CN109376639A - Adjoint personnel's early warning system and method based on Identification of Images - Google Patents
Adjoint personnel's early warning system and method based on Identification of Images Download PDFInfo
- Publication number
- CN109376639A CN109376639A CN201811199697.4A CN201811199697A CN109376639A CN 109376639 A CN109376639 A CN 109376639A CN 201811199697 A CN201811199697 A CN 201811199697A CN 109376639 A CN109376639 A CN 109376639A
- Authority
- CN
- China
- Prior art keywords
- personnel
- target person
- adjoint
- portrait
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Abstract
For the problem that analyzing the method for being generally used ex-post analysis with personnel, can not accomplish to prevent in advance, the present invention provides a kind of adjoint personnel's early warning system and method based on Identification of Images, belongs to Identification of Images applied technical field.The present invention includes: Identification of Images module, the portrait for each point of real-time detection;With rule setting module, for being arranged with rule, and/or the user-defined target person of input;Logic judgment module, for judging whether the portrait of detection is target person, when being determined as target person, records its space-time trajectory, and caching of target personnel portrait characteristic set in each effective adjoint time range for space-time point occur;When the space-time trajectory of target person reaches with testing conditions, according to the set and with rule, the adjoint personnel of target person are obtained;Early warning output module, for that will be exported with personnel's early warning;The present invention can intervene in the awake related management personnel of crime premise, have the function that prevention.
Description
Technical field
The present invention relates to a kind of early warning system and method, in particular to a kind of adjoint personnel's early warning system based on Identification of Images
System and method, belong to Identification of Images applied technical field.
Background technique
In field of face identification, the internal staff's photo registered in picture and system is captured using field camera and is carried out certainly
Two pictures that similarity is more than threshold value are considered as the same person by the way that threshold value is arranged by dynamic feature point extraction and comparison, are exported and are
Identity identification, thus complete face deploy to ensure effective monitoring and control of illegal activities alarm etc. public security case cracking.
But in practical public security and government's anti-terrorism, stability maintenance and security administration work in, most important work be prevention and in time
Note abnormalities personnel or abnormal behaviour, and then early intervenes, and early takes measures, and finds and controls before even committing a crime crime early period as far as possible
Suspect processed avoids " mending the fold after the sheep is lost ".
Therefore, the simple mode using personnel's picture alarm of deploying to ensure effective monitoring and control of illegal activities is not able to satisfy the demand, it is also not possible to all cases
All know that whom crime one's share of expenses for a joint undertaking is in advance, may not necessarily more take the clear face picture of target, therefore often can not be true in real work
Just for used in line manager.
Summary of the invention
For the problem that analyzing the method for being generally used ex-post analysis with personnel, can not accomplish to prevent in advance, this hair
It is bright that a kind of adjoint personnel's early warning system and method based on Identification of Images is provided.
A kind of adjoint personnel's early warning system based on Identification of Images, the system comprises:
Identification of Images module, the portrait for each point of real-time detection;
With rule setting module, for being arranged with rule, and/or the user-defined target person of input;It is described to set
Set the one or more characteristic conditions other than portrait feature being arranged with rule with personnel;
Logic judgment module, the portrait for will test extracts feature to be compared with the characteristic set in target person library
It is right, judged by similarity threshold, when being determined as target person, records the space-time trajectory of the target person, and caching of target
Personnel's portrait characteristic set in each effective adjoint time range for space-time point occur;It is also used to the space-time when target person
When track is reached with testing conditions, according to the set and with rule, the adjoint personnel of the target person are obtained;
Early warning output module, for that will be exported with personnel's early warning;
Portrait track library, for storing portrait feature, track and the adjoint rule of each point;
Target person library, for storing the portrait characteristic set of target person.
Preferably, the adjoint testing conditions are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
Preferably, in the logic judgment module, the adjoint personnel of the target person are obtained, comprising:
When the space-time trajectory of target person reaches with testing conditions, to the portrait in the corresponding set of the target person
Feature carries out clustering, obtains the space-time trajectory with personnel;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine this with people
Member is the adjoint personnel of the target person.
Preferably, the characteristic condition in the adjoint rule setting module is with personnel identity definition, with front and back
Time, same personnel track merge period, adjoint personnel and target person frequency of occurrence, gender, age, clothing or wearing simultaneously
Object.
Preferably, the logic judgment module is also used to when determining target person is without the adjoint people met with rule
When member, which is individually trip;
The early warning output module is also used to the target person individually gone on a journey carrying out early warning output.
Preferably, feature in the logic judgment module, portrait feature for will test and target person library into
Row compares, comprising:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, are sentenced
The portrait that breaks is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, described in judgement
Portrait is non-targeted personnel's portrait.
The invention also includes a kind of adjoint personnel's method for early warning based on Identification of Images, which is characterized in that the method packet
It includes:
The portrait of each point of S1, real-time detection;
S2, setting are with rule, and/or the user-defined target person of input;The setting is setting companion with rule
With one or more characteristic conditions other than portrait feature of personnel;
Store the portrait feature of each point, track and with rule to portrait track library;
S3, the portrait that will test extract feature and are compared with the characteristic set in target person library, pass through similarity threshold
Value judgement records the space-time trajectory of the target person when being determined as target person, and caching of target personnel it is each occur when
Portrait characteristic set in effective adjoint time range of null point position;It is also used to reach when the space-time trajectory of target person with detection
When condition, according to the set and with rule, the adjoint personnel of the target person are obtained;
The characteristic set of target person library storage target person;
S4, it will be exported with personnel's early warning.
Preferably, the adjoint testing conditions are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
Preferably, in the S3, the adjoint personnel of the target person are obtained, comprising:
When the space-time trajectory of target person reaches with testing conditions, to the portrait in the corresponding set of the target person
Feature carries out clustering, obtains the space-time trajectory with personnel;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine this with people
Member is the adjoint personnel of the target person.
Preferably, in the S3, the characteristic condition is with personnel identity definition, with surrounding time, same person
Member track merges period, adjoint personnel and target person frequency of occurrence, gender, age, clothing or wear simultaneously.
Preferably, the S3 further include: when determining target person without the adjoint personnel with rule are met, the target
Personnel are individually trip;
The S4 further include: the target person individually gone on a journey is subjected to early warning output.
Preferably, in the S3, the portrait feature for will test is compared with the feature in target person library, packet
It includes:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, are sentenced
The portrait that breaks is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, described in judgement
Portrait is non-targeted personnel's portrait.
Beneficial effects of the present invention, the present invention is based on portrait detection and comparison and identification technologies, in real time to all passing points
The personnel of position analyze, and cache front and back demographic data, carry out target person with state point according to Identification of Images result
Analysis, so that real-time early warning output is carried out to adjoint state personnel set by user are reached, it is related so as to wake up in crime premise
Administrative staff intervene, and reach early warning, the effect of prevention.
Detailed description of the invention
Fig. 1 is the schematic illustration of adjoint personnel's early warning system based on Identification of Images in the specific embodiment of the invention;
Fig. 2 is the flow diagram of the specific embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art without creative labor it is obtained it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The present invention will be further explained below with reference to the attached drawings and specific examples, but not as the limitation of the invention.
A kind of adjoint personnel's early warning system based on Identification of Images of present embodiment, as shown in Figure 1, present embodiment
System includes:
Identification of Images module, the portrait for each point of real-time detection;
With rule setting module, for being arranged with rule, and/or the user-defined target person of input;It is described to set
Set the one or more characteristic conditions other than portrait feature being arranged with rule with personnel;
Logic judgment module, the portrait for will test extracts feature to be compared with the characteristic set in target person library
It is right, judged by similarity threshold, when being determined as target person, merge the period judgement, record the target person when
Empty track, and caching of target personnel portrait characteristic set in each effective adjoint time range for space-time point occur;Also use
When the space-time trajectory when target person reaches with testing conditions, according to the set and with rule, the target is obtained
The adjoint personnel of personnel;
Early warning output module, for that will be exported with personnel's early warning;
Portrait track library, for storing portrait, track and the adjoint rule of each point;
Target person library, for storing the characteristic set of target person.
The feature of present embodiment target person library storage includes: portrait feature and advanced features, and advanced features include companion
Merge the period with personnel identity definition, with surrounding time, same personnel track, go out occurrence simultaneously with personnel and target person
Number, gender, age, clothing and/or wear;The portrait track library of present embodiment is certain for storing in certain time range
The magnanimity portrait track in place (point) and adjoint rule, portrait track are used to obtain target person or the space-time rail with personnel
Mark, it may be assumed that all personnel by point of storage are convenient for subsequent judgement early warning.
In present embodiment, merge the period by the way that same personnel track is arranged with rule setting module, for that will set
Personnel in time carry out time of occurrence point and place merges, and avoid a people meaningless multiplicating output in a short time, such as
One people hovers before video camera, and a space-time point is calculated as in the period.
Present embodiment is detected using portrait, feature identification and face recognition technology, to the mesh for meeting certain figure and features features
The aspect ratio pair of mark personnel (such as children, old man) and the emphasis personnel being pre-stored in target person library carry out identity validation,
Space-time trajectory record is carried out to the target person of confirmation, and caches the face characteristic in front and back a period of time of each of which appearance point
Record carries out real-time monitoring record with this logic, when the track for confirming target person meets with testing conditions, obtains therewith
The personnel's space-time trajectory information occurred simultaneously, according to the adjoint personnel for obtaining target person with rule of setting, early warning output.
Present embodiment is analyzed by the personnel of point all, and caches front and back demographic data, according to Identification of Images result pair
Target person is carried out with state analysis, so that real-time early warning output is carried out to adjoint state personnel set by user are reached, from
And can intervene in the awake related management personnel of crime premise, reach early warning, the effect of prevention.
In preferred embodiment, the adjoint testing conditions of present embodiment are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
In present embodiment, according to the space-time trajectory of target person, will occur in some point/several points or
In some point/several points frequency of occurrence as threshold value, with to determine whether needing to detect the adjoint people of the target person
Member.
In preferred embodiment, in the logic judgment module of present embodiment, the adjoint personnel of the target person are obtained, are wrapped
It includes:
When the space-time trajectory of target person reaches with testing conditions, to the portrait in the corresponding set of the target person
Feature carries out clustering, and merges period judgement, obtains the space-time trajectory with personnel;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine this with people
Member is the adjoint personnel of the target person.
Present embodiment will be compared with the space-time trajectory of personnel with the space-time trajectory of target person, with space-time
Frequency meets setting condition, such as: with number, present embodiment obtains the space-time trajectory of same administrative staff according to cluster result
Information is exported with the personnel of spatio-temporal frequency setting condition to meeting, is realized to target emphasis gathering of people early warning, can also
Target person early warning is trailed to someone to realize.
In preferred embodiment, in present embodiment, the characteristic condition in the adjoint rule setting module is with personnel
Identity definition merges period setting with surrounding time, same personnel track, goes out occurrence simultaneously with personnel and target person
Number, gender, age, clothing (color, texture) or wear (cap, glasses, mask).
Present embodiment reduces the scope for option, with face characteristic carry out with or combine, improve early warning range or
Precision.
In preferred embodiment, the logic judgment module of present embodiment is also used to when determining target person is adjoint without meeting
When the adjoint personnel of rule, which is individually trip;
The early warning output module is also used to the target person individually gone on a journey carrying out early warning output.
Present embodiment goes on a journey alone early warning to target person unsupervised according to setting condition.
In preferred embodiment, the logic judgment module of present embodiment, portrait feature and target person for will test
Feature in library is compared, comprising:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, are sentenced
The portrait that breaks is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, described in judgement
Portrait is non-targeted personnel's portrait.
Present embodiment supports that personnel's progress identity validation, confirmation external staff is not in target person library, confirmation weight
Point personnel are emphasis personnel in target person library, and user can be allowed to meet practical business demand by configuring flexible realization.Companion
It is identical as target person identity validation mode with the identity validation of personnel.
Present embodiment also provides a kind of adjoint personnel's method for early warning based on Identification of Images, the method packet of present embodiment
It includes:
The portrait of each point of S1, real-time detection;
S2, setting are with rule, and/or the user-defined target person of input;The setting is setting companion with rule
With one or more characteristic conditions other than portrait feature of personnel;
Store the portrait of each point, track and with rule to portrait track library;
S3, the portrait that will test extract feature and are compared with the characteristic set in target person library, pass through similarity threshold
Value judgement records the space-time trajectory of the target person when being determined as target person, and caching of target personnel it is each occur when
Portrait characteristic set in effective adjoint time range of null point position;It is also used to reach when the space-time trajectory of target person with detection
When condition, according to the set and with rule, the adjoint personnel of the target person are obtained;
The characteristic set of target person library storage target person;
S4, it will be exported with personnel's early warning.
In preferred embodiment, the adjoint testing conditions of present embodiment are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
In preferred embodiment, in the S3 of present embodiment, the adjoint personnel of the target person are obtained, comprising:
When the space-time trajectory of target person reaches with testing conditions, to the portrait in the corresponding set of the target person
Feature carries out clustering, and merges period judgement, obtains the space-time trajectory with personnel;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine this with people
Member is the adjoint personnel of the target person.
In preferred embodiment, in the S3, the characteristic condition is with personnel identity definition, with surrounding time, companion
With personnel and target person frequency of occurrence, gender, age, clothing or wear simultaneously.
In preferred embodiment, the S2 of present embodiment further include: when determine target person without meet with rule it is adjoint
When personnel, which is individually trip;
The S4 further include: the target person individually gone on a journey is subjected to early warning output.
The spy in portrait feature and target person library in preferred embodiment, in the S3 of present embodiment, for will test
Sign is compared, comprising:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, are sentenced
The portrait that breaks is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, described in judgement
Portrait is non-targeted personnel's portrait.
Specific embodiment: as shown in Fig. 2, a kind of adjoint personnel's method for early warning based on Identification of Images of present embodiment,
Include the following steps:
Step 1: the portrait of each point of real-time detection;
Step 2: there is the progress feature identification of portrait target to each, and carries out face characteristic with target person library and compare,
Advanced features are carried out after comparing successfully to be matched, and judge whether the portrait target is target person, the advanced spy in this step
Sign include: with personnel identity definition, with surrounding time, with personnel and target person frequency of occurrence, gender, year simultaneously
Age, clothing and/or wear are transferred to step 3 if successful match, if it is not, portrait and track characteristic are stored in portrait track library
In;
Step 3: recording target person id, be compared with portrait track library, and check whether to meet same personnel rail
Mark merges periodic condition, if it is satisfied, merging, is otherwise calculated as individual space-time node, counts ID personnel's frequency of occurrence;
Step 4: if it is more than threshold value that the id personnel, which add up frequency of occurrence, step 5 is transferred to, if it is not, by target person id
In portrait and track characteristic deposit portrait track library;
Step 5: recording and count all personnel people in this id personnel in each adjoint time range for point occur
As characteristic set;
Step 6: personnel's cluster being carried out to portrait characteristic set, and checks whether that meeting same personnel track merges period item
Otherwise part is calculated as individual space-time node, obtains the space-time trajectory of each id if it is satisfied, merging;
Step 7: the space-time trajectory for each id that step 6 obtains is compared with the space-time trajectory of target person id, if
Reach with frequency threshold value, determines that corresponding id is to be transferred to step 8, otherwise, which terminates with personnel id;
Step 8: judge whether the adjoint personnel identity of the id meets with rule, if so, will be exported with personnel's early warning,
And the site occurred with personnel is recorded, if it is not, the thread terminates.
Although describing the present invention herein with reference to specific embodiment, it should be understood that, these realities
Apply the example that example is only principles and applications.It should therefore be understood that can be carried out to exemplary embodiment
Many modifications, and can be designed that other arrangements, without departing from spirit of the invention as defined in the appended claims
And range.It should be understood that different appurtenances can be combined by being different from mode described in original claim
Benefit requires and feature described herein.It will also be appreciated that the feature in conjunction with described in separate embodiments can be used
In other described embodiments.
Claims (12)
1. a kind of adjoint personnel's early warning system based on Identification of Images, which is characterized in that the system comprises:
Identification of Images module, the portrait for each point of real-time detection;
With rule setting module, for being arranged with rule, and/or the user-defined target person of input;The setting companion
Anywhere rule one or more characteristic conditions other than portrait feature for adjoint personnel are arranged;
Logic judgment module, the portrait for will test extract feature and are compared with the characteristic set in target person library, lead to
Similarity threshold judgement is crossed, when being determined as target person, records the space-time trajectory of the target person, and caching of target personnel exist
Portrait characteristic set in each effective adjoint time range for space-time point occur;It is also used to reach when the space-time trajectory of target person
When to testing conditions, according to the set and with rule, the adjoint personnel of the target person are obtained;
Early warning output module, for that will be exported with personnel's early warning;
Portrait track library, for storing portrait feature, track and the adjoint rule of each point;
Target person library, for storing the characteristic set of target person.
2. adjoint personnel's early warning system according to claim 1 based on Identification of Images, which is characterized in that described with inspection
Survey condition are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
3. adjoint personnel's early warning system according to claim 1 or 2 based on Identification of Images, which is characterized in that described to patrol
It collects in judgment module, obtains the adjoint personnel of the target person, comprising:
When the space-time trajectory of target person reaches with testing conditions, to the portrait feature in the corresponding set of the target person
Clustering is carried out, the space-time trajectory with personnel is obtained;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine that this is with personnel
The adjoint personnel of the target person.
4. adjoint personnel's early warning system according to claim 3 based on Identification of Images, which is characterized in that described with rule
Then the characteristic condition in setup module is to merge period, companion with personnel identity definition, with surrounding time, same personnel track
With personnel and target person frequency of occurrence, gender, age, clothing or wear simultaneously.
5. adjoint personnel's early warning system according to claim 1 based on Identification of Images, which is characterized in that the logic is sentenced
Disconnected module is also used to when determining target person without the adjoint personnel with rule are met, which is individually trip;
The early warning output module is also used to the target person individually gone on a journey carrying out early warning output.
6. adjoint personnel's early warning system according to claim 1 based on Identification of Images, which is characterized in that the logic is sentenced
Disconnected module, the portrait feature for will test are compared with the feature in target person library, comprising:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, judge institute
Stating portrait is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, judge the portrait
For non-targeted personnel's portrait.
7. a kind of adjoint personnel's method for early warning based on Identification of Images, which is characterized in that the described method includes:
The portrait of each point of S1, real-time detection;
S2, setting are with rule, and/or the user-defined target person of input;The setting is arranged with rule with people
One or more characteristic conditions other than portrait feature of member;
Store the portrait feature of each point, track and with rule to portrait track library;
S3, the portrait that will test extract feature and are compared with the characteristic set in target person library, are sentenced by similarity threshold
It is disconnected, when being determined as target person, the space-time trajectory of the target person is recorded, and caching of target personnel event occur each
Portrait characteristic set in effective adjoint time range of position;It is also used to reach when the space-time trajectory of target person with testing conditions
When, according to the set and with rule, obtain the adjoint personnel of the target person;Target person library stores target person
Characteristic set;
S4, it will be exported with personnel's early warning.
8. adjoint personnel's method for early warning according to claim 7 based on Identification of Images, which is characterized in that described with inspection
Survey condition are as follows:
Whether the space-time trajectory of target person is more than the threshold value for space-time point or frequency of occurrence occur.
9. adjoint personnel's method for early warning according to claim 7 or 8 based on Identification of Images, which is characterized in that the S3
In, obtain the adjoint personnel of the target person, comprising:
When the space-time trajectory of target person reaches with testing conditions, to the portrait feature in the corresponding set of the target person
Clustering is carried out, the space-time trajectory with personnel is obtained;
When certain with the space-time trajectory of personnel meet target person adjoint spatio-temporal frequency be arranged condition, determine that this is with personnel
The adjoint personnel of the target person.
10. adjoint personnel's method for early warning according to claim 9 based on Identification of Images, which is characterized in that in the S3,
The characteristic condition is to merge the period, with personnel and mesh with personnel identity definition, with surrounding time, same personnel track
Mark personnel while frequency of occurrence, gender, age, clothing or wear.
11. adjoint personnel's method for early warning according to claim 7 based on Identification of Images, which is characterized in that the S3 is also
It include: when determining target person without the adjoint personnel with rule are met, which is individually trip;
The S4 further include: the target person individually gone on a journey is subjected to early warning output.
12. adjoint personnel's method for early warning according to claim 7 based on Identification of Images, which is characterized in that in the S3,
Portrait feature for will test is compared with the feature in target person library, comprising:
Any feature or a few feature alignment similarities in the portrait feature that will test and target person library are more than threshold value, judge institute
Stating portrait is target person portrait;
All feature alignment similarities in the portrait feature that will test and target person library are below threshold value, judge the portrait
For non-targeted personnel's portrait.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811199697.4A CN109376639B (en) | 2018-10-16 | 2018-10-16 | Accompanying personnel early warning system and method based on portrait recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811199697.4A CN109376639B (en) | 2018-10-16 | 2018-10-16 | Accompanying personnel early warning system and method based on portrait recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109376639A true CN109376639A (en) | 2019-02-22 |
CN109376639B CN109376639B (en) | 2021-12-17 |
Family
ID=65399851
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811199697.4A Active CN109376639B (en) | 2018-10-16 | 2018-10-16 | Accompanying personnel early warning system and method based on portrait recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109376639B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109947793A (en) * | 2019-03-20 | 2019-06-28 | 深圳市北斗智能科技有限公司 | Analysis method, device and the storage medium of accompanying relationship |
CN109977108A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of a variety of track collision analysis methods in Behavior-based control track library |
CN110276272A (en) * | 2019-05-30 | 2019-09-24 | 罗普特科技集团股份有限公司 | Confirm method, apparatus, the storage medium of same administrative staff's relationship of label personnel |
CN110569720A (en) * | 2019-07-31 | 2019-12-13 | 安徽四创电子股份有限公司 | audio and video intelligent identification processing method based on audio and video processing system |
CN110674749A (en) * | 2019-09-24 | 2020-01-10 | 北京明略软件系统有限公司 | Fake-licensed vehicle identification method and device and storage medium |
CN111222404A (en) * | 2019-11-15 | 2020-06-02 | 北京市商汤科技开发有限公司 | Method, device and system for detecting co-pedestrian, electronic equipment and storage medium |
CN112364176A (en) * | 2020-10-26 | 2021-02-12 | 青岛海信网络科技股份有限公司 | Method, equipment and system for constructing personnel action track |
CN112653990A (en) * | 2020-09-18 | 2021-04-13 | 武汉爱迪科技股份有限公司 | Screening algorithm and system for close contact personnel |
CN114863637A (en) * | 2022-03-30 | 2022-08-05 | 财上门科技(北京)有限公司 | Hotel safety management system and method |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040017929A1 (en) * | 2002-04-08 | 2004-01-29 | Newton Security Inc. | Tailgating and reverse entry detection, alarm, recording and prevention using machine vision |
CN103400148A (en) * | 2013-08-02 | 2013-11-20 | 上海泓申科技发展有限公司 | Video analysis-based bank self-service area tailgating behavior detection method |
US20130314232A1 (en) * | 2012-05-23 | 2013-11-28 | Honeywell International Inc. | Tailgating detection |
CN104183039A (en) * | 2014-08-19 | 2014-12-03 | 花韬 | Anti-following system with function of human body biologic characteristic identification |
CN105022999A (en) * | 2015-07-12 | 2015-11-04 | 上海微桥电子科技有限公司 | Man code company real-time acquisition system |
US20160284183A1 (en) * | 2014-08-19 | 2016-09-29 | Sensormatic Electronics, LLC | Tailgating Detection in Frictionless Access Control System |
CN106778655A (en) * | 2016-12-27 | 2017-05-31 | 华侨大学 | A kind of entrance based on human skeleton is trailed and enters detection method |
CN106875679A (en) * | 2017-03-14 | 2017-06-20 | 东软集团股份有限公司 | Recognize the method and device of escort vehicle |
CN107292907A (en) * | 2017-07-14 | 2017-10-24 | 灵动科技(北京)有限公司 | A kind of method to following target to be positioned and follow equipment |
CN107861979A (en) * | 2017-09-27 | 2018-03-30 | 汉柏科技有限公司 | A kind of adjoint personnel's acquisition methods and system based on recognition of face |
CN108122013A (en) * | 2017-12-29 | 2018-06-05 | 重庆锐纳达自动化技术有限公司 | One kind, which follows, to be excluded non-to follow mesh calibration method in movement |
-
2018
- 2018-10-16 CN CN201811199697.4A patent/CN109376639B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040017929A1 (en) * | 2002-04-08 | 2004-01-29 | Newton Security Inc. | Tailgating and reverse entry detection, alarm, recording and prevention using machine vision |
US20130314232A1 (en) * | 2012-05-23 | 2013-11-28 | Honeywell International Inc. | Tailgating detection |
CN103400148A (en) * | 2013-08-02 | 2013-11-20 | 上海泓申科技发展有限公司 | Video analysis-based bank self-service area tailgating behavior detection method |
CN104183039A (en) * | 2014-08-19 | 2014-12-03 | 花韬 | Anti-following system with function of human body biologic characteristic identification |
US20160284183A1 (en) * | 2014-08-19 | 2016-09-29 | Sensormatic Electronics, LLC | Tailgating Detection in Frictionless Access Control System |
CN105022999A (en) * | 2015-07-12 | 2015-11-04 | 上海微桥电子科技有限公司 | Man code company real-time acquisition system |
CN106778655A (en) * | 2016-12-27 | 2017-05-31 | 华侨大学 | A kind of entrance based on human skeleton is trailed and enters detection method |
CN106875679A (en) * | 2017-03-14 | 2017-06-20 | 东软集团股份有限公司 | Recognize the method and device of escort vehicle |
CN107292907A (en) * | 2017-07-14 | 2017-10-24 | 灵动科技(北京)有限公司 | A kind of method to following target to be positioned and follow equipment |
CN107861979A (en) * | 2017-09-27 | 2018-03-30 | 汉柏科技有限公司 | A kind of adjoint personnel's acquisition methods and system based on recognition of face |
CN108122013A (en) * | 2017-12-29 | 2018-06-05 | 重庆锐纳达自动化技术有限公司 | One kind, which follows, to be excluded non-to follow mesh calibration method in movement |
Non-Patent Citations (1)
Title |
---|
李晋等: "基于双层异构深度神经网络模型的人脸识别关键技术研究", 《电信工程技术与标准化》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109947793A (en) * | 2019-03-20 | 2019-06-28 | 深圳市北斗智能科技有限公司 | Analysis method, device and the storage medium of accompanying relationship |
CN109977108A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of a variety of track collision analysis methods in Behavior-based control track library |
CN109977108B (en) * | 2019-04-03 | 2021-04-27 | 深圳市甲易科技有限公司 | Behavior trajectory library-based multi-trajectory collision analysis method |
CN110276272A (en) * | 2019-05-30 | 2019-09-24 | 罗普特科技集团股份有限公司 | Confirm method, apparatus, the storage medium of same administrative staff's relationship of label personnel |
CN110569720A (en) * | 2019-07-31 | 2019-12-13 | 安徽四创电子股份有限公司 | audio and video intelligent identification processing method based on audio and video processing system |
CN110674749A (en) * | 2019-09-24 | 2020-01-10 | 北京明略软件系统有限公司 | Fake-licensed vehicle identification method and device and storage medium |
CN110674749B (en) * | 2019-09-24 | 2022-10-25 | 北京明智和术科技有限公司 | Fake-licensed vehicle identification method and device and storage medium |
CN111222404A (en) * | 2019-11-15 | 2020-06-02 | 北京市商汤科技开发有限公司 | Method, device and system for detecting co-pedestrian, electronic equipment and storage medium |
CN112653990A (en) * | 2020-09-18 | 2021-04-13 | 武汉爱迪科技股份有限公司 | Screening algorithm and system for close contact personnel |
CN112364176A (en) * | 2020-10-26 | 2021-02-12 | 青岛海信网络科技股份有限公司 | Method, equipment and system for constructing personnel action track |
CN114863637A (en) * | 2022-03-30 | 2022-08-05 | 财上门科技(北京)有限公司 | Hotel safety management system and method |
CN114863637B (en) * | 2022-03-30 | 2023-10-17 | 财上门科技(北京)有限公司 | Hotel security management system and method |
Also Published As
Publication number | Publication date |
---|---|
CN109376639B (en) | 2021-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109376639A (en) | Adjoint personnel's early warning system and method based on Identification of Images | |
US20200202113A1 (en) | Object tracking and best shot detection system | |
US9875392B2 (en) | System and method for face capture and matching | |
US9646228B2 (en) | Role-based tracking and surveillance | |
CN101266704B (en) | ATM secure authentication and pre-alarming method based on face recognition | |
Lyon | Technology vs ‘terrorism’: circuits of city surveillance since September 11th | |
KR101215948B1 (en) | Image information masking method of monitoring system based on face recognition and body information | |
CN102201061B (en) | Intelligent safety monitoring system and method based on multilevel filtering face recognition | |
CN103714631B (en) | ATM cash dispenser intelligent monitor system based on recognition of face | |
WO2018180588A1 (en) | Facial image matching system and facial image search system | |
US20030040925A1 (en) | Vision-based method and apparatus for detecting fraudulent events in a retail environment | |
CN101556717A (en) | ATM intelligent security system and monitoring method | |
JP7201072B2 (en) | Surveillance device, suspicious object detection method, and program | |
TWI797411B (en) | information processing device | |
KR101957677B1 (en) | System for learning based real time guidance through face recognition and the method thereof | |
JP2019096179A (en) | Behavior monitoring system | |
Kale et al. | Real Time Face Mask Detection-A Survey | |
Dirgantara et al. | Design of Face Recognition Security System on Public Spaces | |
KR20210007672A (en) | System and method for detection of dangerous situation | |
Geng et al. | Abnormal behavior detection for early warning of terrorist attack | |
Aparna et al. | Data Anonymization on Biometric Security Using Iris Recognition Technology | |
CN117953569A (en) | Face recognition system and logistics system of face recognition system | |
Ganiyu et al. | Intelligent Criminal Identification System For Semi-Regulated Environments | |
Patil et al. | A Review: Office Monitoring and Surveillance System | |
Seemanthini et al. | Real Time Unusual Event Detection In Videos To Enhance Atm Security |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |