CN106156729A - A kind of agricultural greenhouse warning system based on IB Adaboost Face datection and method - Google Patents
A kind of agricultural greenhouse warning system based on IB Adaboost Face datection and method Download PDFInfo
- Publication number
- CN106156729A CN106156729A CN201610494268.4A CN201610494268A CN106156729A CN 106156729 A CN106156729 A CN 106156729A CN 201610494268 A CN201610494268 A CN 201610494268A CN 106156729 A CN106156729 A CN 106156729A
- Authority
- CN
- China
- Prior art keywords
- image
- video image
- adaboost
- face datection
- face
- 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
- 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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of agricultural greenhouse warning system based on IB Adaboost Face datection, comprising: identification module, for obtaining the video image at scene;Image capture module, is connected with described identification module, is used for gathering described video image, and digitizes described video image;Flush bonding processor, is connected with described image capture module, for receiving the video image after digitlization, and is analyzed video image by embedded IB Adaboost Face datection algorithm and processes;And mobile terminal, it is used for reception processing result.The invention still further relates to the using method of said system.The present invention can efficiently reduce the stolen situation of booth and occur.
Description
Technical field
The present invention relates to agricultural greenhouse security technology area, particularly relate to a kind of based on IB-Adaboost Face datection
Agricultural greenhouse warning system and method.
Background technology
With the large-scale application of Polyhouse technology, because the stolen event times of booth remains high, the damage brought to orchard worker
Lose increasing.In order to reduce the stolen order of severity of booth and the supervision to thief for the raising, increasing advanced technology
It is applied to agricultural greenhouse security control field.In the stolen event of booth, the main colony that is injured is that arduous plantation is but without receiving
Those the orchard worker householders becoming.Therefore, thief-proof for agricultural greenhouse, if can do sth. in advance to farmer before the stolen event of vegetables and fruits occurs
Notifying orchard worker and recording thief's information, not only vegetables and fruits can avoid being stolen, and also can obtain the identity of thief in time, and by it
Restrain by law.Suspect or unobstructed or wear when checking crime video recording after generally there occurs crime case
Shelter, unscreened in the case of detect face information by identification;Can bring to clear up a criminal case in the case of blocking
Certain difficulty.So, block or the unobstructed warning system that can develop the automatic identification to suspicious figure for no matter having
System has important using value and is widely applied prospect.
Content of the invention
The technical problem to be solved is to provide a kind of agricultural greenhouse report based on IB-Adaboost Face datection
Alarm system and method, can efficiently reduce the stolen situation of booth and occur.
The technical solution adopted for the present invention to solve the technical problems is: provide a kind of based on the inspection of IB-Adaboost face
The agricultural greenhouse warning system surveyed, comprising: identification module, for obtaining the video image at scene;Image capture module, and described
Identification module be connected, be used for gathering described video image, and described video image digitized;Flush bonding processor, with institute
The image capture module stated is connected, and is used for the video image after receiving digitlization, and by embedded IB-Adaboost face inspection
Video image is analyzed and processes by method of determining and calculating;And mobile terminal, it is used for reception processing result.
First to image during the embedded IB-Adaboost Face datection algorithm process video image of described flush bonding processor
Carry out illumination compensation process, improve the even impact on picture quality of uneven illumination;Improve face classification in conjunction with Adaboost algorithm
Performance;Then pass through YCbCr color space conversion binary image, attempt reducing Face datection region to reduce missing inspection;So
After carry out area of skin color feature extraction, to reach improve Face datection effect, improve system real-time face detection property
Energy.
Described identification module is ccd video camera.
Described image capture module is image pick-up card.
The described agricultural greenhouse warning system based on IB-Adaboost Face datection also includes being connected with flush bonding processor
Memory cell, described memory cell is for storing suspicious video image.
Result is sent to described mobile terminal by GPRS cat by described flush bonding processor.
The technical solution adopted for the present invention to solve the technical problems is: also provide one to use above-mentioned based on IB-
The method of the agricultural greenhouse warning system of Adaboost Face datection, including system initialization, obtains on-the-spot video image;Right
Video image is acquired, and will gather after video image be digitized process;IB-Adaboost Face datection is used to calculate
Video image after digitized processing is processed and analyzes by method, it may be judged whether have suspicious figure to occur, wherein, system is initial
Change includes whether working identification module, the resolution ratio of the collection image of identification module, the OpenCV vision loading oneself training
Training storehouse, loading eye detection grader, nose detection grader, mouth detection grader;Described flush bonding processor passes through interior
Video image is analyzed by embedding IB-Adaboost algorithm and process specifically includes following steps:
Use " reference white " standardization color appearance: using the value of 5% before pixel intensity in image as reference white;
First use Haar-like character representation face, use " integrogram " to realize the quick calculating of character numerical value;Use
Adaboost algorithm picks out some rectangular characteristic that can represent face as Weak Classifier, will according to the mode of Nearest Neighbor with Weighted Voting
Weak Classifier is configured to a strong classifier;The some strong classifiers obtaining training are composed in series the stacking of a cascade structure
Grader;
Carry out the conversion of YCbCr color space to image, thus realize improving the function of energy resolution;
Utilize morphological method to carry out binaryzation process to band detection image, reject non-face region;
Detect that human face region carries out identification to human face region, it may be judged whether can recognize that whom the other side's identity is, as
Fruit inspection does not measures, and sends information to greenhouse gardening personnel.
Described method also comprises determining whether the step blocking the suspicious figure of face, if be detected that there is screening in face
Gear, then point out removing to block, if not according to prompting operation, then sending information to greenhouse gardening personnel.
Beneficial effect
Owing to have employed above-mentioned technical scheme, the present invention compared with prior art, has the following advantages that and actively imitates
Really:
The present invention can help greenhouse gardening householder to have full understanding to stealing, to ensure that householder can be as early as possible effectively
To whether there being generation stealing situation to make correct reflection, thus reduce the generation stealing this criminal offence.The present invention is by knowing
Other module, image capture module, flush bonding processor, mobile terminal and GPRS cat carry out agricultural greenhouse security control warning.
The present invention can to suspicious figure stealing detect in real time, have low cost, high safety, with intelligence, report
Police is timely, be easy to the features such as universal maintenance expense is low, can be used for all agricultural greenhouses, strengthens the security of agricultural greenhouse, reduces
Agricultural greenhouse stolen crime rate.
Brief description
Fig. 1 is the system block diagram of the present invention;
Fig. 2 is the IB-Adaboost algorithm flow chart of the present invention;
Fig. 3 is Adaboost algorithm flow chart.
Detailed description of the invention
Below in conjunction with specific embodiment, the present invention is expanded on further.Should be understood that these embodiments are merely to illustrate the present invention
Rather than restriction the scope of the present invention.In addition, it is to be understood that after having read the content that the present invention lectures, people in the art
The present invention can be made various changes or modifications by member, and these equivalent form of values fall within the application appended claims equally and limited
Scope.
As it is shown in figure 1, a kind of agricultural greenhouse based on improved Adaboost Face datection that the present invention provides is controlled safely
Warning system processed, including identification module, it is for obtaining the video image at scene;Image capture module, with described identification mould
Block is connected, and is used for gathering described video image, and digitizes described video image;Flush bonding processor, with described image
Acquisition module is connected, and is used for the video image after receiving digitlization, and by embedded improved IB-Adaboost Face datection
Video image is analyzed and processes by algorithm;And mobile terminal, it is used for reception processing result.This system is sentenced by reporting to the police in advance
Disconnected, decrease the possibility that crime one's share of expenses for a joint undertaking is speculated, improve the security of agricultural greenhouse, meanwhile, to the detection work stealing crime
Make there has been very big help.
Described identification module is ccd video camera.Described image capture module is image pick-up card.Described based on IB-
The agricultural greenhouse warning system of Adaboost Face datection also includes the memory cell being connected with flush bonding processor, described storage
Unit is for storing suspicious video image.Result is sent to described movement by GPRS cat by described flush bonding processor
Terminal.
Picture recognition module uses ccd video camera, obtains on-the-spot video image by ccd video camera, can enter scene
Row monitoring simultaneously determines whether can occur with target.Image is acquired, utilizes video capture device that identification module is transmitted
The analog signal coming over catches and is digitized.The image collecting needs to carry out gray processing, the purpose of gray processing
It is to speed up detecting speed, it is ensured that reach real-time purpose.
As can be seen here, the present invention can help greenhouse gardening householder to have full understanding to stealing effectively, to ensure
Householder as early as possible to whether there being generation stealing situation to make correct reflection, thus can reduce the generation stealing this criminal offence.This
Invention carries out agricultural greenhouse safety by identification module, image capture module, flush bonding processor, mobile terminal and GPRS cat
Control is reported to the police.
System initialization, obtains on-the-spot video image;Video image is acquired, and will gather after video image
It is digitized processing;IB-Adaboost Face datection algorithm is used to carry out processing and dividing to digitized processing rear video image
Analysis, and determine whether to block the suspicious figure of face;If be detected that face, then mate with stored face,
If identifying unsuccessful, then send information to plant householder;If be detected that face blocks, prompting removing is blocked, if not
According to prompting operation, then send information to plant householder.
Transmitted information is multimedia message, with the photo of the suspicious figure gathering in multimedia message.Wherein, when identification module can not
When correctly carrying out template matches or detected that suspicious figure does not removes shelter, start multimedia-message-alarming system.This system
Major function for being sent to the mobile terminal of relevant staff by alarm picture information by GPRS cat.
In conjunction with Fig. 2, this algorithm is suitably modified based on traditional Adaboost algorithm, proposes a kind of improved
IB-Adaboost (Illumination compensation and Binarization) method for detecting human face.The method is first
First pretreatment is compensated to image irradiation, improve image irradiation quality;Secondly, face grader is trained based on Adaboost algorithm;
Then carry out the conversion of YCbCr color space binary conversion treatment to image, reduce face region of search;Again through R, G, B color
The coloured image that superposition obtains skin area realizes Face datection.People i.e. can be detected in the case that face does not blocks well
Face simultaneously carries out identification, once identity information does not mates, then opens multimedia-message-alarming mode annunciations staff and notes;And work as
Existing face then can judge the facial personage blocked when deliberately blocking, if any then pointing out removing shelter, if continuous three times
Point out not removed blocking, then open multimedia-message-alarming mode annunciations staff and note.
In conjunction with Fig. 3, Adaboost algorithm, according to the feedback of weak study, adjusts the error rate of hypothesis adaptively, is examined
The higher strong classifier of survey rate, to improve classification performance.First use Haar-like character representation face, use " integrogram " real
The quick calculating of existing character numerical value;Adaboost algorithm is used to pick out some rectangular characteristic (weak typings that can represent face
Device), according to the mode of Nearest Neighbor with Weighted Voting, Weak Classifier is configured to a strong classifier;Some strong classifier strings that training is obtained
Joint group becomes the cascade filtering of a cascade structure, and cascade structure can be effectively improved the detection speed of grader.
It is seen that, suspicious figure's stealing can be detected by the present invention in real time, has low cost, high safety, band
Have intelligence, warning is timely, be easy to the features such as universal maintenance expense is low, can be used for all agricultural greenhouses, strengthens the peace of agricultural greenhouse
Quan Xing, reduces the stolen crime rate of agricultural greenhouse.
Claims (8)
1. the agricultural greenhouse warning system based on IB-Adaboost Face datection, it is characterised in that include: identification module,
For obtaining the video image at scene;Image capture module, is connected with described identification module, is used for gathering described video figure
Picture, and described video image is digitized;Flush bonding processor, is connected with described image capture module, is used for receiving numeral
Video image after change, and by embedded IB-Adaboost Face datection algorithm video image be analyzed and process;And
Mobile terminal, is used for reception processing result.
2. the agricultural greenhouse warning system based on IB-Adaboost Face datection according to claim 1, its feature exists
First image is carried out when, described flush bonding processor embedded IB-Adaboost Face datection algorithm process video image
Illumination compensation process, improves the even impact on picture quality of uneven illumination;Improve face classification performance in conjunction with Adaboost algorithm;
Then pass through YCbCr color space conversion binary image, attempt reducing Face datection region to reduce missing inspection;Then carry out
Area of skin color feature extraction, to reaching to improve the effect of Face datection, improves the real-time face detection performance of system.
3. the agricultural greenhouse warning system based on IB-Adaboost Face datection according to claim 1, its feature exists
In described identification module is ccd video camera.
4. the agricultural greenhouse warning system based on IB-Adaboost Face datection according to claim 1, its feature exists
In described image capture module is image pick-up card.
5. the agricultural greenhouse warning system based on IB-Adaboost Face datection according to claim 1, its feature exists
In, also including the memory cell being connected with flush bonding processor, described memory cell is for storing suspicious video image.
6. the agricultural greenhouse warning system based on IB-Adaboost Face datection according to claim 1, its feature exists
By GPRS cat, result is sent to described mobile terminal in, described flush bonding processor.
7. the agricultural greenhouse based on IB-Adaboost Face datection using as described in arbitrary in claim 1-6 is reported to the police
The method of system, it is characterised in that include system initialization, obtains on-the-spot video image;Video image is acquired, and
Video image after gathering is digitized processing;After using IB-Adaboost Face datection algorithm to digitized processing
Video image processes and analyzes, it may be judged whether have suspicious figure to occur, wherein, system initialization include to identification module be
No work, the resolution ratio gathering image of identification module, the OpenCV visual exercise storehouse loading oneself training, loading eye detection
Grader, nose detection grader, mouth detection grader;Described flush bonding processor is by embedded IB-Adaboost algorithm
Video image is analyzed and process specifically includes following steps:
Use " reference white " standardization color appearance: using the value of 5% before pixel intensity in image as reference white;
First use Haar-like character representation face, use " integrogram " to realize the quick calculating of character numerical value;Use
Adaboost algorithm picks out some rectangular characteristic that can represent face as Weak Classifier, will according to the mode of Nearest Neighbor with Weighted Voting
Weak Classifier is configured to a strong classifier;The some strong classifiers obtaining training are composed in series the stacking of a cascade structure
Grader;
Carry out the conversion of YCbCr color space to image, thus realize improving the function of energy resolution;
Utilize morphological method to carry out binaryzation process to band detection image, reject non-face region;
Detect that human face region carries out identification to human face region, it may be judged whether can recognize that whom the other side's identity is, if inspection
Do not measure, send information to greenhouse gardening personnel.
8. method according to claim 7, it is characterised in that also comprise determining whether to block facial suspicious figure's
Step, if be detected that face blocks, then points out removing to block, if not according to prompting operation, then sending information to booth
Plant personnel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610494268.4A CN106156729A (en) | 2016-06-29 | 2016-06-29 | A kind of agricultural greenhouse warning system based on IB Adaboost Face datection and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610494268.4A CN106156729A (en) | 2016-06-29 | 2016-06-29 | A kind of agricultural greenhouse warning system based on IB Adaboost Face datection and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106156729A true CN106156729A (en) | 2016-11-23 |
Family
ID=57349641
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610494268.4A Pending CN106156729A (en) | 2016-06-29 | 2016-06-29 | A kind of agricultural greenhouse warning system based on IB Adaboost Face datection and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106156729A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112034896A (en) * | 2020-09-14 | 2020-12-04 | 广东生太修复科技有限公司 | Fishpond water level control method and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101620673A (en) * | 2009-06-18 | 2010-01-06 | 北京航空航天大学 | Robust face detecting and tracking method |
CN102542246A (en) * | 2011-03-29 | 2012-07-04 | 广州市浩云安防科技股份有限公司 | Abnormal face detection method for ATM (Automatic Teller Machine) |
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN103198567A (en) * | 2013-03-07 | 2013-07-10 | 刘文萍 | ATM alarming system based on Adaboost face detection and method |
-
2016
- 2016-06-29 CN CN201610494268.4A patent/CN106156729A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101620673A (en) * | 2009-06-18 | 2010-01-06 | 北京航空航天大学 | Robust face detecting and tracking method |
CN102542246A (en) * | 2011-03-29 | 2012-07-04 | 广州市浩云安防科技股份有限公司 | Abnormal face detection method for ATM (Automatic Teller Machine) |
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN103198567A (en) * | 2013-03-07 | 2013-07-10 | 刘文萍 | ATM alarming system based on Adaboost face detection and method |
Non-Patent Citations (2)
Title |
---|
陈晓宾: ""基于肤色和AdaBoost算法的人脸检测方法研究"", 《万方数据库》 * |
雍宝虎: ""基于肤色分割和AdaBoost算法的人脸检测"", 《科学技术与工程》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112034896A (en) * | 2020-09-14 | 2020-12-04 | 广东生太修复科技有限公司 | Fishpond water level control method and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105868689B (en) | A kind of face occlusion detection method based on concatenated convolutional neural network | |
CN108009473B (en) | Video structuralization processing method, system and storage device based on target behavior attribute | |
CN108053427B (en) | Improved multi-target tracking method, system and device based on KCF and Kalman | |
Craye et al. | Spatio-temporal semantic segmentation for drone detection | |
CN101655907B (en) | Trainman driving state monitoring intelligent alarm system | |
CN102013006B (en) | Method for automatically detecting and identifying face on the basis of backlight environment | |
CN108647582A (en) | Goal behavior identification and prediction technique under a kind of complex dynamic environment | |
CN110309719A (en) | A kind of electric network operation personnel safety cap wears management control method and system | |
CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
CN107392112A (en) | A kind of facial expression recognizing method and its intelligent lock system of application | |
CN106204815A (en) | A kind of gate control system based on human face detection and recognition | |
CN101715111B (en) | Method for automatically searching abandoned object in video monitoring | |
CN105260715B (en) | Towards the toy object detection method in remote location | |
CN107911663A (en) | A kind of elevator passenger hazardous act intelligent recognition early warning system based on Computer Vision Detection | |
CN106355162A (en) | Method for detecting intrusion on basis of video monitoring | |
CN106327738A (en) | Intelligent grading monitoring system | |
CN111259718B (en) | Staircase retention detection method and system based on Gaussian mixture model | |
CN110188715A (en) | A kind of video human face biopsy method of multi frame detection ballot | |
CN112149576A (en) | Elevator safety real-time monitoring management system based on image analysis | |
CN108416289A (en) | A kind of working at height personnel safety band wears detection device and detection method for early warning | |
CN105227918B (en) | A kind of intelligent control method | |
CN207636791U (en) | A kind of large passenger flow quick security check door | |
CN111401310B (en) | Kitchen sanitation safety supervision and management method based on artificial intelligence | |
CN207883073U (en) | A kind of thermal imaging human bioequivalence monitoring alarm device | |
CN112949439A (en) | Method and system for monitoring invasion of personnel in key area of oil tank truck |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161123 |
|
RJ01 | Rejection of invention patent application after publication |