CN109606678A - A kind of crawler-type unmanned machine being automatically positioned bridge pad - Google Patents
A kind of crawler-type unmanned machine being automatically positioned bridge pad Download PDFInfo
- Publication number
- CN109606678A CN109606678A CN201811396449.9A CN201811396449A CN109606678A CN 109606678 A CN109606678 A CN 109606678A CN 201811396449 A CN201811396449 A CN 201811396449A CN 109606678 A CN109606678 A CN 109606678A
- Authority
- CN
- China
- Prior art keywords
- crawler
- bridge pad
- image
- neural networks
- convolutional neural
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENTS OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENTS OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/08—Arrangements of cameras
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01D—CONSTRUCTION OF BRIDGES, ELEVATED ROADWAYS OR VIADUCTS; ASSEMBLY OF BRIDGES
- E01D19/00—Structural or constructional details of bridges
- E01D19/02—Piers; Abutments ; Protecting same against drifting ice
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Abstract
The invention discloses a kind of crawler-type unmanned machines for being automatically positioned bridge pad, including fuselage, crawler type bracket and attachment device, crawler type bracket includes crawler belt and bracket, bracket includes two frames disposed in parallel, multiple rotating bars are rotatably connected between two frames, crawler belt is set in rotating bar, and fuselage passes through attachment device connection framework；In addition, the crawler-type unmanned machine further includes image capture module and control module, image capture module acquires the image of bridge pad, and control module automatically determines the position of support according to image and controls the relative position of unmanned plane adjust automatically and support.The present invention can relative position between adjust automatically unmanned plane and bridge pad, and improve the stability of unmanned plane.
Description
Technical field
The present invention relates to civil engineering and artificial intelligence interleaving techniques, more particularly to a kind of automatic positioning bridge pad
Crawler-type unmanned machine.
Background technique
With the fast development of infrastructure construction in china in recent years, building industry development is rapid, a large amount of road and bridge
Construction finishes, and consequent is late detection and maintenance work.Bridge pad is the important structure for connecting bridge upper and lower part structure
Part is to count for much where the throat of a bridge block, once there is disease, such as finds and handle not in time, will affect structure
Stress and traffic safety.The detection work main path or artificial detection of bridge pad at present, this method time-consuming,
Arduously and it will affect traffic.It is some build remote mountains in, marine bridge is difficult to realize by the method for artificial detection, or is difficult
Guarantee the safety of bridge machinery personnel.Therefore, there is an urgent need for a kind of dresses for being automatically positioned bridge pad and acquiring support image
It sets.
With the fast development of unmanned air vehicle technique, the application of unmanned plane also more penetrates into all trades and professions, however, existing
Often because there are certain safe distance, shootings between unmanned plane and barrier when shooting support with unmanned plane in technology
When support unmanned plane at a distance from bridge lower surface farther out, this will affect the shooting angle and shooting quality of support, and nobody
The stability of unmanned plane itself can be caused to reduce because of air-flow when machine is close to floorings, the branch of high quality can not be obtained
Seat photo.And when at this stage using unmanned plane shooting bridge pad, the relative position between unmanned plane and bridge pad is adjusted
It all relies on and manually carries out, this method efficiency is lower.
Summary of the invention
Goal of the invention: the object of the present invention is to provide a kind of crawler-type unmanned machines for being automatically positioned bridge pad, can be certainly
Relative position between dynamic adjustment unmanned plane and bridge pad, and improve the stability of unmanned plane.
Technical solution: the crawler-type unmanned machine of automatic positioning bridge pad of the present invention, including fuselage, crawler type branch
Frame and attachment device, crawler type bracket include crawler belt and bracket, and bracket includes two frames disposed in parallel, between two frames
Multiple rotating bars are rotatably connected to, crawler belt is set in rotating bar, and fuselage passes through attachment device connection framework；In addition, the shoe
Belt unmanned plane further includes image capture module and control module, and image capture module acquires the image of bridge pad, controls mould
Root tuber automatically determines the position of support according to image and controls the relative position of unmanned plane adjust automatically and support.
Further, the attachment device is scalable.
Further, the attachment device includes grip part, connecting rod and the fixation being fixedly connected between two frames
Bar, grip part connect one end of connecting line, and connecting rod is equipped with boss, and fixed link is fixedly connected with track, and track is separately connected bullet
One end of spring and one end of adjusting rod, the other end of spring is located at below boss, and the other end of spring is separately connected connecting line
The other end and adjusting rod the other end.
Further, the shape of the grip part is ring-type, and connecting rod is made of elastic material, makes unmanned plane top in this way
With certain shock-absorbing function when floorings bottom.
Further, there are two the tracks, the two sides of connecting rod are located at.
Further, the boss has multiple.
Further, all rotating bars are uniformly distributed in the circumferential direction of two frames.
Further, the control module automatically determines the position of support by convolutional neural networks, convolutional neural networks
Establish the following steps are included:
S1: obtaining the image of bridge pad, adjusts the size of bridge pad image and demarcates the location information of support, to figure
As being pre-processed；
S2: bridge pad image is divided into training set and test set, training set is used for training convolutional neural networks, test
Collection is for testing convolutional neural networks；
S3: establishing convolutional neural networks, including input layer, output layer, convolutional layer and pond layer, convolutional neural networks it is defeated
Value is the location information of support in bridge pad image out；
S4: the support position information demarcated in convolutional neural networks real output value and step S1 is measured by loss function
Between error obtain and by the weight of gradient descent method and each layer of back-propagation algorithm repetitive exercise convolutional neural networks
Convolutional neural networks with automatic positioning bridge pad function.
Further, in the step S1, the calibration of support position information carries out in the following manner: with the upper left corner of picture
Cartesian coordinate system is established for the origin of reference axis, support position draws rectangle frame in picture, with the angle point of rectangle frame
The position of coordinate representation support.
Further, the loss function in the step S4 is mean square error MSE, is obtained according to formula (1):
In formula (1), n is the number of the image of input convolutional neural networks every time；yiFor the output valve of convolutional neural networks,For the support position information demarcated in step S1.
The utility model has the advantages that the invention discloses a kind of crawler-type unmanned machines for being automatically positioned bridge pad, with prior art phase
Than, have it is following the utility model has the advantages that
1) present invention passes through the cooperation of control module and image capture module, being capable of adjust automatically unmanned plane and bridge pad
Between relative position improve efficiency without manually adjusting；
2) present invention passes through the design of crawler type bracket, and unmanned plane is enabled to be located in floorings by crawler type bracket
Lower section；And there are stiction between crawler belt and floorings, and when unmanned plane rolls shooting along floorings, only rotating bar occurs
Rotation, can be improved the stability of unmanned plane in this way.
Detailed description of the invention
Fig. 1 is the structure chart of unmanned plane in the specific embodiment of the invention；
Fig. 2 is the structure chart of crawler type bracket in the specific embodiment of the invention；
Fig. 3 is the structure chart for removing the unmanned plane after crawler belt in the specific embodiment of the invention；
Fig. 4 is the structure chart of second embodiment of attachment device in the specific embodiment of the invention；
Fig. 5 be the specific embodiment of the invention in attachment device second embodiment in attachment device in the raw
When structure chart；
Fig. 6 is the structure in the specific embodiment of the invention in second embodiment of attachment device when the pull-up of grip part
Figure.
Specific embodiment
Present embodiment discloses a kind of crawler-type unmanned machine for being automatically positioned bridge pad, as shown in Figure 1, including
Fuselage 1, crawler type bracket 2, attachment device 3, image capture module and control module, fuselage 1 pass through 3 connecting band track of attachment device
Formula bracket 2, image capture module acquire the image of bridge pad, and control module automatically determines position and the control of support according to image
The relative position of unmanned plane adjust automatically and support processed.
As shown in Figure 1, crawler type bracket 2 includes crawler belt 21 and bracket 22.As shown in Fig. 2, bracket 22 includes two parallel
The frame 221 of setting is rotatably connected to multiple rotating bars 222 between two frames 221, and crawler belt 21 is set in rotating bar 222.
Rotating bar 222 is uniformly distributed in the circumferential direction of two frames 221.
One embodiment of attachment device 3 is as shown in figures 1 and 3, including connecting rod that is orthogonal and being fixedly connected
And fixed link, fixed link are fixed between two frames 221.Attachment device 3 is non-telescoping in the embodiment.
Second embodiment of attachment device 3 is as shown in figure 4, include circular grip part 31, connecting rod 33 and solid
Surely the fixed link 32 being connected between two frames 221.As shown in figure 5, grip part 31 connects one end of connecting line 341, connection
It is set on bar 33 there are four boss 331, fixed link 32 is fixedly connected with two tracks 34, and two tracks 34 are located at connecting rod 33
Two sides, track 34 are separately connected one end of spring 35 and one end of adjusting rod 36, and the other end of spring 35 is located under boss 331
Side, and the other end of spring 35 is separately connected the other end of connecting line 341 and the other end of adjusting rod 36.Spring 35, adjusting rod
36 respectively have two groups, there are two one group.Connecting rod 33 is made of elastic material, such as rubber.Shell is additionally provided with outside track 34
37, as shown in Figure 4.Attachment device 3 is scalable in the embodiment, be described below how to realize it is flexible: when 31 quilt of grip part
When pull-up, as shown in fig. 6, connecting line 341 drives adjusting rod 36 to rotate, spring 35 is compressed, and can be controlled at this time
Connecting rod 33 upwardly or downwardly moves, and adjusting rod 36 can move in track 34, upwardly or downwardly moves to connecting rod 33
When to suitable position, namely when attachment device 3 is shunk or is extended to appropriate length, decontrol grip part 31.Attachment device 3 is long
The adjusting (flexible) of degree be it is discrete, the integral multiple of distance between boss 331 can only be adjusted.
The equipment that can shoot high-definition image, such as Canon's 5D3 camera can be used in image capture module.
Control module use artificial intelligence chip, artificial intelligence chip may be selected the Chinese Academy of Sciences publication towards low-power consumption scene
The Cambrian 1H8 of vision application.It is different from traditional die, the neuron of the Cambrian artificial intelligence chip simulation brain of a new generation
And cynapse, one instructs the processing that one group of neuron can be completed, and for this calculating mode when doing Intelligent treatment, efficiency is than passing
The system high hundred times of chip, power dissipation ratio of performance also realize leap.
Control module automatically determines the position of support by convolutional neural networks, and the foundation of convolutional neural networks includes following
Step:
S1: obtaining the image of bridge pad, adjusts the size of bridge pad image and demarcates the location information of support, to figure
As being pre-processed；
S2: bridge pad image is divided into training set and test set, training set is used for training convolutional neural networks, test
Collection is for testing convolutional neural networks；
S3: establishing convolutional neural networks, including input layer, output layer, convolutional layer and pond layer, convolutional neural networks it is defeated
Value is the location information of support in bridge pad image out；
S4: the support position information demarcated in convolutional neural networks real output value and step S1 is measured by loss function
Between error obtain and by the weight of gradient descent method and each layer of back-propagation algorithm repetitive exercise convolutional neural networks
Convolutional neural networks with automatic positioning bridge pad function.
In step S1, the calibration of support position information carries out in the following manner: using the upper left corner of picture as reference axis
Origin establishes cartesian coordinate system, and support position draws rectangle frame in picture, indicates branch with the angular coordinate of rectangle frame
The position of seat.The preprocess method of image are as follows: calculate the sum of pixel value of all images and then obtain one divided by the quantity of image
A mean value image subtracts the pixel value of the mean value image in every piece image.
Loss function in step S4 is mean square error MSE, is obtained according to formula (1):
In formula (1), n is the number of the image of input convolutional neural networks every time；yiFor the output valve of convolutional neural networks,For the support position information demarcated in step S1.
In step S4, the specific steps of gradient descent method are as follows: calculate loss function to the gradient of each weight, from any point
Start, the opposite direction along the gradient moves a distance, continues along gradient reverse direction operation a distance, in this way in new position
The continuous weight for updating network.The specific steps of back-propagation algorithm are as follows: updating convolution mind using gradient descent method iteration
When weight through each layer of network, gradient is successively propagated forward according to chain type Rule for derivation from the last layer of network.
Claims (10)
1. a kind of crawler-type unmanned machine for being automatically positioned bridge pad, it is characterised in that: including fuselage (1), crawler type bracket (2)
With attachment device (3), crawler type bracket (2) includes crawler belt (21) and bracket (22), and bracket (22) includes two disposed in parallel
Frame (221) is rotatably connected to multiple rotating bars (222) between two frames (221), and crawler belt (21) is set in rotating bar
(222) on, fuselage (1) passes through attachment device (3) connection framework (221)；In addition, the crawler-type unmanned machine further includes that image is adopted
Collect module and control module, image capture module acquires the image of bridge pad, and control module automatically determines support according to image
Position and control the relative position of unmanned plane adjust automatically and support.
2. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 1, it is characterised in that: the connection dress
It is scalable to set (3).
3. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 2, it is characterised in that: the connection dress
Setting (3) includes grip part (31), connecting rod (33) and the fixed link (32) being fixedly connected between two frames (221), is held
One end of portion (31) connection connecting line (341) is held, connecting rod (33) is equipped with boss (331), and fixed link (32) is fixedly connected with rail
Road (34), track (34) are separately connected one end of spring (35) and one end of adjusting rod (36), and the other end of spring (35) is located at
Below boss (331), and the other end of spring (35) be separately connected connecting line (341) the other end and adjusting rod (36) it is another
End.
4. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 3, it is characterised in that: the grip part
(31) shape is ring-type, and connecting rod (33) is made of elastic material.
5. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 3, it is characterised in that: the track
(34) there are two, the two sides of connecting rod (33) are located at.
6. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 3, it is characterised in that: the boss
(331) have multiple.
7. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 1, it is characterised in that: all rotating bars
(222) uniformly distributed in the circumferential direction of two frames (221).
8. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 1, it is characterised in that: the control mould
Block automatically determines the position of support by convolutional neural networks, the foundation of convolutional neural networks the following steps are included:
S1: obtaining the image of bridge pad, adjusts the size of bridge pad image and demarcates the location information of support, to image into
Row pretreatment；
S2: bridge pad image is divided into training set and test set, training set is used for training convolutional neural networks, and test set is used
In test convolutional neural networks；
S3: convolutional neural networks, including input layer, output layer, convolutional layer and pond layer, the output valve of convolutional neural networks are established
For the location information of support in bridge pad image；
S4: it is measured between the support position information demarcated in convolutional neural networks real output value and step S1 by loss function
Error had and by the weight of gradient descent method and each layer of back-propagation algorithm repetitive exercise convolutional neural networks
It is automatically positioned the convolutional neural networks of bridge pad function.
9. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 8, it is characterised in that: the step S1
In, the calibration of support position information carries out in the following manner: establishing Descartes by the origin of reference axis of the upper left corner of picture
Coordinate system, support position draws rectangle frame in picture, and the position of support is indicated with the angular coordinate of rectangle frame.
10. the crawler-type unmanned machine of automatic positioning bridge pad according to claim 8, it is characterised in that: the step
Loss function in S4 is mean square error MSE, is obtained according to formula (1):
In formula (1), n is the number of the image of input convolutional neural networks every time；yiFor the output valve of convolutional neural networks,For
The support position information demarcated in step S1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811396449.9A CN109606678B (en) | 2018-11-22 | 2018-11-22 | Crawler-type unmanned aerial vehicle capable of automatically positioning bridge support |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811396449.9A CN109606678B (en) | 2018-11-22 | 2018-11-22 | Crawler-type unmanned aerial vehicle capable of automatically positioning bridge support |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109606678A true CN109606678A (en) | 2019-04-12 |
| CN109606678B CN109606678B (en) | 2021-09-07 |
Family
ID=66003455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811396449.9A Active CN109606678B (en) | 2018-11-22 | 2018-11-22 | Crawler-type unmanned aerial vehicle capable of automatically positioning bridge support |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109606678B (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003099656A1 (en) * | 2002-05-23 | 2003-12-04 | Gerhard Mellmann | Aircraft comprising a rescue device |
| US20090206199A1 (en) * | 2008-02-14 | 2009-08-20 | Jackson Rick A | Debris deflecting device, system, and method |
| CN102541064A (en) * | 2012-03-27 | 2012-07-04 | 沈阳中兴电力通信有限公司 | Magnetic navigation routing inspection robot |
| CN103459250A (en) * | 2011-03-29 | 2013-12-18 | 法国高等航空和航天学院 | Remotely controlled micro/nanoscale aerial vehicle comprising a system for traveling on the ground, vertical takeoff, and landing |
| CN103712035A (en) * | 2014-01-08 | 2014-04-09 | 北京理工大学 | Cage type pipeline aircraft |
| CN204161620U (en) * | 2014-10-16 | 2015-02-18 | 云南电网公司红河供电局 | The full landform retractable landing gear of depopulated helicopter |
| US20150158579A1 (en) * | 2013-12-10 | 2015-06-11 | Isaiah W. Cox | Method for maximizing powered aircraft drive wheel traction |
| US20160011080A1 (en) * | 2014-07-11 | 2016-01-14 | General Electric Company | System and method for inspecting turbomachines |
| CN105354568A (en) * | 2015-08-24 | 2016-02-24 | 西安电子科技大学 | Convolutional neural network based vehicle logo identification method |
| US20160307074A1 (en) * | 2014-11-21 | 2016-10-20 | Adobe Systems Incorporated | Object Detection Using Cascaded Convolutional Neural Networks |
| CN106467168A (en) * | 2015-08-17 | 2017-03-01 | 富士通株式会社 | Aircraft frame structure, aircraft, aircraft using method |
| CN106956768A (en) * | 2017-05-02 | 2017-07-18 | 锐合防务技术（北京）有限公司 | Aircraft |
| CN206367593U (en) * | 2016-12-28 | 2017-08-01 | 芜湖元一航空科技有限公司 | A kind of inspection multi-purpose unmanned aerial vehicle |
| CN107352022A (en) * | 2017-06-08 | 2017-11-17 | 国蓉科技有限公司 | A kind of spherical UAS of rotor of impact resistant four |
| CN206756706U (en) * | 2017-05-26 | 2017-12-15 | 中铁十八局集团有限公司 | Bridge bottom disease follow shot system |
| CN107737755A (en) * | 2017-11-07 | 2018-02-27 | 太仓红码软件技术有限公司 | A kind of intelligent mobile based on water generating is removed contamination system and its control method |
| CN207550496U (en) * | 2017-12-15 | 2018-06-29 | 江苏航丰智控无人机有限公司 | Collapsible damping device and the unmanned plane of rising and falling |
| CN108288269A (en) * | 2018-01-24 | 2018-07-17 | 东南大学 | Bridge pad disease automatic identifying method based on unmanned plane and convolutional neural networks |
| CN207670666U (en) * | 2017-12-20 | 2018-07-31 | 深圳市中联讯科技有限公司 | Unmanned plane with shock-damping structure |
| CN207956042U (en) * | 2018-02-07 | 2018-10-12 | 北京交通大学 | A kind of novel unmanned plane undercarriage |
-
2018
- 2018-11-22 CN CN201811396449.9A patent/CN109606678B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003099656A1 (en) * | 2002-05-23 | 2003-12-04 | Gerhard Mellmann | Aircraft comprising a rescue device |
| US20090206199A1 (en) * | 2008-02-14 | 2009-08-20 | Jackson Rick A | Debris deflecting device, system, and method |
| CN103459250A (en) * | 2011-03-29 | 2013-12-18 | 法国高等航空和航天学院 | Remotely controlled micro/nanoscale aerial vehicle comprising a system for traveling on the ground, vertical takeoff, and landing |
| CN102541064A (en) * | 2012-03-27 | 2012-07-04 | 沈阳中兴电力通信有限公司 | Magnetic navigation routing inspection robot |
| US20150158579A1 (en) * | 2013-12-10 | 2015-06-11 | Isaiah W. Cox | Method for maximizing powered aircraft drive wheel traction |
| CN103712035A (en) * | 2014-01-08 | 2014-04-09 | 北京理工大学 | Cage type pipeline aircraft |
| US20160011080A1 (en) * | 2014-07-11 | 2016-01-14 | General Electric Company | System and method for inspecting turbomachines |
| CN204161620U (en) * | 2014-10-16 | 2015-02-18 | 云南电网公司红河供电局 | The full landform retractable landing gear of depopulated helicopter |
| US20160307074A1 (en) * | 2014-11-21 | 2016-10-20 | Adobe Systems Incorporated | Object Detection Using Cascaded Convolutional Neural Networks |
| CN106467168A (en) * | 2015-08-17 | 2017-03-01 | 富士通株式会社 | Aircraft frame structure, aircraft, aircraft using method |
| CN105354568A (en) * | 2015-08-24 | 2016-02-24 | 西安电子科技大学 | Convolutional neural network based vehicle logo identification method |
| CN206367593U (en) * | 2016-12-28 | 2017-08-01 | 芜湖元一航空科技有限公司 | A kind of inspection multi-purpose unmanned aerial vehicle |
| CN106956768A (en) * | 2017-05-02 | 2017-07-18 | 锐合防务技术（北京）有限公司 | Aircraft |
| CN206756706U (en) * | 2017-05-26 | 2017-12-15 | 中铁十八局集团有限公司 | Bridge bottom disease follow shot system |
| CN107352022A (en) * | 2017-06-08 | 2017-11-17 | 国蓉科技有限公司 | A kind of spherical UAS of rotor of impact resistant four |
| CN107737755A (en) * | 2017-11-07 | 2018-02-27 | 太仓红码软件技术有限公司 | A kind of intelligent mobile based on water generating is removed contamination system and its control method |
| CN207550496U (en) * | 2017-12-15 | 2018-06-29 | 江苏航丰智控无人机有限公司 | Collapsible damping device and the unmanned plane of rising and falling |
| CN207670666U (en) * | 2017-12-20 | 2018-07-31 | 深圳市中联讯科技有限公司 | Unmanned plane with shock-damping structure |
| CN108288269A (en) * | 2018-01-24 | 2018-07-17 | 东南大学 | Bridge pad disease automatic identifying method based on unmanned plane and convolutional neural networks |
| CN207956042U (en) * | 2018-02-07 | 2018-10-12 | 北京交通大学 | A kind of novel unmanned plane undercarriage |
Non-Patent Citations (2)
| Title |
|---|
| LI WEI,SUN SHU-YING, LIU JIANG-YI,CAO BIN-QIAN: "Design of the tracked vehicle based on the STM32", 《APPLIED MECHANICS AND MATERIALS》 * |
| 程军,望斌,宋毅: "无人机遥感技术在大型起重机械结构检测的应用前景展望", 《特种设备安全技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109606678B (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111272148B (en) | Unmanned aerial vehicle autonomous inspection self-adaptive imaging quality optimization method for power transmission line | |
| CN108803668B (en) | Intelligent inspection unmanned aerial vehicle nacelle system for static target monitoring | |
| CN110232736A (en) | A kind of down-hole combined mining working three-dimensional scenic fast construction method | |
| CN112164015A (en) | Monocular vision autonomous inspection image acquisition method and device and power inspection unmanned aerial vehicle | |
| CN106628211B (en) | Ground control formula unmanned plane during flying landing system and method based on LED dot matrix | |
| CN105447853A (en) | Flight device, flight control system and flight control method | |
| CN107064169A (en) | A kind of Bridge Crack detection means and detection method | |
| CN104506828B (en) | A kind of fixed point orientation video real-time joining method of nothing effectively overlapping structure changes | |
| CN103729620B (en) | A kind of multi-view pedestrian detection method based on multi-view Bayesian network | |
| CN110335255B (en) | Dam slope crack detection method and bionic gecko crawling detection device | |
| CN111460903A (en) | System and method for monitoring growth of field broccoli based on deep learning | |
| CN106828959A (en) | A kind of intelligent unmanned plane of taking photo by plane based on Internet of Things | |
| CN104949658B (en) | Wire ice-shedding trajectory measurement device based on technique of binocular stereoscopic vision | |
| CN107703936A (en) | Automatic Guided Vehicle system and dolly localization method based on convolutional neural networks | |
| CN105631859A (en) | Three-degree of freedom bionic stereo vision system | |
| CN109606678A (en) | A kind of crawler-type unmanned machine being automatically positioned bridge pad | |
| CN106952231B (en) | A kind of image real time correction method based on cell phone platform | |
| CN109345562A (en) | A kind of traffic picture intelligent dimension system | |
| CN111079277B (en) | Parachute opening process and stabilized-reduction stage resistance area acquisition method | |
| CN205861216U (en) | A kind of based on ultrared noiseless image collecting device | |
| CN109685088A (en) | Narrow band communication intelligent image analysis system based on cloud separation convolutional neural networks | |
| CN116503739A (en) | Scene recognition method and system for robot to move up and down stairs | |
| CN206524916U (en) | A kind of self-adapting detecting and the double devices for taking the photograph optical axis of adjustment | |
| CN116309370A (en) | Real-time detection method and system for apparent diseases of concrete dam | |
| CN113114766B (en) | Potted plant information detection method based on ZED camera |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |