CN110321378A - A kind of mobile monitor image identification system and method - Google Patents
A kind of mobile monitor image identification system and method Download PDFInfo
- Publication number
- CN110321378A CN110321378A CN201910477992.XA CN201910477992A CN110321378A CN 110321378 A CN110321378 A CN 110321378A CN 201910477992 A CN201910477992 A CN 201910477992A CN 110321378 A CN110321378 A CN 110321378A
- Authority
- CN
- China
- Prior art keywords
- data
- face
- portrait
- user
- mobile monitor
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention discloses a kind of mobile monitor image identification system and method, and data acquisition layer and user carry out portrait data interaction, and data acquisition layer provides a user the interactive interface of data manipulation；Data acquisition layer is called by display interface to data operational motion and business driving.Face position by human image collecting front end and carries out ISP optimization for face in real time, portrait data are obtained using face tracking algorithm；Variation of the face from occurring to picture quality during disappearance in video is judged by space-time restriction and image quality measure algorithm, and feature extraction and comparison are carried out to human face photo；Using the deep learning algorithm model of digital nerve network, special training is carried out to portrait data by the data of actual scene, actual user.Processing capacity can linear expansion as needed, the limitation of no single-point, load balancing can be carried out between example by comparing, and improved the stability of machine utilization efficiency and system service, made full use of hardware resource.
Description
Technical field
The present embodiments relate to monitoring technology fields, and in particular to a kind of mobile monitor image identification system and method.
Background technique
Face recognition technology has been widely used in security industry at present, main to be divided into two from technological layer with form
Class, one kind are that 1:1 is compared, this form mainly with AT STATION, harbour, airport etc. the place that needs system of real name to verify, also
It is whether verifying identity document and holder are consistent；Another kind of is that 1:N is compared, and this use is mainly used for " safe city ", " snow
The projects such as bright engineering " are directly realized face snap, identification in camera shooting generator terminal or are led to using the mounting means of fixed video camera
The form for crossing transmission of video carries out recognition of face in server end.
Electronic shooting identifies translation glasses by face, Recognition Algorithm of License Plate and machine translation software directly transplanting in leg of spectacles
Circuit board systems in, circuit board systems are mounted with operating system, and various algorithms are directly run in an operating system.Meanwhile it can
It realizes realtime video transmission function, under daily patrol, bayonet monitoring or spot, traffic control isotype, can incite somebody to action
Live video is real-time transmitted to command centre, plays the function of " mobile camera ".Meanwhile face directly is realized in camera shooting generator terminal
It captures identification translation, identification or carries out recognition of face in server end by way of transmission of video.
Currently, needing processing includes the image of high flow of the people when carrying out identification monitoring using glasses acquisition video image,
Amount of redundant data is more, and there is no limit cause network transmission bandwidth, transmission time and computer disposal resource with the portrait of front-end collection
Waste.Face mobile monitor process is influenced particularly evident, face meeting overexposure when illumination is strong by 24 hours one day light
Light, when light is weak, face meeting noise is obvious.Image-capable is limited by single-point, and scalability is poor.It needs a kind of for knowing
The mobile monitor image recognition technology scheme of other glasses.
Summary of the invention
For this purpose, the embodiment of the present invention provides a kind of mobile monitor image identification system and method, it is based on distributed arithmetic body
System, processing capacity can linear expansion as needed, the limitation of no single-point, load balancing, reasonable distribution ratio can be carried out between example by comparing
To task, guarantees that the comparison task for comparing example reaches balanced, improve the stability of machine utilization efficiency and system service, sufficiently
Using hardware resource, and be conducive to system extension needs.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions: a kind of mobile monitor image recognition system
System, including data acquisition layer, Business Logic and data access layer；
The data acquisition layer is used to carry out portrait data interaction with user, and data acquisition layer includes interactive database, number
The interactive interface of data manipulation is provided a user according to acquisition layer；
The Business Logic grasps data by the display interface for externally providing display interface, data acquisition layer
Work movement is called to be driven with business；
The data access layer is used to carry out the equipment in the interactive database, unit, personnel, portrait characteristic information
Access, data access layer are provided with portrait modeling, retrieval and delete interface.
As the preferred embodiment of mobile monitor image identification system, the data acquisition layer provides a user user interface,
Data acquisition layer is generated the verifying of the data manipulation by page Core Generator, operation, movement, modification, verifies and show boundary
Face.
As the preferred embodiment of mobile monitor image identification system, portrait data are obtained using face tracking algorithm, are passed through
Space-time restriction and image quality measure algorithm judge variation of the face from occurring to picture quality during disappearance in video, to people
Face photo carries out feature extraction and comparison.
As the preferred embodiment of mobile monitor image identification system, interactive database compares standard according to portrait and shines face
The portrait of piece carries out quality evaluation, provides human face photo quality evaluation grade.
As the preferred embodiment of mobile monitor image identification system, the human face photo generates user by prompting interface and mentions
Show information and user's manual intervention entrance is provided, manual portrait positioning modeling is carried out by client.
As the preferred embodiment of mobile monitor image identification system, using the deep learning algorithm mould of digital nerve network
Type, by internet big data carry out algorithm training generate iterative algorithm, by actual scene, actual user data to portrait
Data carry out special training.
It further include human image collecting front end, before human image collecting as the preferred embodiment of mobile monitor image identification system
End position to face and carries out ISP optimization for face in real time.
The embodiment of the present invention also provides a kind of mobile monitor image-recognizing method, comprising the following steps:
Face position by human image collecting front end and carries out ISP optimization for face in real time, using face tracking
Algorithm obtains portrait data；
Judge that face is from occurring to image matter during disappearance in video by space-time restriction and image quality measure algorithm
The variation of amount carries out feature extraction and comparison to human face photo；
The human face photo generates user's prompt information by prompting interface and provides user's manual intervention entrance, passes through visitor
Family end carries out manual portrait positioning modeling；
Using the deep learning algorithm model of digital nerve network, algorithm training generation is carried out by internet big data and is changed
For algorithm, special training is carried out to portrait data by the data of actual scene, actual user.
As the preferred embodiment of mobile monitor image-recognizing method, shown according to time point, type of service condition stub and
The manual modeling of human face photo progress is inquired, evaluation is provided to the human face photo of modeling failure and improves prompt.
The embodiment of the present invention has the advantages that using the ultra-large distributed comparison technology of millions, based on distribution
Operation system, facial image processing ability can linear expansion as needed, the limitation of no single-point；Using distributed more example comparison calculations,
Load balancing can be carried out between comparison example, reasonable distribution compares task, guarantees that the comparison task for comparing example reaches balanced, raising
The stability of machine utilization efficiency and system service, to ensure uninterrupted work normally；Actual scene, actual user can be passed through
Data be targetedly trained, promote the using effect of user；Face can be completed inside human image collecting front end
Positioning, and ISP optimization is made for face in real time, guarantee that face preferentially exposes, makes front-end collection parameter most useful for face snap.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer, which is extended, obtains other implementation attached drawings.
Fig. 1 is a kind of mobile monitor image identification system schematic diagram provided in the embodiment of the present invention；
Fig. 2 is a kind of mobile monitor image-recognizing method flow chart provided in the embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Referring to Fig. 1, a kind of mobile monitor image identification system, including data acquisition layer, Business Logic and data are provided
Access layer.The data acquisition layer is used to carry out portrait data interaction with user, and data acquisition layer includes interactive database, data
Obtain the interactive interface that layer provides a user data manipulation.The Business Logic is obtained for externally providing display interface, data
Take layer data operational motion is called by the display interface and business driving.The data access layer is used for described
Equipment, unit, personnel in interactive database, portrait characteristic information access, and data access layer is provided with portrait modeling, inspection
Rope and deletion interface.
In one embodiment of mobile monitor image identification system, mobile monitor image identification system overall architecture follows number
According to obtaining layer, Business Logic and the separated three-tier architecture mode of data access layer, " high cohesion, low coupling between realization system
It closes ".The data acquisition layer provides a user user interface, and data acquisition layer generates the data behaviour by page Core Generator
Interface is verified and showed to the verifying of work, movement, modification, at operation.Data acquisition layer is mainly interacted with user, is supplied to
The interactive interface of user's operation data.Data acquisition layer is responsible for verifying, operation, movement, modification, verification, the exhibition of each interactive interface
Now etc. the code of functions is realized, can be generated by page Core Generator.Specifically, page Core Generator such as Carrd, can help
Beginner makes simple, responding fast a webpage.Such as Template Stash, gather the template of existing type webpage, it can
To generate desired theme style by keyword retrieval.
In one embodiment of mobile monitor image identification system, portrait data are obtained using face tracking algorithm, are passed through
Space-time restriction and image quality measure algorithm judge variation of the face from occurring to picture quality during disappearance in video, to people
Face photo carries out feature extraction and comparison.Face position by human image collecting front end and carries out ISP for face in real time
Optimization.The human image collecting front end such as video camera that dynamic human face identification uses has face detection module, therefore can be in video camera
The positioning of face is completed in inside, and makes ISP optimization for face in real time, guarantees that face preferentially exposes, makes camera parameters most
Conducive to face snap.
Specifically, ISP is the abbreviation of Image Signal Processor, full name is image processor.In camera imaging
Entire link in, be responsible for receive photosensitive element original signal data, very important effect is played to picture quality.ISP
Optimization includes multiple images algorithm processing module, such as detains dark current (removing the current noise that breaks off the base), and linearisation (it is non-linear to solve data
Problem), shading (solves the brightness decay of camera lens bring and color change), bad point (removing bad point data in sensor) is gone,
Denoising (removal noise), demosaic (raw data switch to RGB data), 3A (automatic white balance, auto-focusing, automatic exposure),
Gamma (brightness mapping curve optimizes part and overall contrast), rotates (angle change), sharpens (adjustment acutance), scaling
(zoom), color space conversion (are transformed into different color space into processing), color enhancing (optional, to adjust color), skin
Color enhancing (optional, the performance of the optimization colour of skin) etc..
In one embodiment of mobile monitor image identification system, interactive database compares standard according to portrait and shines face
The portrait of piece carries out quality evaluation, provides human face photo quality evaluation grade.The flow of the people that mobile monitor faces is big, redundant data
It measures more, it is therefore necessary to do certain limitation to the portrait of front-end collection, reduce the acquisition of redundant data, net is saved greatly with this
The process resource of network transmission bandwidth, transmission time and computer.The technical program face is acquired in real time using face tracking technology,
By space-time restriction and image quality measure algorithm, can in intelligent decision video face from occurring to picture quality during disappearance
Variation, automatically select and be most able to satisfy the optimal face picture of system requirements, image quality and carry out feature extraction and comparison, greatly
Improve comparison effect, saved the computing resource of server, network bandwidth and the expensive real estate for storing equipment.
Specifically, face tracking can be realized based on neural network tracking.Artificial nerve network model has human brain thinking
Characteristic feature, such as self-organizing, associative memory, non-linear, large-scale parallel connection.And there is powerful learning ability.It wants
Having to explicitly face recognition features are described it is extremely difficult, and neural network then can by study, automatically be identified
The covert expression of rule.For example, Valentin proposes a kind of method, 50 pivots of face are extracted first, then use auto-correlation
Neural network maps it in 5 dimension spaces, then is differentiated with a common multilayer perceptron.In addition, Intrator etc.
A kind of hybrid neural network is proposed to carry out face tracking, wherein non-supervisory neural network is used for feature extraction, and is supervised
Neural network is for classifying.
In one embodiment of mobile monitor image identification system, the human face photo generates user by prompting interface and mentions
Show information and user's manual intervention entrance is provided, manual portrait positioning modeling is carried out by client.During building depositary management reason,
It supports to compare standard according to portrait, quality evaluation is carried out to various photos and portrait, provides photographic quality opinion rating.It is modeling
Automatic photograph quality evaluation function is provided in the process, the quality of data of portrait is automatically judged and evaluated.It modeled
User's prompt information is generated by prompting interface in journey and user's manual intervention entrance is provided, manual portrait can be carried out in client
Positioning modeling；Have synchronous intervention and asynchronous intervention selection, can be controlled by system parameter；It can temporally items such as point, type of service
Part classification is shown and inquiry, carries out manual modeling again；Evaluation is provided to not can be carried out successfully modeled images, and improvement is provided and is mentioned
Show.
In one embodiment of mobile monitor image identification system, using the deep learning algorithm mould of digital nerve network
Type, by internet big data carry out algorithm training generate iterative algorithm, by actual scene, actual user data to portrait
Data carry out special training.An algorithm iteration monthly can be all generated, it being capable of fast lifting algorithm quality.Iterative algorithm utilizes
The computer speed of service is fast, is suitble to the characteristics of doing repetitive operation, and computer is allowed to repeat a group instruction (or certain step)
It executes, when executing this group instruction (or these steps) every time, its a new value is all released from the initial value of variable.It can pass through
Actual scene, actual user data be targetedly trained, promote the using effect of user.The embodiment of the present invention uses
Mature .NET multi-tier systematic structure, make entirely to set system and have many advantages, such as to stablize, safely, it is extendible.System is using distributed
Framework is compared, hardware resource is made full use of, and is conducive to system extension needs.
Referring to fig. 2, the embodiment of the present invention also provides a kind of mobile monitor image-recognizing method, includes the following steps, S1: logical
It crosses human image collecting front end face position and carries out ISP optimization for face in real time, people is obtained using face tracking algorithm
As data；
S2: judge that face is from occurring to image during disappearance in video by space-time restriction and image quality measure algorithm
The variation of quality carries out feature extraction and comparison to human face photo；
S3: the human face photo generates user's prompt information by prompting interface and provides user's manual intervention entrance, leads to
It crosses client and carries out manual portrait positioning modeling；
S4: using the deep learning algorithm model of digital nerve network, algorithm training life is carried out by internet big data
At iterative algorithm, special training is carried out to portrait data by the data of actual scene, actual user.
The embodiment of the present invention is based on distributed arithmetic using the ultra-large distributed comparison technology of millions of mature and reliable
System, video processing capabilities can linear expansion as needed, the limitation of no single-point.The more example comparison calculations of distribution of use, than
Between that can carry out load balancing example, reasonable distribution compares task, guarantees that the comparison task for comparing example reaches balanced, mutually
Be it is hot standby, improve the stability of machine utilization efficiency and system service to ensure round-the-clock uninterrupted normal work.Pass through interconnection
Net big data carries out algorithm training, monthly generates an algorithm iteration, being capable of fast lifting algorithm quality.And reality can be passed through
Scene, the data of actual user are targetedly trained, and promote the using effect of user.It can be completed inside video camera
The positioning of face, and ISP optimization is made for face in real time, guarantee that face preferentially exposes, makes camera parameters most useful for face
It captures.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (9)
1. a kind of mobile monitor image identification system, which is characterized in that including data acquisition layer, Business Logic and data access
Layer；
The data acquisition layer is used to carry out portrait data interaction with user, and data acquisition layer includes interactive database, and data obtain
Layer is taken to provide a user the interactive interface of data manipulation；
For the Business Logic for externally providing display interface, data acquisition layer is dynamic to data manipulation by the display interface
It is called and is driven with business；
The data access layer is for visiting the equipment in the interactive database, unit, personnel, portrait characteristic information
It asks, data access layer is provided with portrait modeling, retrieval and deletes interface.
2. a kind of mobile monitor image identification system according to claim 1, which is characterized in that the data acquisition layer to
User provides user interface, data acquisition layer generated by the page Core Generator verifying of the data manipulation, operation, movement,
Modify, verify and show interface.
3. a kind of mobile monitor image identification system according to claim 1, which is characterized in that use face tracking algorithm
Portrait data are obtained, judge to scheme during face is from occurring to disappearing in video by space-time restriction and image quality measure algorithm
The variation of image quality amount carries out feature extraction and comparison to human face photo.
4. a kind of mobile monitor image identification system according to claim 1, which is characterized in that interactive database is according to people
Quality evaluation is carried out to the portrait of human face photo as comparing standard, provides human face photo quality evaluation grade.
5. a kind of mobile monitor image identification system according to claim 3, which is characterized in that the human face photo passes through
Prompting interface generates user's prompt information and provides user's manual intervention entrance, carries out manual portrait positioning by client and builds
Mould.
6. a kind of mobile monitor image identification system according to claim 1, which is characterized in that use digital nerve network
Deep learning algorithm model, by internet big data carry out algorithm training generate iterative algorithm, pass through actual scene, reality
The data of user carry out special training to portrait data.
7. a kind of mobile monitor image identification system according to claim 1, which is characterized in that before further including human image collecting
End position to face and carries out ISP optimization for face in real time by human image collecting front end.
8. a kind of mobile monitor image-recognizing method, which comprises the following steps:
Face position by human image collecting front end and carries out ISP optimization for face in real time, using face tracking algorithm
Obtain portrait data；
Judge that face is from occurring to picture quality during disappearance in video by space-time restriction and image quality measure algorithm
Variation carries out feature extraction and comparison to human face photo；
The human face photo generates user's prompt information by prompting interface and provides user's manual intervention entrance, passes through client
Carry out manual portrait positioning modeling；
Using the deep learning algorithm model of digital nerve network, algorithm training is carried out by internet big data and generates iteration calculation
Method carries out special training to portrait data by the data of actual scene, actual user.
9. a kind of mobile monitor image-recognizing method according to claim 8, which is characterized in that according to time point, business
Type condition classification is shown and inquiry human face photo carries out manual modeling, provides evaluation and improvement to the human face photo of modeling failure
Prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477992.XA CN110321378A (en) | 2019-06-03 | 2019-06-03 | A kind of mobile monitor image identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477992.XA CN110321378A (en) | 2019-06-03 | 2019-06-03 | A kind of mobile monitor image identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321378A true CN110321378A (en) | 2019-10-11 |
Family
ID=68119366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910477992.XA Pending CN110321378A (en) | 2019-06-03 | 2019-06-03 | A kind of mobile monitor image identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321378A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131771A (en) * | 2019-12-12 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Video monitoring system |
| CN112584044A (en) * | 2020-12-07 | 2021-03-30 | 上海商米科技集团股份有限公司 | System for automatically adjusting image brightness of camera according to human face light environment |
| CN114007037A (en) * | 2021-09-18 | 2022-02-01 | 华中科技大学 | Video front-end intelligent monitoring system and method, computer equipment and terminal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140147000A1 (en) * | 2012-11-23 | 2014-05-29 | National Taiwan University | Image tracking device and image tracking method thereof |
| CN104714529A (en) * | 2015-02-16 | 2015-06-17 | 北京新能源汽车股份有限公司 | Remote monitoring platform system of electric automobile |
| CN106022233A (en) * | 2016-05-12 | 2016-10-12 | 广东履安实业有限公司 | Face capture and personnel positioning alarm camera |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN106815575A (en) * | 2017-01-22 | 2017-06-09 | 上海银晨智能识别科技有限公司 | Optimization system and method for face detection result set |
| CN107346426A (en) * | 2017-07-10 | 2017-11-14 | 深圳市海清视讯科技有限公司 | A kind of face information collection method based on video camera recognition of face |
| CN108197604A (en) * | 2018-01-31 | 2018-06-22 | 上海敏识网络科技有限公司 | Fast face positioning and tracing method based on embedded device |
| CN109508648A (en) * | 2018-10-22 | 2019-03-22 | 成都臻识科技发展有限公司 | A kind of face snap method and apparatus |
-
2019
- 2019-06-03 CN CN201910477992.XA patent/CN110321378A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140147000A1 (en) * | 2012-11-23 | 2014-05-29 | National Taiwan University | Image tracking device and image tracking method thereof |
| CN104714529A (en) * | 2015-02-16 | 2015-06-17 | 北京新能源汽车股份有限公司 | Remote monitoring platform system of electric automobile |
| CN106022233A (en) * | 2016-05-12 | 2016-10-12 | 广东履安实业有限公司 | Face capture and personnel positioning alarm camera |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN106815575A (en) * | 2017-01-22 | 2017-06-09 | 上海银晨智能识别科技有限公司 | Optimization system and method for face detection result set |
| CN107346426A (en) * | 2017-07-10 | 2017-11-14 | 深圳市海清视讯科技有限公司 | A kind of face information collection method based on video camera recognition of face |
| CN108197604A (en) * | 2018-01-31 | 2018-06-22 | 上海敏识网络科技有限公司 | Fast face positioning and tracing method based on embedded device |
| CN109508648A (en) * | 2018-10-22 | 2019-03-22 | 成都臻识科技发展有限公司 | A kind of face snap method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| J49MXBK4TGB : "货物需求及技术规格要求", 《HTTPS://WWW.DOC88.COM/P-6641181547894.HTML》 * |
| 申情: "《C语言程序设计学习与试验指导》", 31 May 2017, 哈尔滨工程大学出版社 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131771A (en) * | 2019-12-12 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Video monitoring system |
| CN111131771B (en) * | 2019-12-12 | 2021-08-13 | 中国科学院深圳先进技术研究院 | Video monitoring system |
| CN112584044A (en) * | 2020-12-07 | 2021-03-30 | 上海商米科技集团股份有限公司 | System for automatically adjusting image brightness of camera according to human face light environment |
| CN114007037A (en) * | 2021-09-18 | 2022-02-01 | 华中科技大学 | Video front-end intelligent monitoring system and method, computer equipment and terminal |
| CN114007037B (en) * | 2021-09-18 | 2023-03-07 | 华中科技大学 | Video front-end intelligent monitoring system and method, computer equipment and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898579B (en) | Image definition recognition method and device and storage medium | |
| JP3940759B2 (en) | Iris registration method, iris registration device, and iris registration program | |
| CN106778645B (en) | A kind of image processing method and device | |
| CN104091176B (en) | Portrait comparison application technology in video | |
| CN110321378A (en) | A kind of mobile monitor image identification system and method | |
| CN106161980A (en) | Photographic method and system based on dual camera | |
| CN105022999B (en) | A kind of adjoint real-time acquisition system of people's code | |
| US20230334890A1 (en) | Pedestrian re-identification method and device | |
| CN107040726B (en) | Double-camera synchronous exposure method and system | |
| Peng et al. | LVE-S2D: Low-light video enhancement from static to dynamic | |
| CN110213501A (en) | A kind of grasp shoot method, device, electronic equipment and storage medium | |
| CN104504408A (en) | Human face identification comparing method and system for realizing the method | |
| CN110414376A (en) | Update method, face recognition cameras and the server of human face recognition model | |
| CN109819176A (en) | A kind of image pickup method, system, device, electronic equipment and storage medium | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| CN106815803A (en) | The processing method and processing device of picture | |
| CN109637123A (en) | A kind of complexity traffic environment downlink people living things feature recognition and traffic control system | |
| CN114187221A (en) | Infrared and visible light image fusion method based on adaptive weight learning | |
| CN114298942A (en) | Image deblurring method and device, computer readable medium and electronic equipment | |
| CN111767826A (en) | Timing fixed-point scene abnormity detection method | |
| KR101753651B1 (en) | Photographing apparatus low energy for security and disaster monitoring and monitoring system including the same | |
| CN117152182B (en) | Ultralow-illumination network camera image processing method and device and electronic equipment | |
| CN106878625A (en) | Dual camera synchronization exposure method and system | |
| US11816181B2 (en) | Blur classification and blur map estimation | |
| US20230334774A1 (en) | Site model updating method and system |
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: 20191011 |