技股份有限公司 | Operation and maintenance monitoring service management system based on Internet of things |
| CN115225298A (en) * | 2021-04-17 | 2022-10-21 | 华为技术有限公司 | Prompting method, related device and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105404895A (en) * | 2015-11-03 | 2016-03-16 | 中国联合网络通信集团有限公司 | Abnormal state identification method and identification system |
| CN106033530A (en) * | 2015-03-11 | 2016-10-19 | 中兴通讯股份有限公司 | Identification method and apparatus for suspected person |
| CN107958382A (en) * | 2017-12-06 | 2018-04-24 | 北京小度信息科技有限公司 | Abnormal behaviour recognition methods, device, electronic equipment and storage medium |
-
2018
- 2018-05-11 CN CN201810448414.9A patent/CN108664608A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033530A (en) * | 2015-03-11 | 2016-10-19 | 中兴通讯股份有限公司 | Identification method and apparatus for suspected person |
| CN105404895A (en) * | 2015-11-03 | 2016-03-16 | 中国联合网络通信集团有限公司 | Abnormal state identification method and identification system |
| CN107958382A (en) * | 2017-12-06 | 2018-04-24 | 北京小度信息科技有限公司 | Abnormal behaviour recognition methods, device, electronic equipment and storage medium |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784175A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Abnormal behaviour people recognition methods, equipment and storage medium based on micro- Expression Recognition |
| CN109815820A (en) * | 2018-12-26 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Object localization method and relevant apparatus |
| CN110321582A (en) * | 2019-03-22 | 2019-10-11 | 贵阳博烁科技有限公司 | A kind of pyramid schemes analysis method and device |
| CN110321582B (en) * | 2019-03-22 | 2023-05-26 | 贵阳博烁科技有限公司 | Method and device for analyzing marketing activity |
| CN112016363A (en) * | 2019-05-30 | 2020-12-01 | 富泰华工业（深圳）有限公司 | Personnel monitoring method and device, computer device and readable storage medium |
| CN110298254A (en) * | 2019-05-30 | 2019-10-01 | 罗普特科技集团股份有限公司 | A kind of analysis method and system for personnel's abnormal behaviour |
| CN111309954A (en) * | 2020-02-24 | 2020-06-19 | 浙江力石科技股份有限公司 | Scenic spot shopping guide behavior recognition system |
| CN111309954B (en) * | 2020-02-24 | 2023-10-17 | 浙江力石科技股份有限公司 | Scenic spot shopping guide behavior identification system |
| CN111353414A (en) * | 2020-02-25 | 2020-06-30 | 重庆中科云从科技有限公司 | Identity recognition method, system, machine readable medium and equipment |
| CN111353426A (en) * | 2020-02-28 | 2020-06-30 | 山东浪潮通软信息科技有限公司 | Abnormal behavior detection method and device |
| CN113343743A (en) * | 2020-03-03 | 2021-09-03 | 杭州海康威视系统技术有限公司 | Target person identification method and device, electronic equipment and storage medium |
| CN113343743B (en) * | 2020-03-03 | 2024-02-13 | 杭州海康威视系统技术有限公司 | Target person identification method, device, electronic equipment and storage medium |
| CN111553192A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Hierarchical authority unlocking method and device and storage medium |
| CN111552007A (en) * | 2020-05-26 | 2020-08-18 | 上海量卿科技有限公司 | Inspection system and method |
| CN111694854A (en) * | 2020-06-05 | 2020-09-22 | 北京百度网讯科技有限公司 | Method and device for monitoring entrance and exit of area, electronic equipment and storage medium |
| CN111694854B (en) * | 2020-06-05 | 2023-07-21 | 北京百度网讯科技有限公司 | Regional access monitoring method and device, electronic equipment and storage medium |
| CN112507772A (en) * | 2020-09-03 | 2021-03-16 | 广州市标准化研究院 | Face recognition security system and suspicious person detection and early warning method |
| WO2022165685A1 (en) * | 2021-02-03 | 2022-08-11 | 京东方科技集团股份有限公司 | Method for determining dangerousness of person, apparatus, system and storage medium |
| CN115225298A (en) * | 2021-04-17 | 2022-10-21 | 华为技术有限公司 | Prompting method, related device and system |
| CN115225298B (en) * | 2021-04-17 | 2024-05-10 | 华为技术有限公司 | Prompting method, related device and system |
| CN114898516A (en) * | 2022-04-13 | 2022-08-12 | 深圳市鸿普森科技股份有限公司 | Operation and maintenance monitoring service management system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664608A (en) | Recognition methods, device and the computer readable storage medium of a suspect | |
| CN108629322A (en) | Monitoring method, device and the computer readable storage medium of a suspect | |
| US10271017B2 (en) | System and method for generating an activity summary of a person | |
| WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
| CN111008568B (en) | Ticket escape detection method and related device thereof | |
| CN106022296B (en) | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| CN103578018A (en) | Method, device and system for detecting lost sales due to an out-of-shelf condition | |
| CN109961587A (en) | A kind of monitoring system of self-service bank | |
| CN108171340A (en) | For carrying out mirror method for distinguishing, equipment and storage medium to bicycle repairing information | |
| US8200595B1 (en) | Determing a disposition of sensor-based events using decision trees with splits performed on decision keys | |
| CN111476177A (en) | Method and device for detecting suspect | |
| CN101692281A (en) | Safety monitoring method, safety monitoring device and automatic teller machine (ATM) system | |
| CN110321582B (en) | Method and device for analyzing marketing activity | |
| CN107920224A (en) | A kind of abnormality alarming method, equipment and video monitoring system | |
| CN108171187A (en) | A kind of abnormal behaviour automatic identifying method and device based on the extraction of bone point | |
| CN116778657A (en) | Method and system for intelligently identifying intrusion behavior | |
| CN111126167A (en) | Method and system for quickly identifying series activities of multiple specific persons | |
| CN113408445A (en) | Method, device, equipment and storage medium for analyzing violation behaviors of locomotive crew members | |
| CN111144180B (en) | Risk detection method and system for monitoring video | |
| CN117690189B (en) | Charging station dangerous behavior identification method and monitoring system based on artificial intelligence | |
| KR102644230B1 (en) | Mysterious symptom detection system using AI variable threshold | |
| KR102659067B1 (en) | Door access management system applying deep learning | |
| CN117354469B (en) | District monitoring video target tracking method and system based on security precaution | |
| CN116757336B (en) | Track traffic risk prediction method and system based on data driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181016 |
|
| RJ01 | Rejection of invention patent application after publication |