CN109711369A - Pedestrian count method, apparatus, system, computer equipment and storage medium - Google Patents
Pedestrian count method, apparatus, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109711369A CN109711369A CN201811637152.7A CN201811637152A CN109711369A CN 109711369 A CN109711369 A CN 109711369A CN 201811637152 A CN201811637152 A CN 201811637152A CN 109711369 A CN109711369 A CN 109711369A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- condition code
- count
- time video
- real time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
This application involves a kind of pedestrian count method, apparatus, system, computer equipment and storage mediums, wherein this method comprises: obtaining pedestrian count request;According to the corresponding real time video data of the pedestrian count request;Extract pedestrian's condition code of the multiple pedestrians occurred in the real time video data;It is compared pedestrian's condition code of the multiple pedestrian to obtain comparison result;Duplicate removal is carried out according to quantity of the comparison result to pedestrian to count to obtain pedestrian count result.The present invention is extracted and preserved by carrying out condition code structuring to real-time video, and carries out processing and collect statistics to condition code using big data technology, is realized the underproduction and is manually participated in and simultaneously it can be concluded that more accurate pedestrian count number.
Description
Technical field
The present invention relates to technical field of video processing, more particularly to a kind of pedestrian count method, apparatus, system, calculating
Machine equipment and storage medium.
Background technique
Currently, building as the rapid development of sociaty and economy, video monitoring system is just being graduallyd mature in the application of various industries
And if the number of cameras to come into operation just quicklys increase.Using with being arranged in that the crowd is dense or the camera of bayonet can obtain
A large amount of pedestrian information is taken, how effectively to monitor public place crowd density using these video cameras, is preferably safeguarded
Social stability is harmonious, has become an extremely urgent problem of law enforcement agency, entire society.
In the conventional technology, traditional demographic method lies substantially in the stage manually participated in, has plenty of and utilizes people
For the mode of counting, have plenty of and completed using equipment such as other electronic sensors, almost requires manually to participate in completing.This side
Formula spends a large amount of manpower, time, under efficiency is very low.In addition, crowd in advancing due to exist largely block, merge,
How separation realizes that accurate pedestrian count is one and challenging studies a question.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide one kind can reduce it is artificial participate in and be able to achieve acquisition compared with
For accurately pedestrian count method, apparatus, system, computer equipment and storage medium.
A kind of pedestrian count method, which comprises
Obtain pedestrian count request;
According to the corresponding real time video data of the pedestrian count request;
Extract pedestrian's condition code of the multiple pedestrians occurred in the real time video data;
It is compared pedestrian's condition code of the multiple pedestrian to obtain comparison result;
Duplicate removal is carried out according to quantity of the comparison result to pedestrian to count to obtain pedestrian count result.
The step of pedestrian's condition code for extracting the multiple pedestrians occurred in real-time video in one of the embodiments,
Further include:
The real time video data is decoded and carries out structured analysis;
Extract pedestrian's condition code of the multiple pedestrians occurred in the real time video data;
Wherein, pedestrian's condition code include: the depth length of pedestrian's hair, cap, jacket color, whether wear glasses,
Gender and facial characteristics.
It is described in one of the embodiments, to be compared pedestrian's condition code of the multiple pedestrian to obtain comparison result
The step of include:
The pedestrian's condition code information that will acquire the multiple pedestrian is compared;
Calculate the characteristic information similarity of pedestrian's condition code of multiple pedestrians;
Judge whether the multiple pedestrian is same people according to the characteristic similarity of pedestrian's condition code.
The characteristic similarity according to pedestrian's condition code judges the multiple pedestrian in one of the embodiments,
The step of whether being same people includes:
Judge whether the characteristic information similarity of pedestrian's condition code reaches threshold value;
Characteristic information similarity by multiple pedestrian's condition codes is more than that the pedestrian of threshold value is classified as the same person;
The pedestrian that the characteristic information similarity of all pedestrian's condition codes is no more than threshold value is regarded as into different pedestrians.
It is special in the pedestrian of the multiple pedestrians for extracting and occurring in the real time video data in one of the embodiments,
After the step of levying code further include:
Extract pedestrian's picture in the real time video data;
It sends pedestrian's picture in picture servers;
It sends pedestrian's condition code in database server;
Pedestrian's condition code of multiple pedestrians is obtained from the database server.
A kind of pedestrian count device, described device include:
First obtains module, and the acquisition module is for obtaining pedestrian count request;
Second obtains module, and described second, which obtains module, is used for according to the corresponding real-time view of the pedestrian count request
Frequency evidence;
Characteristic extracting module, the feature climbing form block is for extracting the multiple pedestrians' occurred in the real time video data
Pedestrian's condition code;
Comparison module, the comparison module are used to that pedestrian's condition code of the multiple pedestrian to be compared to obtain comparison knot
Fruit;
Statistical module, the statistical module are used to carry out duplicate removal according to quantity of the comparison result to pedestrian to count to obtain
Pedestrian count result.
A kind of pedestrian count system, the system comprises:
Above-mentioned pedestrian count device;
Video camera, the video camera obtain real time video data for shooting;
Access server, the access server are used to the video camera accessing the system;
Media forwarding server, the media forwarding server are used to send the video camera to the pedestrian count device
Shooting obtains real time video data;
Client, the client is for receiving the pedestrian count knot that the pedestrian count device is returned to the client
Fruit is simultaneously shown.
In one of the embodiments, the system also includes:
Picture servers, the picture servers are used to store pedestrian's picture that the pedestrian count device is sent;
Database server, the database server are used to store pedestrian's feature that the pedestrian count device is sent
Code.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes above-mentioned any one method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above-mentioned any one method is realized when row.
Above-mentioned pedestrian count method, apparatus, system, computer equipment and storage medium, by obtaining pedestrian count request;
According to the corresponding real time video data of the pedestrian count request;Extract the multiple rows occurred in the real time video data
Pedestrian's condition code of people;It is compared pedestrian's condition code of the multiple pedestrian to obtain comparison result;It is tied according to the comparison
Fruit carries out duplicate removal to the quantity of pedestrian and counts to obtain pedestrian count result.The present invention is by carrying out condition code structure to real-time video
Change is extracted and preserved, and carries out processing and collect statistics to condition code using big data technology, realizes the underproduction and manually participates in simultaneously
Simultaneously it can be concluded that more accurate pedestrian count number.
Detailed description of the invention
Fig. 1 is the application scenario diagram of pedestrian count method in one embodiment;
Fig. 2 is the flow diagram of pedestrian count method in one embodiment;
Fig. 3 is process the step of extracting pedestrian's condition code of the multiple pedestrians occurred in real-time video in one embodiment
Schematic diagram;
Fig. 4 is the stream that pedestrian's condition code of multiple pedestrians is compared to the step of obtaining comparison result in one embodiment
Journey schematic diagram;
Fig. 5 is to judge whether multiple pedestrians are same people according to the characteristic similarity of pedestrian's condition code in one embodiment
The flow diagram of step;
Fig. 6 is the flow diagram of pedestrian count method in another embodiment;
Fig. 7 is the sequence chart of pedestrian count method in one embodiment;
Fig. 8 is the structural block diagram of pedestrian count device in one embodiment;
Fig. 9 is the structural block diagram of pedestrian count device in another embodiment;
Figure 10 is the structural block diagram of pedestrian count system in one embodiment;
Figure 11 is the structural block diagram of pedestrian count system in another embodiment;
Figure 12 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
Pedestrian count method provided by the embodiment of the present invention may be used in application environment as shown in Figure 1.The application
It include: management server (CMS) in environment;Access server (APS);Intelligent engine server (SES);Picture servers
(TGI);Database server (DBS);Media forwarding server (SMT) and the real-time calculation server of big data (DMS).Its
In, management server, for in system video camera and each server module be managed collectively, such as be responsible for user management,
Role Management, district management, structure tasks management, video resource management, rights management, log management etc..Access server,
For carrying out Signalling exchange with headend equipment (such as: video camera) or platform.Intelligent engine server, for providing parser
The real-time video exported to common camera carries out intellectual analysis, extracts the condition code information of pedestrian.Picture servers are used
In the pedestrian's condition code picture for saving candid photograph.Database server, it is special for storing the pedestrian that intelligent engine server is exported
Levy code information.Media forwarding server, for forwarding the real-time video of common camera to be analyzed to intelligent engine server.
The real-time calculation server of big data, for passing through big data technology on backstage to pedestrian's condition code information of real-time grasp shoot in system
It is compared, and is uniformly summarized in real time, calculate pedestrian's quantity information.
In one embodiment, as shown in Fig. 2, providing a kind of pedestrian count method, it is applied in Fig. 1 in this way
It is illustrated for application environment, this method comprises:
Step 202, pedestrian count request is obtained;
Step 204, according to the corresponding real time video data of pedestrian count request;
Step 206, pedestrian's condition code of the multiple pedestrians occurred in real time video data is extracted;
Step 208, it is compared pedestrian's condition code of multiple pedestrians to obtain comparison result;
Step 210, duplicate removal is carried out according to quantity of the comparison result to pedestrian to count to obtain pedestrian count result.
Specifically, with reference to Fig. 7, video camera passes through access server access system.Streaming Media forwarding server draws to intelligence
It holds up server and sends real-time video.Intelligent engine server obtains pedestrian count request, receives real-time video according to the request
Afterwards, real-time video is decoded to and carried out structured analysis, extracts the pedestrian's condition code occurred in video.Intelligent engine server will
Obtained pedestrian's condition code information preservation is analyzed to database server.The real-time calculation server of big data is from database server
Middle acquisition intelligent engine server is saved in the pedestrian's condition code information captured in the real-time video in database server.Big number
Pedestrian's condition code information that calculation server will acquire when factually is compared, and is by the similar label of multiple characteristic informations
People regards as different pedestrians when similarity is less than certain threshold value after all characteristic informations compare.Finally uniformly summarized, and will
Calculated result returns to client and is shown.
In the present embodiment, based on video structural by obtaining pedestrian count request;According to pedestrian count request
Corresponding real time video data;Extract pedestrian's condition code of the multiple pedestrians occurred in real time video data;By multiple pedestrians'
Pedestrian's condition code is compared to obtain comparison result;Duplicate removal is carried out according to quantity of the comparison result to pedestrian to count to obtain pedestrian's system
Count result.The present embodiment is extracted and preserved by carrying out condition code structuring to real-time video, and using big data technology to spy
Sign code carries out processing and collect statistics, realizes the underproduction and manually participates in and simultaneously it can be concluded that more accurate pedestrian count number.
In one embodiment, a kind of pedestrian count method is provided, as shown in figure 3, extracting real-time video in this method
The step of pedestrian's condition code of multiple pedestrians of middle appearance includes:
Step 302, real time video data is decoded and carries out structured analysis;
Step 304, pedestrian's condition code of the multiple pedestrians occurred in real time video data is extracted;Wherein, pedestrian's condition code
Include: the depth length of pedestrian's hair, cap, jacket color, whether wear glasses, gender and facial characteristics.
Specifically, with reference to Fig. 7, after intelligent engine server receives real-time video, real-time video is decoded and is tied
Structureization analysis, extracts pedestrian's condition code for occurring in video, depth length, cap, jacket color including pedestrian's hair, whether
It wears glasses, gender and facial characteristics etc., while pedestrian being intercepted from video and is come out.
In the present embodiment, it realizes and pedestrian's condition code of multiple pedestrians is extracted, pass through the ratio of pedestrian's condition code
To may determine that whether the multiple pedestrians intercepted in video are same people, the mistake of statistics is duplicated when avoiding pedestrian count
Accidentally, the accuracy of pedestrian count is improved.
In one embodiment, a kind of pedestrian count method is provided, as shown in figure 4, by multiple pedestrians' in this method
Pedestrian's condition code is compared the step of obtaining comparison result and includes:
Step 402, the pedestrian's condition code information that will acquire multiple pedestrians is compared;
Step 404, the characteristic information similarity of pedestrian's condition code of multiple pedestrians is calculated;
Step 406, judge whether multiple pedestrians are same people according to the characteristic similarity of pedestrian's condition code.
In one embodiment, a kind of pedestrian count method is provided, as shown in figure 5, according to pedestrian's feature in this method
The characteristic similarity of code judges that the step of whether multiple pedestrians are same people includes:
Step 502, judge whether the characteristic information similarity of pedestrian's condition code reaches threshold value;
Step 504, the pedestrian that the characteristic information similarity of multiple pedestrian's condition codes is more than threshold value is classified as same
People;
Step 506, the pedestrian that the characteristic information similarity of all pedestrian's condition codes is no more than threshold value is regarded as into difference
Pedestrian.
Specifically, with reference to Fig. 7, pedestrian's condition code information that the real-time calculation server of big data will acquire is compared, will
The condition code that similarity is greater than certain threshold value is classified as the same person, and similarity is less than certain threshold after all characteristic informations compare
Different pedestrians are regarded as when value, which can be preset by configuring accordingly.
In the present embodiment, it is compared by comparing multiple characteristic information similarities of the pedestrian intercepted in video, it is real
Show to whether the pedestrian intercepted in video is that same people judges, has achieved the purpose that duplicate removal counts.Solves conventional pedestrian
Statistical efficiency is low, the low problem of accuracy rate, improves pedestrian count digitlization and intelligent level, and be suitable for multiple indoor room
Outer scene.
In one embodiment, a kind of pedestrian count method is provided, as shown in fig. 6, extracting view in real time in this method
After the step of pedestrian's condition code for multiple pedestrians that frequency occurs in further include:
Step 602, pedestrian's picture in real time video data is extracted;
Step 604, it sends pedestrian's picture in picture servers;
Step 606, it sends pedestrian's condition code in database server;
Step 608, pedestrian's condition code of multiple pedestrians is obtained from database server.
Specifically, with reference to Fig. 7, intelligent engine server stores the pedestrian's picture analyzed and interception obtains to photo services
In device.Intelligent engine server can also be by the obtained pedestrian's condition code information preservation of analysis to database server.Big data
Real-time calculation server is saved in the real-time view in database server from acquisition intelligent engine server in database server
The pedestrian's condition code information captured in frequency.
In the present embodiment, the interception and storage to pedestrian's picture are realized, also achieves and pedestrian's condition code is deposited
Storage and acquisition.
It should be understood that although each step in the flow chart of Fig. 2-7 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-7
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 8, providing a kind of pedestrian count device 800, which includes:
First obtains module 801, for obtaining pedestrian count request;
Second obtains module 802, for according to the corresponding real time video data of pedestrian count request;
Characteristic extracting module 803, for extracting pedestrian's condition code of the multiple pedestrians occurred in real time video data;
Comparison module 804, for being compared pedestrian's condition code of multiple pedestrians to obtain comparison result;
Statistical module 805 counts to obtain pedestrian count result for carrying out duplicate removal according to quantity of the comparison result to pedestrian.
In one embodiment, characteristic extracting module 803 is also used to: real time video data being decoded and carries out structuring point
Analysis;Extract pedestrian's condition code of the multiple pedestrians occurred in real time video data;Wherein, pedestrian's condition code includes: pedestrian's hair
Depth length, cap, jacket color, whether wear glasses, gender and facial characteristics.
In one embodiment, comparison module 804 is also used to: the pedestrian's condition code information that will acquire multiple pedestrians compares
It is right;Calculate the characteristic information similarity of pedestrian's condition code of multiple pedestrians;Institute is judged according to the characteristic similarity of pedestrian's condition code
State whether multiple pedestrians are same people.
In one embodiment, comparison module 804 is also used to: judging whether the characteristic information similarity of pedestrian's condition code reaches
To threshold value;Characteristic information similarity by multiple pedestrian's condition codes is more than that the pedestrian of threshold value is classified as the same person;To own
The pedestrian that the characteristic information similarity of pedestrian's condition code is no more than threshold value regards as different pedestrians.
In one embodiment, as shown in figure 9, providing a kind of pedestrian count device 800, which further includes sending mould
Block 806 is used for: extracting pedestrian's picture in real time video data;It sends pedestrian's picture in picture servers;By pedestrian spy
Sign code is sent in database server.
Specific about pedestrian count device limits the restriction that may refer to above for pedestrian count method, herein not
It repeats again.
In one embodiment, as shown in Figure 10, a kind of pedestrian count system 1000 is provided, which includes:
Such as the pedestrian count device 1001 in above-mentioned any embodiment;
Video camera 1002 obtains real time video data for shooting;
Access server 1003 is used for video camera access system;
Media forwarding server 1004 shoots to obtain real time video data for sending video camera to pedestrian count device;
Client 1005, for receiving pedestrian count result that pedestrian count device is returned to client and being shown.
In one embodiment, shown in Figure 11, a kind of pedestrian count system 1000, the system are provided further include:
Picture servers 1006, for storing pedestrian's picture of pedestrian's statistic device transmission;
Database server 1007, for storing pedestrian's condition code of pedestrian's statistic device transmission.
Specifically, with reference to Fig. 7, addition is used for the common camera of video monitoring, and Allocation Analysis plan in systems.?
Structured analysis server is added in system, and distributes common camera to structured analysis server.Addition figure in systems
Piece server, and picture servers distribution structure Analysis server is given, the structured analysis server distributed is pedestrian spy
Code storage is levied into picture servers.Database server is added in systems, is divided for storage configuration Analysis server
The condition code information of analysis.Media forwarding server is added in systems, and distributes video camera loaded list, by common camera
Real-time video is transmitted to structured analysis server and is analyzed.All condition codes of the real-time calculation server of big data pedestrian
Information is loaded into memory, and is carried out multiple characteristic informations and compared comprehensively, and similar pedestrian is excluded, and is obtained and is more accurately gone
People's statistical number.
The system realizes that the process of pedestrian count includes: that common camera passes through network insertion APS server.Pass through client
The servers such as intelligent engine server, picture servers, database server and media forwarding are added to system and carry out pipe by end
Reason.After video flowing is sent to intelligent engine server by network by Streaming Media forwarding server, start intelligent engine service
Start real-time video structural analysis service.Pedestrian's picture, which is deposited, to be stored up to picture servers, and pedestrian's condition code will be stored to database.
Start the real-time calculation server of big data, the real-time calculation server of big data is constantly compared and converges to condition code
Total statistics, generates pedestrian count information, and calculated result is returned to client and is shown.
In the present embodiment, real-time video is acquired by video camera, real-time video is carried out by pedestrian count device special
Sign code structuring is extracted and preserved, and carries out processing and collect statistics to condition code using big data technology, by comparing duplicate removal
Reach the statistics of certain accuracy to the crowd in traveling afterwards.
Specific about pedestrian count system limits the limit that may refer to above for pedestrian count device and method
Fixed, details are not described herein.
In one embodiment, a kind of computer equipment is provided, internal structure chart is shown in Fig.12.The calculating
Machine equipment includes processor, memory and the network interface connected by system bus.Wherein, the processing of the computer equipment
Device is for providing calculating and control ability.The memory of the computer equipment includes non-volatile memory medium, built-in storage.It should
Non-volatile memory medium is stored with operating system, computer program and database.The built-in storage is non-volatile memories Jie
The operation of operating system and computer program in matter provides environment.The network interface of the computer equipment is used for and external end
End passes through network connection communication.To realize a kind of pedestrian count method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Figure 12, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor are realized when executing computer program in above each embodiment of the method
The step of.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
The step in above each embodiment of the method is realized when machine program is executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of pedestrian count method, which comprises
Obtain pedestrian count request;
According to the corresponding real time video data of the pedestrian count request;
Extract pedestrian's condition code of the multiple pedestrians occurred in the real time video data;
It is compared pedestrian's condition code of the multiple pedestrian to obtain comparison result;
Duplicate removal is carried out according to quantity of the comparison result to pedestrian to count to obtain pedestrian count result.
2. pedestrian count method according to claim 1, which is characterized in that occur in the extraction real-time video multiple
The step of pedestrian's condition code of pedestrian further include:
The real time video data is decoded and carries out structured analysis;
Extract pedestrian's condition code of the multiple pedestrians occurred in the real time video data;
Wherein, whether pedestrian's condition code includes: the depth length of pedestrian's hair, cap, jacket color, wears glasses, gender
And facial characteristics.
3. pedestrian count method according to claim 1, which is characterized in that pedestrian's feature by the multiple pedestrian
Code is compared the step of obtaining comparison result and includes:
The pedestrian's condition code information that will acquire the multiple pedestrian is compared;
Calculate the characteristic information similarity of pedestrian's condition code of multiple pedestrians;
Judge whether the multiple pedestrian is same people according to the characteristic similarity of pedestrian's condition code.
4. pedestrian count method according to claim 3, which is characterized in that the feature according to pedestrian's condition code
Similarity judges that the step of whether the multiple pedestrian is same people includes:
Judge whether the characteristic information similarity of pedestrian's condition code reaches threshold value;
Characteristic information similarity by multiple pedestrian's condition codes is more than that the pedestrian of threshold value is classified as the same person;
The pedestrian that the characteristic information similarity of all pedestrian's condition codes is no more than threshold value is regarded as into different pedestrians.
5. pedestrian count method according to claim 1-4, which is characterized in that extract the real-time view described
After the step of pedestrian's condition code for multiple pedestrians that frequency occurs in further include:
Extract pedestrian's picture in the real time video data;
It sends pedestrian's picture in picture servers;
It sends pedestrian's condition code in database server;
Pedestrian's condition code of multiple pedestrians is obtained from the database server.
6. a kind of pedestrian count device, which is characterized in that described device includes:
First obtains module, and the acquisition module is for obtaining pedestrian count request;
Second obtains module, and described second, which obtains module, is used for according to the corresponding real-time video number of the pedestrian count request
According to;
Characteristic extracting module, the feature climbing form block are used to extract the pedestrian of the multiple pedestrians occurred in the real time video data
Condition code;
Comparison module, the comparison module is for being compared pedestrian's condition code of the multiple pedestrian to obtain comparison result;
Statistical module, the statistical module are used to carry out duplicate removal according to quantity of the comparison result to pedestrian to count to obtain pedestrian
Statistical result.
7. a kind of pedestrian count system, which is characterized in that the system comprises:
Pedestrian count device according to claim 6;
Video camera, the video camera obtain real time video data for shooting;
Access server, the access server are used to the video camera accessing the system;
Media forwarding server, the media forwarding server are used to send the video camera shooting to the pedestrian count device
Obtain real time video data;
Client, the client are used to receive pedestrian count result that the pedestrian count device is returned to the client simultaneously
It is shown.
8. pedestrian count system according to claim 7, which is characterized in that the system also includes:
Picture servers, the picture servers are used to store pedestrian's picture that the pedestrian count device is sent;
Database server, the database server are used to store pedestrian's condition code that the pedestrian count device is sent.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 5 institute when executing the computer program
The step of stating method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637152.7A CN109711369A (en) | 2018-12-29 | 2018-12-29 | Pedestrian count method, apparatus, system, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637152.7A CN109711369A (en) | 2018-12-29 | 2018-12-29 | Pedestrian count method, apparatus, system, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109711369A true CN109711369A (en) | 2019-05-03 |
Family
ID=66259568
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811637152.7A Pending CN109711369A (en) | 2018-12-29 | 2018-12-29 | Pedestrian count method, apparatus, system, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109711369A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
CN205451095U (en) * | 2015-12-02 | 2016-08-10 | 深圳市商汤科技有限公司 | A face -identifying device |
CN105979210A (en) * | 2016-06-06 | 2016-09-28 | 深圳市深网视界科技有限公司 | Pedestrian identification system based on multi-ball multi-gun camera array |
CN106331657A (en) * | 2016-11-02 | 2017-01-11 | 北京弘恒科技有限公司 | Video analysis and detection method and system for crowd gathering and moving |
CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技(深圳)有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
CN107330386A (en) * | 2017-06-21 | 2017-11-07 | 厦门中控智慧信息技术有限公司 | A kind of people flow rate statistical method and terminal device |
CN108492151A (en) * | 2018-04-13 | 2018-09-04 | 郑俊杰 | A kind of stream of people's statistical method being applicable in market survey |
CN108537184A (en) * | 2018-04-13 | 2018-09-14 | 郑俊杰 | A kind of stream of people's statistical system being applicable in market survey |
CN108984799A (en) * | 2018-08-21 | 2018-12-11 | 北京深瞐科技有限公司 | A kind of video data handling procedure and device |
-
2018
- 2018-12-29 CN CN201811637152.7A patent/CN109711369A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
CN205451095U (en) * | 2015-12-02 | 2016-08-10 | 深圳市商汤科技有限公司 | A face -identifying device |
CN105979210A (en) * | 2016-06-06 | 2016-09-28 | 深圳市深网视界科技有限公司 | Pedestrian identification system based on multi-ball multi-gun camera array |
CN106331657A (en) * | 2016-11-02 | 2017-01-11 | 北京弘恒科技有限公司 | Video analysis and detection method and system for crowd gathering and moving |
CN106998444A (en) * | 2017-02-14 | 2017-08-01 | 北京中科天云科技有限公司 | A kind of big data face monitoring system and device |
CN107330386A (en) * | 2017-06-21 | 2017-11-07 | 厦门中控智慧信息技术有限公司 | A kind of people flow rate statistical method and terminal device |
CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技(深圳)有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
CN108492151A (en) * | 2018-04-13 | 2018-09-04 | 郑俊杰 | A kind of stream of people's statistical method being applicable in market survey |
CN108537184A (en) * | 2018-04-13 | 2018-09-14 | 郑俊杰 | A kind of stream of people's statistical system being applicable in market survey |
CN108984799A (en) * | 2018-08-21 | 2018-12-11 | 北京深瞐科技有限公司 | A kind of video data handling procedure and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105163067B (en) | A kind of throwing object in high sky evidence-obtaining system based on digital image processing techniques | |
CN106060442B (en) | Video storage method, device and system | |
CN110225299B (en) | Video monitoring method and device, computer equipment and storage medium | |
CN101860731B (en) | Video information processing method, system and server | |
CN109308460B (en) | Article detection method, system and computer readable storage medium | |
US10515117B2 (en) | Generating and reviewing motion metadata | |
CN110298862A (en) | Method for processing video frequency, device, computer readable storage medium and computer equipment | |
CN110738178A (en) | Garden construction safety detection method and device, computer equipment and storage medium | |
CN111161206A (en) | Image capturing method, monitoring camera and monitoring system | |
CN113992893A (en) | Park inspection method and device, storage medium and electronic device | |
CN111241938A (en) | Face recognition method and device based on image verification and computer equipment | |
CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
CN111177469A (en) | Face retrieval method and face retrieval device | |
CN112818173A (en) | Method and device for identifying associated object and computer readable storage medium | |
CN111191506A (en) | Personnel flow statistical method and device, computer equipment and storage medium | |
CN111586432B (en) | Method and device for determining air-broadcast live broadcast room, server and storage medium | |
CN112347856A (en) | Non-perception attendance system and method based on classroom scene | |
CN109960969A (en) | The method, apparatus and system that mobile route generates | |
CN111435435B (en) | Companion identification method, device, server and system | |
CN107071337A (en) | The transmission method and device of a kind of video monitoring image | |
CN114786038A (en) | Low-custom live broadcast behavior monitoring method based on deep learning | |
CN114915753A (en) | Architecture of cloud server, data processing method and storage medium | |
CN113744221A (en) | Shot object counting method and device, computer equipment and storage medium | |
CN109711369A (en) | Pedestrian count method, apparatus, system, computer equipment and storage medium | |
CN114863364B (en) | Security detection method and system based on intelligent video monitoring |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |