CN108803668A - A kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring - Google Patents
A kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring Download PDFInfo
- Publication number
- CN108803668A CN108803668A CN201810651606.XA CN201810651606A CN108803668A CN 108803668 A CN108803668 A CN 108803668A CN 201810651606 A CN201810651606 A CN 201810651606A CN 108803668 A CN108803668 A CN 108803668A
- Authority
- CN
- China
- Prior art keywords
- module
- gondola
- target
- unmanned plane
- picture
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000003068 static effect Effects 0.000 title claims abstract description 30
- 230000007547 defect Effects 0.000 claims abstract description 9
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000003321 amplification Effects 0.000 claims abstract description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 5
- 230000033001 locomotion Effects 0.000 claims description 17
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000000465 moulding Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 5
- 238000007689 inspection Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 3
- 235000013350 formula milk Nutrition 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000571 coke Substances 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 125000006850 spacer group Chemical group 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 229940082150 encore Drugs 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0094—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
This application involves air vehicle technique fields, more particularly to a kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring, the system can capture target by the planning course line of preset patrol task and initial pose state modulator unmanned plane and gondola, it is identified by deep learning algorithm and training pattern, position target, and it controls gondola and gradually adjusts holder posture and camera focus, locking, amplification target simultaneously captures monitoring image, for artificial or intelligent recognition component defect, to realize intelligent capture, locking, capture component target, improve system job efficiency efficiency, reduction personnel's skill set requirements.
Description
Technical field
The present invention relates to the intelligent patrol detection unmanned plane gondolas that air vehicle technique field more particularly to a kind of static object monitor
System.
Background technology
The industries such as power grid, railway, water conservancy, oil-gas pipeline have a large amount of installations and facilities for being erected at earth's surface, because of long-term exposure
In the natural environment, the quality process lifetime for not only having itself, also subject to normal operating load and climatic effect, thus can not
The defects of avoiding the occurrence of damaged pollution, displacement deformation and risk, directly affect the operational safety and benefit of system.
For this purpose, every profession and trade establishes circuit manual inspection system, is maked an inspection tour along staff, observe the shape of earth's surface installations and facilities
State finds that component defect, guarantee are safeguarded, safeguards system normal operation in time.
In recent years as unmanned air vehicle technique develops, line data-logging is attempted to introduce high-performance, the small and medium size unmanned aerial vehicles of low cost, leads to
It crosses scene and captures the professional artificial or intelligent diagosis of component high-definition image and backstage, control observes point, technical ability warp because of patrol officer
Missing inspection false retrieval caused by the limitation possibility with responsibility consciousness is tested, inspection quality and efficiency are improved.
General patrol unmanned machine needs profession flies control hand on-site manual and manipulates unmanned plane, selects take pictures point, lock onto target
And capture pictures, Field Force's technical ability skill requirement is first greatly improved, existing patrol officer is difficult to be competent at, and influences personnel's adjustment
And human cost, second on-site manual manipulation, which is captured, is difficult to ensure high efficiency, comprehensive monitoring component state, also needs to continue to lift up
The technical performance of unmanned plane cruising inspection system.
Invention content
This application provides a kind of static object monitoring intelligent patrol detection unmanned plane Towed bird system, with intelligent capture, locking,
Component target is captured, system job efficiency efficiency is improved, reduces personnel's skill set requirements.
In order to solve the above technical problems, the application provides the following technical solutions：
This application provides a kind of static object monitoring intelligent patrol detection unmanned plane Towed bird system, with intelligent capture, locking,
Component target is captured, system job efficiency efficiency is improved, reduces personnel's skill set requirements.
In order to solve the above technical problems, the application provides the following technical solutions：
A kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring, including：It is earth station's patrol task module, airborne
Flight control modules, gondola module, identify locating module and locking control module；Earth station's patrol task module is preset to patrol
Inspection task plans course line and unmanned plane and the initial pose parameter of gondola module accordingly, and sends it to described airborne winged
Row control module, the hovering of control unmanned plane and the gondola module posture, obtain monitoring objective initial pictures；The gondola mould
Block, including sensor and multiple degrees of freedom holder, execute the onboard flight control module, locking control module instruction, and control is adjusted
The lens focus of whole the multiple degrees of freedom holder posture and the sensor sequentially enters initial attitude, locking posture and candid photograph
Posture obtains the photo or video image of target and its defect, risk, including initial, locking and monitoring image；The identification is fixed
The embedding assembly platform for having deep learning algorithm is transplanted in position module, apolegamy, and gondola module obtains initial graph described in intelligent recognition
Monitoring objective as in, and solving target pixel coordinate, extraction target signature image, are sent to the locking control module；Institute
State locking control module, using the identify locating module resolve object pixel coordinate, extraction target signature image as template,
Template matches, the real-time pixel coordinate and picture of solving target are carried out to the real-time target lock image that the gondola module obtains
Accounting, substep control adjust the holder posture of the gondola module, camera focus to lock, amplification target and the prison for capturing target
Altimetric image.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, the gondola
The sensor of module is the one or more of visible light, infrared light, ultraviolet light and multispectral sensor, and the sensor has fixed
Burnt or zoom lens.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, in unmanned plane
Under pose and gondola attitude accuracy, the initial pictures that the onboard flight control module instruction obtains are executed in the gondola module
In, monitoring objective length or area are located at the gondola visual field and picture accounting 10-20%, and the identify locating module identification, which captures, to be supervised
Survey target and solving target pixel coordinate, extraction target signature image；The locking control module is executed in the gondola module
It instructs in the monitoring image obtained, monitoring objective length or area are located at the gondola visual field and picture accounting 40-60%.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, the identification
Locating module is instructed by deep learning algorithm, and using target training pattern and the onboard flight control module, and identification is caught
Catch monitoring objective.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, the locking
Control module includes：Outer shroud PID controller and inner ring PID controller；Object pixel center position coordinate and picture central point
Phase of the target in picture is calculated as the outer shroud PID controller input signal, through outer shroud PID controller in position coordinates
Hope movement velocity；The desired motion speed and the movement speed of target pixel central point are as the inner ring PID control
The adjustment information of the gondola module holder is calculated through inner ring PID controller for the input signal of device.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, the inner ring
The input signal of PID controller further includes：Current target pixel center point expected that translational speed and last moment target picture
Plain central point expected that translational speed.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, work as target picture
Plain center continues to reach preset value in the time of picture central threshold, and the locking control module is sent out to the gondola module
Zoom instructions, the gondola module are sent to change lens focus according to zoom information.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, when target is drawn
Width accounting reaches preset threshold range, and object pixel center continues to reach preset value in the time of picture central threshold
Afterwards, the locking control module is sent to the gondola module captures monitoring image instruction.
The intelligent patrol detection unmanned plane Towed bird system of static object monitoring as described above, wherein preferably, predetermined threshold value
Ranging from 40% to 60%.
The intelligent patrol detection unmanned plane Towed bird system of relatively above-mentioned background technology, static object monitoring provided by the present invention can
To capture target by the planning course line of preset patrol task and initial pose state modulator unmanned plane and gondola, pass through deep learning
Algorithm and training pattern identification, positioning target, and control gondola and gradually adjust holder posture and camera focus, locking, amplification mesh
Monitoring image is marked and captures, for artificial or intelligent recognition component defect, to realize intelligent capture, locking, capture component mesh
Mark improves system job efficiency efficiency, reduces personnel's skill set requirements.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments described in invention can also be obtained according to these attached drawings other for those of ordinary skill in the art
Attached drawing.
Fig. 1 is a kind of showing for the intelligent patrol detection unmanned plane Towed bird system for static object monitoring that the embodiment of the present application is provided
It is intended to；
Fig. 2 is the schematic diagram for the locking control module that the embodiment of the present application is provided；
Fig. 3 is the camera optics zoom figure that the embodiment of the present application is provided.
Specific implementation mode
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
This application provides a kind of intelligent patrol detection unmanned plane Towed bird systems of static object monitoring, by taking power grid inspection as an example,
On regular visit transmission line of electricity and the component target of shaft tower, includes mainly conductor spacer, stockbridge damper, presses shading ring, insulation
Son etc., the intelligent patrol detection unmanned plane Towed bird system of static object monitoring, unmanned plane select electronic more rotor types, gondola module
High definition zoom digital camera is matched, to provide intelligent capture, identification, locking and capture conductor spacer, stockbridge damper, pressure shielding
The function of the components such as ring, insulator, for damaged, the displacement deformation of pollution etc. that artificial or intelligent recognition component is likely to occur from the background
Defect and risk.
As shown in Figure 1, the intelligent patrol detection unmanned plane Towed bird system of static object monitoring provided by the present application includes：Earth station
Patrol task module 11, onboard flight control module 12, gondola module 13, identify locating module 14 and locking control module 15.
Wherein, earth station's patrol task module 11 supports those skilled in the art's design, preset whole patrol tasks corresponding
13 initial pose parameter of planning course line and unmanned plane and gondola module, support task management personnel select this patrol task,
The initial pose parameter of corresponding planning route information and gondola module 13 is sent to onboard flight control module 12, field control
The preset initial pose of inspection of unmanned plane hovering, then control gondola module 13 and enter preset initial attitude, it is initial to obtain monitoring objective
Image.
Gondola module 13, apolegamy high definition zoom digital camera and multiple degrees of freedom holder, execution onboard flight control module 12,
It locks control module 15 to instruct, control adjustment holder posture (gondola roll angle, pitch angle) and lens focus, sequentially enter initial
Posture, locking posture and capture posture, obtain the photo or video image of target and its defect, risk, including initial, locking and
Monitoring image sends initial pictures and gives locking control module 15 to identify locating module 14, lock image.
Identify locating module 14 is matched with GPU, CPU, memory, flash memory and runs the embedding assembly for having operating system
Platform, transplanting have deep learning algorithm, intelligent recognition gondola module 13 to obtain the monitoring objective in initial pictures, solving target picture
Plain coordinate, extraction target signature image are sent to locking control module 15.
Control module 15 is locked, the target signature image of the object pixel coordinate, extraction that are resolved with identify locating module 14
For template, template matches, the real-time pixel coordinate of solving target are carried out to the real-time target lock image that gondola module 13 obtains
With picture accounting, the holder posture of substep control adjustment gondola module 13, camera focus to lock, amplification target and capture target
Monitoring image.
For gondola module 13 in initial and locking posture, camera is set as video mode, and initial and lock image is to regard
Frequency takes out frame image；When capturing posture, camera is set as exposal model, and monitoring image is high definition photo.
The deep learning algorithm that identify locating module 14 is transplanted is a branch of machine learning, and operation commonly relies on
GPU, program are to be based on CUDA frameworks, and summarizing statistical law existing for a large amount of target sample data by training study forms mould
Type carries out target identification using training pattern, and the object module in the application is the training that monitoring objective is screened by professional
Sample is simultaneously completed in dedicated training system.
Onboard flight control module 12 be unmanned plane completion take off, airflight, execution task and recycling etc. of giving an encore it is entire
The core system of flight course generally comprises sensor, airborne computer and servo action equipment three parts, realizes unmanned plane
Attitude stabilization and control, unmanned plane task device management and emergency flight control three categories major function.
Since during capturing positioning, target is captured in locking, unmanned plane spot hover existence position is drifted about and posture
It waves, gondola has response delay and Adjustment precision in addition, and target may be caused to be shaken in camera fields of view and even deviated from, therefore
In the application, following technical measures are designed：
Press monitoring objective length or area picture accounting 10-20% design configurations in the initial pictures of the acquisition of gondola module 13
Unmanned plane and the initial pose parameter of gondola, to ensure under UAV position and orientation and gondola attitude accuracy, monitoring objective is located at camera
In the visual field and its resolution ratio supports the identification of identify locating module 14 to capture monitoring objective and solving target pixel coordinate, extraction target
Characteristic image.
Press monitoring objective length or area picture accounting 40-60% design configurations in the monitoring image of the acquisition of gondola module 13
It locks control module and captures preset value, to ensure under UAV position and orientation and gondola attitude accuracy, monitoring objective is regarded positioned at camera
Simultaneously its resolution ratio supports artificial or intelligent recognition target defect to the Yezhong heart.
During target lock-on amplifies, the posture of 15 adjust automatically gondola module 13 of configuration locking control module, with
Ensure under UAV position and orientation and gondola attitude accuracy, monitoring objective is located at camera fields of view center.
As shown in Fig. 2, locking control module 15 includes：Outer shroud PID controller 151 and inner ring PID controller 152, it is above-mentioned
The target real-time pixel coordinate that the object pixel coordinate and locking control panel 15 that identify locating module 14 calculates in embodiment obtain
Feedback signal is can be used as, selected objective target pixel center point position coordinates are as feedback signal, picture center point in the application
The position coordinates for setting the central point for the video image that coordinate is shooting, by object pixel center position coordinate and picture central point
Input signal of the position coordinates as outer shroud PID controller 151, can be will be in object pixel center position coordinate and picture
Heart point position coordinates seek difference horizontally and vertically, and target then, which is calculated, through outer shroud PID controller 151 exists
Desired motion speed in picture；Desired motion speed and the movement velocity of target pixel central point are controlled as inner ring PID
The input signal of device processed, wherein object pixel central point movement velocity are the real-time movement velocitys of target, can by it is current when
It carves and the position coordinates of last moment is calculated, can also be obtained by the directly test of the components such as sensor, through inner ring PID
The adjustment information of gondola holder is calculated in controller 152, and the adjustment information of gondola holder includes pitch axis pwm signal and course
Axis pwm signal, gondola module 13 adjust gondola holder posture according to the adjustment information of gondola holder in real time.
To prevent the deviation of signal that outer shroud PID controller 151 and inner ring PID controller 152 input excessive, execution machine is caused
Structure substantially acts, therefore can also carry out deviation signal processing to input signal, specifically can be as follows：
When the deviation of input signal is more than given threshold, spy uses inverted parabolic curve signal processing method, threshold calculations formula
For：Wherein lineat_dist is linearly interval threshold value, and acc_max is that target object is moved in picture
Peak acceleration limits, and p is scale factor.
When desired motion speed of the target in picture with object pixel central point movement speed absolute value of the bias linear
When in interval threshold, the input of inner ring PID controller 152 is former departure, i.e.,：PID_input=error_rate works as target
It is interior when desired motion speed in picture is more than linearly interval threshold value with object pixel central point movement speed absolute value of the bias
The input of ring PID controller 152 is the value that former departure passes through inverted parabolic curve transformation, and transformation for mula is：Wherein PID_input be inner ring PID controller 152 input quantity,
Error_rate is desired motion speed and actual motion velocity deviation.
Vibration and swing during being controlled due to UAV position and orientation influence the effect of target lock-on control, inner ring PID controls
Feed-forward process link is added in device 152 processed, with the variation of quick response external disturbance, believes please continue to refer to Fig. 2, that is, in input
Increase the desired speed of feedforward in number, the desired speed of the feedforward is it is expected mobile speed by current target pixel center point
Degree and last moment object pixel central point expected that translational speed are calculated, specifically can be as follows：
Current target pixel center point expected that translational speed and last moment object pixel central point it is expected to move
Velocity deviation does scale operation after inverted parabolic curve is handled, and calculates the desired speed signal for feedforward, i.e.,：Wherein, PID_input_
Forward is：Desired speed signal, the target_rate (t) of feedforward be：Current time desired speed；In inner ring PID control
After the desired speed for increasing feedforward in the input signal of device 152, the signal that finally enters of inner ring PID controller 152 is：Wherein, input_PIDinner_ringFor inner ring PID controller 152
Finally enter signal；Inner ring PID input signals directly obtain the pwm control signal of motor after PID arithmetic, and calculation formula is：,
In, PWM (n) is the pwm control signal of motor, Kp is proportional gain, Ki is storage gain, Kd is the differential gain；PWM control letters
Number will directly act on holder brushless motor, motor rotation change target picture position coordinates formed negative-feedback.
It on the basis of the above embodiments, can in order to ensure that target length or area occupy suitable ratio in picture
With when object pixel center continues when the time of picture central threshold reaching preset value, locking control module 15 is to gondola
Module 13 sends zoom instructions, and gondola module 13 changes camera focus according to zoom information；As shown in figure 3, changing the coke of camera
Away from that can realize zoom by optical lens structure, moved by the eyeglass of camera to amplify and reduce the object for needing to shoot
Body, when imaging surface moves in the horizontal direction, visual angle and focal length will change；When object pixel length or area are drawn
Width accounting reaches predetermined threshold value, and locking control module 15 sends photographing instruction to gondola module 13, and gondola module 13 is according to taking pictures
Instruction control camera is taken pictures.
It locks control module 15 and sends zoom instructions to gondola module 13, difference can be executed according to target picture accounting
Zoom magnification, such as：The picture accounting of object pixel length or area executes 3 times of optics and becomes when accounting is 10-20%
Coke expands when accounting is 20-40%, executes 2 Zoom Lens, when accounting is 40-60%, executes 1 Zoom Lens.
In order to ensure that the quality the taken pictures i.e. clarity of photo, selected objective target pixel center position continue in picture center threshold
Time and object pixel area in value account for the ratio of the picture area duration in preset threshold range and reach pre-
If after value, locking control module 15 sends photographing instruction to gondola module 13, action of continuously taking pictures is executed, so far locking control mould
15 inspections of block take pictures task completion.
The intelligent patrol detection unmanned plane Towed bird system monitored due to the static object of the application whole Intelligent flight and can be caught
It catches, lock, capturing component target, greatly improving system job efficiency efficiency, reduce personnel's skill set requirements, manually being patrolled with existing
Inspection and winged control hand manipulation unmanned plane inspection have significant technology and warp in monitoring quality, routing inspection efficiency and job safety etc.
Ji advantage.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiment being appreciated that.
Claims (9)
1. a kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring, including：
Earth station's patrol task module, onboard flight control module, gondola module, identify locating module and locking control module；
At the beginning of the preset patrol task of earth station's patrol task module plans course line and unmanned plane and the gondola module accordingly
Beginning pose parameter, and the onboard flight control module is sent it to, the hovering of control unmanned plane and the gondola module posture,
Obtain monitoring objective initial pictures；
The gondola module, including sensor and multiple degrees of freedom holder execute the onboard flight control module, locking control mould
Block instruction, control adjust the lens focus of the multiple degrees of freedom holder posture and the sensor, sequentially enter initial attitude, lock
Determine posture and capture posture, obtains the photo or video image of target and its defect, risk, including initial, locking and monitoring figure
Picture；
The identify locating module, apolegamy transplanting have the embedding assembly platform of deep learning algorithm, gondola described in intelligent recognition
Module obtains the monitoring objective in initial pictures, and solving target pixel coordinate, extraction target signature image, is sent to the lock
Determine control module；
The locking control module, the target signature image of the object pixel coordinate, extraction that are resolved with the identify locating module
For template, template matches are carried out to the real-time target lock image that the gondola module obtains, the real-time pixel of solving target is sat
Mark and picture accounting, substep control adjust the holder posture of the gondola module, camera focus to lock, amplification target and capture
The monitoring image of target.
2. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 1, wherein the gondola mould
The sensor of block is the one or more of visible light, infrared light, ultraviolet light and multispectral sensor, and the sensor has fixed-focus
Or zoom lens.
3. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 1, wherein in unmanned seat in the plane
Under appearance and gondola attitude accuracy, the initial pictures that the onboard flight control module instruction obtains are executed in the gondola module
In, monitoring objective length or area are located at the gondola visual field and picture accounting 10-20%, and the identify locating module identification, which captures, to be supervised
Survey target and solving target pixel coordinate, extraction target signature image；The locking control module is executed in the gondola module
It instructs in the monitoring image obtained, monitoring objective length or area are located at the gondola visual field and picture accounting 40-60%.
4. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 1, wherein the identification is fixed
Position module is instructed by deep learning algorithm, and using target training pattern and the onboard flight control module, and identification captures
Monitoring objective.
5. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 1, wherein the locking control
Molding block includes：Outer shroud PID controller and inner ring PID controller；Object pixel center position coordinate and picture center point
Coordinate is set as the outer shroud PID controller input signal, expectation of the target in picture is calculated through outer shroud PID controller
Movement velocity；The desired motion speed and the movement speed of target pixel central point are as the inner ring PID controller
Input signal, the adjustment information of the gondola module holder is calculated through inner ring PID controller.
6. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 5, wherein the inner ring
The input signal of PID controller further includes：Current target pixel center point expected that translational speed and last moment target picture
Plain central point expected that translational speed.
7. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 5, wherein work as object pixel
Center continues to reach preset value in the time of picture central threshold, and the locking control module is sent to the gondola module
Zoom instructions, the gondola module change lens focus according to zoom information.
8. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 5, wherein when target picture
Accounting reaches preset threshold range, and object pixel center continues after the time of picture central threshold reaches preset value,
The locking control module is sent to the gondola module captures monitoring image instruction.
9. the intelligent patrol detection unmanned plane Towed bird system of static object monitoring according to claim 8, wherein predetermined threshold value model
Enclose is 40% to 60%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810651606.XA CN108803668B (en) | 2018-06-22 | 2018-06-22 | Intelligent inspection unmanned aerial vehicle nacelle system for static target monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810651606.XA CN108803668B (en) | 2018-06-22 | 2018-06-22 | Intelligent inspection unmanned aerial vehicle nacelle system for static target monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108803668A true CN108803668A (en) | 2018-11-13 |
| CN108803668B CN108803668B (en) | 2021-08-24 |
Family
ID=64084560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810651606.XA Active CN108803668B (en) | 2018-06-22 | 2018-06-22 | Intelligent inspection unmanned aerial vehicle nacelle system for static target monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108803668B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765939A (en) * | 2018-12-21 | 2019-05-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Cloud platform control method, device and the storage medium of unmanned plane |
| CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
| CN110312071A (en) * | 2019-04-30 | 2019-10-08 | 中国联合网络通信集团有限公司 | The control method and unmanned plane of unmanned plane |
| CN110351483A (en) * | 2019-08-05 | 2019-10-18 | 深圳职业技术学院 | A kind of adaptive zoom monitoring unmanned platform of more camera lenses and control method |
| CN110602484A (en) * | 2019-08-29 | 2019-12-20 | 海南电网有限责任公司海口供电局 | Online checking method for shooting quality of power transmission line equipment |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN110825110A (en) * | 2019-11-13 | 2020-02-21 | 昆明能讯科技有限责任公司 | Acquisition flight method for power line visible light point cloud resolving photo |
| CN110879602A (en) * | 2019-12-06 | 2020-03-13 | 安阳全丰航空植保科技股份有限公司 | Unmanned aerial vehicle control law parameter adjusting method and system based on deep learning |
| CN111669501A (en) * | 2020-06-18 | 2020-09-15 | 南方电网数字电网研究院有限公司 | Shooting method and device based on unmanned aerial vehicle, computer equipment and medium |
| CN111860461A (en) * | 2020-08-05 | 2020-10-30 | 西安应用光学研究所 | Automatic zooming method for built-in optical sensor of photoelectric pod |
| CN112363176A (en) * | 2020-11-06 | 2021-02-12 | 日立楼宇技术（广州）有限公司 | Elevator shaft inspection and modeling method and device and inspection modeling system |
| CN112585946A (en) * | 2020-03-27 | 2021-03-30 | 深圳市大疆创新科技有限公司 | Image shooting method, image shooting device, movable platform and storage medium |
| CN113415433A (en) * | 2021-07-30 | 2021-09-21 | 成都纵横大鹏无人机科技有限公司 | Pod attitude correction method and device based on three-dimensional scene model and unmanned aerial vehicle |
| CN114511551A (en) * | 2022-02-22 | 2022-05-17 | 金华高等研究院(金华理工学院筹建工作领导小组办公室) | Ground damage identification system based on machine vision |
| CN114564049A (en) * | 2022-03-21 | 2022-05-31 | 厦门大学 | Unmanned aerial vehicle wide area search device and method based on deep learning |
| WO2022126375A1 (en) * | 2020-12-15 | 2022-06-23 | 深圳市大疆创新科技有限公司 | Zooming method, imaging device, gimbal and movable platform |
| CN116543619A (en) * | 2023-07-04 | 2023-08-04 | 中国科学院长春光学精密机械与物理研究所 | Unmanned aerial vehicle photoelectric pod simulation training system |
| CN117750204A (en) * | 2023-11-14 | 2024-03-22 | 东南大学 | Visual synchronous tracking shooting method and device for moving target on conveying line |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0232415A (en) * | 1988-07-21 | 1990-02-02 | Fujitsu Ltd | Displaying controller for detecting movement of pointing device |
| CN101811578A (en) * | 2010-04-23 | 2010-08-25 | 福建省电力有限公司福州电业局 | Special photoelectric nacelle of power patrol unmanned helicopter |
| CN102183955A (en) * | 2011-03-09 | 2011-09-14 | 南京航空航天大学 | Transmission line inspection system based on multi-rotor unmanned aircraft |
| CN103149939A (en) * | 2013-02-26 | 2013-06-12 | 北京航空航天大学 | Dynamic target tracking and positioning method of unmanned plane based on vision |
| CN104796672A (en) * | 2015-05-09 | 2015-07-22 | 合肥工业大学 | Emergency monitoring cloud platform device for unmanned aerial vehicle and operating method of emergency monitoring cloud platform device for unmanned aerial vehicle |
| CN204992418U (en) * | 2015-09-22 | 2016-01-20 | 南方电网科学研究院有限责任公司 | Automatic inspection device for defects of unmanned aerial vehicle power transmission line |
| CN105578101A (en) * | 2015-12-23 | 2016-05-11 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Helicopter photoelectric pod storage system and implementation method thereof |
| CN105959181A (en) * | 2016-06-17 | 2016-09-21 | 国网山东省电力公司电力科学研究院 | System and method for inspecting and detection power inspection unmanned aerial vehicle |
| CN106005455A (en) * | 2016-08-08 | 2016-10-12 | 北京宇鹰科技有限公司 | Two-axis pod system based on geographic coordinate system pointing control |
| CN205920414U (en) * | 2016-07-29 | 2017-02-01 | 苏州天地衡遥感科技有限公司 | Machine carries optoelectronic pod platform |
| CN106502259A (en) * | 2016-11-21 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Electric inspection process low profile photovoltaic gondola control device, gondola, unmanned plane and method |
| CN106647814A (en) * | 2016-12-01 | 2017-05-10 | 华中科技大学 | System and method of unmanned aerial vehicle visual sense assistant position and flight control based on two-dimensional landmark identification |
| CN106741008A (en) * | 2016-12-29 | 2017-05-31 | 北京交通大学 | Rail track method for recognizing impurities and system |
| CN106774436A (en) * | 2017-02-27 | 2017-05-31 | 南京航空航天大学 | The control system and method for the rotor wing unmanned aerial vehicle tenacious tracking target of view-based access control model |
| CN107203184A (en) * | 2017-06-20 | 2017-09-26 | 南京理工大学 | The dynamic control method of straight line steering wheel Electric Loading System |
| CN107544531A (en) * | 2017-09-27 | 2018-01-05 | 成都纵横自动化技术有限公司 | Line data-logging method, apparatus and unmanned plane |
| US9886871B1 (en) * | 2011-12-27 | 2018-02-06 | PEAR Sports LLC | Fitness and wellness system with dynamically adjusting guidance |
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| CN108107920A (en) * | 2017-12-19 | 2018-06-01 | 天津工业大学 | A kind of microminiature twin shaft vision stablizes holder target detection tracing system |
-
2018
- 2018-06-22 CN CN201810651606.XA patent/CN108803668B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0232415A (en) * | 1988-07-21 | 1990-02-02 | Fujitsu Ltd | Displaying controller for detecting movement of pointing device |
| CN101811578A (en) * | 2010-04-23 | 2010-08-25 | 福建省电力有限公司福州电业局 | Special photoelectric nacelle of power patrol unmanned helicopter |
| CN102183955A (en) * | 2011-03-09 | 2011-09-14 | 南京航空航天大学 | Transmission line inspection system based on multi-rotor unmanned aircraft |
| US9886871B1 (en) * | 2011-12-27 | 2018-02-06 | PEAR Sports LLC | Fitness and wellness system with dynamically adjusting guidance |
| CN103149939A (en) * | 2013-02-26 | 2013-06-12 | 北京航空航天大学 | Dynamic target tracking and positioning method of unmanned plane based on vision |
| CN104796672A (en) * | 2015-05-09 | 2015-07-22 | 合肥工业大学 | Emergency monitoring cloud platform device for unmanned aerial vehicle and operating method of emergency monitoring cloud platform device for unmanned aerial vehicle |
| CN204992418U (en) * | 2015-09-22 | 2016-01-20 | 南方电网科学研究院有限责任公司 | Automatic inspection device for defects of unmanned aerial vehicle power transmission line |
| CN105578101A (en) * | 2015-12-23 | 2016-05-11 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Helicopter photoelectric pod storage system and implementation method thereof |
| CN105959181A (en) * | 2016-06-17 | 2016-09-21 | 国网山东省电力公司电力科学研究院 | System and method for inspecting and detection power inspection unmanned aerial vehicle |
| CN205920414U (en) * | 2016-07-29 | 2017-02-01 | 苏州天地衡遥感科技有限公司 | Machine carries optoelectronic pod platform |
| CN106005455A (en) * | 2016-08-08 | 2016-10-12 | 北京宇鹰科技有限公司 | Two-axis pod system based on geographic coordinate system pointing control |
| CN106502259A (en) * | 2016-11-21 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Electric inspection process low profile photovoltaic gondola control device, gondola, unmanned plane and method |
| CN106647814A (en) * | 2016-12-01 | 2017-05-10 | 华中科技大学 | System and method of unmanned aerial vehicle visual sense assistant position and flight control based on two-dimensional landmark identification |
| CN106741008A (en) * | 2016-12-29 | 2017-05-31 | 北京交通大学 | Rail track method for recognizing impurities and system |
| CN106774436A (en) * | 2017-02-27 | 2017-05-31 | 南京航空航天大学 | The control system and method for the rotor wing unmanned aerial vehicle tenacious tracking target of view-based access control model |
| CN107203184A (en) * | 2017-06-20 | 2017-09-26 | 南京理工大学 | The dynamic control method of straight line steering wheel Electric Loading System |
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| CN107544531A (en) * | 2017-09-27 | 2018-01-05 | 成都纵横自动化技术有限公司 | Line data-logging method, apparatus and unmanned plane |
| CN108107920A (en) * | 2017-12-19 | 2018-06-01 | 天津工业大学 | A kind of microminiature twin shaft vision stablizes holder target detection tracing system |
Non-Patent Citations (3)
| Title |
|---|
| BAO GUI WANG: "The Control System Design of the Pod Based on Fuzzy-PID", 《APPLIED MECHANICS AND MATERIALS》 * |
| SHANZHONG LIU: "Research on stabilizing and tracking control system of tracking and sighting pod", 《JOURNAL OF CONTROL THEORY AND APPLICATIONS》 * |
| 王柯: "基于PID的电力巡检光电吊舱稳定平台控制系统设计", 《控制工程》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109765939A (en) * | 2018-12-21 | 2019-05-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Cloud platform control method, device and the storage medium of unmanned plane |
| CN109977924A (en) * | 2019-04-15 | 2019-07-05 | 北京麦飞科技有限公司 | For real time image processing and system on the unmanned plane machine of crops |
| CN110312071B (en) * | 2019-04-30 | 2021-02-02 | 中国联合网络通信集团有限公司 | Unmanned aerial vehicle control method and unmanned aerial vehicle |
| CN110312071A (en) * | 2019-04-30 | 2019-10-08 | 中国联合网络通信集团有限公司 | The control method and unmanned plane of unmanned plane |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN110351483A (en) * | 2019-08-05 | 2019-10-18 | 深圳职业技术学院 | A kind of adaptive zoom monitoring unmanned platform of more camera lenses and control method |
| CN110602484A (en) * | 2019-08-29 | 2019-12-20 | 海南电网有限责任公司海口供电局 | Online checking method for shooting quality of power transmission line equipment |
| CN110825110A (en) * | 2019-11-13 | 2020-02-21 | 昆明能讯科技有限责任公司 | Acquisition flight method for power line visible light point cloud resolving photo |
| CN110879602A (en) * | 2019-12-06 | 2020-03-13 | 安阳全丰航空植保科技股份有限公司 | Unmanned aerial vehicle control law parameter adjusting method and system based on deep learning |
| CN112585946A (en) * | 2020-03-27 | 2021-03-30 | 深圳市大疆创新科技有限公司 | Image shooting method, image shooting device, movable platform and storage medium |
| WO2021189429A1 (en) * | 2020-03-27 | 2021-09-30 | 深圳市大疆创新科技有限公司 | Image photographing method and device, movable platform, and storage medium |
| CN111669501A (en) * | 2020-06-18 | 2020-09-15 | 南方电网数字电网研究院有限公司 | Shooting method and device based on unmanned aerial vehicle, computer equipment and medium |
| CN111669501B (en) * | 2020-06-18 | 2021-10-22 | 南方电网数字电网研究院有限公司 | Shooting method and device based on unmanned aerial vehicle, computer equipment and medium |
| CN111860461A (en) * | 2020-08-05 | 2020-10-30 | 西安应用光学研究所 | Automatic zooming method for built-in optical sensor of photoelectric pod |
| CN111860461B (en) * | 2020-08-05 | 2024-02-27 | 西安应用光学研究所 | Autonomous zooming method for built-in optical sensor of photoelectric pod |
| CN112363176A (en) * | 2020-11-06 | 2021-02-12 | 日立楼宇技术（广州）有限公司 | Elevator shaft inspection and modeling method and device and inspection modeling system |
| CN112363176B (en) * | 2020-11-06 | 2023-08-04 | 日立楼宇技术（广州）有限公司 | Elevator hoistway inspection and modeling method and device and inspection and modeling system |
| WO2022126375A1 (en) * | 2020-12-15 | 2022-06-23 | 深圳市大疆创新科技有限公司 | Zooming method, imaging device, gimbal and movable platform |
| CN113415433B (en) * | 2021-07-30 | 2022-11-29 | 成都纵横大鹏无人机科技有限公司 | Pod attitude correction method and device based on three-dimensional scene model and unmanned aerial vehicle |
| CN113415433A (en) * | 2021-07-30 | 2021-09-21 | 成都纵横大鹏无人机科技有限公司 | Pod attitude correction method and device based on three-dimensional scene model and unmanned aerial vehicle |
| CN114511551A (en) * | 2022-02-22 | 2022-05-17 | 金华高等研究院(金华理工学院筹建工作领导小组办公室) | Ground damage identification system based on machine vision |
| CN114564049A (en) * | 2022-03-21 | 2022-05-31 | 厦门大学 | Unmanned aerial vehicle wide area search device and method based on deep learning |
| CN116543619A (en) * | 2023-07-04 | 2023-08-04 | 中国科学院长春光学精密机械与物理研究所 | Unmanned aerial vehicle photoelectric pod simulation training system |
| CN116543619B (en) * | 2023-07-04 | 2023-08-29 | 中国科学院长春光学精密机械与物理研究所 | Unmanned aerial vehicle photoelectric pod simulation training system |
| CN117750204A (en) * | 2023-11-14 | 2024-03-22 | 东南大学 | Visual synchronous tracking shooting method and device for moving target on conveying line |
| CN117750204B (en) * | 2023-11-14 | 2024-09-24 | 东南大学 | Visual synchronous tracking shooting method and device for moving target on conveying line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108803668B (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108803668A (en) | A kind of intelligent patrol detection unmanned plane Towed bird system of static object monitoring | |
| CN111272148B (en) | Unmanned aerial vehicle autonomous inspection self-adaptive imaging quality optimization method for power transmission line | |
| CN112164015B (en) | Monocular vision autonomous inspection image acquisition method and device and power inspection unmanned aerial vehicle | |
| CN106468918B (en) | Standardized data acquisition method and system for line inspection | |
| WO2021189456A1 (en) | Unmanned aerial vehicle inspection method and apparatus, and unmanned aerial vehicle | |
| US11017228B2 (en) | Method and arrangement for condition monitoring of an installation with operating means | |
| CN112904877A (en) | Automatic fan blade inspection system and method based on unmanned aerial vehicle | |
| CN108229587B (en) | Autonomous transmission tower scanning method based on hovering state of aircraft | |
| US20170142309A1 (en) | Imaging apparatus and imaging method | |
| CN112327906A (en) | Intelligent automatic inspection system based on unmanned aerial vehicle | |
| CN108475075A (en) | A kind of control method, device and holder | |
| CN109660721B (en) | Unmanned aerial vehicle flight shooting quality optimization method, system, equipment and storage medium | |
| JP7188832B1 (en) | Inspection system for unmanned flying vehicle and wind power generation equipment, and method for inspection of wind power generation equipment | |
| CN112859905A (en) | Unmanned aerial vehicle inspection route generation method and device for overhead power line and unmanned aerial vehicle | |
| CN115442532B (en) | Method, system, equipment and storage medium for fan non-stop inspection | |
| CN107509055A (en) | A kind of rotary panorama focus identification optronic tracker and its implementation | |
| CN111830045A (en) | Unmanned aerial vehicle wind power detection system and method based on BIM technology | |
| Ohta et al. | Image acquisition of power line transmission towers using UAV and deep learning technique for insulators localization and recognition | |
| CN111123962A (en) | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection | |
| CN106210647A (en) | Based on the method and system building base station coverage area full-view image of taking photo by plane | |
| CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
| CN207200874U (en) | A kind of rotary panorama focus identification optronic tracker | |
| CN112585945A (en) | Focusing method, device and equipment | |
| CN115713696A (en) | Reflective film identification method based on unmanned aerial vehicle acquired image | |
| CN115471764A (en) | Power transmission channel hidden danger detection method, system, equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191121 Address after: 510507 floor 9-11, A4, No. 181, science Avenue, Science City, Luogang District, Guangzhou City, Guangdong Province Applicant after: Guangzhou Bureau of Extra High Voltage Transmission Company of China Southern Power Grid Co., Ltd. Address before: 101399 silicon Shield Technology Park, 10 South Street, Shunyi District military camp, Beijing Applicant before: Aerospace Scene (Beijing) Technology Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |