CN108770122A - Based on the adaptive room lighting method of ambient light and space density - Google Patents
Based on the adaptive room lighting method of ambient light and space density Download PDFInfo
- Publication number
- CN108770122A CN108770122A CN201810602432.8A CN201810602432A CN108770122A CN 108770122 A CN108770122 A CN 108770122A CN 201810602432 A CN201810602432 A CN 201810602432A CN 108770122 A CN108770122 A CN 108770122A
- Authority
- CN
- China
- Prior art keywords
- light
- illumination
- ambient light
- room lighting
- lighting 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
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/10—Controlling the intensity of the light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The room lighting method adaptive based on ambient light and space density that the invention discloses a kind of, it is detected by human body contour outline and the Spatial Data Clustering algorithm based on density realizes indoor best region illumination, and the complementation of LED light and natural light is realized according to the difference of ambient light, the Inner-lighting Technology of lamplight brightness adjusting is finally carried out according to lighting criteria.
Description
Technical field
The present invention relates to one kind to be calculated based on human body contour outline detection algorithm and DBSCAN (Spatial Data Clustering based on density)
Method realizes indoor best region illumination, and the technology of permanent illumination illumination is realized by LED light and natural light complementation.The invention belongs to intelligence
It can lighting area.
Background technology
Power shortage is one of the major issue for fettering socio-economic development and people's lives.Intelligent lighting and avoid electric energy
Waste is very necessary.Currently, the indoor illumination light fitting that China largely uses all cannot be according to the illuminance of external environment
Realize the adjusting of brightness, when the light of external environment is stronger, the power of indoor illumination light fitting will not change, and cause money
The waste in source.China's power shortage, for people life imbalance between supply and demand than more prominent.Reinforcing the same of China's power construction
When, the combination of intelligent lighting and energy-saving illumination seems particularly critical.Lamps and lanterns are rationally controlled according to indoor specific physical activity region
Switch distribution, indoor lamp intensity of illumination change with the variation of external environmental light intensity of illumination, make full use of electric energy, be room
The important trend of intraoral illumination lamps and lanterns.
With the development of smart home, intelligent lighting technology is also constantly improving.The present invention devises a kind of based on people
Body contour detecting algorithm realizes space density automatic adjusument, by acquisition ambient enviroment light intensity information, feeds back to control system,
Realize that LED light and natural light are complementary by PWM light modulations, illuminance sensor transmits Lighting information to realize that lamps and lanterns perseverance is shone in real time
The need of work of degree.LED light source system is controlled based on ZigBee LAN protocols, light intensity sensing module is added, according to extraneous ring
The light intensity of different location LED light source in the control room of border tentatively realizes that adaptive indoor intelligent illuminator, lamps and lanterns can be according to the external worlds
The intensity of illumination of the illuminance automatic adjustment interior different location LED of environment.
Invention content
The present invention is directed to the shortcomings that uncomfortable illuminance in existing lighting engineering, waste of energy, proposes that one kind passing through human body wheel
Exterior feature detects and the Spatial Data Clustering algorithm based on density realizes indoor best region illumination, and according to the difference of ambient light come real
The complementation of existing LED light and natural light, finally carries out the Inner-lighting Technology of lamplight brightness adjusting according to lighting criteria.
Further, the human body contour outline detection technique is to be based on HOG-SVM algorithms, for specific room lighting field
Scape, the head and shoulder for choosing human body are trained as feature, are filtered to the rectangle identified, are only retained maximum rectangle frame, are carried
The accuracy and practicability of high human testing model.
It includes image preprocessing and feature extraction to extract HOG features mainly.To after color space normalized
Image both horizontally and vertically seeks gradient and gradient direction at it respectively, and horizontal direction gradient operator is [- 10 1], vertically
Direction gradient operator is [- 10 1]T.Horizontal direction gradient, vertical gradient are respectively G at a certain pixel (x, y) in figurex
(x,y)、Gy(x, y), gradient G (x, y) and gradient direction θ (x, y) are as follows:
Gx(x, y)=I (x+1, y)-I (x-1, y)
Gy(x, y)=I (x, y+1)-I (x, y-1)
Following steps are realized using HOG-SVM human body contour outline detection algorithms:
1. by autoexec, pending positive negative sample is unified into format, size and name;
2. sample path and categorization vector are read in container;
3. reading in pending sample size, sample matrix and type matrix are generated;
4. once reading in positive and negative samples picture, HOG features are extracted respectively;
5. by positive and negative sample characteristics mark after, be stored in sample characteristics matrix in, positive sample classification be 1, negative sample classification be-
1;
6. training generates HOG-SVM graders;
7. handling picture using generated HOG-SVM graders.
Further, the Spatial Data Clustering algorithm based on density is based primarily upon the noisy spatial data of tool, mesh
Marking peg is to the cluster of high density area domain discovery arbitrary shape and divides, for the object in a certain cluster, in given radius
(Eps) in neighborhood, data object number has to be larger than given threshold value.The algorithm is to find position that indoor human body is often located
It sets, room area illumination is fed back and instructed.
Further, the LED light passes through difference nature with the control section that natural light complementation refers to lighting system
The feedback of light adjusts the output light flux of LED light source, realizes the real-time complementation of LED light and natural light.The present invention uses
BH1750FVI ambient light intensity sensors measure the intensity of illumination under natural light and LED illumination light hybird environment, and will measure
Data feedback compared with the intensity of illumination of default, generates an error to control unit;System is according to error signal and works as
The output of preceding LED light source calculates new output signal;The signal passes through power module regulating illumination intensity.
Further, carry out lamplight brightness according to lighting criteria and adjust to refer to unstable for natural light, LED light with from
Right light complementation feeds back to the control section of lighting system through light intensity sensor, reaches permanent illumination by PWM light modulations.
Compared with the prior art, the advantages of the present invention are as follows:
(1) interior lighting system of the present invention is in order to save the energy, self adaptive control area illumination, using human body wheel
Wide detection algorithm and Spatial Data Clustering algorithm based on density obtain the movable hotspot range of indoor human body, by hot spot model
The acquisition and analysis for enclosing data, can obtain rational illumination region.Optimal zone of the technology to intelligent illuminating system indoors
Domain illumination has directive significance, also has active influence to saving the energy;
(2) lighting system of the present invention is directed to the feature that unstable natural light causes indoor illumination intensity unstable, proposes LED
Light and natural light complementation ensure the stability of intelligent illuminating system illumination.Detecting system can acquire the information of unstable natural light
And information is fed back to the control section of system by illuminance sensor, LED light source is modulated by PWM light modulations, into
And realize that LED light and natural light are complementary, meet under people's different condition the needs of to illuminance.
Description of the drawings
Fig. 1 is interior lighting system distribution map;
Fig. 2 is based on the adaptive Lighting control flow chart of space density;
Fig. 3 is LED light and ambient light compensation flow chart based on complement arithmetic.
Specific implementation mode
Invention is further described in detail with reference to the accompanying drawings and detailed description.
Fig. 1 is the illumination partitioning scenario of lighting system indoors, and the number of subregion, this hair can be set according to the size in space
It is bright by taking 4 subregions as an example.
Fig. 2 is based on the adaptive Lighting control flow chart of space density.Lighting system uses human body contour outline detection algorithm, will
The condition that indoor human body active signal is opened as system, when detecting presence of people, activation system carries out brightness value ratio
Compared with if more than 300lx, then the subregion for being in open state carries out operation of turning off the light, and is otherwise not processed.If brightness value is less than
Physical activity picture in process chamber is detected 1 area someone, the lamp in 1st areas Ze Kai, nobody then keeps suspend mode by 300lx, system
Then state detects the physical activity situation in 2,3,4 areas successively.If indoor someone, system automatically open hot spot in respective chamber/chambers
Region lamps and lanterns simultaneously carry out light compensation.If it is indoor nobody, system if, enters dormant state.
Fig. 3 is LED light and ambient light compensation flow chart based on complement arithmetic.Public affairs described below are obtained according to flow chart
Formula:
In formula, F (t) is output of the LED light source in t moment;S (t) is intensity of illumination of the sensor measured by t moment;N
(t) be sensor measure indoor natural light t moment light intensity;R (t) is the target luminous intensity that user is arranged in t moment;ε is
Error amount.
If the value of F (t)+e is less than zero, expression does not need LED light source output, i.e. F (t+1)=0.Certainly, if surrounding ring
The intensity of illumination in border changes suddenly, and system also can make corresponding adjustment according to inside setting.
The control section of the invention carries out output flow to the LED light source in real time by the feedback of difference natural light
Compensation is completed permanent illumination and is adjusted.
Claims (7)
1. a kind of room lighting method adaptive based on ambient light and space density, it is characterised in that:By being based on human body wheel
Exterior feature detects and the Spatial Data Clustering algorithm based on density realizes indoor best region illumination, and according to the difference of ambient light come real
The complementation of existing LED light and natural light, finally carries out lamplight brightness adjusting according to lighting criteria.
2. the room lighting method adaptive based on ambient light and space density according to claim 1, it is characterised in that:
Described detected based on human body contour outline is to be based on HOG-SVM algorithms, for specific indoor scene, chooses human head and shoulder feature and is instructed
Practice, filter operation is taken to the overlapping rectangles frame identified, detects physical activity situation.
3. the room lighting method adaptive based on ambient light and space density according to claim 2, it is characterised in that:
It includes image preprocessing and feature extraction to extract HOG features;To the image after color space normalized, respectively at it
Gradient and gradient direction are both horizontally and vertically sought, horizontal direction gradient operator is [- 10 1], vertical gradient operator
For [- 10 1]T;Horizontal direction gradient, vertical gradient are respectively G at a certain pixel (x, y) in figurex(x, y), Gy(x,
Y), gradient G (x, y) and gradient direction θ (x, y) are as follows:
Gx(x, y)=I (x+1, y)-I (x-1, y)
Gy(x, y)=I (x, y+1)-I (x, y-1)
Following steps are realized using HOG-SVM human body contour outline detection algorithms:
1) by autoexec, pending positive negative sample is unified into format, size and name;
2) sample path and categorization vector are read in into container;
3) pending sample size is read in, sample matrix and type matrix are generated;
4) positive and negative samples picture is once read in, extracts HOG features respectively;
5) it after marking positive and negative sample characteristics, is stored in sample characteristics matrix, positive sample classification is 1, and negative sample classification is -1;
6) training generates HOG-SVM graders;
7) picture is handled using generated HOG-SVM graders.
4. the room lighting method adaptive based on ambient light and space density according to claim 1, it is characterised in that:
The Spatial Data Clustering algorithm based on density is based on having noisy spatial data, using indoor human body activity as object,
In the neighborhood of given radius (Eps), when there is human body to occur, by judging to image procossing and through illuminating zone control tactics
Afterwards, physical activity hot spot region lamps and lanterns are opened and carry out illuminance compensation.
5. the room lighting method adaptive based on ambient light and space density according to claim 1, it is characterised in that:
The complementary feedback by each illumination subregion difference natural light of the LED light and natural light, adjusts the defeated of corresponding points LED light source
Go out luminous flux, adjusts light source in real time as needed, make intensity of illumination substantially constant.
6. the room lighting method adaptive based on ambient light and space density according to claim 5, it is characterised in that:
The intensity of illumination under natural light and LED illumination light hybird environment is measured using BH1750FVI ambient light intensity sensors, and will
Measurement data feeds back to control section compared with the intensity of illumination of default, generates an error;According to error signal and work as
The output of preceding LED light source calculates new output signal, to meet the needs of lighting system permanent illumination indoors.
7. the room lighting method adaptive based on ambient light and space density according to claim 1, it is characterised in that:
It is that LED light feeds back to lighting system with natural light complementation through light intensity sensor to carry out lamplight brightness adjusting according to lighting criteria
Control section reaches permanent illumination by PWM light modulations.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810602432.8A CN108770122A (en) | 2018-06-12 | 2018-06-12 | Based on the adaptive room lighting method of ambient light and space density |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810602432.8A CN108770122A (en) | 2018-06-12 | 2018-06-12 | Based on the adaptive room lighting method of ambient light and space density |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108770122A true CN108770122A (en) | 2018-11-06 |
Family
ID=64022471
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810602432.8A Pending CN108770122A (en) | 2018-06-12 | 2018-06-12 | Based on the adaptive room lighting method of ambient light and space density |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108770122A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113795072A (en) * | 2021-11-16 | 2021-12-14 | 深圳市奥新科技有限公司 | Intelligent library lighting system and control method and device thereof |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103310183A (en) * | 2012-03-16 | 2013-09-18 | 日电(中国)有限公司 | People group gathering detection method and device |
US20150002027A1 (en) * | 2011-01-31 | 2015-01-01 | Industrial Technology Research Institute | Multi-function lighting system |
CN106211515A (en) * | 2016-07-28 | 2016-12-07 | 四川观堂建筑工程设计股份有限公司 | A kind of classroom intelligence control system of permanent illumination |
CN106934380A (en) * | 2017-03-19 | 2017-07-07 | 北京工业大学 | A kind of indoor pedestrian detection and tracking based on HOG and MeanShift algorithms |
-
2018
- 2018-06-12 CN CN201810602432.8A patent/CN108770122A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150002027A1 (en) * | 2011-01-31 | 2015-01-01 | Industrial Technology Research Institute | Multi-function lighting system |
CN103310183A (en) * | 2012-03-16 | 2013-09-18 | 日电(中国)有限公司 | People group gathering detection method and device |
CN106211515A (en) * | 2016-07-28 | 2016-12-07 | 四川观堂建筑工程设计股份有限公司 | A kind of classroom intelligence control system of permanent illumination |
CN106934380A (en) * | 2017-03-19 | 2017-07-07 | 北京工业大学 | A kind of indoor pedestrian detection and tracking based on HOG and MeanShift algorithms |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113795072A (en) * | 2021-11-16 | 2021-12-14 | 深圳市奥新科技有限公司 | Intelligent library lighting system and control method and device thereof |
CN113795072B (en) * | 2021-11-16 | 2022-03-08 | 深圳市奥新科技有限公司 | Intelligent library lighting system and control method and device thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11696382B2 (en) | Measuring lighting levels using a visible light sensor | |
CN105050247B (en) | Light intelligent regulating system and its method based on expression Model Identification | |
CN207219101U (en) | A kind of colour temperature adjusts illuminator in real time | |
CN102946663A (en) | Image recognition intelligent illumination control system and control method thereof | |
CN107179793A (en) | A kind of LED illumination lamp intelligence control system | |
CN105916270A (en) | Building intelligent illumination control system | |
CN109041322B (en) | Intelligent indoor lighting system | |
CN109068440A (en) | A kind of energy-saving illumination intelligent control method and system | |
CN105517276B (en) | A kind of indoor LED intelligent illumination system based on Fusion | |
CN108235518B (en) | LED intelligent control energy-saving system | |
CN106163064A (en) | Road lamp energy-saving automatic control system based on road target detection and method | |
CN110139436A (en) | Based on crowd density information interconnection type campus lighting energy saving control method | |
Galindo et al. | Development of street lighting system with object detection | |
CN108770122A (en) | Based on the adaptive room lighting method of ambient light and space density | |
CN205566715U (en) | Indicator lamp with automatic brightness adjusting function and electronic device comprising same | |
CN205179441U (en) | Indoor LED lighting system of intelligence bluetooth of mobile phone control | |
CN109445393A (en) | Light sensing automatic lighting system based on mobile terminal location | |
CN110049604A (en) | A kind of street lighting power-economizing method and system | |
CN205584536U (en) | Control system of intelligent regulation LED luminance | |
CN206112646U (en) | Intelligent light -adjusting desk lamp | |
CN205389287U (en) | Energy -conserving illumination remote control system of intelligence | |
CN109526094A (en) | A kind of room for individual study light automatic control system | |
CN110191557A (en) | A kind of Intelligent lightening device and control method based on image recognition | |
CN206498561U (en) | A kind of intelligent illuminating system | |
CN109661069A (en) | A kind of LED illumination intelligence control system and method based on support vector machines |
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 |
Application publication date: 20181106 |
|
RJ01 | Rejection of invention patent application after publication |