CN106054646A - Intelligent household control method - Google Patents
Intelligent household control method Download PDFInfo
- Publication number
- CN106054646A CN106054646A CN201610532818.7A CN201610532818A CN106054646A CN 106054646 A CN106054646 A CN 106054646A CN 201610532818 A CN201610532818 A CN 201610532818A CN 106054646 A CN106054646 A CN 106054646A
- Authority
- CN
- China
- Prior art keywords
- image
- coordinate
- panoramic
- controllable
- original
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000000875 corresponding effect Effects 0.000 claims abstract description 23
- 230000009471 action Effects 0.000 claims abstract description 4
- 238000003384 imaging method Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses an intelligent household control method. The method is characterized by comprising the following steps: 1, creating an original panoramagram; 2, creating a controllable coordinate database, i.e., selecting controllable points, setting types of the controllable points, calculating an area coordinate scope corresponding to each controllable point, and creating a coordinate database for the area coordinate scopes; 3, obtaining a real-time image; 4, processing the real-time image; 5, performing mode matching, i.e., superposing a real-time panoramagram with the original panoramagram; and 6, activating the controllable points, i.e., selecting control points on the real-time panoramagram, calculating coordinates of the selected control points, comparing the coordinates with the coordinate database, if the coordinates are within the scope of the coordinate database, obtaining current states of the corresponding controllable points and performing corresponding action, and if the coordinates are beyond the scope of the coordinate database, not taking action. According to the invention, through matching between the real-time panoramagram and the original panoramagram, operation can be visually performed according to the real-time image on a display screen, the interface is simple, and the applicable user scope is wide.
Description
Technical field
The present invention relates to a kind of Smart Home, especially a kind of intelligent home system control method.
Background technology
The concept that Smart Home is beyond doubt very powerful and exceedingly arrogant, the residential quarters of some top grades are the most supporting has compared
Kind intelligent home network, wherein the close friendization of human-computer interaction interface and intellectuality are particularly important.Simultaneously along with intellectuality
Go deep into, intelligence is also embodied in and is controlled according to scene, and then reaches the requirement of user.The raising of system intelligent degree is big
While reducing greatly habitant's management and controlling household workload, too increase kinsfolk and complexity is operated recognizing of interface
Know ability, such as the button in the face of meeting the eye on every side and icon, mixed and disorderly interface subject, some shirtsleeve operations can be made on the contrary to complicate, very
To the people that also some can be unfamiliar with these operation interfaces, cause new puzzlement such as old man, child, visitor etc., run counter to " science and technology
People-oriented " theory, away from home intelligence with allow the original intention that becomes simple of life.
Summary of the invention
The technical problem to be solved is to provide a kind of intelligent home system control method, easy to operate and straight
See, applied widely.
The present invention solves the technical scheme that above-mentioned technical problem used: a kind of intelligent home system control method, its
It is characterised by, comprises the steps:
1) establishment of original panoramic figure:
A) image is obtained: the original household image transmitting of shooting is to Intelligent home monitoring system;
B) Image semantic classification;
C) image mosaic: carry out seamless spliced by pretreated image, is then converted into curved panoramic by spliced image
Figure;
2) create controlled coordinate storehouse: selected controllable dot, set the type of each controllable dot, calculate the district corresponding to each controllable dot
Territory coordinate range, to described area coordinate scope creation coordinate database;
3) acquisition of real time imaging: shoot real-time household image, and be transferred to Intelligent home monitoring system;
4) process of real time imaging: real time imaging is carried out pretreatment, and pretreated real time imaging is carried out seamless spelling
Connect, be then converted into curved panoramic figure;
5) pattern match: real time panoramic figure is overlapped with original panoramic figure, mates so that each picture of real time panoramic figure
Element and the pixel one_to_one corresponding of original panoramic figure;
6) controllable dot is activated: selection control point on real time panoramic figure, the coordinate of the current control point selected by calculating, and will
The coordinate of described current control point compares with described coordinate database, if the coordinate of described current control point is in coordinate database
In the range of, then obtain the current state of corresponding controllable dot, carry out corresponding action;If the coordinate of described current control point exists
Outside the scope of coordinate database, the most do not take action.
Described original household image or in real time household image seamless spliced, comprises the following steps:
A) feature point detection: extract image characteristic point based on SURF algorithm, utilizes the office of approximation Hessian matrix determinant
Portion's maximum detects in two width images has the characteristic point in the position of high multiplicity;
B) characteristic point describes: response to single order Haar small echo in the horizontal and vertical directions, SURF algorithm pair according to image
The principal direction of characteristic point is determined, utilize simultaneously grayscale distribution information in a certain little neighborhood of characteristic point formed describe son to
Amount;
C) characteristic point and images match: carry out characteristic point according to Euclidean distance or mahalanobis distance and describe the coupling of operator, find out
The correspondence position of point to be matched, so that it is determined that transformation relation between adjacent two width images, estimates that the mathematics of two width images becomes simultaneously
Die change type;
D) image co-registration: merged by the image with overlapping region, obtains the seamless image splicing seamlessly transitted.
In step 2) in, selected controllable dot is adopted manually, drags virtual view-finder to each controllable dot, thus
Calculate the coordinate range of virtual view-finder as corresponding area coordinate scope.
In step 2) in, selected controllable dot uses automatic mode, in step 1) obtain original panoramic figure after, by controlled
Household be switched to and step 1) in relative to state, obtain contrast panorama sketch by same method, by original panoramic figure and right
Make correlation operation than panorama sketch, obtain original panoramic figure and the difference of contrast panorama sketch, obtain each controllable dot.
In step 6) in, the method obtaining the current state of corresponding controllable dot, by each controlled home habitation monitoring electricity
Pressure, electric current or feedback of status, it is judged that current state, and this status information is mated with corresponding controllable dot.
Compared with prior art, it is an advantage of the current invention that: by obtaining original panoramic figure, selected in original panoramic figure
Controllable dot, then gathers real time imaging, by mating of real time panoramic figure and original panoramic figure, and can root the most on a display screen
Operating according to real time imaging, interface is simple, easy to operate, and the user scope being suitable for is wide.
Accompanying drawing explanation
Fig. 1 is the flow chart of the control method of the present invention.
Detailed description of the invention
See Fig. 1, a kind of intelligent home system control method, it is characterised in that comprise the steps:
1) establishment of original panoramic figure:
A) image is obtained: the original household image transmitting of shooting is to Intelligent home monitoring system;
B) Image semantic classification;
C) image mosaic: carry out seamless spliced by pretreated image, is then converted into curved panoramic by spliced image
Figure;
2) create controlled coordinate storehouse: selected controllable dot, set the type of each controllable dot, calculate the district corresponding to each controllable dot
Territory coordinate range, to described area coordinate scope creation coordinate database;
3) acquisition of real time imaging: shoot real-time household image, and be transferred to Intelligent home monitoring system;
4) process of real time imaging: real time imaging is carried out pretreatment, and pretreated real time imaging is carried out seamless spelling
Connect, be then converted into curved panoramic figure;
5) pattern match: real time panoramic figure is overlapped with original panoramic figure, mates so that each picture of real time panoramic figure
The pixel one_to_one corresponding of element original panoramic figure;
6) controllable dot is activated: selection control point on real time panoramic figure, the coordinate of the current control point selected by calculating,
The coordinate of described current control point is compared with described coordinate database, if the coordinate of described current control point is at coordinate
In the range of data base, then obtain the current state of corresponding controllable dot, carry out corresponding action;If described current control point
Coordinate, outside the scope of coordinate database, does not the most take action.
Wherein, existing picture joining method has angular-point detection method, adapting to image split-join model algorithm, and SIFT is special
Levy matching algorithm, and SURF algorithm etc., in the present invention, using SURF algorithm, SURF algorithm is base to the detection of characteristic point
In Scale-space theory, according to the local maximum location feature point position of Hessian matrix determinant, simultaneously also ranks
The value of formula is as the selection gist of metric space.
The original household image being preferably used in the present invention or the image split-joint method of real-time household image, the most permissible
It is divided into following step:
A) feature point detection: based on SURF (Speed Up Robust Feature) Speed Up Robust Feature) calculate
Method extracts image characteristic point, utilizes the local maximum of approximation Hessian matrix determinant to detect in two width images and has Gao Chong
Characteristic point in the position of multiplicity;
B) characteristic point describes: response to single order Haar small echo in the horizontal and vertical directions, SURF algorithm pair according to image
The principal direction of characteristic point is determined, utilize simultaneously grayscale distribution information in a certain little neighborhood of characteristic point formed describe son to
Amount;
C) characteristic point and images match: carry out characteristic point according to Euclidean distance or mahalanobis distance and describe the coupling of operator, find out
The correspondence position of point to be matched, so that it is determined that transformation relation between adjacent two width images, estimates that the mathematics of two width images becomes simultaneously
Die change type;
D) image co-registration, merges the image with overlapping region, obtains the seamless image splicing seamlessly transitted.Due to
Normal image can only reflect people's image at the visual angle in some direction of fixed view, and can not be left before and after a scene
The right side is presented in observer at the moment with covering all at one glance.It is thus desirable to certain center chosen in scene is fixed view, observe whole
Individual scene, and by the image record of scene around on the environment mapping sphere centered by this point or cube face, real
In the way of panoramic picture, the scene description at its center viewpoint is provided on border.
According to the difference of projection pattern, projection model can be divided into: spherical projection, cubic projection and cylindrical surface projecting,
In the present invention, it is preferred to employing cylindrical surface projecting mode.
Aforesaid step 1) in a) obtain image, be to utilize common digital camera in fixed view, prevent as far as possible
The deflection of camera lens and pitching, rotating a circle in the horizontal direction obtains a series of border and has the continuous of to a certain degree overlapping region
Image sequence.
Cylindrical panoramic image is through seamless spliced technology these images, projects to cylinder space coordinates.Cylindrical panoramic image
Generation mainly comprise three below step: 1. pair topography carries out cylindrical surface projecting, 2. according to the dependency of pixel to two
Width overlap projection picture determines overlapped scope and mates, and 3. splices the image that two width are overlapping.
In step 2) in, need first to select one or more controllable dot in original panoramic figure, such as curtain, light fixture, TV
Machine etc..The selected of controllable dot can be in the way of using manually or automatically.
Adopt manually, can use existing, as first touch display screen in monitoring system (can also be
Computer display, now can pass through mouse or keyboard operation) on set up coordinate system, drag virtual view-finder controlled to certain
Point, virtual view-finder can be square, circular etc.;Calculate the coordinate of the most virtual view-finder, when virtual view-finder is square,
Calculate two coordinates on summit on diagonal, as controllable dot corresponding area coordinate scope, when virtual view-finder is circular,
Calculate central coordinate of circle and radius, as controllable dot corresponding area coordinate scope;Then, virtual view-finder is dragged to next
Individual controllable dot, calculates area coordinate scope now, constantly repeats, until selected all of controllable dot, by these controllable dot
Area coordinate scope stores, and sets up coordinate database.
The foregoing is only the preferred embodiment of the present invention, it is noted that for those of ordinary skill in the art
Speech, without departing under the principle premise of the present invention, it is also possible to make various deformation and improvement, this also should be considered as the guarantor of the present invention
Protect scope.
Claims (5)
1. an intelligent home system control method, it is characterised in that comprise the steps:
1) establishment of original panoramic figure:
A) image is obtained: the original household image transmitting of shooting is to Intelligent home monitoring system;
B) Image semantic classification;
C) image mosaic: carry out seamless spliced by pretreated image, is then converted into curved panoramic by spliced image
Figure;
2) create controlled coordinate storehouse: selected controllable dot, set the type of each controllable dot, calculate the district corresponding to each controllable dot
Territory coordinate range, to described area coordinate scope creation coordinate database;
3) acquisition of real time imaging: shoot real-time household image, and be transferred to Intelligent home monitoring system;
4) process of real time imaging: real time imaging is carried out pretreatment, and pretreated real time imaging is carried out seamless spelling
Connect, be then converted into curved panoramic figure;
5) pattern match: real time panoramic figure is overlapped with original panoramic figure, mates so that each picture of real time panoramic figure
Element and the pixel one_to_one corresponding of original panoramic figure;
6) controllable dot is activated: selection control point on real time panoramic figure, the coordinate of the current control point selected by calculating, and will
The coordinate of described current control point compares with described coordinate database, if the coordinate of described current control point is in coordinate database
In the range of, then obtain the current state of corresponding controllable dot, carry out corresponding action;If the coordinate of described current control point exists
Outside the scope of coordinate database, the most do not take action.
2. the intelligent home system control method as described in claim 1, it is characterised in that described original household image or reality
Shi Jiaju image seamless spliced, comprises the following steps:
A) feature point detection: extract image characteristic point based on SURF algorithm, utilizes the office of approximation Hessian matrix determinant
Portion's maximum detects in two width images has the characteristic point in the position of high multiplicity;
B) characteristic point describes: response to single order Haar small echo in the horizontal and vertical directions, SURF algorithm pair according to image
The principal direction of characteristic point is determined, utilize simultaneously grayscale distribution information in a certain little neighborhood of characteristic point formed describe son to
Amount;
C) characteristic point and images match: carry out characteristic point according to Euclidean distance or mahalanobis distance and describe the coupling of operator, find out
The correspondence position of point to be matched, so that it is determined that transformation relation between adjacent two width images, estimates that the mathematics of two width images becomes simultaneously
Die change type;
D) image co-registration: merged by the image with overlapping region, obtains the seamless image splicing seamlessly transitted.
3. the intelligent home system control method as described in claim 1 or 2, it is characterised in that in step 2) in, selected
Controllable dot is adopted manually, drags virtual view-finder to each controllable dot, thus calculates the coordinate range of virtual view-finder
As corresponding area coordinate scope.
4. the intelligent home system control method as described in claim 1 or 2, it is characterised in that in step 2) in, selected
Controllable dot uses automatic mode, in step 1) obtain after original panoramic figure, controlled household is switched to and step 1) in
Relative state, obtains contrast panorama sketch by same method, original panoramic figure and contrast panorama sketch is made correlation operation, takes
Obtain original panoramic figure and the difference of contrast panorama sketch, obtain each controllable dot.
5. the intelligent home system control method as described in claim 1 or 2, it is characterised in that in step 6) in, obtain
The method of the current state of corresponding controllable dot, by each controlled home habitation monitoring voltage, electric current or feedback of status, it is judged that current
State, and this status information is mated with corresponding controllable dot.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610532818.7A CN106054646A (en) | 2016-07-08 | 2016-07-08 | Intelligent household control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610532818.7A CN106054646A (en) | 2016-07-08 | 2016-07-08 | Intelligent household control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106054646A true CN106054646A (en) | 2016-10-26 |
Family
ID=57185650
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610532818.7A Pending CN106054646A (en) | 2016-07-08 | 2016-07-08 | Intelligent household control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106054646A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112462616A (en) * | 2020-11-02 | 2021-03-09 | 青岛海尔空调器有限总公司 | Control method and control device for shared household electrical appliance |
CN114740749A (en) * | 2022-05-24 | 2022-07-12 | 广东顺德胜上智能家居有限公司 | Intelligent household control system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003036403A1 (en) * | 2001-10-26 | 2003-05-01 | Kajima Corporation | Facility control monitor method and facility control monitor apparatus |
CN103020941A (en) * | 2012-12-28 | 2013-04-03 | 昆山市工业技术研究院有限责任公司 | Panoramic stitching based rotary camera background establishment method and panoramic stitching based moving object detection method |
CN103294024A (en) * | 2013-04-09 | 2013-09-11 | 宁波杜亚机电技术有限公司 | Intelligent home system control method |
CN105678719A (en) * | 2014-11-20 | 2016-06-15 | 深圳英飞拓科技股份有限公司 | Panoramic stitching seam smoothing method and panoramic stitching seam smoothing device |
CN105676652A (en) * | 2014-11-20 | 2016-06-15 | 无锡美诺塑业有限公司 | Smart home system control method |
-
2016
- 2016-07-08 CN CN201610532818.7A patent/CN106054646A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003036403A1 (en) * | 2001-10-26 | 2003-05-01 | Kajima Corporation | Facility control monitor method and facility control monitor apparatus |
CN103020941A (en) * | 2012-12-28 | 2013-04-03 | 昆山市工业技术研究院有限责任公司 | Panoramic stitching based rotary camera background establishment method and panoramic stitching based moving object detection method |
CN103294024A (en) * | 2013-04-09 | 2013-09-11 | 宁波杜亚机电技术有限公司 | Intelligent home system control method |
CN105678719A (en) * | 2014-11-20 | 2016-06-15 | 深圳英飞拓科技股份有限公司 | Panoramic stitching seam smoothing method and panoramic stitching seam smoothing device |
CN105676652A (en) * | 2014-11-20 | 2016-06-15 | 无锡美诺塑业有限公司 | Smart home system control method |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112462616A (en) * | 2020-11-02 | 2021-03-09 | 青岛海尔空调器有限总公司 | Control method and control device for shared household electrical appliance |
CN112462616B (en) * | 2020-11-02 | 2022-10-28 | 青岛海尔空调器有限总公司 | Control method and control device for shared household electrical appliance |
CN114740749A (en) * | 2022-05-24 | 2022-07-12 | 广东顺德胜上智能家居有限公司 | Intelligent household control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103294024B (en) | Intelligent home system control method | |
US10157477B2 (en) | Robust head pose estimation with a depth camera | |
CN110166685B (en) | Intelligent guidance for capturing digital images aligned with a target image model | |
US10694146B2 (en) | Video capture systems and methods | |
CN105676652A (en) | Smart home system control method | |
US10026017B2 (en) | Scene labeling of RGB-D data with interactive option | |
US10755438B2 (en) | Robust head pose estimation with a depth camera | |
WO2020125499A1 (en) | Operation prompting method and glasses | |
JP5966510B2 (en) | Information processing system | |
CN102638653B (en) | Automatic face tracing method on basis of Kinect | |
US20210232858A1 (en) | Methods and systems for training an object detection algorithm using synthetic images | |
US11087561B2 (en) | Three-dimensional sketching in mobile augmented reality | |
CN107665508A (en) | Realize the method and system of augmented reality | |
Schütt et al. | Semantic interaction in augmented reality environments for microsoft hololens | |
CN106054646A (en) | Intelligent household control method | |
Bhuiyan et al. | On tracking of eye for human-robot interface | |
Narducci et al. | Enabling consistent hand-based interaction in mixed reality by occlusions handling | |
Liu | Semantic mapping: a semantics-based approach to virtual content placement for immersive environments | |
CN113434046A (en) | Three-dimensional interaction system, method, computer device and readable storage medium | |
Yücel et al. | Resolution of focus of attention using gaze direction estimation and saliency computation | |
CN103903269A (en) | Structural description method and system of dome camera monitor video | |
US10845888B2 (en) | Techniques for integrating different forms of input with different forms of output when interacting with an application | |
CN115769182A (en) | Intelligent interactive panel and brightness adjusting method thereof | |
CN113778233A (en) | Method and device for controlling display equipment and readable medium | |
Song et al. | Real-time 3D finger pointing for an augmented desk |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161026 |
|
WD01 | Invention patent application deemed withdrawn after publication |