CN207233038U - Face is called the roll and number system - Google Patents
Face is called the roll and number system Download PDFInfo
- Publication number
- CN207233038U CN207233038U CN201720788509.6U CN201720788509U CN207233038U CN 207233038 U CN207233038 U CN 207233038U CN 201720788509 U CN201720788509 U CN 201720788509U CN 207233038 U CN207233038 U CN 207233038U
- Authority
- CN
- China
- Prior art keywords
- face
- roll
- camera
- unit
- call
- 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.)
- Active
Links
Abstract
Artificial intelligence and automation field are the utility model is related to, discloses a kind of face roll-call and number system, including：Depth camera, general camera, Face datection unit and roll-call and counting unit；Depth camera is connected with general camera；General camera is connected with Face datection unit；Face datection unit and depth camera are connected with calling the roll with counting unit respectively.Pass through depth camera and face snap camera, personnel are counted to associate with facial image and completes face roll-call and counts, except accurate demographics can be provided as a result, the face information for the personnel of being counted can also be provided, suitable for the place of security requirement higher.
Description
Technical field
Artificial intelligence and automation field are the utility model is related to, more particularly to a kind of face is called the roll and number system.
Background technology
As a typical case of computer vision field, the people in particular place (such as public security supervision, prison etc.)
Member call the roll count, and in common chamber place (such as large-scale style venue entrances etc.) demographics in public safety, people
Many aspects such as flow business data statistical analysis have important application value.
In the prior art, the demographics in above application scene, are typically only capable to realize demographics substantially, it is impossible to
Accurate demographics are provided as a result, the face information for the personnel of being counted can not be provided, in accuracy, real-time etc.
All have much room for improvement.
Therefore, accuracy and the face roll-call of real-time and number system are met there is an urgent need for a kind of at present, so as to improve public
Real-time, the accuracy of indoor place demographic method, and the face information for the personnel of being counted can be provided.
The content of the invention
The purpose of this utility model is to provide a kind of roll-call of face and number system, it is not only able to provide accurate number
Statistical result, moreover it is possible to provide the face information for the personnel of being counted, meet the security requirement of higher standard.
In order to solve the above technical problems, the embodiment of the utility model discloses a kind of face roll-call and number system,
Including：
Depth camera, general camera, Face datection unit and roll-call and counting unit；
Depth camera is connected with general camera；
General camera is connected with Face datection unit；
Face datection unit and depth camera are connected with calling the roll with counting unit respectively；
Depth camera, for gathering the depth image of scene, when detecting that someone reaches by depth image, carries out head and shoulder
Detection is counted with number；
General camera, for capturing facial image, obtains human face image sequence；
Face datection unit, the human face image sequence for being captured to general camera carry out human face detection and tracing；
Call the roll and counting unit, for associating this counting of face that face detection unit detects to depth camera,
Obtain number of people entering information and corresponding face information.
Compared with prior art, the main distinction and its effect are the utility model embodiment：
By the way that depth camera and face snap camera is used in combination, personnel are counted to associate with facial image and complete people
Face is called the roll and counted, and except that can provide accurate demographics as a result, the face information for the personnel of being counted can also be provided, is fitted
Place for security requirement higher.
Further, by combine RGB-D information and RGB information, carry out Multi-information acquisition judgement, carry out face snap,
Head and shoulder is detected with that than reciprocity intelligent video analysis, can reach more preferable personnel and call the roll and demographics effect.
Further, the more common Visible Light Camera of depth camera can more accurately reduce the 3D information of target, to head and shoulder
The effect of detection is more preferable, and it is more accurate to count.
Further, after detecting face, with given list, that is, the Face Sample Storehouse for needing to call the roll is compared, sentences
Whether disconnected be personnel in list, is called the roll suitable for supervision, prison and the scenes such as personnel search.
Further, during capturing facial image, light compensating lamp is enabled when face is excessively dark and carries out light filling, with guarantor
Face image it is clear reliable.
Further, face snap is carried out by the double camera installed in different height, the people of different heights can be solved
Face snap problem.
Brief description of the drawings
Fig. 1 is the structural schematic block diagram that a kind of face is called the roll with number system in the utility model first embodiment；
Fig. 2 is the structure diagram that a kind of face is called the roll with number system in the utility model first embodiment；
Fig. 3 is the control flow chart that a kind of face is called the roll with number system in the utility model first embodiment.
Embodiment
In the following description, many ins and outs are proposed in order to make reader more fully understand the application.But this
Even if the those of ordinary skill in field is appreciated that without these ins and outs and many variations based on following embodiment
And modification, it can also realize each claim of the application technical solution claimed.
It is new to this practicality below in conjunction with attached drawing to make the purpose of this utility model, technical solution and advantage clearer
The embodiment of type is described in further detail.
The utility model first embodiment is related to a kind of face roll-call and number system.Fig. 1 is that face is called the roll and counted
The structural schematic block diagram of system, Fig. 2 are the structure diagrams that the face is called the roll with number system.
Specifically, as depicted in figs. 1 and 2, which calls the roll and includes with number system：
Depth camera 11, general camera 12, Face datection unit (not shown in Fig. 2) and roll-call are with counting unit (in Fig. 2
It is not shown)；
Depth camera 11 is connected with general camera 12；
General camera 12 is connected with Face datection unit；
Face datection unit and depth camera 11 are connected with calling the roll with counting unit respectively；
Depth camera 11, for gathering the depth image of scene, when detecting that someone reaches by depth image, into wardrobe
Shoulder is detected to be counted with number；
The more common Visible Light Camera of depth camera can more accurately reduce the 3D information of target, to the effect of head and shoulder detection
More preferably, it is more accurate to count.
General camera 12, for capturing facial image, obtains human face image sequence；
It should be noted that in each embodiment of the utility model, following two realities can be had by capturing facial image
Existing mode：
The first, captures camera (i.e. general camera) and is ceaselessly captured according to certain time interval；
Second, when depth camera detects that someone reaches, send trigger signal and capture camera to camera, triggering is captured and open
Begin to capture facial image.
Face datection unit, the human face image sequence for being captured to general camera carry out human face detection and tracing；
Call the roll and counting unit, for associating this counting of face that face detection unit detects to depth camera,
Obtain number of people entering information and corresponding face information.
Further, it is preferable to ground, which calls the roll can also include with number system：Comparing unit.
As shown in Figure 1, comparing unit is connected with Face datection unit, for carrying out face roll-call, by Face datection unit
The face detected carries out face alignment with given list, judges whether it is the personnel in list.
It should be noted that comparing unit is alternatively, only needing (to need the face called the roll with given list
Sample storehouse) need when being compared, call the roll suitable for supervision, prison and the scenes such as personnel search.
Light compensating lamp 13, is connected with general camera, during capturing facial image, when face is excessively dark, to face
Light filling is carried out, to ensure the clear reliable of facial image.
Further, it is preferable that the number of general camera 12 be two, be separately mounted to different height, for pair
The people of different heights is captured.
In addition, it can include system framework 14, as shown in Fig. 2, the system framework 14 is in " inverted L " shape, including：With ground
Distance (the i.e. height of vertical component on parallel horizontal component, and the vertical component vertical with opposite, horizontal component and ground
Degree) it is 3 to 4 meters, the length of horizontal component is 1 to 2 meter.
Depth camera 11 is installed on the horizontal component of system framework 14.
Two general cameras 12 are vertically installed on the vertical component of system framework 14, one of them is installed on distance
The place that 1.6 meters or so of ground, another is installed on apart from the place on 1.8 meters or so of ground.
Light compensating lamp 13 is installed on the vertical component of system framework 14, and between two general cameras 12.
Face snap is carried out by the double camera installed in different height, the face snap of the people of different heights can be solved
Problem.
Finally, face is called the roll and can also be included with number system：Push unit.
As shown in Figure 1, push unit, is connected with calling the roll with counting unit and comparing unit, for face to be counted respectively
Business platform or the mobile terminal of user are pushed to roll-call information.
Face is counted after being pushed to business platform and mobile terminal with roll-call information, supervisor (or other related personnel) can
To be directly viewable on mobile terminals.
In general, business platform refers to existing information system, such as business platform supervised etc..Mobile terminal refers to
The terminal devices such as mobile phone, tablet.
It should be noted that Face datection unit, roll-call and counting unit, comparing unit and push unit, can be independent
It is arranged on special server, can also be integrated in depth camera 11.
RGB-D information will be substantially better than common RGB camera, it is crucial that more one-dimensional depth information, for the number of people and
Head and shoulder infomation detection is more accurate.By analyzing the feature of the number of people and head and shoulder, feature differentiation is carried out with reference to visible ray RGB information.Knot
Face snap is closed, can accurately quote number of people entering and corresponding face information.
In conclusion the technical solution of the utility model is specifically designed during calling the roll for face and count scene, it is right
By the detection of the quantity and face state of personnel.
By the way that depth camera and face snap camera is used in combination, personnel are counted to associate with face and complete face point
Name, except that can provide accurate demographics as a result, the face information for the personnel of being counted can also be provided, is suitable for counting
The place of security requirement higher.
In addition, depth camera, general camera, Face datection unit, roll-call and counting unit, light compensating lamp, comparing unit and
Push unit is all matured product of the prior art and technology, is no longer further elaborated on herein.
The preferred embodiment that face is called the roll with number system is described in detail below.
For system construction drawing as shown in Fig. 2, a length of 1.5 meters of the horizontal component of system framework 14, depth camera 11 is installed on water
The middle position of flat part.The vertical component length 3.2 meters (namely height of system framework 14) of system framework 14, two common phases
Machine 12 is vertically installed on vertical component, is separately mounted to apart from the place on 1.6 meters and 1.8 meters or so of ground.
System control process figure is as shown in Figure 3.
The face is called the roll includes human face image collecting device (i.e. general camera 12 in Fig. 2) with number system, depth is believed
Harvester (i.e. general camera 11 in Fig. 2) and roll-call and counting unit are ceased, specifically,
1. human face image collecting device, it mainly performs following steps：
A) it is system acquisition facial image；
B) double camera (as shown in Figure 2) of the system framework apart from 1.6 meters and 1.8 meters or so of ground is installed on, for solving
The candid photograph problem of different height people；
C) image sequence is got；
D) when face is excessively dark, light compensating lamp is enabled, carries out light filling；
E) quality of human face image strengthens.
2. depth information harvester, it mainly performs following steps：
A) RGB-D (depth) information is obtained；
B) depth information noise filtering and enhancing.
That is, depth camera after depth image is collected, can also carry out depth image noise filtering with increasing
By force, including following sub-step：
Using region growing in depth image edge Color Image Edge extraction erroneous pixel corresponding with the depth image
The region at place, the direction of region growing is instructed with corresponding range image；
Utilize weighting pattern filtering algorithm filling cavity；
Noise is removed using adaptive combined two-sided filter.
By carrying out noise filtering and enhancing to depth image, it is possible to increase the quality of depth image, improves counting and head
The accuracy and real-time of shoulder detection.
3. roll-call and counting unit, it mainly performs following steps：
A) human face detection and tracing is carried out to the image sequence that human face image collecting device obtains.
Wherein, the process of human face detection and tracing, mainly includes the following steps that
(1) Face datection based on deep learning is carried out to human face image sequence, using big data advantage, had more preferable
Detection result.
Method for detecting human face effect based on deep learning is better than traditional method for detecting human face (such as AdaBoost
Deng).Method for detecting human face based on deep learning is to train deep neural network by substantial amounts of face sample (big data),
It is generally necessary to GPU (graphics processing unit) is supported.After training deep neural network, in arithmetic server deployment depth god
It is used for Face datection through network.Method for detecting human face based on deep learning has been current mainstream method for detecting human face.
(2) face detected by the method for detecting human face based on deep learning is merged.
The face for capturing camera candid photograph is merged using different methods, the face that same camera is captured is merged
Using the method for face tracking, the method using similarity measure is merged to the face that different cameral is captured.
Preferably, face tracking method uses KCF algorithms (Kernelized Correlation Filters).KCF is calculated
Method accuracy rate is higher, and speed is fast.The algorithm has constructed the training sample of grader by circulating offset, so that total
Become a circular matrix according to matrix.The solution of problem has been transformed to Fourier transformation by the characteristic for being then based on circular matrix
Domain, so as to avoid the process of matrix inversion, greatly reduces the complexity of algorithm.
The method of similarity measure, extraction face LBP features (Local Binary Pattern, local binary patterns),
The distance between LBP features that two faces obtain are calculated, calculate COS distance as measuring similarity.COS distance refer to
Size of the cosine value of two feature vector angles as difference between two features of measurement, cosine similarity more fill in quantity space
Weigh difference of two feature vectors on direction.
(3) detected by the head and shoulder of above-mentioned depth camera, distant place interference information is filtered to the face after merging.
Face information after above-mentioned merging, filtering will more accurately and reliably.
(4) be used for supervise, prison roll-call scene, after detecting face, (need the face sample called the roll with given list
Storehouse) it is compared, judge whether it is the personnel in list.
Preferably, face alignment can use DeepID methods or FaceNet methods.
The field that DeepID is applied is the subdomains of recognition of face --- face verification, and it is not exactly to judge two pictures
It is same person.Face verification problem is easy for that recognition of face problem can be changed into, and recognition of face is exactly multiple face verification.
Applications of the FaceNet from other deep learning methods on face is different, and FaceNet is not with traditional
Softmax modes carry out classification learning, then extract wherein a certain layer as feature, but directly carry out end-to-end study one
Coding method from image to theorem in Euclid space, is then based on this coding and does recognition of face, face verification and face cluster etc. again.
Discrimination is 99.63% on LFW data sets.
B) head and shoulder detection is carried out based on RGB-D information and counted, it is mainly included the following steps that：
(1) RGB-D information will be substantially better than common RGB camera, it is crucial that more one-dimensional depth information, for the number of people
And head and shoulder infomation detection is more accurate
(2) by analyzing the feature of the number of people and head and shoulder, carry out feature differentiation (3) with reference to visible ray RGB information and combine face
Capture, system accurately quotes number of people entering and corresponding face information
By combining the RGB-D information of depth camera and the RGB information of general camera, Multi-information acquisition judgement is carried out, into
Row face snap, head and shoulder detection are with that than reciprocity intelligent video analysis, can reach more preferable personnel and call the roll and demographics effect.
4. data-pushing unit, face is counted and is pushed to business platform and mobile terminal with roll-call information.
After being pushed to terminal, supervisor can be directly viewable on mobile phone etc..
It should be noted that each unit mentioned in each equipment embodiment of the utility model is all logic unit, in thing
In reason, a logic unit can be a part for a physical location or a physical location, can also be with multiple
The combination of physical location realizes that the Physical realization of these logic units in itself is not most important, these logic units
The combination for the function of being realized is only the key for solving the technical problem that the utility model is proposed.In addition, in order to protrude this reality
With new innovative part, the above-mentioned each equipment embodiment of the utility model does not have and will be proposed with solving the utility model
The less close unit of technical problem relation introduces, this is not intended that the said equipment embodiment and there is no other units.
It should be noted that in the claim and specification of this patent, such as first and second or the like relation
Term is used merely to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying
There are any actual relationship or order between these entities or operation.Moreover, term " comprising ", "comprising" or its
Any other variant is intended to non-exclusive inclusion so that process, method, article including a series of elements or
Equipment not only includes those key elements, but also including other elements that are not explicitly listed, or further include for this process,
Method, article or the intrinsic key element of equipment.In the absence of more restrictions, wanted by what sentence " including one " limited
Element, it is not excluded that also there are other identical element in the process, method, article or apparatus that includes the element.
Although by referring to some preferred embodiments of the utility model, the utility model has been shown and
Description, but it will be understood by those skilled in the art that can to it, various changes can be made in the form and details, without inclined
From the spirit and scope of the utility model.
Claims (6)
1. a kind of face is called the roll and number system, it is characterised in that including：Depth camera, general camera, Face datection unit and
Roll-call and counting unit；
The depth camera is connected with the general camera；
The general camera is connected with the Face datection unit；
The Face datection unit and the depth camera are connected with the roll-call with counting unit respectively；
The depth camera, for gathering the depth image of scene, when detecting that someone reaches by depth image, carries out head and shoulder
Detection is counted with number；
The general camera, for capturing facial image, obtains human face image sequence；
The Face datection unit, the human face image sequence for being captured to the general camera carry out Face datection with knowing
Not；
The roll-call and counting unit, face being somebody's turn to do to the depth camera detected for associating the Face datection unit
Secondary counting, obtains number of people entering information and corresponding face information.
2. face according to claim 1 is called the roll and number system, it is characterised in that further includes：
Comparing unit, is connected with the Face datection unit, and for carrying out face roll-call, the Face datection unit is detected
Face carry out face alignment with given list, judge whether it is the personnel in list.
3. face according to claim 1 is called the roll and number system, it is characterised in that further includes：
Light compensating lamp, is connected with the general camera, during capturing facial image, when face is excessively dark, to face into
Row light filling.
4. face according to claim 3 is called the roll and number system, it is characterised in that the number of the general camera is two
It is a, different height is separately mounted to, for being captured to the people of different heights.
5. face according to claim 2 is called the roll and number system, it is characterised in that further includes：
Push unit, is connected with calling the roll with counting unit and comparing unit respectively, is pushed for counting face with roll-call information
To business platform or the mobile terminal of user.
6. face according to claim 4 is called the roll and number system, it is characterised in that further includes：
In the system framework of " inverted L " shape, which includes：Horizontal component parallel to the ground, and it is vertical with opposite
The distance on vertical component, horizontal component and ground is 3 to 4 meters, and the length of horizontal component is 1 to 2 meter；
The depth camera is installed on the horizontal component of the system framework；
Described two general cameras are vertically installed on the vertical component of the system framework, one of them is installed on distance
The place that 1.6 meters of ground, another is installed on apart from the place on 1.8 meters of ground；
The light compensating lamp is also mounted at the vertical component of the system framework, and between two general cameras.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720788509.6U CN207233038U (en) | 2017-06-30 | 2017-06-30 | Face is called the roll and number system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720788509.6U CN207233038U (en) | 2017-06-30 | 2017-06-30 | Face is called the roll and number system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207233038U true CN207233038U (en) | 2018-04-13 |
Family
ID=61852120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201720788509.6U Active CN207233038U (en) | 2017-06-30 | 2017-06-30 | Face is called the roll and number system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207233038U (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108806010A (en) * | 2018-06-12 | 2018-11-13 | 成都恒泰信安科技有限责任公司 | Personnel's automatic roll-calling based on living things feature recognition and demographics method for early warning |
| CN108989677A (en) * | 2018-07-27 | 2018-12-11 | 上海与德科技有限公司 | A kind of automatic photographing method, device, server and storage medium |
| CN109118602A (en) * | 2018-07-19 | 2019-01-01 | 安顺市众创电子科技发展有限公司 | A kind of human face identification work-attendance checking system |
| CN109215150A (en) * | 2017-06-30 | 2019-01-15 | 上海弘视通信技术有限公司 | Face is called the roll and method of counting and its system |
-
2017
- 2017-06-30 CN CN201720788509.6U patent/CN207233038U/en active Active
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109215150A (en) * | 2017-06-30 | 2019-01-15 | 上海弘视通信技术有限公司 | Face is called the roll and method of counting and its system |
| CN108806010A (en) * | 2018-06-12 | 2018-11-13 | 成都恒泰信安科技有限责任公司 | Personnel's automatic roll-calling based on living things feature recognition and demographics method for early warning |
| CN109118602A (en) * | 2018-07-19 | 2019-01-01 | 安顺市众创电子科技发展有限公司 | A kind of human face identification work-attendance checking system |
| CN108989677A (en) * | 2018-07-27 | 2018-12-11 | 上海与德科技有限公司 | A kind of automatic photographing method, device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207233038U (en) | Face is called the roll and number system | |
| CN104091176B (en) | Portrait comparison application technology in video | |
| CN107256377B (en) | Method, device and system for detecting object in video | |
| CN104123544B (en) | Anomaly detection method and system based on video analysis | |
| CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
| CN105940430B (en) | Personnel's method of counting and its device | |
| CN104301712B (en) | A kind of monitoring camera blur detecting method based on video analysis | |
| CN105631515B (en) | People flow counting system | |
| CN109670441A (en) | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN105868689A (en) | Cascaded convolutional neural network based human face occlusion detection method | |
| Fu et al. | Real-time accurate crowd counting based on RGB-D information | |
| CN102004906A (en) | Face identification system and method | |
| CN106886216A (en) | Robot automatic tracking method and system based on RGBD Face datections | |
| Srivastava et al. | Crowd flow estimation using multiple visual features for scenes with changing crowd densities | |
| CN107657244A (en) | A kind of human body tumble behavioral value system and its detection method based on multiple-camera | |
| CN106709438A (en) | Method for collecting statistics of number of people based on video conference | |
| CN106570449B (en) | A kind of flow of the people defined based on region and popularity detection method and detection system | |
| CN106548158A (en) | Crowd density intelligent monitor system and method based on machine vision | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN106599880A (en) | Discrimination method of the same person facing examination without monitor | |
| CN110363087A (en) | A kind of Long baselines binocular human face in-vivo detection method and system | |
| Carletti et al. | An efficient and effective method for people detection from top-view depth cameras | |
| CN108563998A (en) | Vivo identification model training method, biopsy method and device | |
| CN109215150A (en) | Face is called the roll and method of counting and its system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |