CN108032994A - A kind of unmanned helicopter - Google Patents
A kind of unmanned helicopter Download PDFInfo
- Publication number
- CN108032994A CN108032994A CN201711276100.7A CN201711276100A CN108032994A CN 108032994 A CN108032994 A CN 108032994A CN 201711276100 A CN201711276100 A CN 201711276100A CN 108032994 A CN108032994 A CN 108032994A
- Authority
- CN
- China
- Prior art keywords
- equipment
- image
- test
- model
- unmanned helicopter
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C11/00—Propellers, e.g. of ducted type; Features common to propellers and rotors for rotorcraft
- B64C11/46—Arrangements of, or constructional features peculiar to, multiple propellers
- B64C11/48—Units of two or more coaxial propellers
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Stereoscopic And Panoramic Photography (AREA)
Abstract
The present invention provides a kind of unmanned helicopter, including fuselage body, the fuselage body upper end is provided with main rotating-blade propeller, and the both sides of the fuselage body are provided with auxiliary stand, electric propeller is provided with the auxiliary stand, the lower end of the fuselage body is provided with undercarriage.Unmanned helicopter of the present invention is provided with the electric propeller of auxiliary in fuselage body both sides, and assist is good, can assist in the stability of equilibrium of adjustment unmanned helicopter, simple in structure, stablizing effect is good.
Description
Technical field
The present invention relates to a kind of aircraft, more particularly to a kind of unmanned helicopter.
Background technology
Aircraft (flight vehicle) is to be manufactured by the mankind, can fly away from ground, controlled in space flight and by people
The apparatus flying object to fly in endoatmosphere or exoatmosphere space (space).The referred to as aircraft of flight in endoatmosphere,
It is known as spacecraft in space flight.
Unmanned helicopter, its construction is fairly simple, price also than less expensive, what is more important it need not send out at all
Penetrate system, moreover it is possible to VTOL, more can freely hover, and flexibility of flying is quite superb, can with various speed, with each
Fly in the air route of kind flight profile, mission profile.In general flight quality, the important feature of " two small one is high " can be also showed：Shake
Quivering, small, noise is small, and Reliability comparotive is high.Therefore, begun to very early in the country of Helicopter Technology prosperity, pilotless helicopter
Develop.Some existing unmanned helicopters are mostly single rotor tail propeller arrangement, and flying speed is restricted, balance and stability
The more difficult operation of property.
The content of the invention
(1) technical problems to be solved
The technical problem to be solved in the present invention is to provide a kind of electric propeller that auxiliary is provided with fuselage body both sides
, overall be pushed forward the unmanned helicopter good with stablizing effect.
(2) technical solution
In order to solve the above technical problems, the present invention provides a kind of unmanned helicopter, including fuselage body, the fuselage body
Upper end is provided with main rotating-blade propeller, and the both sides of the fuselage body are provided with auxiliary stand, electricity is provided with the auxiliary stand
Dynamic propeller, the lower end of the fuselage body is provided with undercarriage.
Further, further include：Wind-force measuring apparatus, is arranged on the fuselage body, for detecting unmanned helicopter
It is currently located the instant wind-force size of air position；Inclination angle identification equipment, is arranged on the fuselage body, for detecting nobody
The pitch angle of current flight posture during helicopter flight in the air；Embedded processing equipment, is arranged on the fuselage body, point
Be not connected with the wind-force measuring apparatus and the inclination angle identification equipment, for based on the instant wind-force size received by institute
State the pitch angle that the instant wind-force size that the pitch angle of current flight posture is adjusted to and receives matches；Aerial photography is set
It is standby, it is arranged on the chassis of the fuselage body, towards ground, for when unmanned helicopter declines, starting to ground environment
Chassis lower images collection is carried out, to obtain and export chassis lower images；
Further, further include：
Subregion detection device, is arranged on the fuselage body, is connected with the Aerial photography equipment, for receiving
Chassis lower images are stated, determine the signal-to-noise ratio of each subject area in the lower images of chassis, and be based on chassis lower images
The signal-to-noise ratio in middle each object region determines the current signal of whole chassis lower images；
Amount of images determines equipment, is connected with the subregion detection device, for low in the current signal received
When equal to predetermined lower threshold value, selection and the test image of current signal corresponding number test quantity as default, currently
Signal-to-noise ratio is lower, and the quantity of test image is more, and is additionally operable to be higher than predetermined lower threshold value in the current signal received
When, the test image of fixed qty is selected as default test quantity；
Color space conversion equipment, determines that equipment is connected with described image quantity, for each type scene, chooses default
The image of quantity is tested as test image, the test image of all types scene is all transformed into YUV color spaces to obtain
Multiple test color images；
Size adjusting equipment, is connected with color space conversion equipment, for receiving the multiple test color image, to institute
State multiple test color images and perform normalized respectively to obtain multiple standard testing images of fixed dimension；
Feature amount selecting device, is connected with the size adjusting equipment and the subregion detection device, according to current respectively
Signal-to-noise ratio determines the input quantity type of the model of selection, and the input quantity type according to selection carries out each standard testing image
Feature extraction meets input quantity type, the corresponding test feature amount of the standard testing image of selection to obtain, wherein, currently
Signal-to-noise ratio is lower, and the corresponding data processing amount of input quantity type of the model of selection is more；
Model measurement equipment, is connected with the feature amount selecting device, corresponding each for receiving each standard testing image
A test feature amount, each test feature amount is respectively outputted to complete the test of model parameter in model, wherein, model bag
Input layer, hidden layer and output layer are included, the output quantity of the output layer is standard testing image and the matching for presetting photography scene
Degree；
Model performs equipment, is connected respectively with the feature amount selecting device and the subregion detection device, for receiving
Chassis lower images, to chassis lower images successively YUV color space conversions, normalized and input quantity according to selection
The feature extraction of type meets input quantity type, the corresponding identification feature amount of the chassis lower images of selection to obtain, will
Input of the corresponding identification feature amount of the chassis lower images as the input layer of model after training, to pass through model after training
The output quantity of output layer obtains the chassis lower images and the matching degree of default photography scene, when the matching with default photography scene
When degree is more than or equal to preset matching threshold value, scene identification signal is sent；
Wherein, the embedded processing equipment also performs equipment with the model and is connected, for receiving the scene
During identification signal, the decrease speed of unmanned helicopter is adjusted until unmanned helicopter reaches floating state；The model is performed and set
It is standby to be additionally operable to, when the matching degree with default photography scene is less than preset matching threshold value, send the unidentified signal of scene.
(3) beneficial effect
Unmanned helicopter of the present invention is provided with the electric propeller of auxiliary in fuselage body both sides, and assist is good, can
The stability of equilibrium of adjustment unmanned helicopter is assisted, simple in structure, stablizing effect is good.
Brief description of the drawings
Fig. 1 is the structure diagram of unmanned helicopter of the present invention；
Block diagrams of the Fig. 2 between unmanned helicopter equipment of the present invention；
Wherein：1 it is fuselage body, 2 be fuselage body, 3 be auxiliary stand, 4 be electric propeller, 5 is undercarriage.
Embodiment
Refering to Fig. 1 and Fig. 2, the present invention provides a kind of unmanned helicopter, including fuselage body 1, the installation of 1 upper end of fuselage body
There is main rotating-blade propeller 2, the both sides of fuselage body 1 are provided with auxiliary stand 3, electric propeller 4, machine are provided with auxiliary stand 3
The lower end of body body 1 is provided with undercarriage 5.
The present embodiment unmanned helicopter is provided with the electric propeller of auxiliary in fuselage body both sides, and assist is good, energy
Enough stability of equilibrium for assisting adjustment unmanned helicopter, simple in structure, stablizing effect is good.
The application of unmanned helicopter, shooting etc. of particularly finding a view in tracking rescue, high-altitude are convenient.Currently, it is desirable to nothing
People's helicopter can slowly enter stable floating state when reaching ground soon, so as to be rescued, followed the trail of, shoot etc. respectively
Kind operation, however, some existing unmanned helicopters lack effective hovering means, exists and cannot be introduced into hovering pattern
Technical problem, operation is too urgent to cause unmanned helicopter flight shakiness to cause to fall.Therefore, also wrapped refering to Fig. 2, the present embodiment
Include：Wind-force measuring apparatus, is arranged on fuselage body 1, and the instant wind of air position is currently located for detecting unmanned helicopter
Power size；Inclination angle identification equipment, is arranged on fuselage body 1, current flight during for detecting unmanned helicopter flight in the air
The pitch angle of posture；Embedded processing equipment, is arranged on fuselage body 1, is identified respectively with wind-force measuring apparatus and inclination angle
Equipment connect, for based on the instant wind-force size received by the pitch angle of current flight posture be adjusted to and receive i.e.
The pitch angle that Shi Fengli sizes match；Aerial photography equipment, is arranged on the chassis of fuselage body 1, towards ground, for
When unmanned helicopter declines, start and chassis lower images collection is carried out to ground environment, to obtain and export chassis lower images；
Wherein, the present embodiment further includes：
Subregion detection device, is arranged on fuselage body 1, is connected with Aerial photography equipment, for receiving below chassis
Image, determines the signal-to-noise ratio of each subject area in the lower images of chassis, and based on each object in the lower images of chassis
The signal-to-noise ratio in region determines the current signal of whole chassis lower images；
Amount of images determines equipment, is connected with subregion detection device, for the current signal received less than etc.
When predetermined lower threshold value, selection and the test image of current signal corresponding number test quantity, current noise as default
Than lower, the quantity of test image is more, and is additionally operable to when the current signal received is higher than predetermined lower threshold value, choosing
The test image of fixed qty is selected as default test quantity；
Color space conversion equipment, determines that equipment is connected with amount of images, for each type scene, chooses default test
It is multiple to obtain all to be transformed into YUV color spaces as test image by the image of quantity for the test image of all types scene
Test color image；
Size adjusting equipment, is connected with color space conversion equipment, for receiving multiple test color images, to multiple surveys
Examination color image performs normalized to obtain multiple standard testing images of fixed dimension respectively；
Feature amount selecting device, is connected with size adjusting equipment and subregion detection device respectively, true according to current signal
Determine the input quantity type of the model of selection, the input quantity type according to selection carries out feature extraction to each standard testing image
To obtain the input quantity type, the corresponding test feature amount of the standard testing image that meet selection, wherein, current signal is got over
Low, the corresponding data processing amount of input quantity type of the model of selection is more；
Model measurement equipment, is connected with feature amount selecting device, for receiving the corresponding each survey of each standard testing image
Characteristic quantity is tried, each test feature amount is respectively outputted to complete the test of model parameter in model, wherein, model includes defeated
Enter layer, hidden layer and output layer, the output quantity of output layer is standard testing image and the matching degree for presetting photography scene；
Model performs equipment, is connected respectively with feature amount selecting device and subregion detection device, for receiving below chassis
Image, to the spy of chassis lower images successively YUV color space conversions, normalized and input quantity type according to selection
Sign extraction meets input quantity type, the corresponding identification feature amount of the chassis lower images of selection to obtain, by under the chassis
Input of the corresponding identification feature amount of square image as the input layer of model after training, to pass through the output layer of model after training
Output quantity obtains the chassis lower images and the matching degree of default photography scene, when the matching degree with default photography scene is more than etc.
When preset matching threshold value, scene identification signal is sent；
Wherein, embedded processing equipment also performs equipment with model and is connected, for when receiving scene identification signal, adjusting
The decrease speed of whole unmanned helicopter is until unmanned helicopter reaches floating state；Model performs equipment and is additionally operable to take the photograph when with default
When the matching degree of shadow scene is less than preset matching threshold value, the unidentified signal of scene is sent.
The present embodiment realizes unmanned helicopter from rapid decrease by the identification of the shooting scene based on deep neural network
To the switching slowly hovered, the quality of shooting image is improved.Corresponding image recognition is determined based on the corresponding signal-to-noise ratio of image
Pattern so that the image of low signal-to-noise ratio, the identifying processing operation of acquisition is finer, while causes the identification of the image of high s/n ratio
Simplify, accelerate the speed of identifying processing operation；Signal-to-noise ratio based on each object region in image determines working as whole image
Preceding signal-to-noise ratio, improves the efficiency of signal noise ratio (snr) of image judgement；By the identification of the shooting scene based on deep neural network, realize
Unmanned helicopter improves the quality of shooting image from the switching slowly hovered is rapidly dropped to.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, some improvements and modifications can also be made, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. a kind of unmanned helicopter, it is characterised in that including fuselage body (1), fuselage body (1) upper end is provided with main rotation
Propeller (2), the both sides of the fuselage body (1) are provided with auxiliary stand (3), are provided with the auxiliary stand (3) electronic
Propeller (4), the lower end of the fuselage body (1) are provided with undercarriage (5).
2. unmanned helicopter as claimed in claim 1, it is characterised in that further include：Wind-force measuring apparatus, is arranged on the machine
On body body (1), the instant wind-force size of air position is currently located for detecting unmanned helicopter；Inclination angle identification equipment, if
Put on the fuselage body (1), the pitch angle of current flight posture during for detecting unmanned helicopter flight in the air；It is embedded
Formula processing equipment, is arranged on the fuselage body (1), respectively with the wind-force measuring apparatus and the inclination angle identification equipment
Connection, for based on the instant wind-force size received by the pitch angle of the current flight posture be adjusted to and receive i.e.
The pitch angle that Shi Fengli sizes match；Aerial photography equipment, is arranged on the chassis of the fuselage body (1), towards ground,
Chassis lower images collection is carried out to ground environment for when unmanned helicopter declines, starting, to obtain and export under chassis
Square image；
3. unmanned helicopter as claimed in claim 2, it is characterised in that further include：
Subregion detection device, is arranged on the fuselage body (1), is connected with the Aerial photography equipment, for receiving
Chassis lower images are stated, determine the signal-to-noise ratio of each subject area in the lower images of chassis, and be based on chassis lower images
The signal-to-noise ratio in middle each object region determines the current signal of whole chassis lower images；
Amount of images determines equipment, is connected with the subregion detection device, for the current signal received less than etc.
When predetermined lower threshold value, selection and the test image of current signal corresponding number test quantity, current noise as default
Than lower, the quantity of test image is more, and is additionally operable to when the current signal received is higher than predetermined lower threshold value, choosing
The test image of fixed qty is selected as default test quantity；
Color space conversion equipment, determines that equipment is connected with described image quantity, for each type scene, chooses default test
It is multiple to obtain all to be transformed into YUV color spaces as test image by the image of quantity for the test image of all types scene
Test color image；
Size adjusting equipment, is connected with color space conversion equipment, for receiving the multiple test color image, to described more
A test color image performs normalized to obtain multiple standard testing images of fixed dimension respectively；
Feature amount selecting device, is connected with the size adjusting equipment and the subregion detection device, according to current noise respectively
Than the input quantity type of the model of definite selection, the input quantity type according to selection carries out feature to each standard testing image
Extraction meets input quantity type, the corresponding test feature amount of the standard testing image of selection to obtain, wherein, current noise
Than lower, the corresponding data processing amount of input quantity type of the model of selection is more；
Model measurement equipment, is connected with the feature amount selecting device, for receiving the corresponding each survey of each standard testing image
Characteristic quantity is tried, each test feature amount is respectively outputted to complete the test of model parameter in model, wherein, model includes defeated
Enter layer, hidden layer and output layer, the output quantity of the output layer is standard testing image and the matching degree for presetting photography scene；
Model performs equipment, is connected respectively with the feature amount selecting device and the subregion detection device, for receiving chassis
Lower images, to chassis lower images successively YUV color space conversions, normalized and input quantity type according to selection
Feature extraction to obtain input quantity type, the corresponding identification feature amount of the chassis lower images of selection of meeting, by the bottom
Input of the corresponding identification feature amount of disk lower images as the input layer of model after training, to pass through the output of model after training
The output quantity of layer obtains the chassis lower images and the matching degree of default photography scene, when big with the matching degree of default photography scene
When equal to preset matching threshold value, scene identification signal is sent；
Wherein, the embedded processing equipment also performs equipment with the model and is connected, for receiving the scene identification
During signal, the decrease speed of unmanned helicopter is adjusted until unmanned helicopter reaches floating state；The model performs equipment also
For when the matching degree with default photography scene is less than preset matching threshold value, sending the unidentified signal of scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711276100.7A CN108032994A (en) | 2017-12-06 | 2017-12-06 | A kind of unmanned helicopter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711276100.7A CN108032994A (en) | 2017-12-06 | 2017-12-06 | A kind of unmanned helicopter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108032994A true CN108032994A (en) | 2018-05-15 |
Family
ID=62095477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711276100.7A Pending CN108032994A (en) | 2017-12-06 | 2017-12-06 | A kind of unmanned helicopter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108032994A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412488A (en) * | 2013-08-12 | 2013-11-27 | 北京航空航天大学 | Small-sized unmanned rotary-wing aircraft high-precision control method based on adaptive neural network |
| CN103760906A (en) * | 2014-01-29 | 2014-04-30 | 天津大学 | Control method for neural network and nonlinear continuous unmanned helicopter attitude |
| CN205044949U (en) * | 2015-09-21 | 2016-02-24 | 温州乐享科技信息有限公司 | Unmanned aerial vehicle with multiple rotor wings |
| CN105644776A (en) * | 2016-03-17 | 2016-06-08 | 秦建法 | Multi-rotor unmanned helicopter |
| CN106275410A (en) * | 2016-11-17 | 2017-01-04 | 湖南科瑞特科技股份有限公司 | A kind of wind disturbance resistant unmanned plane |
| CN107103600A (en) * | 2017-04-13 | 2017-08-29 | 北京海风智能科技有限责任公司 | A kind of defects of insulator automatic testing method based on machine learning |
| CN107172360A (en) * | 2017-07-06 | 2017-09-15 | 杨顺伟 | Unmanned plane is with shooting method and device |
| CN107392901A (en) * | 2017-07-24 | 2017-11-24 | 国网山东省电力公司信息通信公司 | A kind of method for transmission line part intelligence automatic identification |
-
2017
- 2017-12-06 CN CN201711276100.7A patent/CN108032994A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412488A (en) * | 2013-08-12 | 2013-11-27 | 北京航空航天大学 | Small-sized unmanned rotary-wing aircraft high-precision control method based on adaptive neural network |
| CN103760906A (en) * | 2014-01-29 | 2014-04-30 | 天津大学 | Control method for neural network and nonlinear continuous unmanned helicopter attitude |
| CN205044949U (en) * | 2015-09-21 | 2016-02-24 | 温州乐享科技信息有限公司 | Unmanned aerial vehicle with multiple rotor wings |
| CN105644776A (en) * | 2016-03-17 | 2016-06-08 | 秦建法 | Multi-rotor unmanned helicopter |
| CN106275410A (en) * | 2016-11-17 | 2017-01-04 | 湖南科瑞特科技股份有限公司 | A kind of wind disturbance resistant unmanned plane |
| CN107103600A (en) * | 2017-04-13 | 2017-08-29 | 北京海风智能科技有限责任公司 | A kind of defects of insulator automatic testing method based on machine learning |
| CN107172360A (en) * | 2017-07-06 | 2017-09-15 | 杨顺伟 | Unmanned plane is with shooting method and device |
| CN107392901A (en) * | 2017-07-24 | 2017-11-24 | 国网山东省电力公司信息通信公司 | A kind of method for transmission line part intelligence automatic identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105790155B (en) | A kind of autonomous cruising inspection system of power transmission line unmanned machine and method based on differential GPS | |
| CN109739253B (en) | Aircraft battery monitoring method and device, battery and aircraft | |
| US11021266B2 (en) | Pod operating system for a vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV) | |
| US10436941B2 (en) | Image and/or radio signals capturing platform | |
| CN105235912B (en) | Public security fire-fighting law enforcement collection unmanned plane and its control method of taking photo by plane | |
| US20170225799A1 (en) | Composition and process for applying hydrophobic coating to fibrous substrates | |
| CN106347694B (en) | A kind of Information Acquisition System based near space floating platform | |
| KR102160734B1 (en) | Image taking system using wireless rechargeable drones | |
| CN107820585A (en) | Aircraft landing method, aircraft and computer-readable recording medium | |
| CN203747305U (en) | Miniature quad-rotor unmanned aerial vehicle electric power line infrared patrol inspection system | |
| CN205384516U (en) | Unmanned aerial vehicle rescue system | |
| CN209480012U (en) | A kind of oblique photograph measuring system based on composite wing unmanned plane | |
| CN106628180A (en) | Flight airdropping device and airdropping method thereof | |
| EP3476734A1 (en) | Drone for searching and marking a target | |
| WO2021212832A1 (en) | Dropsonde and reconnaissance system | |
| CN206012982U (en) | A kind of small-sized electric fixed-wing unmanned plane for oblique photograph | |
| CN109649654B (en) | Low-altitude search positioning method | |
| CN108227745A (en) | Unmanned plane method of work and UAV system | |
| US20060208132A1 (en) | Autonomous in-flight refueling system | |
| US11435743B2 (en) | Throwable unmanned aerial vehicle and method of operation | |
| WO2017158326A2 (en) | Image data capturing arrangement | |
| CN109612456B (en) | Low-altitude search positioning system | |
| CN108032994A (en) | A kind of unmanned helicopter | |
| Lewis | Evaluating the use of a low-cost unmanned aerial vehicle platform in acquiring digital imagery for emergency response | |
| CN206782064U (en) | A kind of collapsible rotor wing unmanned aerial vehicle of four axle six |
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: 20180515 |