CN102170563A - Intelligent person capture system and person monitoring management method - Google Patents
Intelligent person capture system and person monitoring management method Download PDFInfo
- Publication number
- CN102170563A CN102170563A CN2011100714455A CN201110071445A CN102170563A CN 102170563 A CN102170563 A CN 102170563A CN 2011100714455 A CN2011100714455 A CN 2011100714455A CN 201110071445 A CN201110071445 A CN 201110071445A CN 102170563 A CN102170563 A CN 102170563A
- Authority
- CN
- China
- Prior art keywords
- face
- people
- subwindow
- grader
- image
- 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
Images
Landscapes
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to video monitoring and discloses an intelligent person capture system and a person monitoring management method. In the invention, the whole system comprises a front-end human face snapshot subsystem, a center analyzing server and a data management subsystem, wherein the human face snapshot subsystem, the center analyzing server and the data management subsystem are respectively connected with a switchboard; and the switchboard is utilized for forming a local area network for carrying out mutual communication. Because a front-end snapshot and rear-end analysis mode is adopted in the whole system, the system is not just in charge of acquisition of images, realizes intelligent person capture, can support retrieval afterwards, thereby being greatly convenient for the rapid search and gradual check of a public security department on criminal suspects.
Description
Technical field
The present invention relates to video monitoring, particularly the personnel control's administrative skill in the video monitoring.
Background technology
In recent years, with improving constantly of work rapid development of economy and living standards of the people, the negative factor of bringing out and growing crime exists in a large number, means of crime is progressively to high-tech, intellectuality, specialized direction development, strengthened the sudden, uncertain of criminal offence, bring great difficulty for strick precaution and detection work, and public security bayonet socket supervisory control system is a requisite important means in social security prevention and control, criminal investigation, the traffic administration.At present in whole security monitoring, though carried out for many years for the bayonet socket of vehicle monitoring, to people's management with to establish card almost nil.
At present, proposed some intelligent monitor systems, the people through bayonet socket has been carried out security monitoring by establishing card at personnel's bayonet socket.Main still by the real time image collection function of video camera in existing bayonet socket supervisory control system, realize personnel control through bayonet socket.
Yet, the present inventor finds, these present systems are based on mostly that the SD image carries out, resolution is 720*576 to the maximum, although it is enough for the monitoring of general indoor gateway (width of gateway is a 1-2 rice), but for the security monitoring on the road, its monitoring range often has 4-5 rice wide (by the width estimation on common people trade), be issued to the required face's resolution of recognition of face in this scope, the resolution of monitoring camera gets 1,000,000 high definitions above (the general resolution that must need 1080P) at least.And for 1,000,000 high definition code streams, will certainly be subjected to the serious restriction of the network bandwidth, and the video after the compression of what is more important process coding and decoding video, its picture quality can be had a strong impact on, and must influence the accuracy rate of recognition of face.
In addition, these present systems do not support search function afterwards yet, can't inquire about personnel's database of capturing for public security department to facilitate in the criminal investigation process afterwards.
Summary of the invention
The object of the present invention is to provide a kind of intelligent personnel's Gate System and personnel control's management method, realize personnel's bayonet socket of intelligence, for public security department provides convenience to suspect's quick search investigation.
For solving the problems of the technologies described above, embodiments of the present invention provide a kind of intelligent personnel's Gate System, comprise:
People's face is captured subsystem, is used to obtain the high definition facial image through all personnel of bayonet socket;
The center Analysis server is used for the high definition facial image is carried out feature extraction and afterwards according to characteristic key;
Data administration subsystem, be used for to people's face capture the high definition facial image that subsystem obtains, the characteristic that the center Analysis server extracts is carried out storage administration;
People's face is captured subsystem, the center Analysis server is connected with switch respectively with data administration subsystem, utilizes switch to constitute a local area network (LAN), carries out communication each other.
Embodiments of the present invention also provide a kind of personnel control's management method, comprise following steps:
Utilize the video camera of front end to obtain high definition facial image through all personnel of bayonet socket;
Utilize the center Analysis server of rear end that the high definition facial image is carried out feature extraction, characteristic and the high definition facial image that extracts is stored in the database;
When needs were retrieved, the center Analysis server of rear end inquired the pairing high definition facial image of the feature that is complementary with search condition according to search condition in database.
Embodiment of the present invention compared with prior art, the main distinction and effect thereof are:
Whole system is captured subsystem, center Analysis server and data administration subsystem three parts by front end people face and is constituted, and people's face is captured the high definition facial image that subsystem responsible is obtained all personnel of process bayonet socket; The center Analysis server is responsible for the high definition facial image is carried out feature extraction and afterwards according to characteristic key; The high definition facial image that data administration subsystem is used to store and the characteristic of extraction.People's face is captured subsystem, the center Analysis server is connected with switch respectively with data administration subsystem, utilizes switch to constitute a local area network (LAN), carries out communication each other.Because whole system has adopted front end to capture the pattern that adds back-end analysis, what people's face of front end was captured subsystem output is the high definition facial image, and non-face characteristic, center Analysis server by the rear end carries out feature extraction, reduced the operand of people's face candid photograph subsystem, feasible detection to people's face, candid photograph function can directly be integrated in the video camera, video camera is the collection of responsible image not merely only, realized intelligent personnel's bayonet socket, and can support afterwards retrieval, big convenience the quick search investigation of public security department to the suspect.
Further, the video camera that people's face is captured in the subsystem starts the detection of people's face when the pedestrian enters the virtual coil of setting, the pedestrian's face of going forward side by side follow the tracks of to form the pursuit path of face's target, and the highest image of the face partition that will pick out from pursuit path is as this pedestrian's candid photograph image.Face partition is meant according to human face posture and definition the people's face that detects or trace into is estimated, people's face that attitude is positive more and definition is high more, and its corresponding scoring is also just high more.According to the candid photograph image that face tracking, face partition obtain, effectively guaranteed to obtain to pass through setting regions all personnel's high definition human face photo, thereby can promote the accuracy rate of recognition of face.And, consider the candid photograph at night and unfavorable cloudy day of illumination, people's face is captured in the subsystem and is also included the light filling lamp, thereby has realized round-the-clock people's face candid photograph.
Further, can be the light-duty cascade structure grader of a Weak Classifier by being integrated with each grade in the video camera, the subwindow to be measured in the current image to be detected be carried out people's face detect; Also can the subwindow to be measured in the current image to be detected be carried out people's face detect by being integrated with the cascade vector tree structure detector that comprises a plurality of node classifiers.Because it is non-face that each Weak Classifier of light-duty cascade structure grader can be removed part; Cascade vector tree structure detector is by introducing cascade classifier between the branch node grader, utilize cascade classifier that the non-face subwindow in each branch is effectively removed step by step, reduce the complexity of branch node grader, reduced contained Weak Classifier number.Therefore carry out people's face by light-duty cascade structure grader or cascade vector tree structure detector and detect, can further reduce operand, improve detection speed, guaranteed that further detection, the candid photograph function to people's face can directly be realized by video camera.
Further, video camera also be used for according to current detection to face's average luminance information of people's face the light filling lamp is carried out automatic exposure control, can further effectively improve the definition of face area.
Further, the feature of center Analysis server extraction comprises the human body attributive character and is used for face's texture model feature that people's face is compared.The center Analysis server inquires the pairing high definition facial image of the feature that is complementary with search condition according to search condition in data administration subsystem afterwards according to characteristic key the time; Wherein, search condition is the face's texture model feature according to people's face picture extraction to be checked of input, and/or the human body attributive character of input.Utilization is based on the back search method of face's texture model feature and human body attributive character, can be public security department and when inquiry candid photograph personnel database, effectively dwindle the investigation scope, location suspicion personnel improve the speed of arresting criminal fast, reach the purpose of quick clear up a criminal case.
Description of drawings
Fig. 1 is the structural representation according to intelligent personnel's Gate System of first embodiment of the invention;
Fig. 2 carries out the schematic diagram that people's face detects according to the light-duty cascade structure grader in the first embodiment of the invention;
Fig. 3 is the structural representation according to the cascade vector tree structure detector in the second embodiment of the invention;
Fig. 4 is the personnel control's management method flow chart according to third embodiment of the invention;
Fig. 5 is the flow chart that obtains according to the high definition facial image in the third embodiment of the invention;
Fig. 6 is the feature extraction flow chart according to the center Analysis server of third embodiment of the invention;
Fig. 7 is the figure of retrieval flow afterwards according to the center Analysis server of third embodiment of the invention.
Embodiment
In the following description, in order to make the reader understand the application better many ins and outs have been proposed.But, persons of ordinary skill in the art may appreciate that even without these ins and outs with based on the many variations and the modification of following each execution mode, also can realize each claim of the application technical scheme required for protection.
For making the purpose, technical solutions and advantages of the present invention clearer, embodiments of the present invention are described in further detail below in conjunction with accompanying drawing.
First embodiment of the invention relates to a kind of intelligent personnel's Gate System.Intelligent personnel's Gate System of present embodiment adopts front end to capture the pattern that adds back-end analysis, specifically constitute by people's face candid photograph subsystem of front end, the center Analysis server and data administration subsystem three parts of rear end, people's face is captured subsystem, the center Analysis server is connected with switch respectively with data administration subsystem, utilize switch to constitute a local area network (LAN), carry out communication each other, as shown in Figure 1.Also comprised client in intelligent personnel's Gate System shown in Figure 1, this client is connected with switch, is used to realize operating personnel's the instruction input and the feedback result output of intelligent personnel's Gate System.
Wherein, people's face candid photograph subsystem is used to obtain the high definition facial image through all personnel of bayonet socket; The center Analysis server is used for the high definition facial image is carried out feature extraction and afterwards according to characteristic key; Data administration subsystem is used for the high definition facial image that people's face candid photograph subsystem is obtained, the characteristic that the center Analysis server extracts is carried out storage administration.
Specifically, it is the front end core of whole personnel's Gate System that people's face is captured subsystem, be responsible for all personnel through bayonet socket is captured automatically, obtain high definition facial image and corresponding panoramic picture, this people's face candid photograph subsystem is captured three parts such as video camera, light filling lamp, transmission unit by the embedded integrated high definition that possesses people's face candid photograph function and is formed.
Wherein, video camera adopts the video triggering mode that the virtual coil rule is set, starting people's face when the pedestrian enters the virtual coil of setting detects, the pedestrian's face of going forward side by side follow the tracks of to form the pursuit path of face's target, and the highest image of the face partition that will pick out from pursuit path is as this pedestrian's candid photograph image.This video camera also is used at the highest image of the face partition of picking out during as this pedestrian's candid photograph image, write down the shooting time and the location information of the highest image of this face partition, at last information such as the pedestrian's that obtains candid photograph image, corresponding panoramic picture, shooting time, place are reached in the Analysis server of center by network.Owing to do not need the physical trigger device auxiliary in the whole candid photograph process, finish by software fully, so front end candid photograph subsystem structure is simple.According to the candid photograph image that face tracking, face partition obtain, effectively guaranteed to obtain to pass through setting regions all personnel's high definition human face photo, thereby can promote the accuracy rate of recognition of face.And, consider the candid photograph at night and unfavorable cloudy day of illumination, the light filling lamp also is installed near the front end capture machine in the present embodiment, thereby is realized round-the-clock people's face candid photograph.
What deserves to be mentioned is, video camera can according to current detection to face's average luminance information of people's face the light filling lamp is carried out automatic exposure control, thereby further effectively improved the definition of face area.
In addition, video camera can be the light-duty cascade structure grader of a Weak Classifier by each integrated grade of inside, realizes that the subwindow to be measured in the current image to be detected is carried out people's face to be detected, and detects people's face window.Whether each grade Weak Classifier in this light-duty cascade structure grader is the classification of people's face to this subwindow to be measured one by one, if this subwindow to be measured is categorized as non-face by the one-level Weak Classifier, then stop the classification of next stage Weak Classifier to this subwindow to be measured, exporting this subwindow to be measured is non-face testing result; Be people's face if this subwindow to be measured is all classified by each grade Weak Classifier in the described light-duty cascade structure grader, then export the testing result of this subwindow behaviour face to be measured, as shown in Figure 2.Wherein, each grade Weak Classifier in the light-duty cascade structure grader is trained on the basis of all Weak Classifiers before the Weak Classifier at the corresponding levels and is obtained.Because for windows to be detected a large amount of in the image, with respect to non-face window, the people's face window that wherein comprises is few.Therefore must be as a result for the non-face scheme in part that can be removed, rear with respect to the grader of cascade structure at all Weak Classifiers in calculating a strong classifier, it is non-face that each Weak Classifier of light-duty cascade structure grader can be removed part, thereby can judge more fast by a spot of Weak Classifier, reduce operand, reached detection speed faster.
The center Analysis server is the core of whole intelligent personnel's Gate System, main realizes capturing the feature extraction of the pedestrian in the image and function such as personnel's retrieval afterwards.The feature extraction of wherein capturing image comprises the human body attributive character and is used for face's texture model Feature Extraction that people's face is compared.Face's texture model feature is the local grain feature of face just, and these features often are suitable for people's face compare of analysis, but does not possess any physical significance.The human body attributive character just meets the feature of human identification custom, can describe in words, can be used as afterwards the label of retrieval, for example whether the people wears glasses, hair style feature (long hair, bob, shaven head, straight hair or curly hair), beard feature (sparse, dense or do not have), shape of face (state's word face, oval face, round face etc.), height feature (high, short, fat and thin) and the clothing feature (clothes of grid clothes, certain pure color) of being worn etc.
Specifically, the center Analysis server can be realized the human body attributive character and be used for face's texture model Feature Extraction that people's face is compared by comprising following submodule:
The preliminary treatment subelement is used for the high definition facial image of pending feature extraction is carried out preliminary treatment, comprises illumination compensation and noise-removed filtering.
Location normalizing subelement is used for carry out the normalization alignment of positioning feature point and image through the pretreated image of preliminary treatment subelement.
The feature extraction subelement, be used for the image after handling through location normalizing subelement is carried out the extraction of face's texture model Feature Extraction and human body attributive character, and all features that will extract are stored to data administration subsystem by switch, generation candid photograph database.
The center Analysis server is retrieved in data administration subsystem according to search condition afterwards according to characteristic key the time, inquires the pairing high definition facial image of the feature that is complementary with search condition,, returns the facial image that satisfies condition that is.Wherein, search condition is the face's texture model feature according to people's face picture extraction to be checked of input, or the human body attributive character of input.That is to say that retrieval mode mainly contains following two kinds:
(1) based on the retrieval of face's texture model feature: at first import people's face picture to be checked, then carry out positioning feature point, normalization alignment and the texture model Feature Extraction of people's face, calculate this faceform then and capture the similarity between each faceform in the database, sort those and human face similarity facial image to be checked in the output database at last according to similarity.
(2) based on the retrieval of human body attributive character: because each people who is captured has just finished the extraction of human body attributive character in feature extraction, therefore when the retrieval of carrying out based on attributive character, only need select Checking label, system just can finish retrieval apace, for example system can support for wear glasses, long hair and wear the people's of white clothes retrieval.
People's face picture or human body attributive character to be checked can be imported from client, transfer to the center Analysis server by switch.The center Analysis server is by switch, the pairing high definition facial image of feature that is complementary with search condition that inquires to client feedback.
Be not difficult to find, in the present embodiment, because whole system has adopted front end to capture the pattern that adds back-end analysis, and the not only only collection of responsible image, realized intelligent personnel's bayonet socket, and can support afterwards retrieval, big convenience the quick search investigation of public security department to the suspect.And, based on the back search method of faceform's feature and attributive character, can be public security department and when inquiry candid photograph personnel database, dwindle the investigation scope, locate the suspicion personnel fast, improve the speed of arresting criminal.For example public security department need be in capturing database retrieval have a suspect of certain feature (as wear glasses, long hair, state's word face, tall person, wear grid clothes etc.) or import an a suspect's facial image, utilize the back search function to inquire about, thus the facial image the most close in the return data storehouse with a suspect.And the human body attributive character is the feature that available language is described, and has further facilitated the search investigation of public security department.
In addition, need to prove, in the present embodiment, can also expand the real-time comparison that realizes blacklist and report to the police.Such as, in data administration subsystem, store suspect's feature (comprising face's texture model feature and human body attributive character) in advance, the center Analysis server is after the candid photograph image according to the pedestrian extracts feature, directly compare with the suspect's who stores feature, if feature conforms to, output alarm signal then.
Second embodiment of the invention relates to a kind of intelligent personnel's Gate System.Second execution mode improves on the basis of first execution mode, and main improvements are:
In the first embodiment, search condition is the face's texture model feature according to people's face picture extraction to be checked of input, or the human body attributive character of input.
And in the present embodiment, search condition not only can be the face's texture model feature according to people's face picture extraction to be checked of input, or the input the human body attributive character in any, can also be according to the face's texture model feature of people's face picture extraction to be checked of importing and the human body attributive character of input.That is to say intelligent personnel's Gate System support mixed index afterwards of present embodiment.By supporting mixed index mode simultaneously, thereby can reach the better retrieval result, finally in the criminal investigation process, accurately dwindle the investigation scope, reach the purpose of quick clear up a criminal case for public security based on faceform's feature and human body attributive character.
In addition, in the present embodiment, video camera also can carry out people's face to the subwindow to be measured in the current image to be detected and detect by the integrated cascade vector tree structure detector that comprises a plurality of node classifiers in inside.Comprise at least one branch node grader (node classifier that a plurality of child nodes are promptly arranged) in this cascade vector tree structure detector, and, before at least one branch node grader, the no branch node grader (node classifier that promptly has only a child node) of at least one cascade is arranged.Such as shown in Figure 3, cascade vector tree structure detector comprises 15 visual angles altogether, the plane inner rotary is divided into 5 attitudes, is followed successively by the full side (90 ,-54) in a left side, a left side half side (54,-18), accurate positive (18 ,+18), right half side (+18 ,+54) and right full side (+54, + 90) 5 visual angles are subdivided into rotary viewing angle in 3 planes under each inner rotary visual angle, plane again, are followed successively by rotation-30 (45,-15), 0 degree (15 ,+15) and 30 degree (+15 ,+45).Scope that the detectability of this cascade vector tree structure detector can overlay planes outward turning turnback and the scope that the plane inward turning turn 90 degrees like this.
Cascade vector tree structure detector is when carrying out the detection of people's face to the subwindow to be measured in the current image to be detected, when the no branch node grader in the cascade vector tree structure detector is judged to be non-face subwindow with subwindow to be measured, stop and the further detection of the branch node grader of this no branch node grader cascade this subwindow to be measured; When no branch node grader was judged subwindow to be measured for people's face window, the branch node grader that this subwindow to be measured is delivered to this no branch node grader cascade continued detection.
Specifically, for a subwindow to be measured, begin to travel through each node classifier from root node it is carried out the judgement of category attribute, if the node classifier in a certain branch in the cascade vector tree structure detector should be judged to non-face by subwindow to be measured, then stop to visit its child nodes downwards, then the recurrence that makes progress is visited the node classifier in other branch.If subwindow to be measured is by all node classifiers in a certain branch, up to leaf node, then this subwindow is judged to the face for the people, and the visual angle classification of this people's face is exactly the pairing classification of this leaf node.That is to say, each that comprises root node obtains the node classifier of subwindow input to be measured and handles as follows: if be judged to be non-face subwindow, then finish the detection (promptly no longer deliver in child nodes detect) of this branch to this subwindow to be measured; Otherwise, if this node is not a leaf node, then will this subwindow to be measured delivers at least one child node of this node and further detect, if this node has been a leaf node, then judge this subwindow behaviour face, and the visual angle classification of this people's face is exactly the pairing classification of this leaf node.By between the branch node grader, introducing cascade classifier, utilize cascade classifier that the non-face subwindow in each branch is effectively removed step by step, reduced the complexity of branch node grader, reduced contained Weak Classifier number, thereby reduced operand, when guaranteeing verification and measurement ratio, improved detection speed.
Certainly, video camera also can carry out people's face by other algorithms and detect, and does not give unnecessary details one by one in this application.
Third embodiment of the invention relates to a kind of personnel control's management method, and idiographic flow as shown in Figure 4.
In step 410, utilize the video camera of front end to obtain high definition facial image through the personnel of bayonet socket.Specifically, as shown in Figure 5, start people's face and detect when the pedestrian enters the virtual coil of setting, and detected people's face is carried out the pursuit path that face tracking forms face's target, the highest image of the face partition that will pick out from pursuit path is as this pedestrian's candid photograph image.At the highest image of the face partition of picking out during as this pedestrian's candid photograph image, write down the shooting time and the location information of the highest image of this face partition, the panoramic picture that obtains the highest image of this face partition together transfers to the rear end with each pedestrian's candid photograph image and corresponding shooting time, location information, panoramic picture by switch center Analysis server.Wherein, video camera also can according to current detection to face's average luminance information of people's face the light filling lamp is carried out automatic exposure control, utilize the light filling lamp to expose, shown in the dotted portion among Fig. 5 for video camera.
In step 420, utilize the center Analysis server of rear end that the high definition facial image is carried out feature extraction, characteristic and the high definition facial image that extracts is stored in the database.
Specifically, the feature of center Analysis server extraction comprises the human body attributive character and is used for face's texture model feature that people's face is compared.The idiographic flow of feature extraction as shown in Figure 6, capture image for one, at first carry out image preliminary treatment (comprising illumination compensation and noise-removed filtering), carry out the normalization alignment of positioning feature point and image then, carry out the extraction of face's texture model Feature Extraction and human body attributive character at last, and all features are stored, generate and capture database.
When needs are retrieved, enter step 430, the center Analysis server of rear end inquires the pairing high definition facial image of the feature that is complementary with search condition according to search condition in database.Wherein, search condition is the face's texture model feature according to people's face picture extraction to be checked of input, or the human body attributive character of input.
Specifically, at first, import people's face picture or human body attributive character to be checked by switch center Analysis server to the back-end by client.Retrieval flow as shown in Figure 7, the frame of broken lines among Fig. 7 is the retrieval mode flow chart based on face's texture model feature, solid box is the retrieval mode flow chart based on the human body attributive character.After getting access to result for retrieval, the center Analysis server of rear end is by switch, the pairing high definition facial image of feature that is complementary with search condition that inquires to client feedback.
Be not difficult to find that present embodiment is and the corresponding method execution mode of first execution mode, present embodiment can with the enforcement of working in coordination of first execution mode.The correlation technique details of mentioning in first execution mode is still effective in the present embodiment, in order to reduce repetition, repeats no more here.Correspondingly, the correlation technique details of mentioning in the present embodiment also can be applicable in first execution mode.
Four embodiment of the invention relates to a kind of personnel control's management method.The 4th execution mode improves on the basis of the 3rd execution mode, and main improvements are:
In the 3rd execution mode, search condition is the face's texture model feature according to people's face picture extraction to be checked of input, or the human body attributive character of input.
And in the present embodiment, search condition not only can be the face's texture model feature according to people's face picture extraction to be checked of input, or the input the human body attributive character in any, can also be according to the face's texture model feature of people's face picture extraction to be checked of importing and the human body attributive character of input.That is to say that present embodiment is also supported mixed index afterwards.By supporting mixed index mode simultaneously, thereby can reach the better retrieval result, finally in the criminal investigation process, accurately dwindle the investigation scope, reach the purpose of quick clear up a criminal case for public security based on faceform's feature and human body attributive character.
Be not difficult to find that present embodiment is and the corresponding method execution mode of second execution mode, present embodiment can with the enforcement of working in coordination of second execution mode.The correlation technique details of mentioning in second execution mode is still effective in the present embodiment, in order to reduce repetition, repeats no more here.Correspondingly, the correlation technique details of mentioning in the present embodiment also can be applicable in second execution mode.
Need to prove that each method execution mode of the present invention all can be realized in modes such as software, hardware, firmwares.No matter the present invention be with software, hardware, or the firmware mode realize, instruction code can be stored in the memory of computer-accessible of any kind (for example permanent or revisable, volatibility or non-volatile, solid-state or non-solid-state, fixing or removable medium or the like).Equally, memory can for example be programmable logic array (Programmable Array Logic, be called for short " PAL "), random access memory (Random Access Memory, be called for short " RAM "), programmable read only memory (Programmable Read Only Memory, be called for short " PROM "), read-only memory (Read-Only Memory, be called for short " ROM "), Electrically Erasable Read Only Memory (Electrically Erasable Programmable ROM, be called for short " EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc is called for short " DVD ") or the like.
Though pass through with reference to some of the preferred embodiment of the invention, the present invention is illustrated and describes, but those of ordinary skill in the art should be understood that and can do various changes to it in the form and details, and without departing from the spirit and scope of the present invention.
Claims (20)
1. intelligent personnel's Gate System is characterized in that, comprises:
People's face is captured subsystem, is used to obtain the high definition facial image through all personnel of bayonet socket;
The center Analysis server is used for described high definition facial image is carried out feature extraction and afterwards according to characteristic key;
Data administration subsystem, be used for to described people's face capture the high definition facial image that subsystem obtains, the characteristic that described center Analysis server extracts is carried out storage administration;
Described people's face is captured subsystem, described center Analysis server is connected with switch respectively with data administration subsystem, utilizes described switch to constitute a local area network (LAN), carries out communication each other.
2. intelligent personnel's Gate System according to claim 1 is characterized in that, described people's face is captured subsystem and comprised:
Video camera is used for when the pedestrian enters the virtual coil of setting starting people's face and detects, and the pedestrian's face of going forward side by side is followed the tracks of the pursuit path that forms face's target, and the highest image of the face partition that will pick out from described pursuit path is as this pedestrian's candid photograph image;
The light filling lamp is used to described video camera to expose;
Transmission unit, the candid photograph image that is used for each pedestrian that described video camera is got access to transfers to described center Analysis server by described switch.
3. intelligent personnel's Gate System according to claim 2, it is characterized in that, be integrated with each grade in the described video camera and be the light-duty cascade structure grader of a Weak Classifier, described light-duty cascade structure grader is used for the subwindow to be measured of current image to be detected is carried out the detection of people's face, detects people's face window;
Wherein, described light-duty cascade structure grader is when carrying out the detection of people's face to each described subwindow to be measured, whether each grade Weak Classifier in the described light-duty cascade structure grader is the classification of people's face to this subwindow to be measured one by one, if this subwindow to be measured is categorized as non-face by the one-level Weak Classifier, then stop the classification of next stage Weak Classifier to this subwindow to be measured, exporting this subwindow to be measured is non-face testing result; Be people's face if this subwindow to be measured is all classified by each grade Weak Classifier in the described light-duty cascade structure grader, then export the testing result of this subwindow behaviour face to be measured;
Each grade Weak Classifier in the described light-duty cascade structure grader is trained on the basis of all Weak Classifiers before the Weak Classifier at the corresponding levels and is obtained.
4. intelligent personnel's Gate System according to claim 2, it is characterized in that, be integrated with the cascade vector tree structure detector that comprises a plurality of node classifiers in the described video camera, comprise at least one branch node grader in this cascade vector tree structure detector, and, before at least one branch node grader, the no branch node grader of at least one cascade is arranged;
Described cascade vector tree structure detector is used for the subwindow to be measured of current image to be detected is carried out the detection of people's face, wherein, when the described no branch node grader in the described cascade vector tree structure detector is judged to be non-face subwindow with described subwindow to be measured, stop and the further detection of the branch node grader of this no branch node grader cascade this subwindow to be measured; When described no branch node grader was judged described subwindow to be measured for people's face window, the branch node grader that this subwindow to be measured is delivered to this no branch node grader cascade continued detection.
5. intelligent personnel's Gate System according to claim 2 is characterized in that, described video camera also be used for according to current detection to face's average luminance information of people's face described light filling lamp is carried out automatic exposure control.
6. intelligent personnel's Gate System according to claim 2, it is characterized in that, described video camera also is used at the highest image of the face partition of picking out during as this pedestrian's candid photograph image, write down the shooting time and the location information of the highest image of this face partition, obtain the panoramic picture of the highest image of this face partition;
Described transmission unit together transfers to described center Analysis server by described switch with each pedestrian's candid photograph image and corresponding shooting time, location information, panoramic picture when each pedestrian's of transmission candid photograph image.
7. intelligent personnel's Gate System according to claim 1 is characterized in that, the feature that described center Analysis server extracts comprises the human body attributive character and is used for face's texture model feature of people's face comparison;
Described center Analysis server inquires the pairing high definition facial image of the feature that is complementary with described search condition according to search condition in described data administration subsystem afterwards according to characteristic key the time;
Wherein, described search condition is the face's texture model feature according to people's face picture extraction to be checked of input, and/or the human body attributive character of input.
8. intelligent personnel's Gate System according to claim 7 is characterized in that, described human body attributive character comprises one of following or its combination in any:
Fat or thin degree, wear glasses, hair feature, shape of face, height, clothes feature.
9. intelligent personnel's Gate System according to claim 7 is characterized in that, described intelligent personnel's Gate System also comprises client, and described client is connected with described switch;
Described client is used for by described switch, to described center Analysis server input people's face picture and/or human body attributive character to be checked;
Described center Analysis server is by described switch, the pairing high definition facial image of feature that is complementary with described search condition that inquires to described client feedback.
10. intelligent personnel's Gate System according to claim 7 is characterized in that, described center Analysis server comprises following subelement:
The preliminary treatment subelement is used for the high definition facial image of pending feature extraction is carried out preliminary treatment;
Location normalizing subelement is used for carry out the normalization alignment of positioning feature point and image through the pretreated image of described preliminary treatment subelement;
The feature extraction subelement be used for the image after handling through described location normalizing subelement is carried out the extraction of face's texture model Feature Extraction and human body attributive character, and all features that will extract is stored to described data administration subsystem by described switch.
11. personnel control's management method is characterized in that, comprises following steps:
Utilize the video camera of front end to obtain high definition facial image through all personnel of bayonet socket;
Utilize the center Analysis server of rear end that described high definition facial image is carried out feature extraction, characteristic and the described high definition facial image that extracts is stored in the database;
When needs were retrieved, the center Analysis server of described rear end inquired the pairing high definition facial image of the feature that is complementary with described search condition according to search condition in described database.
12. personnel control's management method according to claim 11 is characterized in that, the described video camera that utilizes front end obtains in the step through all personnel's of bayonet socket high definition facial image, comprises following substep:
Start people's face and detect when the pedestrian enters the virtual coil of setting, the pedestrian's face of going forward side by side is followed the tracks of the pursuit path that forms face's target, and the highest image of the face partition that will pick out from described pursuit path is as this pedestrian's candid photograph image;
Wherein, utilizing the light filling lamp is that described video camera exposes, and each pedestrian's that described video camera will get access to candid photograph image transfers to the center Analysis server of described rear end by switch.
13. personnel control's management method according to claim 12, it is characterized in that, described video camera adopts each grade to be the light-duty cascade structure grader of a Weak Classifier, the subwindow to be measured in the current image to be detected is carried out people's face detect, and detects people's face window;
Wherein, described light-duty cascade structure grader is when carrying out the detection of people's face to each described subwindow to be measured, whether each grade Weak Classifier in the described light-duty cascade structure grader is the classification of people's face to this subwindow to be measured one by one, if this subwindow to be measured is categorized as non-face by the one-level Weak Classifier, then stop the classification of next stage Weak Classifier to this subwindow to be measured, exporting this subwindow to be measured is non-face testing result; Be people's face if this subwindow to be measured is all classified by each grade Weak Classifier in the described light-duty cascade structure grader, then export the testing result of this subwindow behaviour face to be measured;
Each grade Weak Classifier in the described light-duty cascade structure grader is trained on the basis of all Weak Classifiers before the Weak Classifier at the corresponding levels and is obtained.
14. personnel control's management method according to claim 12, it is characterized in that, described video camera adopts the cascade vector tree structure detector that comprises a plurality of node classifiers that the subwindow to be measured in the current image to be detected is carried out people's face and detects, comprise at least one branch node grader in this cascade vector tree structure detector, and, before at least one branch node grader, the no branch node grader of at least one cascade is arranged;
Wherein, if described no branch node grader is judged to be non-face subwindow with described subwindow to be measured, then stop and the further detection of the branch node grader of this no branch node grader cascade this subwindow to be measured; Be people's face window if described no branch node grader is judged described subwindow to be measured, then will this subwindow to be measured deliver to branch node grader continuation detection with this no branch node grader cascade.
15. personnel control's management method according to claim 12 is characterized in that, the described light filling lamp that utilizes is that described video camera carries out comprising following substep in the step of exposing:
Described video camera according to current detection to face's average luminance information of people's face described light filling lamp is carried out automatic exposure control.
16. personnel control's management method according to claim 12 is characterized in that, the described video camera that utilizes front end obtains in the step through all personnel's of bayonet socket high definition facial image, also comprises following substep:
Described video camera during as this pedestrian's candid photograph image, writes down the shooting time and the location information of the highest image of this face partition at the highest image of the face partition of picking out, and obtains the panoramic picture of the highest image of this face partition;
When each pedestrian's of transmission candid photograph image, described video camera together transfers to each pedestrian's candid photograph image and corresponding shooting time, location information, panoramic picture the center Analysis server of described rear end by described switch.
17. personnel control's management method according to claim 11 is characterized in that, the feature that described center Analysis server extracts comprises the human body attributive character and is used for face's texture model feature of people's face comparison;
Described search condition is the face's texture model feature according to people's face picture extraction to be checked of input, and/or the human body attributive character of input.
18. personnel control's management method according to claim 17 is characterized in that,, described human body attributive character comprises one of following or its combination in any:
Fat or thin degree, whether wear glasses, hair style feature, beard feature, shape of face, height feature, clothing feature.
19. personnel control's management method according to claim 17 is characterized in that, also comprises following steps:
When needs are retrieved, import people's face picture and/or human body attributive character to be checked by switch to the center of described rear end Analysis server by client;
The center Analysis server of described rear end is by described switch, the pairing high definition facial image of feature that is complementary with described search condition that inquires to described client feedback.
20. personnel control's management method according to claim 17 is characterized in that, in the described step of the high definition facial image being carried out feature extraction, comprises following substep:
High definition facial image to pending feature extraction carries out preliminary treatment;
To carry out the normalization alignment of positioning feature point and image through described pretreated image;
Image after the normalization alignment of described positioning feature point and image is carried out the extraction of face's texture model Feature Extraction and human body attributive character, and all features that will extract are stored to described database by described switch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100714455A CN102170563A (en) | 2011-03-24 | 2011-03-24 | Intelligent person capture system and person monitoring management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100714455A CN102170563A (en) | 2011-03-24 | 2011-03-24 | Intelligent person capture system and person monitoring management method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102170563A true CN102170563A (en) | 2011-08-31 |
Family
ID=44491518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100714455A Pending CN102170563A (en) | 2011-03-24 | 2011-03-24 | Intelligent person capture system and person monitoring management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102170563A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106400A (en) * | 2013-02-06 | 2013-05-15 | 浙江宇视科技有限公司 | Face detecting method and device |
| CN103188474A (en) * | 2011-12-30 | 2013-07-03 | 中兴通讯股份有限公司 | Video intelligent analysis system and storing and playing method of surveillance video thereof |
| CN103647953A (en) * | 2013-12-25 | 2014-03-19 | 句容云影响软件技术开发有限公司 | Intelligent monitoring system and method |
| CN103841367A (en) * | 2012-11-21 | 2014-06-04 | 深圳市赛格导航科技股份有限公司 | Monitoring system |
| CN105095853A (en) * | 2014-05-21 | 2015-11-25 | 佳能株式会社 | Image processing apparatus and image processing method |
| CN105701486A (en) * | 2014-11-26 | 2016-06-22 | 上海骏聿数码科技有限公司 | Method for realizing human face information analysis and extraction in video camera |
| CN106297292A (en) * | 2016-08-29 | 2017-01-04 | 苏州金螳螂怡和科技有限公司 | Based on highway bayonet socket and the Trajectory System of comprehensively monitoring |
| CN106709424A (en) * | 2016-11-19 | 2017-05-24 | 北京中科天云科技有限公司 | Optimized surveillance video storage system and equipment |
| CN106803936A (en) * | 2017-02-24 | 2017-06-06 | 深圳英飞拓科技股份有限公司 | Video capture method and device based on internal memory encoding mechanism |
| CN107944392A (en) * | 2017-11-25 | 2018-04-20 | 周晓风 | A kind of effective ways suitable for cell bayonet Dense crowd monitor video target mark |
| CN108062416A (en) * | 2018-01-04 | 2018-05-22 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of label on map |
| CN108170732A (en) * | 2017-12-14 | 2018-06-15 | 厦门市美亚柏科信息股份有限公司 | Face picture search method and computer readable storage medium |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN109117797A (en) * | 2018-08-17 | 2019-01-01 | 浙江捷尚视觉科技股份有限公司 | A kind of face snapshot recognition method based on face quality evaluation |
| CN109446364A (en) * | 2018-10-23 | 2019-03-08 | 北京旷视科技有限公司 | Capture search method, image processing method, device, equipment and storage medium |
| CN109889773A (en) * | 2017-12-06 | 2019-06-14 | 中国移动通信集团四川有限公司 | Method, apparatus, equipment and the medium of the monitoring of assessment of bids room personnel |
| CN109993033A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团四川有限公司 | Method, system, server, equipment and the medium of video monitoring |
| CN112131916A (en) * | 2019-06-25 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Target snapshot method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731417A (en) * | 2005-08-19 | 2006-02-08 | 清华大学 | Method of robust human face detection in complicated background image |
| CN1975761A (en) * | 2006-12-15 | 2007-06-06 | 昆明利普机器视觉工程有限公司 | Visual frequency data excavating system and method for automatic identifying human figure |
| CN101227560A (en) * | 2007-01-17 | 2008-07-23 | 三星Techwin株式会社 | Digital photographing apparatus, method for controlling the same, and a recording medium for storing a program to implement the method |
| CN201111084Y (en) * | 2007-07-27 | 2008-09-03 | 上海银晨智能识别科技有限公司 | Portrait contrasting system used for communal security system |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN202121706U (en) * | 2011-03-24 | 2012-01-18 | 杭州海康威视软件有限公司 | Intelligent personnel monitoring system |
-
2011
- 2011-03-24 CN CN2011100714455A patent/CN102170563A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731417A (en) * | 2005-08-19 | 2006-02-08 | 清华大学 | Method of robust human face detection in complicated background image |
| CN1975761A (en) * | 2006-12-15 | 2007-06-06 | 昆明利普机器视觉工程有限公司 | Visual frequency data excavating system and method for automatic identifying human figure |
| CN101227560A (en) * | 2007-01-17 | 2008-07-23 | 三星Techwin株式会社 | Digital photographing apparatus, method for controlling the same, and a recording medium for storing a program to implement the method |
| CN201111084Y (en) * | 2007-07-27 | 2008-09-03 | 上海银晨智能识别科技有限公司 | Portrait contrasting system used for communal security system |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN202121706U (en) * | 2011-03-24 | 2012-01-18 | 杭州海康威视软件有限公司 | Intelligent personnel monitoring system |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103188474A (en) * | 2011-12-30 | 2013-07-03 | 中兴通讯股份有限公司 | Video intelligent analysis system and storing and playing method of surveillance video thereof |
| CN103841367A (en) * | 2012-11-21 | 2014-06-04 | 深圳市赛格导航科技股份有限公司 | Monitoring system |
| CN103106400A (en) * | 2013-02-06 | 2013-05-15 | 浙江宇视科技有限公司 | Face detecting method and device |
| CN103106400B (en) * | 2013-02-06 | 2016-03-23 | 浙江宇视科技有限公司 | A kind of method for detecting human face and device |
| CN103647953A (en) * | 2013-12-25 | 2014-03-19 | 句容云影响软件技术开发有限公司 | Intelligent monitoring system and method |
| CN105095853A (en) * | 2014-05-21 | 2015-11-25 | 佳能株式会社 | Image processing apparatus and image processing method |
| US10146992B2 (en) | 2014-05-21 | 2018-12-04 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium that recognize an image based on a designated object type |
| CN105701486A (en) * | 2014-11-26 | 2016-06-22 | 上海骏聿数码科技有限公司 | Method for realizing human face information analysis and extraction in video camera |
| CN105701486B (en) * | 2014-11-26 | 2019-11-19 | 上海骏聿数码科技有限公司 | A method of it realizing face information analysis in video camera and extracts |
| CN106297292A (en) * | 2016-08-29 | 2017-01-04 | 苏州金螳螂怡和科技有限公司 | Based on highway bayonet socket and the Trajectory System of comprehensively monitoring |
| CN106709424A (en) * | 2016-11-19 | 2017-05-24 | 北京中科天云科技有限公司 | Optimized surveillance video storage system and equipment |
| CN106709424B (en) * | 2016-11-19 | 2022-11-11 | 广东中科人人智能科技有限公司 | Optimized monitoring video storage system |
| CN106803936A (en) * | 2017-02-24 | 2017-06-06 | 深圳英飞拓科技股份有限公司 | Video capture method and device based on internal memory encoding mechanism |
| CN107944392A (en) * | 2017-11-25 | 2018-04-20 | 周晓风 | A kind of effective ways suitable for cell bayonet Dense crowd monitor video target mark |
| CN109889773A (en) * | 2017-12-06 | 2019-06-14 | 中国移动通信集团四川有限公司 | Method, apparatus, equipment and the medium of the monitoring of assessment of bids room personnel |
| CN108170732A (en) * | 2017-12-14 | 2018-06-15 | 厦门市美亚柏科信息股份有限公司 | Face picture search method and computer readable storage medium |
| CN109993033A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团四川有限公司 | Method, system, server, equipment and the medium of video monitoring |
| CN108062416B (en) * | 2018-01-04 | 2019-10-29 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating label on map |
| CN108062416A (en) * | 2018-01-04 | 2018-05-22 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of label on map |
| CN109117797A (en) * | 2018-08-17 | 2019-01-01 | 浙江捷尚视觉科技股份有限公司 | A kind of face snapshot recognition method based on face quality evaluation |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN109446364A (en) * | 2018-10-23 | 2019-03-08 | 北京旷视科技有限公司 | Capture search method, image processing method, device, equipment and storage medium |
| CN112131916A (en) * | 2019-06-25 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Target snapshot method and device, electronic equipment and storage medium |
| CN112131916B (en) * | 2019-06-25 | 2024-06-04 | 杭州海康威视数字技术股份有限公司 | Target snapshot method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102170563A (en) | Intelligent person capture system and person monitoring management method | |
| CN110942545B (en) | Dense person entrance guard control system and method based on face recognition and video fence | |
| CN109934176B (en) | Pedestrian recognition system, recognition method, and computer-readable storage medium | |
| CN104200671B (en) | A kind of virtual bayonet socket management method based on large data platform and system | |
| CN109711370B (en) | Data fusion method based on WIFI detection and face clustering | |
| CN104303193B (en) | Target classification based on cluster | |
| CN100481112C (en) | Human face recognition system and recognition method | |
| CN110853295A (en) | High-altitude parabolic early warning method and device | |
| CN103049459A (en) | Feature recognition based quick video retrieval method | |
| CN107808152A (en) | Lift the method and face identification system of face recognition accuracy rate | |
| CN108710827B (en) | A kind of micro- police service inspection in community and information automatic analysis system and method | |
| CN112200106A (en) | Cross-camera pedestrian re-identification and tracking method | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| CN202121706U (en) | Intelligent personnel monitoring system | |
| CN108769598A (en) | Across the camera video method for concentration identified again based on pedestrian | |
| CN109214324A (en) | Most face image output method and output system based on polyphaser array | |
| CN110276265A (en) | Pedestrian monitoring method and device based on intelligent three-dimensional solid monitoring device | |
| CN107657232A (en) | A kind of pedestrian's intelligent identification Method and its system | |
| WO2022156234A1 (en) | Target re-identification method and apparatus, and computer-readable storage medium | |
| CN112347856A (en) | Non-perception attendance system and method based on classroom scene | |
| CN109963113B (en) | Method and device for monitoring interested target | |
| Wang et al. | V2I-CARLA: A novel dataset and a method for vehicle reidentification-based V2I environment | |
| CN110324589A (en) | A kind of monitoring system and method for tourist attraction | |
| Feris et al. | Case study: IBM smart surveillance system | |
| CN107018359A (en) | A kind of vehicle-carried mobile monitoring system that there is intelligent picture to recognize |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: HANGZHOU HAIKANG WEISHI SOFTWARE CO., LTD. Effective date: 20120905 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 310012 HANGZHOU, ZHEJIANG PROVINCE TO: 310051 HANGZHOU, ZHEJIANG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20120905 Address after: Hangzhou City, Zhejiang province 310051 Binjiang District East Road Haikang Science Park No. 700, No. 1 Applicant after: Hangzhou Hikvision Digital Technology Co., Ltd. Address before: Xihu District Ma Cheng Road Hangzhou City, Zhejiang province 310012 Hikvision Building No. 36 Applicant before: Hangzhou Haikang Weishi Software Co., Ltd. |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110831 |