CN108197507A - A kind of privacy real-time protection method and system - Google Patents
A kind of privacy real-time protection method and system Download PDFInfo
- Publication number
- CN108197507A CN108197507A CN201711491152.6A CN201711491152A CN108197507A CN 108197507 A CN108197507 A CN 108197507A CN 201711491152 A CN201711491152 A CN 201711491152A CN 108197507 A CN108197507 A CN 108197507A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- monitoring range
- privacy
- real
- 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
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/82—Protecting input, output or interconnection devices
- G06F21/84—Protecting input, output or interconnection devices output devices, e.g. displays or monitors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of method and system of privacy real-time guard, the method includes:Monitoring range image W is extracted in preset monitoring range c;Preset algorithm detection motion target area image D is used in monitoring range image W;Target identification is carried out in motion target area image D, obtains target identification confidence level;The target identification confidence level of acquisition with default believability threshold is compared, when target identification confidence level is more than default believability threshold, takes preset secret protection measure.Advantageous effect of the present invention:The real-time monitoring under low computing load is realized, can rapidly protect privacy of user automatically, avoids the hysteresis quality of manual operation, in time, is effectively protected privacy of user, rate of false alarm is low.
Description
Technical field
The present invention relates to secret protection field, more particularly to a kind of privacy real-time protection method and system.
Background technology
In some electronic products in use, privacy information is often shown on the display screen of electronic product, as user is close
Code, Bank Account Number, personal mail etc..In public places or in open working environment, these information be easy to be seen by people and
It causes privacy leakage or even can be utilized by malicious person to do illegal purposes.
To avoid privacy leakage, user need to shield or hide important privacy information manually, and service speed is slow, and operation is completed
Preceding privacy is still easily divulged a secret, and many puzzlements are brought to user.
The prior art is usually used machine vision technique and uses imaging sensor (being commonly called as camera) acquisition display screen week
It is specific to enclose image, automatic identification face (CN201610875768, CN200810064371), eye (CN201310313489) etc.
Target judges whether there is other people and is in the visual range of display screen, so as to the privacy on protection display screen that takes measures.
However when target is the larger personal side or the back side of deviation display screen angle, often also need to be aided with half body inspection
Go out with systemic targets detection etc. multiple detection algorithms, come avoid omit detection target.And carrying out face, half body, whole body mesh
During mark detection, it is difficult to distinguish the portrait in true portrait and drawing, sculpture, it is also necessary to be aided with moving target detection algorithm to sentence
It is disconnected whether true target, otherwise can generate flase drop.
But in order to preferably protect privacy, generally require quickly to start secret protection within the time less than 0.1 second and arrange
It applies, and larger system resource can be occupied by running multiple detection algorithms so that system response time is slack-off, is not only difficult to avoid that hidden
Private leakage, and other system applications can be influenced.
Invention content
The present invention proposes a kind of privacy real-time protection method and system, and algorithm is detected using the moving target of speed,
Motion target area is extracted in the background, shields the pseudo- target such as static picture, sculpture, then in motion target area,
Detection improves operational efficiency, improves the applicability of this system, solve the prior art with the presence or absence of face, half body target
In it is above-mentioned the problem of.
The technical proposal of the invention is realized in this way:
A kind of privacy real-time protection method applied to privacy real-time guard system, includes the following steps:
Monitoring range image W is extracted in preset monitoring range c;
Preset algorithm detection motion target area image D is used in monitoring range image W;
Target identification is carried out in motion target area image D, obtains target identification confidence level;
The target identification confidence level of acquisition is compared with default believability threshold, when target identification confidence level is more than in advance
If during believability threshold, take preset secret protection measure.
Further, privacy real-time protection method of the present invention, it is described that monitoring is extracted in preset monitoring range c
The step of range image W, includes:
Monitoring range c, monitoring range c is set to exclude the region including user itself;
Picture frame M is obtained under preset monitoring frequency;
Monitoring range image W is extracted in picture frame M according to monitoring range c.
Further, privacy real-time protection method of the present invention, it is described in monitoring range image W using preset
The step of algorithm detection motion target area image D, includes:
Background model Md is established using gauss hybrid models GMM algorithms;
Background model Md and monitoring range image W is compared, when gap is smaller, GMM is added in monitoring range image W and calculates
Method update background model Md;When gap is larger, the error image Δ between monitoring range image W and background model Md is calculated:
Undersized difference region in error image Δ is filtered out using morphological erosion operation;
Rectangle is merged into the difference region of integrated distribution in error image Δ;
According to moving target filter condition y, exclude not meeting the rectangle of moving target filter condition y;
According to rectangle position, motion target area image D is intercepted in monitoring range image W.
Further, privacy real-time protection method of the present invention, the moving target filter condition y include movement mesh
Mark size bound, Aspect Ratio and the area bound of area image D.
Further, privacy real-time protection method of the present invention, it is described to carry out mesh in motion target area image D
The step of mark is other, acquisition target identification confidence level includes:
Using human face target detection algorithm detection human face target in motion target area image D, obtain human face target and know
Other confidence level Kr;
When not detecting human face target, user's upper part of the body target detection algorithm detection people's upper part of the body target obtains people's upper half
Body target identification confidence level Kb.
Preferably, privacy real-time protection method of the present invention, the human face target detection algorithm, which specifically uses, to be based on
Motion target area image D is identified in the Adaboost graders of Haar characteristics of image, and output human face target identification is credible
Spend Kr, target location and size.
Preferably, privacy real-time protection method of the present invention, people's upper part of the body target detection algorithm specifically use
Histograms of oriented gradients HOG algorithms are extracted characteristics of image, are identified using SVM classifier, export upper part of the body recognition credibility
Kb。
A kind of privacy real-time guard system, using above-mentioned privacy real-time protection method, including:
Monitoring algorithm module, for obtaining target identification confidence level in preset monitoring range c;
Secret protection module for the target identification confidence level of acquisition to be compared with default believability threshold, works as mesh
When marking recognition credibility more than default believability threshold, preset secret protection measure is taken, is connect with monitoring algorithm module.
Further, privacy real-time guard system of the present invention, further includes:
User's setting module for setting monitoring range c and functional parameter, is connect with monitoring algorithm module.
Further, privacy real-time guard system of the present invention, further includes:
Monitoring modular for obtaining picture frame M under preset monitoring frequency, is connect with monitoring algorithm module.
Beneficial effects of the present invention are:
Privacy real-time protection method and system of the present invention, realize the real-time monitoring under low computing load, can be with
Automatically privacy of user is rapidly protected, avoids the hysteresis quality of manual operation, in time, be effectively protected privacy of user, accurately
Property it is high, rate of false alarm is low.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of main process figure of privacy real-time protection method one embodiment of the present invention;
Fig. 2 is the detail flowchart of a kind of privacy real-time protection method of the present invention and system one embodiment.
Symbol description in figure:
M:Video frame;
W:Monitoring range image;
D:Motion target area image;
v:Monitoring frequency;
c:Monitoring range;
y:Moving target filter condition;
r:Face detects threshold value;
b:People detects threshold values above the waist;
Fy:Moving target detects algorithm;
Fr:Human face target detects algorithm;
Fb:People's upper part of the body target detects algorithm;
Kr:Human face target confidence level;
Kb:People's upper part of the body target confidence level;
Y:Logical truth;
N:Logical falsehood.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
In order to which technical scheme of the present invention is enable more clearly to show, the present invention is made below in conjunction with the accompanying drawings further
Explanation.
As shown in Figs. 1-2, a kind of privacy real-time protection method and system of the present invention, include the following steps and mould
Block:
Privacy real-time guard system of the present invention includes user setting module S1, monitoring modular S2, monitoring algorithm mould
Block S3 and secret protection module S4.
S1:User setting module S1 is an interface program, for pre-setting monitoring frequency v, monitoring range c, movement
Goal filtering condition y, human face target detection threshold value r and people's upper part of the body target detection threshold values b.
Certainly, monitoring range c can be by user's voluntarily manual setting;Or monitoring range c can also be by computer program
Middle default setting, so as to which user can directly use the monitoring range c of computer program default setting, the specific steps are:
Exclude user's self zone when user starts for the first time manually in image entirety A, remaining area is monitoring range c;
Picture frame M is obtained under pre-set monitoring frequency v (5~30Hz);
Monitoring range image W is extracted in picture frame M according to monitoring range c;
User's own range image V is extracted in picture frame M according to user's self zone;
Using MeanShift algorithm keeps track targets in user's own range image V, correct user's self zone and
Remaining area, that is, monitoring range c.
S2:Monitoring modular S2 by monitoring device SPY, obtains display with pre-set monitoring frequency v (5~30Hz)
Shield the picture frame M in SCR scope of sight.
S3:Monitoring algorithm module S3 is by judging in preset monitoring range c with the presence or absence of motion target area, extraction
Motion target area image D obtains the target identifications confidence level such as face or people's upper part of the body in motion target area image D, from
And the danger of privacy leakage is judged whether there is, then decide whether to take secret protection measure.
Wherein, the process of target identification confidence level acquisition is:Monitoring algorithm module S3 is by judging in preset monitoring model
Enclose in c with the presence or absence of motion target area, extract motion target area image D, to the face in motion target area image D or
The targets such as people's upper part of the body carry out feature extraction, obtain characteristic information, then characteristic information is identified, and obtain identification information,
Identification information includes target classification, target identification confidence level and target position in the picture, size and Orientation.
Monitoring algorithm module S3 includes monitoring range image submodule S31, motion target area submodule S32, face mesh
Mark detection submodule S33 and people's upper part of the body target detection submodule S34, specific method are:
S31:Monitoring range image submodule S31 according to pre-set preset monitoring range c, is carried in picture frame M
Take monitoring range image W;
By setting preset monitoring range c, the region without detection can be excluded (including the area where validated user User
Domain), so as to alleviate system burden, be conducive to the quick response of system.
S32:Motion target area submodule S32 is detected using moving target detection algorithm Fy in monitoring range image W
Whether the motion target area image D that meets moving target filter condition y is had;
Motion target area image D is rectangle, and size, Aspect Ratio and area bound meet moving target filtering rod
Part y;
If not meeting the motion target area image D of moving target filter condition y, execution monitoring modular is returned
S2 continues to obtain the picture frame M in display screen SCR scope of sight;
If there is meeting the motion target area image D of moving target filter condition y, then human face target detection submodule is performed
Whether there is human face target R in block S33, detection motion target area image D;
Moving target detection algorithm Fy establishes the back of the body using gauss hybrid models (Gaussian Mixture Model, GMM)
Scape model M d is compared with monitoring range image W.When gap is smaller, GMM algorithms update background is added in monitoring range image W
Model M d;When gap is larger, the error image Δ between monitoring range image W and background model Md is calculated;
It is filtered out in error image Δ using morphological erosion operation (Mathematical Morphology Operator)
Undersized difference region;The difference region for merging the integrated distribution in error image Δ is rectangle;According to moving target mistake
Filter condition y excludes not meeting the rectangle of the condition;According to rectangle position, moving target is intercepted in monitoring range image W
Area image D.
Moving target detection algorithm takes small with EMS memory occupation, and it is follow-up that static monitoring range image W has been blocked to enter
Operation greatly reduces system load, while eliminates the pseudo- target such as picture in indoor environment, sculpture, improves accuracy rate.
S33:Human face target detects submodule S33, and motion target area figure is calculated using human face target detection algorithm Fr
As the human face target confidence level Kr of D, then compare the size of human face target confidence level Kr and face detection threshold value r, need to illustrate
, what is carried out at this time is face detection:It is found out in various images with the presence or absence of human face target image rather than face alignment:
It is compared to determine similarity degree between facial image;
Human face target detection algorithm Fr is used to detect front or the smaller side face target R of angle.Using based on Harr
Motion target area image D is identified in the Adaboost graders of feature, human face target confidence level Kr is calculated, so as to sentence
It is disconnected with the presence or absence of human face target R, the calculating speed of the Adaboost graders based on Harr features than very fast, recognition accuracy compared with
It is high.It is of course also possible to use depth convolutional neural networks
(CNN), Recognition with Recurrent Neural Network (RNN) or deep neural network (DNN) substitute the Adaboost based on Harr features
Motion target area image D is identified in grader, calculates human face target confidence level Kr;
When human face target confidence level Kr is less than or equal to face detection threshold value r, illustrate do not have in motion target area image D
There is human face target R, then executor's upper part of the body target detection submodule S34, whether there is people in detection motion target area image D
Upper part of the body target B;
When human face target confidence level Kr is more than face detection threshold value r, illustrate there is face mesh in motion target area image D
R is marked, then performs secret protection module S4, takes secret protection measure;
S34:People's upper part of the body target detects submodule S34, and user's upper part of the body target detection algorithm Fb calculates movement mesh
The people upper part of the body target confidence level Kb of area image D is marked, then compares people's upper part of the body target confidence level Kb and people detects above the waist
The size of threshold values b;
People's upper part of the body target detection algorithm Fb uses histograms of oriented gradients (Histogram of Oriented
Gradient, HOG) algorithm, it detects in motion target area image D with the presence or absence of people upper part of the body target B, histograms of oriented gradients
For the calculating speed of (Histogram of Oriented Gradient, HOG) algorithm than very fast, recognition accuracy is higher.Certainly,
Depth convolutional neural networks (CNN), Recognition with Recurrent Neural Network (RNN) or deep neural network (DNN) alternative orientation can also be used
Histogram of gradients (Histogram of Oriented Gradient, HOG) algorithm, detecting in motion target area image D is
It is no that there are people's upper part of the body target B;
When people's upper part of the body target confidence level Kb is less than or equal to people detection threshold values b above the waist, illustrate motion target area
There is no people upper part of the body target B in image D, then return and perform monitoring modular S2, continue to obtain in display screen SCR scope of sight
Picture frame M;
When people's upper part of the body target confidence level Kb is more than people detection threshold values b above the waist, illustrate in motion target area image D
There are people upper part of the body target B, then perform secret protection module S4, take secret protection measure.
S4:Secret protection module S4 is used for taking preset secret protection measure H.Secret protection measure H can be pop-up
Warning window blocks the privacy information on screen or starts screen protection program or start screen locking program etc..
In addition, privacy real-time guard system of the present invention, further includes false triggering module S35, for using process
In, when validated user User itself is moved in the preset monitoring range c set, secret protection measure false triggering is caused to show
As.False triggering module S35 can update preset monitoring range c according to the region where validated user User.
Intimacy protection system of the present invention realizes the real-time monitoring under low computing load, can automatically rapidly
Privacy of user is protected, avoids the hysteresis quality of manual operation, in time, is effectively protected privacy of user, accuracy is high, rate of false alarm
It is low.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
With within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention god.
Claims (10)
1. a kind of privacy real-time protection method, which is characterized in that include the following steps:
Monitoring range image W is extracted in preset monitoring range c;
Preset algorithm detection motion target area image D is used in monitoring range image W;
Target identification is carried out in motion target area image D, obtains target identification confidence level;
The target identification confidence level of acquisition is compared with default believability threshold, when target identification confidence level be more than it is default can
During confidence threshold, preset secret protection measure is taken.
2. privacy real-time protection method according to claim 1, which is characterized in that described in preset monitoring range c
The step of extracting monitoring range image W includes:
Monitoring range c, monitoring range c is set to exclude the region including user itself;
Picture frame M is obtained under preset monitoring frequency;
Monitoring range image W is extracted in picture frame M according to monitoring range c.
3. privacy real-time protection method according to claim 1, which is characterized in that described to make in monitoring range image W
The step of detecting motion target area image D with preset algorithm includes:
Background model Md is established using gauss hybrid models GMM algorithms;
Background model Md and monitoring range image W is compared, when gap is smaller, GMM algorithms are added in more with monitoring range image W
New background model Md;When gap is larger, the error image Δ between monitoring range image W and background model Md is calculated:
Undersized difference region in error image Δ is filtered out using morphological erosion operation;
Rectangle is merged into the difference region of integrated distribution in error image Δ;
According to moving target filter condition y, exclude not meeting the rectangle of moving target filter condition y;
According to rectangle position, motion target area image D is intercepted in monitoring range image W.
4. privacy real-time protection method according to claim 3, which is characterized in that the moving target filter condition y packets
Include size bound, Aspect Ratio and the area bound of motion target area image D.
5. privacy real-time protection method according to claim 1, which is characterized in that described in motion target area image D
The step of middle carry out target identification, acquisition target identification confidence level, includes:
Using human face target detection algorithm detection human face target in motion target area image D, obtaining human face target identification can
Reliability Kr;
When not detecting human face target, user's upper part of the body target detection algorithm detection people's upper part of the body target obtains people's upper part of the body mesh
Mark recognition credibility Kb.
6. privacy real-time protection method according to claim 5, which is characterized in that the human face target detection algorithm is specific
Motion target area image D is identified using based on the Adaboost graders of Haar characteristics of image, exports human face target
Recognition credibility Kr, target location and size.
7. privacy real-time protection method according to claim 5, which is characterized in that people's upper part of the body target detects algorithm
Characteristics of image is specifically extracted using histograms of oriented gradients HOG algorithms, is identified using SVM classifier, output is known above the waist
Other confidence level Kb.
8. a kind of privacy real-time guard system, which is characterized in that including:
Monitoring algorithm module, for obtaining target identification confidence level in preset monitoring range c;
Secret protection module, for the target identification confidence level of acquisition to be compared with default believability threshold, when target is known
Other confidence level is taken preset secret protection measure, is connect with monitoring algorithm module when default believability threshold.
9. privacy real-time guard system according to claim 8, which is characterized in that further include:
User's setting module for setting monitoring range c and functional parameter, is connect with monitoring algorithm module.
10. privacy real-time guard system according to claim 9, which is characterized in that further include:
Monitoring modular for obtaining picture frame M under preset monitoring frequency, is connect with monitoring algorithm module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711491152.6A CN108197507A (en) | 2017-12-30 | 2017-12-30 | A kind of privacy real-time protection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711491152.6A CN108197507A (en) | 2017-12-30 | 2017-12-30 | A kind of privacy real-time protection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108197507A true CN108197507A (en) | 2018-06-22 |
Family
ID=62587286
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711491152.6A Pending CN108197507A (en) | 2017-12-30 | 2017-12-30 | A kind of privacy real-time protection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108197507A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022105541A1 (en) * | 2020-11-19 | 2022-05-27 | 腾讯科技(深圳)有限公司 | Picture encryption method and apparatus, computer device, storage medium, and program product |
Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070126868A1 (en) * | 2005-12-06 | 2007-06-07 | Hitachi Kokusai Electric Inc. | Image processing apparatus, image processing system, and recording medium for programs therefor |
CN101409004A (en) * | 2008-11-24 | 2009-04-15 | 浙江大学 | Safety defense monitoring method based on Symbian intelligent mobile phone platform |
CN101576943A (en) * | 2008-05-06 | 2009-11-11 | 英业达股份有限公司 | Peeping-preventing electronic device and peeping-preventing method |
CN101625716A (en) * | 2008-07-09 | 2010-01-13 | 联想(北京)有限公司 | Method for preventing peep on computer and computer with method |
CN101739551A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for identifying moving objects |
CN101854516A (en) * | 2009-04-02 | 2010-10-06 | 北京中星微电子有限公司 | Video monitoring system, video monitoring server and video monitoring method |
CN102360423A (en) * | 2011-10-19 | 2012-02-22 | 丁泉龙 | Intelligent human body tracking method |
CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
CN103020986A (en) * | 2012-11-26 | 2013-04-03 | 哈尔滨工程大学 | Method for tracking moving object |
CN103049704A (en) * | 2012-12-07 | 2013-04-17 | 哈尔滨工业大学深圳研究生院 | Self-adaptive privacy protection method and device for mobile terminal |
CN103218579A (en) * | 2013-03-28 | 2013-07-24 | 东莞宇龙通信科技有限公司 | Method for preventing content on screen from being peeped, and mobile terminal thereof |
CN103324899A (en) * | 2012-03-23 | 2013-09-25 | 富泰华工业(深圳)有限公司 | Electronic equipment and display screen peeping-prevention method thereof |
CN103402006A (en) * | 2013-07-24 | 2013-11-20 | 江苏晓山信息产业股份有限公司 | Time control-based human eye detection personal screen anti-peep system and method |
CN103425915A (en) * | 2012-05-25 | 2013-12-04 | 汉王科技股份有限公司 | Method and device for identifying whether unauthorized users read display content of electronic device or not and electronic device |
CN103955650A (en) * | 2014-05-04 | 2014-07-30 | 合肥联宝信息技术有限公司 | Method and device for preventing peeping through regulating screen luminance |
CN104219488A (en) * | 2013-05-31 | 2014-12-17 | 索尼公司 | Method and device of generating target image as well as video monitoring system |
CN104318578A (en) * | 2014-11-12 | 2015-01-28 | 苏州科达科技股份有限公司 | Video image analyzing method and system |
CN104616006A (en) * | 2015-03-11 | 2015-05-13 | 湖南智慧平安科技有限公司 | Surveillance video oriented bearded face detection method |
CN106096523A (en) * | 2016-06-02 | 2016-11-09 | 王玉德 | The detection of a kind of Moving Object in Video Sequences and Deviant Behavior parser |
CN106557711A (en) * | 2016-11-04 | 2017-04-05 | 深圳大学 | The screen privacy guard method of mobile terminal device and system |
CN106650367A (en) * | 2016-09-30 | 2017-05-10 | 维沃移动通信有限公司 | Private content display method and mobile terminal |
CN106886216A (en) * | 2017-01-16 | 2017-06-23 | 深圳前海勇艺达机器人有限公司 | Robot automatic tracking method and system based on RGBD Face datections |
CN107066968A (en) * | 2017-04-12 | 2017-08-18 | 湖南源信光电科技股份有限公司 | The vehicle-mounted pedestrian detection method of convergence strategy based on target recognition and tracking |
CN107194288A (en) * | 2017-04-25 | 2017-09-22 | 上海与德科技有限公司 | The control method and terminal of display screen |
CN107273822A (en) * | 2017-05-26 | 2017-10-20 | 西安电子科技大学 | A kind of method for secret protection based on monitor video multiple target tracking and recognition of face |
-
2017
- 2017-12-30 CN CN201711491152.6A patent/CN108197507A/en active Pending
Patent Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070126868A1 (en) * | 2005-12-06 | 2007-06-07 | Hitachi Kokusai Electric Inc. | Image processing apparatus, image processing system, and recording medium for programs therefor |
CN101576943A (en) * | 2008-05-06 | 2009-11-11 | 英业达股份有限公司 | Peeping-preventing electronic device and peeping-preventing method |
CN101625716A (en) * | 2008-07-09 | 2010-01-13 | 联想(北京)有限公司 | Method for preventing peep on computer and computer with method |
CN101409004A (en) * | 2008-11-24 | 2009-04-15 | 浙江大学 | Safety defense monitoring method based on Symbian intelligent mobile phone platform |
CN101739551A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for identifying moving objects |
CN101854516A (en) * | 2009-04-02 | 2010-10-06 | 北京中星微电子有限公司 | Video monitoring system, video monitoring server and video monitoring method |
CN102360423A (en) * | 2011-10-19 | 2012-02-22 | 丁泉龙 | Intelligent human body tracking method |
CN103324899A (en) * | 2012-03-23 | 2013-09-25 | 富泰华工业(深圳)有限公司 | Electronic equipment and display screen peeping-prevention method thereof |
CN103425915A (en) * | 2012-05-25 | 2013-12-04 | 汉王科技股份有限公司 | Method and device for identifying whether unauthorized users read display content of electronic device or not and electronic device |
CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
CN103020986A (en) * | 2012-11-26 | 2013-04-03 | 哈尔滨工程大学 | Method for tracking moving object |
CN103049704A (en) * | 2012-12-07 | 2013-04-17 | 哈尔滨工业大学深圳研究生院 | Self-adaptive privacy protection method and device for mobile terminal |
CN103218579A (en) * | 2013-03-28 | 2013-07-24 | 东莞宇龙通信科技有限公司 | Method for preventing content on screen from being peeped, and mobile terminal thereof |
CN104219488A (en) * | 2013-05-31 | 2014-12-17 | 索尼公司 | Method and device of generating target image as well as video monitoring system |
CN103402006A (en) * | 2013-07-24 | 2013-11-20 | 江苏晓山信息产业股份有限公司 | Time control-based human eye detection personal screen anti-peep system and method |
CN103955650A (en) * | 2014-05-04 | 2014-07-30 | 合肥联宝信息技术有限公司 | Method and device for preventing peeping through regulating screen luminance |
CN104318578A (en) * | 2014-11-12 | 2015-01-28 | 苏州科达科技股份有限公司 | Video image analyzing method and system |
CN104616006A (en) * | 2015-03-11 | 2015-05-13 | 湖南智慧平安科技有限公司 | Surveillance video oriented bearded face detection method |
CN106096523A (en) * | 2016-06-02 | 2016-11-09 | 王玉德 | The detection of a kind of Moving Object in Video Sequences and Deviant Behavior parser |
CN106650367A (en) * | 2016-09-30 | 2017-05-10 | 维沃移动通信有限公司 | Private content display method and mobile terminal |
CN106557711A (en) * | 2016-11-04 | 2017-04-05 | 深圳大学 | The screen privacy guard method of mobile terminal device and system |
CN106886216A (en) * | 2017-01-16 | 2017-06-23 | 深圳前海勇艺达机器人有限公司 | Robot automatic tracking method and system based on RGBD Face datections |
CN107066968A (en) * | 2017-04-12 | 2017-08-18 | 湖南源信光电科技股份有限公司 | The vehicle-mounted pedestrian detection method of convergence strategy based on target recognition and tracking |
CN107194288A (en) * | 2017-04-25 | 2017-09-22 | 上海与德科技有限公司 | The control method and terminal of display screen |
CN107273822A (en) * | 2017-05-26 | 2017-10-20 | 西安电子科技大学 | A kind of method for secret protection based on monitor video multiple target tracking and recognition of face |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022105541A1 (en) * | 2020-11-19 | 2022-05-27 | 腾讯科技(深圳)有限公司 | Picture encryption method and apparatus, computer device, storage medium, and program product |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6863408B2 (en) | Information processing equipment, information processing methods and programs | |
KR101159164B1 (en) | Fake video detecting apparatus and method | |
WO2020215552A1 (en) | Multi-target tracking method, apparatus, computer device, and storage medium | |
CN106056079B (en) | A kind of occlusion detection method of image capture device and human face five-sense-organ | |
US10691947B2 (en) | Monitoring device | |
KR101735365B1 (en) | The robust object tracking method for environment change and detecting an object of interest in images based on learning | |
CN110648352B (en) | Abnormal event detection method and device and electronic equipment | |
KR101709751B1 (en) | An automatic monitoring system for dangerous situation of persons in the sea | |
CN111898486B (en) | Monitoring picture abnormality detection method, device and storage medium | |
Chansri et al. | Hand gesture recognition for Thai sign language in complex background using fusion of depth and color video | |
WO2018078857A1 (en) | Line-of-sight estimation device, line-of-sight estimation method, and program recording medium | |
Cheong et al. | A novel face detection algorithm using thermal imaging | |
KR101737430B1 (en) | A method of detecting objects in the image with moving background | |
CN104680145B (en) | The on off state change detecting method and device of a kind of | |
WO2020195732A1 (en) | Image processing device, image processing method, and recording medium in which program is stored | |
He et al. | A new segmentation approach for iris recognition based on hand-held capture device | |
Cai et al. | Intelligent video analysis-based forest fires smoke detection algorithms | |
CN108446690A (en) | A kind of human face in-vivo detection method based on various visual angles behavioral characteristics | |
CN107293002A (en) | A kind of intelligent access control system based on recognition of face | |
JP2020518879A (en) | Detection system, detection device and method thereof | |
KR20140029069A (en) | Method and apparatus for monitoring objects from video | |
JP6283008B2 (en) | Tracking device | |
CN103049748B (en) | Behavior monitoring method and device | |
US20140086448A1 (en) | Appearance Model Based Automatic Detection in Sensor Images | |
CN108197507A (en) | A kind of privacy real-time protection 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: 20180622 |