CN109063566A - A kind of optical detecting method for human testing - Google Patents
A kind of optical detecting method for human testing Download PDFInfo
- Publication number
- CN109063566A CN109063566A CN201810712001.7A CN201810712001A CN109063566A CN 109063566 A CN109063566 A CN 109063566A CN 201810712001 A CN201810712001 A CN 201810712001A CN 109063566 A CN109063566 A CN 109063566A
- Authority
- CN
- China
- Prior art keywords
- sensor
- module
- image
- optical detecting
- detecting method
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The invention discloses a kind of optical detecting methods for human testing, comprising the following steps: S1, product are placed under unmanned environment, by the background information in the optical technology module acquisition monitoring region on sensor, as environment templates；S2, it is constantly acquired by the pick-up lens on sensor by the pattern feedback of acquisition to Visual identification technology module；S3, feature extraction is carried out to pattern by Visual identification technology module；S4, the environment templates in the drawing feature and learning database of extraction are compared by the image algorithm module on sensor；S5, by the logic identification algorithm in the Visual identification technology module on sensor to acquisition image analysis, obtain a result, and result is exported to relay；S6, relay make corresponding switch change according to signal and alarm, and the present invention not only solves current technology problem, while also meeting the needs of client, industry technology level is also pushed to a new step three kinds of artificial intelligence, imaging, sensing technological synthesis.
Description
Technical field
The present invention relates to technical field of optical detection more particularly to a kind of optical detecting methods for human testing.
Background technique
The technology and product that use both at home and abroad at present are substantially based on infrared ray or the ultrasonic wave personnel of Doppler effect
Intrusion sensor and based on infrared thermal imaging perception human body sensor, the former can only perceive the human body of movement, for it is static not
Dynamic human body does not react then；The latter's cost is very high, it is difficult to and it is universal, and also resolution ratio is lower, it is difficult to number is differentiated, especially in room
Between in temperature is higher, rate of false alarm is high in the biggish situation of humidity, and existing sensor bulk is very big, at high cost, uncomfortable
It closes civilian.
It can identify dynamic and static human body, and can identify personnel amount and position, pet interference can be excluded, crucial cost is relatively low
A kind of intelligent human-body identification sensor have become technology of Internet of things and intelligent building, smart home, intelligent appliance industry
It just needs, therefore, we have proposed a kind of optical detecting methods for human testing for solving the above problems.
Summary of the invention
The purpose of the present invention is to solve disadvantage existing in the prior art, and propose a kind of for human testing
Optical detecting method.
A kind of optical detecting method for human testing, comprising the following steps:
S1, the embedded scm technology modules that sensor internal is connected by Bluetooth of mobile phone, setting sensor time are same
Step, product is placed under unmanned environment, and the background information in region is monitored by the optical technology module acquisition study on sensor,
As environment templates, and store information into the learning database of embedded scm technology modules；
S2, monitored pattern is constantly acquired by the pick-up lens on sensor, and the pattern of acquisition is fed back
To Visual identification technology module；
S3, the collected pattern of institute is carried out by feature extraction by Visual identification technology module；
S4, the environment templates in the drawing feature and learning database of extraction are carried out by the image algorithm module on sensor
It compares；
S5, by the logic identification algorithm in the Visual identification technology module on sensor to acquisition image analysis, in list
Piece machine calculate analysis under, obtain nobody, someone, number, orientation as a result, and sensor information is exported to warning output mould
Block；
Input information is different from information before in S6, alarm output module, then relay makees corresponding switch change simultaneously
Alarm.
Preferably, the embedded scm technology modules are used to analyze the calculated performance of sensor, monitoring pattern is deposited
Storage, monitoring pattern Memory Allocation and mobile communication.
Preferably, the optical technology module is for the infrared imagery technique of camera lens, pattern light filling, optical filtering and pattern
Luminance Analysis.
Preferably, the Visual identification technology module is for the identification of dynamic people appearance, the identification of static person appearance, animal, household area
Identification, video frequency object tracking, machine learning and monitoring drawing feature is divided to extract.
Preferably, the algorithm in described image algoritic module is extracted for drawing feature, image filter is made an uproar, anamorphose, figure
As cutting, differential profile identification, static identification, dynamic target tracking and target measuring and calculating.
Preferably, the differential profile identification, reads detection picture first, is transformed into gray level image, secondly extract
Detect the characteristic block on picture, and compare selection base map, position best base map and read gray scale base map, then will test picture with
Best base map carries out Difference Calculation, will test figure and base map carries out grayscale image Difference Calculation, export n difference grey scale elements figure,
To each grey scale elements normalized, LBP image then is converted to each grey scale elements figure, goes lighting process, and mention
Take the Hog feature in LBP image, finally by extraction Hog feature and learning database in comparisons export whether the result of someone.
Preferably, the embedded scm technology modules are run under the linux environment of MIPS chipset, and use bottom
The embedded development of layer C Plus Plus.
It preferably, include relay output and the output of 485 interfaces in the alarm output module.
The beneficial effects of the present invention are:
1, it using the infrared light filling of 850 nanometers and optical filtering, solves and is worked normally under daytime, night various light conditions, kept away
Influence of the environmental factor to identification accuracy is exempted from.
2, image recognition algorithm solves the various complicated human bodies such as motionless to the various postures of human body, dynamic motion, static state
Accurate detection identification, similar product are difficult to be equal to.
3, with the classifier technique method of machine learning, successfully the object close with size of human body or animal are accurately divided
Class identifies, is applicable in more wide application scenarios.
4, by unique image/video tracking technique, the human body real-time tracking each identified in environment is calculated,
The information of current persons count and place orientation are uninterruptedly provided for user, pushed infrared sensor market application range.
5, it due to being handled using single-chip microcontroller, runs the Dynamic data exchange of video acquisition and is provided without network and server
Source is effectively protected the individual privacy of user.
Detailed description of the invention
Fig. 1 is a kind of functional block diagram of the optical detecting method for human testing proposed by the present invention.
Specific embodiment
Combined with specific embodiments below the present invention is made further to explain.
A kind of optical detecting method for human testing, comprising the following steps: sensor S1, is connected by Bluetooth of mobile phone
Internal embedded scm technology modules, setting sensor time is synchronous, and product is placed under unmanned environment, sensor is passed through
On optical technology module acquisition study monitoring region background information, as environment templates, and store information into embedding
In the learning database for entering formula singlechip technology module；S2, monitored figure is constantly acquired by the pick-up lens on sensor
Sample, and the pattern of acquisition is fed back to Visual identification technology module；S3, pass through Visual identification technology module for the collected figure of institute
Sample carries out feature extraction；S4, by the image algorithm module on sensor by the environment in the drawing feature and learning database of extraction
Template is compared；S5, by the logic identification algorithm in the Visual identification technology module on sensor to acquisition image analysis,
Single-chip microcontroller calculate analysis under, obtain nobody, someone, number, orientation as a result, and sensor information is exported to warning output
Module；Input information is different from information before in S6, alarm output module, then relay is made corresponding switch change and reported
Alert, the embedded scm technology modules are used to analyze the calculated performance of sensor, monitoring pattern stores, in monitoring pattern
Distribution and mobile communication are deposited, the optical technology module is used for infrared imagery technique, pattern light filling, optical filtering and the figure of camera lens
The Luminance Analysis of sample, the Visual identification technology module are distinguished for the identification of dynamic people appearance, the identification of static person appearance, animal, household
Identification, video frequency object tracking, machine learning and monitoring drawing feature extract, and the algorithm in described image algoritic module is for scheming
Sample feature extraction, image filter make an uproar, anamorphose, image cutting, differential profile identification, static identification, dynamic target tracking and
Target measuring and calculating, the differential profile identification, reads detection picture first, is transformed into gray level image, secondly extracts detection figure
The characteristic block of on piece, and compare selection base map, position best base map and read gray scale base map, it then will test picture and best bottom
Figure carries out Difference Calculation, will test figure and base map carries out grayscale image Difference Calculation, n difference grey scale elements figure is exported, to each
Then grey scale elements normalized is converted to LBP image to each grey scale elements figure, goes lighting process, and extract LBP figure
Hog feature as in, finally by Hog feature and the comparison in learning database of extraction export whether someone's as a result, described embedding
Enter formula singlechip technology module to run under the linux environment of MIPS chipset, and is opened using the embedded of bottom C Plus Plus
It sends out, includes relay output and the output of 485 interfaces in the alarm output module.
In the present embodiment, using optical principle, reliable full-view camera sensing element is chosen, it can not using 850 nanometers
Imaging is reached the optimum efficiency that identification requires, adopted by light-exposed light filling and optical filtering, the parameters such as exposure focal length of appropriate method of adjustment
It with the theoretical method of machine learning, acquires a large amount of image data and carries out analytic learning, allow " brain " someone of product sensor
Body and other animals and object have cognitive ability, using the image recognition technology and logic identification algorithm of artificial intelligence to adopting
Collect image analysis judgement, nobody, someone, number, the result output transducer information in orientation is obtained, in MIPS chipset
Under linux environment, using the embedded development of bottom C Plus Plus, completes the input setting of product sensor, calculates storage control
The functions such as system, output result, management and running.
It include that relay output and 485 interfaces export in alarm output module, the relay way of output: under unmanned state,
Normally-closed contact short circuit, normally opened contact open circuit；Under someone's state, normally-closed contact open circuit, normally opened contact short circuit.
485 way of outputs:
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (8)
1. a kind of optical detecting method for human testing, which comprises the following steps:
S1, the embedded scm technology modules that sensor internal is connected by Bluetooth of mobile phone, setting sensor time is synchronous, will
Product is placed under unmanned environment, by the background information in the optical technology module acquisition study monitoring region on sensor, by it
As environment templates, and store information into the learning database of embedded scm technology modules；
S2, monitored pattern is constantly acquired by the pick-up lens on sensor, and the pattern of acquisition is fed back to view
Feel identification technology module；
S3, the collected pattern of institute is carried out by feature extraction by Visual identification technology module；
S4, the environment templates in the drawing feature and learning database of extraction are compared by the image algorithm module on sensor
It is right；
S5, by the logic identification algorithm in the Visual identification technology module on sensor to acquisition image analysis, in single-chip microcontroller
Calculate analysis under, obtain nobody, someone, number, orientation as a result, and sensor information is exported to alarm output module；
Input information is different from information before in S6, alarm output module, then relay makees corresponding switch change and alarms.
2. a kind of optical detecting method for human testing according to claim 1, which is characterized in that described embedded
Singlechip technology module is used for calculated performance analysis, the storage of monitoring pattern, monitoring pattern Memory Allocation and hand to sensor
Machine communication.
3. a kind of optical detecting method for human testing according to claim 1, which is characterized in that the optics skill
Luminance Analysis of the art module for the infrared imagery technique of camera lens, pattern light filling, optical filtering and pattern.
4. a kind of optical detecting method for human testing according to claim 1, which is characterized in that the vision is known
Other technology modules are used for the identification of dynamic people appearance, the identification of static person appearance, animal, household Division identification, video frequency object tracking, engineering
It practises and monitoring drawing feature extracts.
5. a kind of optical detecting method for human testing according to claim 1, which is characterized in that described image is calculated
Algorithm in method module is made an uproar for drawing feature extraction, image filter, anamorphose, image is cut, differential profile identifies, static knowledge
Not, dynamic target tracking and target measuring and calculating.
6. a kind of optical detecting method for human testing according to claim 5, which is characterized in that the difference wheel
Exterior feature identification, reads detection picture first, is transformed into gray level image, secondly extracts the characteristic block on detection picture, and compare
Base map is selected, best base map is positioned and reads gray scale base map, picture is then will test and best base map carries out Difference Calculation, will examine
Mapping and base map carry out grayscale image Difference Calculation, export n difference grey scale elements figure, to each grey scale elements normalized,
Then LBP image is converted to each grey scale elements figure, goes lighting process, and extract the Hog feature in LBP image, finally
By comparisons in the Hog feature of extraction and learning database export whether the result of someone.
7. a kind of optical detecting method for human testing according to claim 1, which is characterized in that described embedded
Singlechip technology module is run under the linux environment of MIPS chipset, and uses the embedded development of bottom C Plus Plus.
8. a kind of optical detecting method for human testing according to claim 1, which is characterized in that the alarm is defeated
It out include relay output and the output of 485 interfaces in module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810712001.7A CN109063566A (en) | 2018-07-02 | 2018-07-02 | A kind of optical detecting method for human testing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810712001.7A CN109063566A (en) | 2018-07-02 | 2018-07-02 | A kind of optical detecting method for human testing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063566A true CN109063566A (en) | 2018-12-21 |
Family
ID=64818715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810712001.7A Pending CN109063566A (en) | 2018-07-02 | 2018-07-02 | A kind of optical detecting method for human testing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063566A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119691A (en) * | 2019-04-19 | 2019-08-13 | 华南理工大学 | A kind of portrait localization method that based on local 2D pattern and not bending moment is searched |
| CN110298433A (en) * | 2019-07-09 | 2019-10-01 | 杭州麦乐克科技股份有限公司 | A kind of indoor human body quantity survey (surveying) device |
| CN112700614A (en) * | 2020-12-23 | 2021-04-23 | 广东电网有限责任公司佛山供电局 | Safe fence device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339688A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Intrusion checking method and system |
| US20110176126A1 (en) * | 2001-07-19 | 2011-07-21 | Hitachi, Ltd. | Finger identification apparatus |
| CN105799740A (en) * | 2016-03-08 | 2016-07-27 | 浙江大学 | Automatic detecting and early warning method for track foreign matter invasion based on Internet of Things technology |
| CN105929772A (en) * | 2016-04-28 | 2016-09-07 | 天津大学 | Infrared imaging human body identification safety early warning apparatus of driving operation |
-
2018
- 2018-07-02 CN CN201810712001.7A patent/CN109063566A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110176126A1 (en) * | 2001-07-19 | 2011-07-21 | Hitachi, Ltd. | Finger identification apparatus |
| CN101339688A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Intrusion checking method and system |
| CN105799740A (en) * | 2016-03-08 | 2016-07-27 | 浙江大学 | Automatic detecting and early warning method for track foreign matter invasion based on Internet of Things technology |
| CN105929772A (en) * | 2016-04-28 | 2016-09-07 | 天津大学 | Infrared imaging human body identification safety early warning apparatus of driving operation |
Non-Patent Citations (1)
| Title |
|---|
| 万源 等: "LBP和HOG的分层特征融合的人脸识别", 《计算机辅助设计与图形学学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119691A (en) * | 2019-04-19 | 2019-08-13 | 华南理工大学 | A kind of portrait localization method that based on local 2D pattern and not bending moment is searched |
| CN110298433A (en) * | 2019-07-09 | 2019-10-01 | 杭州麦乐克科技股份有限公司 | A kind of indoor human body quantity survey (surveying) device |
| CN112700614A (en) * | 2020-12-23 | 2021-04-23 | 广东电网有限责任公司佛山供电局 | Safe fence device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190236342A1 (en) | Face concealment detection | |
| CN103839373B (en) | A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system | |
| Planinc et al. | Introducing the use of depth data for fall detection | |
| US11196966B2 (en) | Identifying and locating objects by associating video data of the objects with signals identifying wireless devices belonging to the objects | |
| CN103839346B (en) | A kind of intelligent door and window anti-intrusion device and system, intelligent access control system | |
| US11232685B1 (en) | Security system with dual-mode event video and still image recording | |
| CN102521578B (en) | Method for detecting and identifying intrusion | |
| CN110321780B (en) | Abnormal falling behavior detection method based on space-time motion characteristics | |
| CN107133564B (en) | Tooling cap detection method | |
| KR101839827B1 (en) | Smart monitoring system applied with recognition technic of characteristic information including face on long distance-moving object | |
| CN206277403U (en) | A kind of multi-functional service for infrastructure robot | |
| CN109063566A (en) | A kind of optical detecting method for human testing | |
| US10769909B1 (en) | Using sensor data to detect events | |
| CN104123536A (en) | System and method for image analysis | |
| US11302156B1 (en) | User interfaces associated with device applications | |
| US11935297B2 (en) | Item monitoring for doorbell cameras | |
| US10791607B1 (en) | Configuring and controlling light emitters | |
| CN114446026B (en) | Article forgetting reminding method, corresponding electronic equipment and device | |
| CN112270807A (en) | Old man early warning system that tumbles | |
| CN108376237A (en) | A kind of house visiting management system and management method based on 3D identifications | |
| TWI713368B (en) | Image device and method for detecting a thief | |
| CN115223204A (en) | Method, device, equipment and storage medium for detecting illegal wearing of personnel | |
| US10914811B1 (en) | Locating a source of a sound using microphones and radio frequency communication | |
| CN116520315A (en) | Target recognition system, target recognition method and target recognition device | |
| KR101340287B1 (en) | Intrusion detection system using mining based pattern analysis in smart home |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181221 |
|
| WD01 | Invention patent application deemed withdrawn after publication |