CN114827535A - Network video monitoring system based on face recognition - Google Patents
Network video monitoring system based on face recognition Download PDFInfo
- Publication number
- CN114827535A CN114827535A CN202210355801.4A CN202210355801A CN114827535A CN 114827535 A CN114827535 A CN 114827535A CN 202210355801 A CN202210355801 A CN 202210355801A CN 114827535 A CN114827535 A CN 114827535A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- retrieval
- image
- facial
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a network video monitoring system based on face recognition, which is characterized by comprising the following components: the system comprises an image intercepting module, a facial feature processing unit, a face recognition module, a face image database and a retrieval information extracting unit; the output end of the image intercepting module is respectively connected with the input ends of the facial feature processing unit and the retrieval information extracting unit, and the image intercepting module intercepts the whole personnel picture and the facial picture from the monitoring video. The invention realizes the corresponding interception of the whole picture and the facial picture of the personnel through the image interception module, then extracts retrieval limit data through the analysis of the whole picture of the personnel and transmits the retrieval limit data to the facial image database to realize the retrieval and extraction of the facial recognition image, thereby realizing the preliminary screening of a large amount of facial reference image data, then carrying out the facial recognition based on the retrieved facial recognition image extracted as the basic data, and obviously reducing the data volume for carrying out the facial matching recognition.
Description
Technical Field
The invention relates to the technical field of video monitoring systems, in particular to a network video monitoring system based on face recognition.
Background
As is known, the monitoring system is composed of a camera, transmission, control, display and recording 5. The video camera transmits video images to the control host through a coaxial video cable, a network cable and optical fibers, the control host distributes video signals to each monitor and video equipment, and simultaneously voice signals to be transmitted can be synchronously input into the video camera for face recognition, and the biological recognition technology for identity recognition based on face characteristic information of people is provided. The method comprises the following steps of collecting images or video streams containing human faces by using a camera or a camera, automatically detecting and tracking the human faces in the images, and further carrying out face recognition on the detected human faces.
If application number is 2016206181611, the name is a chinese patent of intelligent video monitored control system based on face identification, and it includes remote video surveillance center, monitor terminal and interactive terminal, remote video surveillance center is connected with monitor terminal and interactive terminal respectively, monitor terminal includes collection module, data processing module and storage module, collection module is connected with data processing module, data processing module is connected with storage module, the last wireless network interface and the power and interconnect of being equipped with of monitor terminal, the last LED lamp that is equipped with of monitor terminal, the LED lamp is connected with the power.
Like the above-mentioned application is the same, the video surveillance system based on face identification among the prior art all matches the contrast analysis based on personnel's facial image that video surveillance system gathered and the face reference image that stores in the database and realizes video surveillance and face identification supporting use, but when in actual use, because face reference image data is big, lead to that the recognition efficiency is lower when carrying out face identification and matching the discernment, can't satisfy large-traffic current demand, and influence the stability of system operation.
Disclosure of Invention
The invention aims to provide a network video monitoring system based on face recognition, which aims to overcome the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme: a network video monitoring system based on face recognition comprises: the system comprises an image intercepting module, a facial feature processing unit, a face recognition module, a face image database and a retrieval information extracting unit; the output end of the image intercepting module is respectively connected with the input ends of the facial feature processing unit and the retrieval information extracting unit, and the image intercepting module intercepts a whole personnel picture and a facial picture from a monitoring video, transmits the whole personnel picture to the retrieval information extracting unit and transmits the facial picture to the facial feature processing unit; the retrieval information extraction unit extracts retrieval limiting data based on the analysis of the whole personnel picture and transmits the retrieval limiting data to a face image database to realize retrieval and extraction of a face recognition image; the facial feature extraction unit acquires facial feature data information based on a facial picture and transmits the facial feature data information to the face recognition module, and the face recognition module performs matching analysis on the facial feature data information and a face recognition image extracted by retrieval to realize face recognition.
As a further description of the above technical solution:
the video monitoring unit comprises a plurality of video monitoring terminals, the output end of each video monitoring terminal is connected with the input end of the image intercepting unit, and each video monitoring terminal is used for collecting monitoring videos.
As a further description of the above technical solution:
the image intercepting unit comprises a facial image intercepting module and an overall image intercepting module, the facial image intercepting module is used for identifying faces of people in the monitoring video and intercepting facial images, and the overall image intercepting module is used for identifying the people in the monitoring video and intercepting overall images of the people.
As a further description of the above technical solution:
the retrieval information extraction unit comprises a characteristic information extraction module and a retrieval limiting module, wherein the characteristic information extraction module acquires personnel characteristic information based on the intercepted personnel whole image, and the retrieval limiting module acquires retrieval limiting data based on the acquired characteristic information and transmits the retrieval limiting data to a face image database.
As a further description of the above technical solution:
the characteristic information comprises person gender information, height information and age group information.
As a further description of the above technical solution:
the human face database comprises a human face storage module and a retrieval extraction module, wherein the output end of the human face storage module is connected with the input end of the retrieval extraction module, the human face storage module is used for storing human face reference images, and the retrieval extraction module retrieves and obtains the human face reference images which accord with retrieval limited data in the human face storage module based on the retrieval limited data to form human face recognition images.
As a further description of the above technical solution:
the face storage modules comprise a plurality of face storage modules, and each face storage module stores the face reference image in a distributed mode based on the personnel characteristic information.
As a further description of the above technical solution:
the facial feature processing unit comprises an image processing module and a feature data extraction module, the image processing module is used for carrying out histogram equalization processing on the facial picture, and the feature data extraction module is used for identifying the processed facial picture to obtain the face feature data.
As a further description of the above technical solution:
the video monitoring terminal comprises a monitoring camera and an illumination compensation module, the monitoring camera is used for collecting monitoring video data, and the illumination compensation module is used for assisting in collecting the monitoring video data for the monitoring camera to perform illumination compensation.
As a further description of the above technical solution:
the video monitoring terminal further comprises an adaptive adjusting module, the adaptive adjusting module comprises a video detection processing module and a driving adjusting module, the video detection processing module is used for acquiring monitoring video data acquired by the monitoring camera, acquiring monitoring camera adjusting information based on personnel position information analysis in the monitoring video data, and transmitting the adjusting information to the driving adjusting module, the driving adjusting module is connected with the monitoring camera, and the driving adjusting module receives the adjusting information and then adjusts the position of the monitoring camera.
The invention provides a network video monitoring system based on face recognition. The method has the following beneficial effects:
this network video monitored control system based on face identification realizes corresponding intercepting personnel's whole picture and face picture through image intercepting module, then through the whole picture analysis of personnel extract retrieve limited data and transmit to face image database and realize retrieving and draw the face identification image, realize tentatively carrying out the prescreening to a large amount of face benchmark image data, then extracting face identification image based on the retrieval and carrying out face identification as the basic data, show to reduce the data bulk that carries out face matching identification, face identification efficiency has been improved, satisfy large-traffic current demand, and improve the stability of system operation, the realization is carried out make full use of to the surveillance video data who gathers.
Drawings
Fig. 1 is a schematic view of an overall structure of a network video monitoring system based on face recognition according to the present invention;
FIG. 2 is a schematic diagram of an image capture unit of the present invention;
FIG. 3 is a diagram of a search information extraction unit according to the present invention;
FIG. 4 is a schematic diagram of a face image database according to the present invention;
FIG. 5 is a schematic diagram of a video monitoring terminal according to the present invention;
fig. 6 is a schematic diagram of a facial feature processing unit according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1 to 6, a network video monitoring system based on face recognition includes: the system comprises an image intercepting module, a facial feature processing unit, a face recognition module, a face image database and a retrieval information extracting unit; the output end of the image intercepting module is respectively connected with the input ends of the facial feature processing unit and the retrieval information extracting unit, and the image intercepting module intercepts the whole personnel picture and the facial picture from the monitoring video, transmits the whole personnel picture to the retrieval information extracting unit and transmits the facial picture to the facial feature processing unit; the output end of the retrieval information extraction unit is connected with the input end of the face image database, and the retrieval information extraction unit extracts retrieval limiting data based on the analysis of the whole person image and transmits the retrieval limiting data to the face image database to realize retrieval and extraction of a face recognition image; the output end of the facial feature extraction unit is connected with the input end of the face recognition module, the input end of the face recognition module is further connected with the output end of the face image database, the facial feature extraction unit acquires face feature data information based on a face image and transmits the face feature data information to the face recognition module, and the face recognition module performs matching analysis on the face feature data information and a face recognition image extracted by retrieval to realize face recognition.
The embodiment provides a network video monitoring system based on face identification, realize corresponding whole picture of intercepting personnel and face picture through image intercepting module, then extract the retrieval limited data and transmit to face image database and correspond the retrieval and extract the face identification image through the whole picture analysis of personnel, realize tentatively carrying out the primary screening to a large amount of face benchmark image data of storing in the face image database, then extracting the face identification image based on the retrieval and carrying out face identification as the basic data, show and reduce the data bulk that carries out face matching identification, face identification efficiency has been improved, satisfy large-traffic current demand, and improve the stability of system operation, the realization is carried out make full use of to the surveillance video data who gathers.
The image intercepting unit comprises a facial image intercepting module and an overall image intercepting module, the facial image intercepting module is used for identifying faces of people in the monitoring video and intercepting facial images, and the overall image intercepting module is used for identifying the people in the monitoring video and intercepting overall images of the people.
The retrieval information extraction unit comprises a characteristic information extraction module and a retrieval limiting module, wherein the characteristic information extraction module acquires personnel characteristic information based on the intercepted personnel whole image, the characteristic information comprises personnel gender information, height information and age group information, and the retrieval limiting module acquires retrieval limiting data based on the acquired characteristic information and transmits the retrieval limiting data to a face image database. The characteristic information extraction module obtains sex information of the person as male, the rising information is 165cm-175cm and the age group is 15-35 in the person characteristic information according to the whole person, the retrieval limiting module obtains retrieval limiting data according to the obtained characteristic information, and then the preliminary screening of a large amount of face reference image data stored in a face image database is realized according to the retrieval limiting data. The human face database comprises a human face storage module and a retrieval extraction module, wherein the output end of the human face storage module is connected with the input end of the retrieval extraction module, the human face storage module is used for storing human face reference images, each human face reference image data comprises personal information, the personal information corresponds to the characteristic information extracted by the characteristic information extraction module, namely the personal information is sex information, rising information and age information, and the retrieval extraction module retrieves and obtains human face reference images which accord with retrieval limiting data in the human face storage module based on the retrieval limiting data to form a human face recognition image.
Furthermore, the face storage modules comprise a plurality of face storage modules, and each face storage module performs distributed storage on the face reference image based on the personnel characteristic information. Each face storage module is connected with the retrieval extraction module, and the face reference images are stored in a distributed mode based on a characteristic information classification mode through the face storage modules, so that the retrieval extraction module can retrieve the face reference images which accord with retrieval limit data in the face storage modules based on the retrieval limit data more conveniently.
The facial feature processing unit comprises an image processing module and a feature data extraction module, the output end of the image processing module is connected with the input end of the feature data extraction module, the image processing module is used for carrying out histogram equalization processing on a facial picture, and the feature data extraction module is used for identifying the processed facial picture to obtain face feature data.
The video monitoring unit comprises a plurality of video monitoring terminals, the output end of each video monitoring terminal is connected with the input end of the image capturing unit, and each video monitoring terminal is used for collecting monitoring videos. The video monitoring terminal comprises a monitoring camera and an illumination compensation module, the monitoring camera is used for collecting monitoring video data, and the illumination compensation module is used for assisting in collecting the monitoring video data for the monitoring camera to perform illumination compensation. The illumination problem is always a very important and difficult problem to solve in face detection and recognition, the existing cameras have different degrees of dependence on illumination adjustment when acquiring video image data information, the existence of over-bright and over-dark polarization information can cause the reduction of the recognition rate, and illumination compensation is performed when the monitoring camera acquires monitoring video data through the illumination compensation module, so that the recognition rate is improved. The video monitoring terminal further comprises an adaptive adjusting module, the adaptive adjusting module comprises a video detection processing module and a driving adjusting module, the video detection processing module is used for acquiring monitoring video data acquired by the monitoring camera, acquiring monitoring camera adjusting information based on personnel position information analysis in the monitoring video data, transmitting the adjusting information to the driving adjusting module, the driving adjusting module is connected with the monitoring camera, and the driving adjusting module performs position adjustment on the monitoring camera after receiving the adjusting information.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. A network video monitoring system based on face recognition is characterized by comprising: the system comprises an image intercepting module, a facial feature processing unit, a face recognition module, a face image database and a retrieval information extracting unit; the output end of the image intercepting module is respectively connected with the input ends of the facial feature processing unit and the retrieval information extracting unit, and the image intercepting module intercepts a whole personnel picture and a facial picture from a monitoring video, transmits the whole personnel picture to the retrieval information extracting unit and transmits the facial picture to the facial feature processing unit;
the retrieval information extraction unit extracts retrieval limiting data based on the analysis of the whole personnel picture and transmits the retrieval limiting data to a face image database to realize retrieval and extraction of a face recognition image;
the facial feature extraction unit acquires face feature data information based on a facial picture and transmits the face feature data information to the face recognition module, and the face recognition module performs matching analysis on the face feature data information and a face recognition image extracted by retrieval to realize face recognition.
2. The network video monitoring system based on face recognition according to claim 1, further comprising a video monitoring unit, wherein the video monitoring unit comprises a plurality of video monitoring terminals, an output end of each video monitoring terminal is connected with an input end of the image capturing unit, and each video monitoring terminal is used for collecting monitoring videos.
3. The network video monitoring system based on face recognition as claimed in claim 1, wherein the image capturing unit comprises a facial image capturing module and a whole image capturing module, the facial image capturing module is used for recognizing faces of people in the monitored video and capturing facial images, and the whole image capturing module is used for recognizing people in the monitored video and capturing whole images of people.
4. The system of claim 1, wherein the retrieval information extraction unit comprises a feature information extraction module and a retrieval limitation module, the feature information extraction module obtains the person feature information based on the intercepted whole person image, and the retrieval limitation module obtains retrieval limitation data based on the obtained feature information and transmits the retrieval limitation data to the face image database.
5. The network video monitoring system based on face recognition of claim 4, wherein the characteristic information comprises gender information, height information and age group information of people.
6. The system according to claim 1, wherein the face database comprises a face storage module and a retrieval extraction module, an output end of the face storage module is connected to an input end of the retrieval extraction module, the face storage module is used for storing face reference images, and the retrieval extraction module retrieves face reference images in the face storage module according with retrieval limit data based on retrieval limit data to form a face recognition image.
7. The system according to claim 6, wherein the face storage modules comprise a plurality of face storage modules, and each face storage module stores the face reference image in a distributed manner based on the person feature information.
8. The system according to claim 1, wherein the facial feature processing unit includes an image processing module and a feature data extraction module, the image processing module is configured to perform histogram equalization processing on the facial picture, and the feature data extraction module is configured to identify the processed facial picture to obtain the facial feature data.
9. The network video monitoring system based on face recognition as set forth in claim 2, wherein the video monitoring terminal comprises a surveillance camera for collecting surveillance video data and an illumination compensation module for assisting illumination compensation for the surveillance camera in collecting the surveillance video data.
10. The network video monitoring system based on face recognition according to claim 9, wherein the video monitoring terminal further comprises an adaptive adjustment module, the adaptive adjustment module comprises a video detection processing module and a driving adjustment module, the video detection processing module is configured to obtain surveillance video data collected by the surveillance camera, analyze and obtain adjustment information of the surveillance camera based on position information of a person in the surveillance video data, and transmit the adjustment information to the driving adjustment module, the driving adjustment module is connected to the surveillance camera, and the driving adjustment module performs position adjustment on the surveillance camera after receiving the adjustment information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210355801.4A CN114827535A (en) | 2022-04-06 | 2022-04-06 | Network video monitoring system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210355801.4A CN114827535A (en) | 2022-04-06 | 2022-04-06 | Network video monitoring system based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114827535A true CN114827535A (en) | 2022-07-29 |
Family
ID=82533251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210355801.4A Pending CN114827535A (en) | 2022-04-06 | 2022-04-06 | Network video monitoring system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827535A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117456584A (en) * | 2023-11-13 | 2024-01-26 | 江苏创斯达智能科技有限公司 | Face recognition equipment applied to intelligent safe |
-
2022
- 2022-04-06 CN CN202210355801.4A patent/CN114827535A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117456584A (en) * | 2023-11-13 | 2024-01-26 | 江苏创斯达智能科技有限公司 | Face recognition equipment applied to intelligent safe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107205137A (en) | One kind monitoring recognition methods and device | |
| CN101588443A (en) | Statistical device and detection method for television audience ratings based on human face | |
| CN106355169A (en) | Infrared living body face image acquisition device, identification device and treatment method thereof | |
| CN114996518B (en) | Ultra-high-definition video data storage and classification management system based on cloud platform | |
| CN114827535A (en) | Network video monitoring system based on face recognition | |
| CN101976356A (en) | Face identification method for surfing identification policy, and identification system thereof | |
| CN109903501A (en) | A kind of security protection probe analysis process system based on big data | |
| CN106331646A (en) | Artificial intelligence safety monitoring system | |
| CN115937943A (en) | Robot vision system based on emotion calculation | |
| CN101931789A (en) | High-resolution human figure automatic recording and comparing system and method in key region | |
| CN107749087A (en) | A kind of travel agency manages and uses staff attendance system | |
| CN103345625B (en) | A kind of three-dimensional image analysis method and system | |
| CN215642796U (en) | Intelligent detection and troubleshooting system for hidden troubles of power transmission line | |
| CN112036369A (en) | Face recognition hardware device | |
| CN110321782A (en) | A kind of system detecting characteristics of human body's signal | |
| CN112804492B (en) | Communication prompting method and device for electronic peepholes | |
| CN109214354B (en) | Dynamic face retrieval and identification method based on 3D camera | |
| CN202472689U (en) | Face posture detection system | |
| CN208938125U (en) | A kind of fire-fighting scene face identification system | |
| CN114764792A (en) | Cable flaw detection system and method based on neural network and embedded fusion | |
| CN108664861A (en) | Recognition of face mobile law enforcement logging recorder system based on distribution clouds | |
| CN202696799U (en) | High-definition monitoring system | |
| CN202907062U (en) | Intelligent image system | |
| CN113094537B (en) | Image processing system based on FPGA | |
| CN112487850A (en) | Judicial place quick roll call method based on artificial intelligence face recognition |
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 |