CN109634410A - Unmanned plane photographic method and system based on gesture identification - Google Patents
Unmanned plane photographic method and system based on gesture identification Download PDFInfo
- Publication number
- CN109634410A CN109634410A CN201811437404.1A CN201811437404A CN109634410A CN 109634410 A CN109634410 A CN 109634410A CN 201811437404 A CN201811437404 A CN 201811437404A CN 109634410 A CN109634410 A CN 109634410A
- Authority
- CN
- China
- Prior art keywords
- gesture
- image
- unmanned plane
- identification
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- 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
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of unmanned plane photographic method and system based on gesture identification, comprising: image acquisition step: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;Image processing step: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains gesture area, is denoted as the second image;Gesture identification step: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;Unmanned plane operating procedure: meaning is stated based on gesture, carries out unmanned plane operation.Gesture operation and unmanned plane are combined, realize the relevant operation by gesture operation realization to unmanned plane, and then take pictures for user, reduces operation hand-held remote controller and carries the unfavorable property of hand-held remote controller.
Description
Technical field
The present invention relates to computer visions and unmanned plane combination field, and in particular, to a kind of nothing based on gesture identification
Man-machine photographic method and system.
Background technique
For current unmanned plane market, there is the unmanned planes for serving various industries.Come with rotor wing unmanned aerial vehicle
Say, it is small in size due to there is, it is light-weight the advantages that, and can have with VTOL and be widely applied very much market, but right
For this unmanned plane, remote control is generally required to control the operation of related unmanned plane, and this hand-held remote controller often needs
It carries, this also brings inconvenience to users, and may not too much be suitble to so as to cause it in certain occasions.
It is most of to be taken pictures using self-shooting bars for current self-timer technology, due to self-shooting bar limited length, because
This, also results in the visual field of shooting and sees certain locality.Therefore, it based on by the technology of unmanned plane and combination of taking pictures, just answers
With in actual demand, preferably solves the problems, such as the visual field of taking pictures.
For the technology combined with unmanned plane that will take pictures, presently, there are certain drawbacks, as noted earlier
, need user to pass through hand-held remote controller to control unmanned plane, it is relatively cumbersome, the carrying of hand-held remote controller there is also it is certain not
Benefit.Based on this, if gesture is combined with unmanned plane operation, realizes that unmanned plane reads the gesture of user, carry out executing related behaviour
Make, does not need the participation of hand-held remote controller, the convenience that user uses can be substantially increased.
Patent document CN107861683A discloses a kind of unmanned plane button-free operating method and device, the method packet
It includes: obtaining touch event of the user on the touch screen of button-free;Gesture identification is carried out to the touch event, obtains the touching
Touch gesture-type represented by event;Telecommand, institute are sent to unmanned plane according to the corresponding object run of the gesture-type
It states telecommand and is used to indicate the unmanned plane execution object run.User does not have to that unmanned plane can be operated by button, operates
Simply, the probability of unmanned plane maloperation is reduced.Above patent document needs in the combination that gesture identification and unmanned plane operate
Using the touch screen of button-free, unmanned plane can not directly be identified gesture, have certain limitation.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of unmanned plane side of taking pictures based on gesture identification
Method and system.
A kind of unmanned plane photographic method based on gesture identification provided according to the present invention, comprising:
Image acquisition step: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing step: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains in one's hands
Gesture region is denoted as the second image;
Gesture identification step: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operating procedure: meaning is stated based on gesture, carries out unmanned plane operation.
Preferably, the unmanned plane photographic method based on gesture identification, further includes real-time detection step: setting time
The gap periods of point enable the camera of unmanned plane carry out Image Acquisition at time point, and persistently carry out image in gap periods
Acquisition.
Preferably, described image processing step includes:
Picture depth acquisition step: carrying out graphic analyses by the pixel value to the first image, obtains distinguishing gesture area
Threshold value;
Area information extraction step: building single channel image is based on threshold value, classifies to the pixel value of the first image,
If pixel value is greater than threshold value, the corresponding points in single channel image are set to non-gesture area, it otherwise, then will be in single channel image
Corresponding points be set to gesture area, by after processing single channel image be denoted as the second image.
Preferably, the gesture identification step includes:
Characteristic extraction step: Hu matrix operation is used to the second image, invariant moment features amount is obtained, by invariant moment features amount
It is combined, forms gesture feature vector;
Identification step: being based on gesture feature vector, calculates several between each images of gestures in the second image and gesture library
To there is what characteristic distance the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
A kind of unmanned plane camera system based on gesture identification provided according to the present invention, comprising:
Image capture module: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing module: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains in one's hands
Gesture region is denoted as the second image;
Gesture recognition module: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operation module: meaning is stated based on gesture, carries out unmanned plane operation.
Preferably, the unmanned plane camera system based on gesture identification, further includes real-time detection module: setting time
Interval, enables the camera of unmanned plane persistently carry out Image Acquisition in the time interval.
Preferably, described image processing module includes:
Picture depth acquisition module: carrying out graphic analyses by the pixel value to the first image, obtains distinguishing gesture area
Threshold value;
Area information extraction module: building single channel image is based on threshold value, classifies to the pixel value of the first image,
If pixel value is greater than threshold value, the corresponding points in single channel image are set to non-gesture area, it otherwise, then will be in single channel image
Corresponding points be set to gesture area, by after processing single channel image be denoted as the second image.
Preferably, the gesture recognition module includes:
Characteristic extracting module: Hu matrix operation is used to the second image, invariant moment features amount is obtained, by invariant moment features amount
It is combined, forms gesture feature vector;
Identification module: being based on gesture feature vector, calculates several between each images of gestures in the second image and gesture library
To there is what characteristic distance the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
Preferably, in the gesture library include 5 in images of gestures, respectively finger refers to upwards, finger refers to downwards, finger to
Left finger, finger refers to the right, finger shows V word moulding;The unmanned plane is provided with control device, if gesture statement meaning is finger
Refer to upwards, then control device control unmanned plane flies upwards;If gesture statement meaning is that finger refers to downwards, control device control
Unmanned plane flies downwards;If gesture statement meaning is that finger refers to the left, control device control unmanned plane flies to the left;If gesture
Statement meaning is that finger refers to the right, then control device control unmanned plane flies to the right;If gesture statement meaning is that finger shows V word
Moulding, then control device control unmanned plane is taken pictures;Otherwise, then unmanned plane remains stationary.
Preferably, the camera uses depth transducer;The unmanned plane is provided with visible light camera, depth sensing
Device, it is seen that for light video camera for taking pictures, depth transducer is used for Image Acquisition.
Compared with prior art, the present invention have it is following the utility model has the advantages that
Gesture operation and unmanned plane are combined, realize the relevant operation by gesture operation realization to unmanned plane, into
And be that user takes pictures, reduce operation hand-held remote controller and carries the unfavorable property of hand-held remote controller.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is system flow schematic diagram of the invention.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
As shown in Figure 1, a kind of unmanned plane photographic method based on gesture identification provided according to the present invention, comprising:
Image acquisition step: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing step: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains in one's hands
Gesture region is denoted as the second image;
Gesture identification step: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operating procedure: meaning is stated based on gesture, carries out unmanned plane operation.
Preferably, unmanned plane uses rotor wing unmanned aerial vehicle.
Specifically, the unmanned plane photographic method based on gesture identification, further includes real-time detection step: setting time
The gap periods of point enable the camera of unmanned plane carry out Image Acquisition at time point, and persistently carry out image in gap periods
Acquisition.
Specifically, described image processing step includes:
Picture depth acquisition step: carrying out graphic analyses by the pixel value to the first image, obtains distinguishing gesture area
Threshold value;
Area information extraction step: building single channel image is based on threshold value, classifies to the pixel value of the first image,
If pixel value is greater than threshold value, the corresponding points in single channel image are set to non-gesture area, it otherwise, then will be in single channel image
Corresponding points be set to gesture area, by after processing single channel image be denoted as the second image.
Specifically, the gesture identification step includes:
Characteristic extraction step: Hu matrix operation is used to the second image, invariant moment features amount is obtained, by invariant moment features amount
It is combined, forms gesture feature vector;
Identification step: being based on gesture feature vector, calculates several between each images of gestures in the second image and gesture library
To there is what characteristic distance the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
A kind of computer readable storage medium for being stored with computer program provided according to the present invention, the computer journey
The step of above-mentioned method is realized when sequence is executed by processor.
A kind of unmanned plane camera system based on gesture identification provided according to the present invention, comprising:
Image capture module: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing module: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains in one's hands
Gesture region is denoted as the second image;
Gesture recognition module: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operation module: meaning is stated based on gesture, carries out unmanned plane operation.
Specifically, the unmanned plane camera system based on gesture identification, further includes real-time detection module: setting time
Interval, enables the camera of unmanned plane persistently carry out Image Acquisition in the time interval.
Specifically, described image processing module includes:
Picture depth acquisition module: carrying out graphic analyses by the pixel value to the first image, obtains distinguishing gesture area
Threshold value;
Area information extraction module: building single channel image is based on threshold value, classifies to the pixel value of the first image,
If pixel value is greater than threshold value, the corresponding points in single channel image are set to non-gesture area, it otherwise, then will be in single channel image
Corresponding points be set to gesture area, by after processing single channel image be denoted as the second image.
Specifically, the gesture recognition module includes:
Characteristic extracting module: Hu matrix operation is used to the second image, invariant moment features amount is obtained, by invariant moment features amount
It is combined, forms gesture feature vector;
Identification module: being based on gesture feature vector, calculates several between each images of gestures in the second image and gesture library
To there is what characteristic distance the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
Specifically, in the gesture library include 5 in images of gestures, respectively finger refers to upwards, finger refers to downwards, finger to
Left finger, finger refers to the right, finger shows V word moulding;The unmanned plane is provided with control device, if gesture statement meaning is finger
Refer to upwards, then control device control unmanned plane flies upwards;If gesture statement meaning is that finger refers to downwards, control device control
Unmanned plane flies downwards;If gesture statement meaning is that finger refers to the left, control device control unmanned plane flies to the left;If gesture
Statement meaning is that finger refers to the right, then control device control unmanned plane flies to the right;If gesture statement meaning is that finger shows V word
Moulding, then control device control unmanned plane is taken pictures;Otherwise, then unmanned plane remains stationary.
Specifically, the camera uses depth transducer;The unmanned plane is provided with visible light camera, depth sensing
Device, it is seen that for light video camera for taking pictures, depth transducer is used for Image Acquisition.
Unmanned plane camera system provided by the invention based on gesture identification, can pass through the unmanned plane based on gesture identification
The step process of photographic method is realized.Unmanned plane photographic method based on gesture identification can be interpreted as by those skilled in the art
The preference of the unmanned plane camera system based on gesture identification.
Below in conjunction with preference, the present invention is further elaborated.
Preferably, it in image acquisition step, rotates in unmanned plane, is mounted with that a visible light camera and a depth pass
Sensor is denoted as P respectively1、P2.Wherein, P1It takes pictures for profession to user, P2For acquiring image, to be below from image
The concrete meaning of user gesture is analyzed, and then operates unmanned plane and lays the foundation.When starting unmanned plane switch, the depth of unmanned plane
Sensor P2, just real-time image acquisition then calls visible light to take the photograph when the meaning for having analyzed gesture expression needs to take pictures
Camera P1It takes pictures.
Preferably, in image processing step, the image mainly got to last step, which is split, extracts gesture
Region, specific execution is as follows, firstly, depth transducer sampling depth information: for a user, all relative to its hand area
Interference is all can be regarded as in other regions (other regions of human body and background area) in domain, therefore the extraction of hand region is caused
Interference.Based on this, we tentatively judge hand region using depth transducer.In the collected pictorial information of depth transducer
In, the value of each pixel indicates the pixel with a distance from depth transducer.Therefore, if some object is from the depth
Sensor is remoter, then in depth transducer acquired image, the pixel value of the corresponding pixel of the object in the picture is got over
Greatly, since hand region and other non-hand regions (human region and background area) are different with a distance from unmanned plane (general
For, all it is that hand region is closer from unmanned plane), therefore, hand region can be analyzed by depth transducer.(1) it obtains
Depth information image.For current time i, what depth transducer obtained arrives image MiFor, obtain its image pixel value most
Big value and minimum value, are denoted as respectivelyWith(2) histogram is drawn.Each pixel value of present image is traversed, and is established
Histogram.The abscissa of histogram is the range of pixel value size, i.e.,Ordinate refers to current abscissa institute
The number that the pixel value of representative occurs in present image.(3) threshold value k is found.Histogram is analyzed, it is huge to find the variation of ordinate value
Abscissa value corresponding to big that point, then current abscissa value is exactly the threshold value k of hand region segmentation;Then, hand area
Domain information extracts: (1) constructing a single channel image Pi, the pixel value of image is 0 or 1, PiSize and image MiGreatly
It is small consistent.(2) hand region: point analysis image M pixel-by-pixel is extractediIf the pixel value being located at point (x, y) is greater than threshold value k,
Then in image PiPoint (x, y) at pixel value be set to 0, be expressed as non-hand region, its pixel value be otherwise placed in 1, is expressed as
Hand region.To the complete image M of point analysis pixel-by-pixeliAfterwards, image PiIn, all white areas (region that pixel value is 1), then table
Show hand region, black region (region that pixel value is 0) indicates non-hand region.
Preferably, in gesture identification step, for the image after image processing step post-processing, gesture knowledge is carried out
Not, show that the meaning that its gesture represents, specific implementation details are as follows: for current time at moment i, we have obtained hand
Area image Pi, fetch down, it would be desirable to it be identified, gesture expression meaning is further analyzed.In this link, I
Main definitions 5 kinds of gestures, content it is relatively easy: finger refers to upwards, finger refers to downwards, finger refers to the left, finger refers to the right,
And finger shows V word moulding.Firstly, carrying out feature extraction, the feature of gesture identification is regarded using the Hu matrix of image, specifically
Details is as follows: for piece image f (x, y), size is M × N, then its p+q rank geometric moment mpqWith central moment μpq
Respectively as shown in formula (1), (2), it is located at the pixel value at coordinate points (x, y) and is denoted as f (x, y).In addition, i'=m10/m00, j'
=m01/m00.It is influenced to eliminate image scaled variation bring, definition normalization central moment ηpqAs shown in formula (3).
Following 4 constant square groups (Φ 1, Φ 4) can be exported using the central moment of second order and three rank specifications, respectively as public
Shown in formula (4)-(7).
Φ 1=η20+η02 (4)
Φ 3=(η20-3η12)2+3(η21-η03)2 (6)
Φ 4=(η30+η12)2+(η21+η03)2 (7)
The above constant square group remains unchanged when the variation of image translation, rotation and ratio, and therefore, we utilize
The feature vector that this four invariant moment features amounts form gesture is (Φ1,Φ2,Φ3,Φ4), to realize the identification of gesture;So
Afterwards, gesture identification is carried out: the geometrical characteristic distance D in the images of gestures and gesture library of input between any one images of gesturesm
Can as shown in formula (8), whereinFor input picture PiGeometric moment component, GjFor images of gestures I in gesture library(l)Accordingly
Geometric moment component, l are the images of gestures sum that gesture library possesses, ωiFor component adjustment factor, belong to empirical value, in order to adjust
Each square number of components magnitude is inconsistent in section feature vector.By final geometrical characteristic distance, different hands may finally be realized
Identification between gesture.
As the geometrical characteristic distance D in known input images of gestures and gesture library between any one images of gesturesmLater,
Then find DmGesture GE in value gesture library corresponding when minimum, then the input gesture also just corresponds to gesture GE, thus
Realize final gesture identification.
Preferably, in unmanned plane operating procedure, according to the gesture that gesture identification step analyzes, to carry out unmanned plane
Operation.For the gesture that present analysis goes out: (1) finger refers to upwards, then the included control module of unmanned plane, controls nobody
Machine flies upwards;(2) finger refers to downwards, then the included control module of unmanned plane, and control unmanned plane flies downwards;(3) finger to
Left finger, then the included control module of unmanned plane, control unmanned plane fly to the left;(4) finger refers to the right, then the included control of unmanned plane
Molding block, control unmanned plane fly to the right;(5) finger shows V word moulding, then the included control module of unmanned plane, controls nobody
Machine is taken pictures;(6) other situations, unmanned plane then remain stationary.
Preferably, in real-time detection step, it is operated when the gesture for having analyzed some moment user, and to unmanned plane
Afterwards, with greater need for the gesture of real-time detection user, thus the control implemented to unmanned plane.The depth that unmanned plane carries is passed
For sensor, many images can be shot in 1s if all analyzed all images in this 1s, is still
It is not necessary to, because in 1s, the gesture of user has little time that too many variation occurs, it is based on this, we are when 1000
Between unit, successively execute image acquisition step, image processing step, gesture identification step, unmanned plane operating procedure.If current
Moment i acquires an image, and analyzes, then acquisition image is moment i+1000 next time, and so on, thus most
The real-time operation to unmanned plane is completed eventually.
One skilled in the art will appreciate that in addition to realizing system provided by the invention in a manner of pure computer readable program code
It, completely can be by the way that method and step be carried out programming in logic come so that provided by the invention other than system, device and its modules
System, device and its modules are declined with logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion
The form of controller etc. realizes identical program.So system provided by the invention, device and its modules may be considered that
It is a kind of hardware component, and the knot that the module for realizing various programs for including in it can also be considered as in hardware component
Structure;It can also will be considered as realizing the module of various functions either the software program of implementation method can be Hardware Subdivision again
Structure in part.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (10)
1. a kind of unmanned plane photographic method based on gesture identification characterized by comprising
Image acquisition step: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing step: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains gesture area
Domain is denoted as the second image;
Gesture identification step: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operating procedure: meaning is stated based on gesture, carries out unmanned plane operation.
2. the unmanned plane photographic method according to claim 1 based on gesture identification, which is characterized in that further include examining in real time
Step: the gap periods of setting time point is surveyed, enables the camera of unmanned plane carry out Image Acquisition at time point, and in gap periods
Inside persistently carry out Image Acquisition.
3. the unmanned plane photographic method according to claim 1 based on gesture identification, which is characterized in that described image processing
Step includes:
Picture depth acquisition step: carrying out graphic analyses by the pixel value to the first image, obtains the threshold for distinguishing gesture area
Value;
Area information extraction step: building single channel image is based on threshold value, classifies to the pixel value of the first image, if picture
Element value is greater than threshold value, then the corresponding points in single channel image is set to non-gesture area, otherwise, then by pair in single channel image
It should put and be set to gesture area, be denoted as the second image for single channel image is obtained after processing.
4. the unmanned plane photographic method according to claim 1 based on gesture identification, which is characterized in that the gesture identification
Step includes:
Characteristic extraction step: Hu matrix operation is used to the second image, invariant moment features amount is obtained, invariant moment features amount is carried out
Combination forms gesture feature vector;
Identification step: being based on gesture feature vector, and the geometry calculated between each images of gestures in the second image and gesture library is special
Distance is levied, will there is the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
5. a kind of unmanned plane camera system based on gesture identification characterized by comprising
Image capture module: user area Image Acquisition is carried out by the camera of unmanned plane, obtains the first image;
Image processing module: enabling the first image be handled, and is partitioned into the binary image with gesture area, obtains gesture area
Domain is denoted as the second image;
Gesture recognition module: establishing gesture library, and the second image is enabled to carry out gesture identification, obtains gesture statement meaning;
Unmanned plane operation module: meaning is stated based on gesture, carries out unmanned plane operation.
6. the unmanned plane camera system according to claim 5 based on gesture identification, which is characterized in that further include examining in real time
Module: the gap periods of setting time point is surveyed, enables the camera of unmanned plane carry out Image Acquisition at time point, and in gap periods
Inside persistently carry out Image Acquisition.
7. the unmanned plane camera system according to claim 5 based on gesture identification, which is characterized in that described image processing
Module includes:
Picture depth acquisition module: carrying out graphic analyses by the pixel value to the first image, obtains the threshold for distinguishing gesture area
Value;
Area information extraction module: building single channel image is based on threshold value, classifies to the pixel value of the first image, if picture
Element value is greater than threshold value, then the corresponding points in single channel image is set to non-gesture area, otherwise, then by pair in single channel image
It should put and be set to gesture area, be denoted as the second image for single channel image is obtained after processing.
8. the unmanned plane camera system according to claim 5 based on gesture identification, which is characterized in that the gesture identification
Module includes:
Characteristic extracting module: Hu matrix operation is used to the second image, invariant moment features amount is obtained, invariant moment features amount is carried out
Combination forms gesture feature vector;
Identification module: being based on gesture feature vector, and the geometry calculated between each images of gestures in the second image and gesture library is special
Distance is levied, will there is the images of gestures of minimum geometrical characteristic distance to state meaning as gesture.
9. described in the unmanned plane photographic method or claim 5 according to claim 1 based on gesture identification based on
The unmanned plane camera system of gesture identification, which is characterized in that in the gesture library include 5 in images of gestures, respectively finger to
Upper finger, finger refers to downwards, finger refers to the left, finger refers to the right, finger shows V word moulding;
The unmanned plane is provided with control device, if gesture statement meaning is that finger refers to upwards, control device controls unmanned plane
Flight upwards;If gesture statement meaning is that finger refers to downwards, control device control unmanned plane flies downwards;If gesture statement contains
Justice is that finger refers to the left, then control device control unmanned plane flies to the left;If gesture statement meaning is that finger refers to the right, control
Device control unmanned plane flies to the right;If gesture statement meaning is that finger shows V word moulding, control device control unmanned plane into
Row is taken pictures;Otherwise, then unmanned plane remains stationary.
10. described in the unmanned plane photographic method or claim 5 according to claim 1 based on gesture identification based on
The unmanned plane camera system of gesture identification, which is characterized in that the camera uses depth transducer;The unmanned plane is provided with
Visible light camera, depth transducer, it is seen that for light video camera for taking pictures, depth transducer is used for Image Acquisition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437404.1A CN109634410A (en) | 2018-11-28 | 2018-11-28 | Unmanned plane photographic method and system based on gesture identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437404.1A CN109634410A (en) | 2018-11-28 | 2018-11-28 | Unmanned plane photographic method and system based on gesture identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109634410A true CN109634410A (en) | 2019-04-16 |
Family
ID=66069712
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811437404.1A Pending CN109634410A (en) | 2018-11-28 | 2018-11-28 | Unmanned plane photographic method and system based on gesture identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109634410A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221729A (en) * | 2021-05-10 | 2021-08-06 | 北京航空航天大学 | Unmanned aerial vehicle cluster control method and system based on gesture human-computer interaction |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661556A (en) * | 2009-09-25 | 2010-03-03 | 哈尔滨工业大学深圳研究生院 | Static gesture identification method based on vision |
CN105223957A (en) * | 2015-09-24 | 2016-01-06 | 北京零零无限科技有限公司 | A kind of method and apparatus of gesture manipulation unmanned plane |
CN106980372A (en) * | 2017-03-24 | 2017-07-25 | 普宙飞行器科技(深圳)有限公司 | A kind of unmanned plane control method and system without ground control terminal |
CN107831791A (en) * | 2017-11-17 | 2018-03-23 | 南方科技大学 | A kind of control method of unmanned plane, device, controlling equipment and storage medium |
CN108128455A (en) * | 2017-11-30 | 2018-06-08 | 广州市华科尔科技股份有限公司 | A kind of multi-rotor unmanned aerial vehicle control method |
CN108255298A (en) * | 2017-12-29 | 2018-07-06 | 安徽慧视金瞳科技有限公司 | Infrared gesture identification method and equipment in a kind of projection interactive system |
-
2018
- 2018-11-28 CN CN201811437404.1A patent/CN109634410A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661556A (en) * | 2009-09-25 | 2010-03-03 | 哈尔滨工业大学深圳研究生院 | Static gesture identification method based on vision |
CN105223957A (en) * | 2015-09-24 | 2016-01-06 | 北京零零无限科技有限公司 | A kind of method and apparatus of gesture manipulation unmanned plane |
CN106980372A (en) * | 2017-03-24 | 2017-07-25 | 普宙飞行器科技(深圳)有限公司 | A kind of unmanned plane control method and system without ground control terminal |
CN107831791A (en) * | 2017-11-17 | 2018-03-23 | 南方科技大学 | A kind of control method of unmanned plane, device, controlling equipment and storage medium |
CN108128455A (en) * | 2017-11-30 | 2018-06-08 | 广州市华科尔科技股份有限公司 | A kind of multi-rotor unmanned aerial vehicle control method |
CN108255298A (en) * | 2017-12-29 | 2018-07-06 | 安徽慧视金瞳科技有限公司 | Infrared gesture identification method and equipment in a kind of projection interactive system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221729A (en) * | 2021-05-10 | 2021-08-06 | 北京航空航天大学 | Unmanned aerial vehicle cluster control method and system based on gesture human-computer interaction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10445562B2 (en) | AU feature recognition method and device, and storage medium | |
US10534957B2 (en) | Eyeball movement analysis method and device, and storage medium | |
CN108717524B (en) | Gesture recognition system based on double-camera mobile phone and artificial intelligence system | |
KR102385463B1 (en) | Facial feature extraction model training method, facial feature extraction method, apparatus, device and storage medium | |
US8792722B2 (en) | Hand gesture detection | |
US8750573B2 (en) | Hand gesture detection | |
CN111062312A (en) | Gesture recognition method, gesture control method, device, medium and terminal device | |
WO2019080203A1 (en) | Gesture recognition method and system for robot, and robot | |
CN109657533A (en) | Pedestrian recognition methods and Related product again | |
US10489636B2 (en) | Lip movement capturing method and device, and storage medium | |
US10650234B2 (en) | Eyeball movement capturing method and device, and storage medium | |
CN103208002A (en) | Method and system used for recognizing and controlling gesture and based on hand profile feature | |
WO2021047587A1 (en) | Gesture recognition method, electronic device, computer-readable storage medium, and chip | |
Nath et al. | Real time sign language interpreter | |
CN107330387B (en) | Pedestrian detection method based on image data | |
WO2017197593A1 (en) | Apparatus, method and computer program product for recovering editable slide | |
CN106919326A (en) | A kind of image searching method and device | |
CN109919128B (en) | Control instruction acquisition method and device and electronic equipment | |
EP2790130A1 (en) | Method for object recognition | |
CN112883827B (en) | Method and device for identifying specified target in image, electronic equipment and storage medium | |
CN109634410A (en) | Unmanned plane photographic method and system based on gesture identification | |
CN112839167A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
CN112861571A (en) | Household appliance control method, control device and computer readable storage medium | |
CN108764289B (en) | Method and system for classifying UI (user interface) abnormal pictures based on convolutional neural network | |
CN113792807B (en) | Skin disease classification model training method, system, medium and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |