CN109163928A - A kind of UAV Intelligent water intake system based on binocular vision - Google Patents
A kind of UAV Intelligent water intake system based on binocular vision Download PDFInfo
- Publication number
- CN109163928A CN109163928A CN201810978743.4A CN201810978743A CN109163928A CN 109163928 A CN109163928 A CN 109163928A CN 201810978743 A CN201810978743 A CN 201810978743A CN 109163928 A CN109163928 A CN 109163928A
- Authority
- CN
- China
- Prior art keywords
- water
- point
- unmanned plane
- image
- binocular vision
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 147
- 238000005070 sampling Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000011218 segmentation Effects 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims description 2
- 230000000877 morphologic effect Effects 0.000 claims description 2
- 238000012958 reprocessing Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 239000003643 water by type Substances 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003911 water pollution Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/10—Devices for withdrawing samples in the liquid or fluent state
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- 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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Hydrology & Water Resources (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of UAV Intelligent water intake system based on binocular vision, including multi-rotor unmanned aerial vehicle main body, it is characterized by: being provided with controller, wireless transmitter and GPS positioning system in the multi-rotor unmanned aerial vehicle main body, further include: ground monitoring center: the video image information of drone status, acquisition is received, stored and reprocessed, and information feedback is carried out to unmanned plane according to processing result image, manipulation adjustment is carried out to unmanned plane;Binocular vision module: being used for filming surface video image, and video image is sent to ground monitoring center by wireless transmitter;Line wheel is installed in the shaft of motor, and the rope of certain length is wound in line wheel, and rope connects water module.One kind provided by the invention can intelligently identify polluted water region and carry out the unmanned plane water intake system of the more depth of accurate single-point or multiple spot water quality sampling, and the operating efficiency of unmanned plane water intaking is greatly improved, and reduce manpower consumption, and easy to operate, practical value is high.
Description
Technical field
The present invention relates to a kind of UAV Intelligent water intake system based on binocular vision belongs to unmanned air vehicle technique, water quality prison
Survey technology and technical field of image processing.
Background technique
As economic continuous development and industrialized propulsion, water pollution are got worse, the monitoring and protecting of water environment is carved not
Rong Huan, currently, China's monitoring water environment mainly includes automatic monitoring and personal monitoring.Automatic monitoring relies on water quality online analyzer
Device carries out real-time water quality monitoring, but at high cost, can not widespread adoption, and detection data is single, for complicated water
There is still a need for collection in worksite water samples in laboratory progress water quality test for environment.Personal monitoring is still main mode at this stage, is needed
Personnel, which take after the specified sampled point of ship arrival samples, just can be carried out further water quality detection.The artificial sample period is long,
Working efficiency is low, needs to consume a large amount of manpower and material resources, and due to the complexity and diversity of sampled point, increases artificial
Sample difficulty and risk.
With the continuous development of unmanned air vehicle technique, unmanned plane has been widely used for military affairs, takes photo by plane, electric inspection process, environment
The fields such as mapping, people are still in the purposes for constantly expanding unmanned plane, and in monitoring water environment field, unmanned plane also be used to replace people
Work carries out water quality sampling work, but the current unmanned plane method of sampling lacks water pollution locating module and water surface distance measurement
Module causes unmanned plane that cannot intelligently identify Polluted area, can only sample by personnel's manipulation to specified sampled point, and
And sampling depth is inaccurate.Every unmanned plane is only equipped with a device for fetching water simultaneously, can be only done the sampling operation of single-point single, imitates
Rate is lower and is not suitable for the more depth water quality sampling work of single-point.Therefore how expeditiously to complete water quality sampling is to need at this stage
One of solve the problems, such as.Binocular vision technology obtains depth of view information using the image of binocular camera shooting, can carry out quantitative image
Measurement, measures unmanned plane apart from water surface elevation, Polluted area size etc..
Summary of the invention
The technical problem to be solved by the present invention is to how expeditiously complete water quality sampling.
In order to solve the above technical problems, the present invention provides a kind of UAV Intelligent water intake system based on binocular vision,
Including multi-rotor unmanned aerial vehicle main body, it is characterised in that: be provided with controller, wireless receiving and dispatching dress in the multi-rotor unmanned aerial vehicle main body
It sets and GPS positioning system, the controller is used to coordinate and command the operation of modules on unmanned plane;Modules include taking
Water module, binocular vision module, flight control modules, the wireless transmitter between ground monitoring center for carrying out nothing
Line communication;The GPS positioning system is used for the positioning of multi-rotor unmanned aerial vehicle main body;
Further include:
Ground monitoring center: being received, stored and reprocessed to the video image information of drone status, acquisition, and
Information feedback is carried out to unmanned plane according to processing result image, manipulation adjustment is carried out to unmanned plane, image information reprocessing includes
Marine pollution region is identified in real time using the method that multi-direction gray difference is analyzed, and determines sample point coordinate, based on binocular
Vision precise measurement unmanned plane is apart from water surface elevation;
Binocular vision module: the burnt same model camera such as including two is installed under multi-rotor unmanned aerial vehicle main body module
Portion, is used for filming surface video image, and video image is sent to ground monitoring center by wireless transmitter;
Water module, for sampling of fetching water.
A kind of UAV Intelligent water intake system based on binocular vision above-mentioned, it is characterised in that: water module is installed on
The horn lower end of unmanned plane, water module include electronic gripping arm and sampling bottle, and electronic gripping arm is installed on unmanned plane horn lower end, are used
In stablizing sampling bottle, the shaking of sampling container, line wheel are installed in the shaft of motor when avoiding flight, and a fixed length is wound in line wheel
The rope of degree, rope connect sampling bottle.
A kind of UAV Intelligent water intake system based on binocular vision above-mentioned, it is characterised in that: multi-rotor unmanned aerial vehicle master
Each rotor of body one water module of corresponding installation.
The method for fetching water of UAV Intelligent water intake system above-mentioned based on binocular vision, which is characterized in that including following
Step:
1) Image Acquisition: multi-rotor unmanned aerial vehicle main body is according to presetting flight parameter and flight path in water to be monitored
Flight, using the video image of the binocular vision module photograph water surface, is sent video image by wireless transmitter above domain
To ground monitoring center;
2) pollution positioning: ground monitoring center handles the video image that unmanned plane is shot in real time, using multi-party
The method analyzed to gray difference identifies Polluted area, determines sample point coordinate and is sent to unmanned plane by wireless transmitter
GPS positioning system, control multi-rotor unmanned aerial vehicle target region;
3) unmanned plane hovers: ground monitoring center is accurate by left mesh image, the right mesh image of binocular vision module photograph
Multi-rotor unmanned aerial vehicle main body is calculated away from water surface elevation, and elevation information is sent to controller by wireless transmitter, by
Controller control unmanned plane accurately hovers at the setting height of Polluted area overhead;
4) after unmanned plane hovers over sampled point overhead, water intaking order, more rotors water intaking sampling: are issued by ground monitoring center
After the wireless transmitter of unmanned plane main body receives water intaking order, signal is passed into controller, controller is detected and selected
Not used water module, the electronic gripping arm for controlling the water module are unclamped, and motor operating by motor drag rope, will restrict
The sampling bottle of rope connection submerges polluted water region, and rope lengths to be released meet predetermined water intaking depth and stop putting rope, according to not
With the sampling container of capacity, the time to be set is waited, until sampling bottle fills water;
5) sampling bottle is withdrawn: after sampling bottle fills water, controller controls motor reversal, and by sampling bottle pull-up, pull-up is to setting
When determining height, electronic gripping arm fastens sampling bottle, by the water module labeled as having used, and by water module label and water intaking position
Ground monitoring center is passed in confidence breath combination back, generates water detection sample report;
6) continue to fetch water/continue to test: when executing multiple depth water intaking work, unmanned plane continues hovering in present bit
It sets, repeats the operation of above-mentioned (4)-(5) step.After unmanned plane completes one place water intaking work, if not making there are also water module
With, then can continue water detection, until all water modules are in use state, then return fully loaded information to
Face monitoring center is controlled by ground monitoring center and withdraws unmanned plane, replaces sampling container, and update water module state.
Compared with existing unmanned plane method for fetching water, the UAV Intelligent water intake system of the invention based on binocular vision,
It can intelligently identify polluted water region and carry out the unmanned plane water intake system of the more depth of accurate single-point or multiple spot water quality sampling.It will take
Water module is installed on the horn lower end of unmanned plane, mountable multiple water modules, unmanned plane once sail can be completed multiple spot or
The more depth water intaking operations of single-point, efficiency significantly improve.Method based on the multi-direction gray difference analysis of the water surface identifies Polluted area,
Terminal module directly controls unmanned plane and carries out water intaking sampling, and water intaking operation intelligence degree is high, largely saves manpower.Utilize binocular
Vision module precise measurement unmanned plane is simple and efficient apart from water surface elevation.
Detailed description of the invention
Fig. 1 is water intaking unmanned plane Facad structure figure of the invention;
Fig. 2 is the flow chart of the method for fetching water of UAV Intelligent water intake system of the invention;
Fig. 3 is pollution location algorithm schematic diagram;
Fig. 4 is image three-dimensional intensity profile figure;
Fig. 5 is grey scale change curve;
Fig. 6 is the segmentation result figure of four direction;
Fig. 7 is Polluted area segmentation result figure;
Fig. 8 is binocular range measurement principle schematic diagram.
Specific embodiment
In order to be more clear technical solution of the present invention and implementation steps, it is explained in detail below in conjunction with attached drawing.
Fig. 1 is the unmanned plane front elevation of the present invention for sampling of fetching water, including multi-rotor unmanned aerial vehicle main body 1, binocular
Vision module 2, motor 3, line wheel 4, water module 5, ground monitoring center.Line wheel is installed in the shaft of motor, is twined in line wheel
Around the rope of certain length, for connecting the sampling bottle 7 in water module.Water module is installed on 8 lower end of unmanned plane horn, more
Each rotor of rotor wing unmanned aerial vehicle main body one water module of corresponding installation, unmanned plane have several rotors 9, can install correspondence
The water module of quantity, Fig. 1 are four wing unmanned planes, four water modules of corresponding installation.
Controller, wireless transmitter, navigation positioning system 10 are provided in the multi-rotor unmanned aerial vehicle main body.The control
Device processed is used to coordinate and command the operation of modules on unmanned plane;The wireless transmitter be used for ground monitoring center it
Between carry out wireless communication;The GPS positioning system is used for the positioning of multi-rotor unmanned aerial vehicle main body;
Binocular vision module, the burnt same model camera such as including two.
Water module includes electronic gripping arm 6 and sampling bottle 7, and electronic gripping arm is installed on 8 lower end of unmanned plane horn, for stablizing
Sampling bottle, the shaking of sampling container when avoiding flight.
As shown in Fig. 2, the method for fetching water of the UAV Intelligent water intake system of the invention based on binocular vision, including it is following
Step:
1) Image Acquisition: multi-rotor unmanned aerial vehicle main body is according to presetting flight parameter and flight path in water to be monitored
Flight, using the video image of the binocular vision module photograph water surface, is sent video image by wireless transmitter above domain
To ground monitoring center;
2) pollution positioning: ground monitoring center handles the video image of binocular vision module photograph in real time, base
Polluted-water is polluted compared to cleaning this darker priori knowledge of water body using the method for Threshold segmentation in image
Region recognition, but the water surface causes Surface Picture intensity profile extremely uneven due to stormy waves, using conventional method segmentation effect
Bad, the present invention identifies that Polluted area, algorithm are as shown in Figure 3 using the method for multi-direction gray difference analysis:
(1) the Surface Picture gray processing of binocular vision module photograph is handled first, as shown in figure 4, thinking of the image is
Variation of the grey scale pixel value on two-dimensional surface, gray scale Local modulus maxima is known as wave crest in image, and local minizing point is known as
Grey scale change on two-dimensional surface is decomposed into one-dimensional variation, that is, divided by trough in order to further analyze the variation of grey scale pixel value
Variation of image grayscale curve is not extracted from 0 °, 45 °, 90 °, 135 ° of four directions, acquires the average gray F of every curved_m,
Wherein d indicates 0 °, 45 °, 90 °, 135 ° of four directions, fd_mIt (i) is image the m articles grey scale change song along the direction d
The gray value of ith pixel on line, n are sum of all pixels;
(2) image is calculated according to the following formula along the ash of all grey scale change curves of 0 °, 45 °, 90 °, 135 ° four direction
Spend difference value S:
Select the maximum pixel grey scale change curve of gray difference value S, the grey scale change respectively on four direction
Pixel group of the pixel as subsequent analysis on curve, grey scale pixel value is f on the curved(i);
(3) gray value for traversing all pixels on curve searches for large scale wave crest point and large scale trough point, but practical
In the grey scale change curve be not a smooth curve, there is the grey scale change of many small scales on curve, such as Fig. 5 institute
Show.
According to wave crest and trough point all on following rule search grey scale change curve:
A is the abscissa at any point on grey scale change curve, if fd(a) meet first inequality in formula (1), then
(a,fdIt (a)) is wave crest point, if fd(a) meet second inequality in formula (1), then (a, fdIt (a)) is trough point,
If all wave crest points and trough point are respectively as follows: in grey scale curve
{pd_0(a0,fd(a0)),pd_2(a2,fd(a2)),...,pd_2t(a2t,fd(a2t))}
{pd_1(a1,fd(a1)),pd_3(a3,fd(a3)),...,pd_2t+1(a2t+1,fd(a2t+1))}
a0,a2,...,a2tIndicate wave crest point pixel coordinate, a1,a3,...,a2t+1Expression trough point pixel coordinate, t=0,
1,2,…
Resulting wave crest point is screened again according to above-mentioned formula (1) rule, obtains large scale wave crest point:
{Pd_0(b0,fd(b0)),Pd_2(b2,fd(b2)),...,Pd_2r(b2r,fd(b2r))}
Pd_1(_, _) it is exactly to indicate large scale wave crest point, b0,b2,...,b2rIndicate large scale wave crest point pixel coordinate, r=
0,1,2,…
Similarly, trough point is also subjected to primary screening according to above-mentioned formula (1) rule again, obtains large scale trough point:
{Pd_1(b1,fd(b1)),Pd_3(b3,fd(b3)),...,Pd_2r+1(b2r+1,fd(b2r+1))}
(4) since large scale wave crest and trough are alternately present, adjacent wave crest and trough are matched, obtain 2r+1
Wave crest-trough pair:
{(Pd_0,Pd_1),(Pd_1,Pd_2),(Pd_2,Pd_3),...,(Pd_2r,Pd_2r+1)}
The local segmentation step-length M of pixel between every a pair of wave crest-troughd_jWith local threshold Nd_jAre as follows:
Wherein j=0,1,2 ..., 2r;
(5) according to the following formula respectively on 0 °, 45 °, 90 °, 135 ° of four directions with local segmentation step-length Md_jFor step-length, office
Portion threshold value Nd_jIt is threshold value in [bj,bj+1] the gray level image block f (x, y) on section carries out Polluted area segmentation, segmentation knot
Fruit is gd_j(x, y), wherein (x, y) indicates the coordinate of pixel, section [0, bo] and [b2r+1, n] between image block segmentation step
Long and between threshold value and adjacent wave crest-trough pair image block is consistent, the segmentation result of four direction as shown in fig. 6, are as follows:
Wherein p, q ∈ { -1,0,1 }, p=1, q=0 at d=0 °, p=1, q=-1 at d=45 °, p=0, q at d=90 °
P=-1 when=0, d=135 °, q=-1;
(6) segmentation result of four direction obtained in above-mentioned steps is subjected to intersection operation, obtains final contaminated area
Regional partition result g (x, y), as shown in fig. 7, are as follows:
G (x, y)=g0°(x,y)|g45°(x,y)|g90°(x,y)|g135°(x,y)
g0°(x, y), g45°(x, y), g90°(x, y), g135°(x, y) is respectively original image in 0 °, 45 °, 90 °, 135 ° of directions
On segmentation result;
(7) it is partitioned into after Polluted area and morphologic filtering is carried out to segmentation result, tiny cavity in filling region, and put down
Slide circle calculates the center-of-mass coordinate of Polluted area, is sent to multi-rotor unmanned aerial vehicle master as sampled point, and by sample point coordinate
The GPS positioning system of body.
3, unmanned plane hovers: multi-rotor unmanned aerial vehicle main body flies to sampled point overhead, and ground monitoring center utilizes binocular vision
Feel that the image of module photograph obtains depth of view information, that is, measure multi-rotor unmanned aerial vehicle main body processed apart from water surface elevation, then will height
Information is sent to controller by wireless transmitter, is accurately hovered by controller control multi-rotor unmanned aerial vehicle main body in pollution
At the setting height of region overhead.Binocular range measurement principle is as shown in figure 8, specifically measure multi-rotor unmanned aerial vehicle main body processed apart from the water surface
The step of height are as follows:
According to similar triangle theory:
Obtain distance Z (depth of field) of the spatial point P apart from camera:
Wherein parallax range of the B between binocular camera, f are the focal length of camera, XL,XRRespectively spatial point P is in two cameras
Imaging point P on photoreceptorL,PRAbscissa, XL-XRAs parallax,
(1) camera calibration demarcates binocular camera using Zhang Shi standardization, obtains the inner parameter of single camera
Matrix K and distortion factor matrix D obtain the relative positional relationship between two cameras in left and right, i.e., right camera is relative to a left side
The translation vector T and spin matrix R of camera;
(2) binocular corrects, and is closed according to the monocular internal reference data obtained after camera calibration and two camera relative positions
System carries out left mesh image-right mesh image to eliminate distortion and row registration process respectively;
(3) Stereo matching carries out the Polluted area in left mesh image-right mesh image by sift Feature Points Matching algorithm
Stereo matching calculates parallax, and then calculates multi-rotor unmanned aerial vehicle main body away from water surface elevation by formula (3).
4, water intaking sampling: after unmanned plane hovers over sampled point overhead, by ground monitoring center issue water intaking order, rotor without
After the wireless transmitter of man-machine main body receives water intaking order, signal is passed into controller, controller is detected and selected not
The water module used, the electronic gripping arm that controller controls the module are unclamped, water intaking motor operating, by motor drag rope,
The sampling bottle that rope connects is submerged into polluted water region, rope lengths to be released meet predetermined water intaking depth and stop putting rope.Root
According to the sampling container of different capabilities, the time to be set is waited, until sampling bottle fills water.
5, sampling bottle is withdrawn: after sampling bottle fills water, controller controls motor reversal, and by sampling bottle pull-up, pull-up is to setting
When determining height, electronic gripping arm fastens sampling bottle, by the water module labeled as having used, and by water module label and water intaking position
Ground monitoring center is passed in confidence breath combination back, generates water detection sample report.6, continue to fetch water/continue to test: more when executing
When depth water intaking work, unmanned plane continues hovering in current location, repeats the operation of above-mentioned 4-5 step.Unmanned plane completes one
Place is fetched water after work, if there are also water modules to be not used, can continue water detection, until all water modules are equal
In use state, then fully loaded information is returned to ground monitoring center, is controlled by ground monitoring center and withdraws unmanned plane, replacement
Sampling container, and update water module state.
Claims (6)
1. a kind of UAV Intelligent water intake system based on binocular vision, including multi-rotor unmanned aerial vehicle main body, it is characterised in that: institute
It states and is provided with controller, wireless transmitter and GPS positioning system in multi-rotor unmanned aerial vehicle main body, the controller is for coordinating
With the operation of modules on commander's unmanned plane;The wireless transmitter between ground monitoring center for carrying out channel radio
Letter;The GPS positioning system is used for the positioning of multi-rotor unmanned aerial vehicle main body;
Further include:
Ground monitoring center: being received, stored and reprocessed to the video image information of drone status, acquisition, and according to
Processing result image carries out information feedback to unmanned plane, carries out manipulation adjustment to unmanned plane, image information reprocessing includes real-time
Ground identifies marine pollution region, determines sample point coordinate, is based on binocular vision precise measurement unmanned plane apart from water surface elevation;
Binocular vision module: the burnt same model camera such as including two is used for filming surface video image, and video image passes through
Wireless transmitter is sent to ground monitoring center;
Water module is connect, for sampling of fetching water.
2. a kind of UAV Intelligent water intake system based on binocular vision according to claim 1, it is characterised in that: water intaking
Module is installed on the horn lower end of unmanned plane, and water module includes electronic gripping arm and sampling bottle, and electronic gripping arm is installed on unmanned plane
Horn lower end, for stablizing sampling bottle, line wheel is installed in the shaft of motor, and the rope of certain length, rope are wound in line wheel
Connect sampling bottle.
3. a kind of UAV Intelligent water intake system based on binocular vision according to claim 2, it is characterised in that: more rotations
Each rotor of wing unmanned plane main body one water module of corresponding installation.
4. the method for fetching water of the UAV Intelligent water intake system according to claim 1 based on binocular vision, feature exist
In, comprising the following steps:
1) Image Acquisition: multi-rotor unmanned aerial vehicle main body is according to presetting flight parameter and flight path on waters to be monitored
Video image is sent to ground by wireless transmitter using the video image of the binocular vision module photograph water surface by Fang Feihang
Face monitoring center;
2) pollution positioning: ground monitoring center handles the video image that unmanned plane is shot in real time, utilizes multi-direction ash
The method for spending variance analysis identifies Polluted area, determines sample point coordinate and is sent to unmanned plane by wireless transmitter
GPS positioning system controls multi-rotor unmanned aerial vehicle target region;
3) unmanned plane hovers: ground monitoring center is accurately calculated by left mesh image, the right mesh image of binocular vision module photograph
Multi-rotor unmanned aerial vehicle main body sends controller to by wireless transmitter away from water surface elevation, and by elevation information out, by controlling
Device control unmanned plane accurately hovers at the setting height of Polluted area overhead;
4) water intaking sampling: after unmanned plane hovers over sampled point overhead, by ground monitoring center issue water intaking order, more rotors nobody
After the wireless transmitter of owner's body receives water intaking order, signal is passed into controller, controller detects and selects not make
Water module, the electronic gripping arm for controlling the water module are unclamped, and by motor drag rope, rope is connected for motor operating
The sampling bottle connect submerges polluted water region, and rope lengths to be released meet predetermined water intaking depth and stop putting rope, according to different appearances
The sampling container of amount waits the time to be set, until sampling bottle fills water;
5) sampling bottle is withdrawn: after sampling bottle fills water, controller controls motor reversal, and by sampling bottle pull-up, pull-up is to setting height
When spending, electronic gripping arm fastens sampling bottle, which is labeled as having used, and water module label and water intaking position are believed
Ground monitoring center is passed in breath combination back, generates water detection sample report;
6) continue to fetch water/continue to test: when executing multiple depth water intaking work, unmanned plane continues hovering in current location, weight
The operation of multiple above-mentioned (4)-(5) step.
5. the method for fetching water of the UAV Intelligent water intake system according to claim 4 based on binocular vision, feature exist
In,
In the step 2), determine that the specific steps of sample point coordinate include:
(1) the Surface Picture gray processing of binocular vision module photograph is handled first, the grey scale change on two-dimensional surface is decomposed
For one-dimensional variation, i.e., variation of image grayscale curve is extracted from 0 °, 45 °, 90 °, 135 ° of four directions respectively, acquire every curve
Average gray
Wherein d indicates 0 °, 45 °, 90 °, 135 ° of four directions, fd_mIt (i) is image along the direction d on the m articles grey scale change curve
The gray value of ith pixel, n are sum of all pixels;
(2) image is calculated according to the following formula along the gray scale difference of all grey scale change curves of 0 °, 45 °, 90 °, 135 ° four direction
Different value S:
Select the maximum pixel grey scale change curve of gray difference value S, the grey scale change curve respectively on four direction
On pixel group of the pixel as subsequent analysis, grey scale pixel value is f on the grey scale change curved(i);
(3) gray value for traversing all pixels on grey scale change curve, searches for large scale wave crest point and large scale trough point,
According to wave crest and trough point all on following rule search grey scale change curve:
A is the abscissa at any point on grey scale change curve, if fd(a) meet first inequality in formula (1), then (a, fd
It (a)) is wave crest point, if fd(a) meet second inequality in formula (1), then (a, fdIt (a)) is trough point,
If all wave crest points and trough point are respectively as follows: in grey scale curve
{pd_0(a0,fd(a0)),pd_2(a2,fd(a2)),...,pd_2t(a2t,fd(a2t))}
{pd_1(a1,fd(a1)),pd_3(a3,fd(a3)),...,pd_2t+1(a2t+1,fd(a2t+1))}
a0,a2,...,a2tIndicate wave crest point pixel coordinate, a1,a3,...,a2t+1Expression trough point pixel coordinate, t=0,1,2 ...
Resulting wave crest point is screened again according to above-mentioned formula (1) rule, obtains large scale wave crest point:
{Pd_0(b0,fd(b0)),Pd_2(b2,fd(b2)),...,Pd_2r(b2r,fd(b2r))}
Pd_1(_, _) it is exactly to indicate large scale wave crest point, b0,b2,...,b2rExpression large scale wave crest point pixel coordinate, r=0,1,
2,…
Similarly, trough point is also subjected to primary screening according to above-mentioned formula (1) rule again, obtains large scale trough point:
{Pd_1(b1,fd(b1)),Pd_3(b3,fd(b3)),...,Pd_2r+1(b2r+1,fd(b2r+1))}
(4) since large scale wave crest and trough are alternately present, adjacent wave crest and trough is matched, 2r+1 wave is obtained
Peak-trough pair:
{(Pd_0,Pd_1),(Pd_1,Pd_2),(Pd_2,Pd_3),...,(Pd_2r,Pd_2r+1)}
The local segmentation step-length M of pixel between every a pair of wave crest-troughd_jWith local threshold Nd_jAre as follows:
Wherein j=0,1,2 ..., 2r;
(5) according to the following formula respectively on 0 °, 45 °, 90 °, 135 ° of four directions with local segmentation step-length Md_jFor step-length, local threshold
Value Nd_jIt is threshold value in [bj,bj+1] the gray level image block f (x, y) on section carries out Polluted area segmentation, segmentation result is
gd_j(x, y), wherein (x, y) indicates the coordinate of pixel, section [0, bo] and [b2r+1, n] between image block segmentation step-length and
Image block between threshold value and adjacent wave crest-trough pair is consistent, the segmentation result of four direction are as follows:
Wherein p, q ∈ { -1,0,1 }, p=1, q=0 at d=0 °, p=1, q=-1 at d=45 °, p=0, q=0, d at d=90 °
P=-1, q=-1 at=135 °;
(6) segmentation result of four direction obtained in above-mentioned steps is subjected to intersection operation, obtains final Polluted area point
Result g (x, y) is cut, are as follows:
G (x, y)=g0°(x,y)|g45°(x,y)|g90°(x,y)|g135°(x,y)
g0°(x, y), g45°(x, y), g90°(x, y), g135°(x, y) is respectively original image on 0 °, 45 °, 90 °, 135 ° of directions
Segmentation result;
(7) it is partitioned into after Polluted area and morphologic filtering is carried out to segmentation result, tiny cavity in filling region, and smooth side
Boundary calculates the center-of-mass coordinate of Polluted area, is sent to multi-rotor unmanned aerial vehicle main body as sampled point, and by sample point coordinate
GPS positioning system.
6. the method for fetching water of the UAV Intelligent water intake system according to claim 4 based on binocular vision, feature exist
In,
In the step 3), the step of multi-rotor unmanned aerial vehicle main body is away from water surface elevation is calculated are as follows:
(1) camera calibration demarcates binocular camera using Zhang Shi standardization, obtains the inner parameter matrix of single camera
K and distortion factor matrix D obtain the relative positional relationship between two cameras in left and right, i.e., right camera is relative to left camera shooting
The translation vector T and spin matrix R of head;
(2) binocular corrects, according to the monocular internal reference data obtained after camera calibration and two camera relative positional relationships point
It is other that left mesh image-right mesh image is carried out to eliminate distortion and row registration process;
(3) Stereo matching carries out the Polluted area in left mesh image-right mesh image by sift Feature Points Matching algorithm three-dimensional
Matching, calculates parallax, and then calculates multi-rotor unmanned aerial vehicle main body away from water surface elevation by formula (3),
Wherein parallax range of the B between binocular camera, f are the focal length of camera, XL,XRRespectively spatial point P is photosensitive in two cameras
Imaging point P on deviceL,PRAbscissa, XL-XRAs parallax.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810978743.4A CN109163928A (en) | 2018-08-27 | 2018-08-27 | A kind of UAV Intelligent water intake system based on binocular vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810978743.4A CN109163928A (en) | 2018-08-27 | 2018-08-27 | A kind of UAV Intelligent water intake system based on binocular vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109163928A true CN109163928A (en) | 2019-01-08 |
Family
ID=64896893
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810978743.4A Pending CN109163928A (en) | 2018-08-27 | 2018-08-27 | A kind of UAV Intelligent water intake system based on binocular vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109163928A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111812284A (en) * | 2019-04-12 | 2020-10-23 | 西安天衡计量仪表有限公司 | Unmanned aerial vehicle system for water quality monitoring and method thereof |
CN112802127A (en) * | 2021-03-31 | 2021-05-14 | 深圳中科飞测科技股份有限公司 | Calibration method and device, calibration equipment and storage medium |
CN112946216A (en) * | 2021-01-29 | 2021-06-11 | 海西中科生态环境监测有限公司 | Intelligent water quality monitoring system |
CN113014904A (en) * | 2021-02-24 | 2021-06-22 | 苏州臻迪智能科技有限公司 | Method, device and system for processing inspection image of unmanned aerial vehicle and storage medium |
CN113256840A (en) * | 2021-07-14 | 2021-08-13 | 交通运输部天津水运工程科学研究所 | Port equipment inspection system based on unmanned aerial vehicle |
CN113624930A (en) * | 2021-07-12 | 2021-11-09 | 武汉青绿山水科技有限公司 | Black and odorous water body analysis and evaluation system and method |
CN113776872A (en) * | 2021-02-01 | 2021-12-10 | 深圳市疾病预防控制中心(深圳市卫生检验中心、深圳市预防医学研究所) | Detection sampling method for environmental pollutants |
CN115597498A (en) * | 2022-12-13 | 2023-01-13 | 成都铂贝科技有限公司(Cn) | Unmanned aerial vehicle positioning and speed estimation method |
CN116823822A (en) * | 2023-08-29 | 2023-09-29 | 山东航宇游艇发展有限公司 | Ship sheet metal part welding defect detection method based on visual characteristics |
TWI820975B (en) * | 2022-10-20 | 2023-11-01 | 晶睿通訊股份有限公司 | Calibration method of apparatus installation parameter and related surveillance device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103106659A (en) * | 2013-01-28 | 2013-05-15 | 中国科学院上海微***与信息技术研究所 | Open area target detection and tracking method based on binocular vision sparse point matching |
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 |
CN103871047A (en) * | 2013-12-31 | 2014-06-18 | 江南大学 | Gray level fluctuation threshold segmentation method of image with non-uniform illumination |
CN104122117A (en) * | 2014-08-06 | 2014-10-29 | 青岛理工大学 | River and lake water sample automatic control acquisition system based on multi-rotor unmanned aerial vehicle |
CN204323692U (en) * | 2014-11-19 | 2015-05-13 | 甘甜田 | Many rotor wing unmanned aerial vehicles |
CN104933718A (en) * | 2015-06-23 | 2015-09-23 | 广东省自动化研究所 | Physical coordinate positioning method based on binocular vision |
CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
CN107300486A (en) * | 2017-08-11 | 2017-10-27 | 上海拓攻机器人有限公司 | A kind of water quality sampling method and system based on unmanned plane |
CN206664926U (en) * | 2017-03-01 | 2017-11-24 | 北京中科遥数信息技术有限公司 | It is a kind of to have Aerial photography and the unmanned plane of sampling of water quality function |
-
2018
- 2018-08-27 CN CN201810978743.4A patent/CN109163928A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103106659A (en) * | 2013-01-28 | 2013-05-15 | 中国科学院上海微***与信息技术研究所 | Open area target detection and tracking method based on binocular vision sparse point matching |
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 |
CN103871047A (en) * | 2013-12-31 | 2014-06-18 | 江南大学 | Gray level fluctuation threshold segmentation method of image with non-uniform illumination |
CN104122117A (en) * | 2014-08-06 | 2014-10-29 | 青岛理工大学 | River and lake water sample automatic control acquisition system based on multi-rotor unmanned aerial vehicle |
CN204323692U (en) * | 2014-11-19 | 2015-05-13 | 甘甜田 | Many rotor wing unmanned aerial vehicles |
CN104933718A (en) * | 2015-06-23 | 2015-09-23 | 广东省自动化研究所 | Physical coordinate positioning method based on binocular vision |
CN206664926U (en) * | 2017-03-01 | 2017-11-24 | 北京中科遥数信息技术有限公司 | It is a kind of to have Aerial photography and the unmanned plane of sampling of water quality function |
CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
CN107300486A (en) * | 2017-08-11 | 2017-10-27 | 上海拓攻机器人有限公司 | A kind of water quality sampling method and system based on unmanned plane |
Non-Patent Citations (4)
Title |
---|
WEI WEI, ET AL.: "local Threshold Segmentation method based on multi-direction grayscale wave", 《2010 FIFTH INTERNATIONAL CONFERENCE ON FRONTIER OF COMPUTER SCIENCE AND TECHNOLOGY》 * |
张梁 等: "基于双目视觉的无人飞行器目标跟踪与定位", 《计算机工程与应用》 * |
李庆武等: "基于双目视觉的显著性目标检测方法", 《光学学报》 * |
王亭亭等: "小型无人机立体视觉目标追踪定位方法", 《电光与控制》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111812284A (en) * | 2019-04-12 | 2020-10-23 | 西安天衡计量仪表有限公司 | Unmanned aerial vehicle system for water quality monitoring and method thereof |
CN112946216A (en) * | 2021-01-29 | 2021-06-11 | 海西中科生态环境监测有限公司 | Intelligent water quality monitoring system |
CN113776872A (en) * | 2021-02-01 | 2021-12-10 | 深圳市疾病预防控制中心(深圳市卫生检验中心、深圳市预防医学研究所) | Detection sampling method for environmental pollutants |
CN113776872B (en) * | 2021-02-01 | 2022-08-02 | 深圳市疾病预防控制中心(深圳市卫生检验中心、深圳市预防医学研究所) | Detection sampling method for environmental pollutants |
CN113014904A (en) * | 2021-02-24 | 2021-06-22 | 苏州臻迪智能科技有限公司 | Method, device and system for processing inspection image of unmanned aerial vehicle and storage medium |
CN112802127A (en) * | 2021-03-31 | 2021-05-14 | 深圳中科飞测科技股份有限公司 | Calibration method and device, calibration equipment and storage medium |
CN113624930A (en) * | 2021-07-12 | 2021-11-09 | 武汉青绿山水科技有限公司 | Black and odorous water body analysis and evaluation system and method |
CN113624930B (en) * | 2021-07-12 | 2024-03-15 | 武汉青绿山水科技有限公司 | Black and odorous water body analysis and evaluation system and method |
CN113256840A (en) * | 2021-07-14 | 2021-08-13 | 交通运输部天津水运工程科学研究所 | Port equipment inspection system based on unmanned aerial vehicle |
TWI820975B (en) * | 2022-10-20 | 2023-11-01 | 晶睿通訊股份有限公司 | Calibration method of apparatus installation parameter and related surveillance device |
CN115597498A (en) * | 2022-12-13 | 2023-01-13 | 成都铂贝科技有限公司(Cn) | Unmanned aerial vehicle positioning and speed estimation method |
CN116823822A (en) * | 2023-08-29 | 2023-09-29 | 山东航宇游艇发展有限公司 | Ship sheet metal part welding defect detection method based on visual characteristics |
CN116823822B (en) * | 2023-08-29 | 2023-11-21 | 山东航宇游艇发展有限公司 | Ship sheet metal part welding defect detection method based on visual characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109163928A (en) | A kind of UAV Intelligent water intake system based on binocular vision | |
CN109460740B (en) | Ship identity recognition method based on AIS and video data fusion | |
CN106405040B (en) | A kind of water quality inspection based on unmanned machine, pollutant source tracing method | |
CN109591982B (en) | Unmanned monitoring underwater aquaculture robot | |
CN108919838B (en) | Binocular vision-based automatic tracking method for power transmission line of unmanned aerial vehicle | |
CN111856448A (en) | Marine obstacle identification method and system based on binocular vision and radar | |
CN109949361A (en) | A kind of rotor wing unmanned aerial vehicle Attitude estimation method based on monocular vision positioning | |
CN109711353B (en) | Ship waterline area identification method based on machine vision | |
CN108734103A (en) | The detection of moving target and tracking in satellite video | |
US10303943B2 (en) | Cloud feature detection | |
CN108919811A (en) | A kind of indoor mobile robot SLAM method based on tag label | |
CN109947097A (en) | A kind of the robot localization method and navigation application of view-based access control model and laser fusion | |
CN110110797B (en) | Water surface target training set automatic acquisition method based on multi-sensor fusion | |
CN109848073A (en) | A kind of apparatus and method for sorting coal and gangue | |
CN110147714A (en) | Coal mine gob crack identification method and detection system based on unmanned plane | |
CN108564787A (en) | Traffic observation procedure, system and equipment based on Floating Car method | |
CN114034296B (en) | Navigation signal interference source detection and identification method and system | |
CN116255908B (en) | Underwater robot-oriented marine organism positioning measurement device and method | |
CN109765931A (en) | A kind of near-infrared video automatic navigation method suitable for the patrol unmanned machine of breakwater | |
US10210389B2 (en) | Detecting and ranging cloud features | |
CN116978009A (en) | Dynamic object filtering method based on 4D millimeter wave radar | |
CN111311640B (en) | Unmanned aerial vehicle identification and tracking method based on motion estimation | |
CN114677531B (en) | Multi-mode information fusion method for detecting and positioning targets of unmanned surface vehicle | |
CN112862862B (en) | Aircraft autonomous oil receiving device based on artificial intelligence visual tracking and application method | |
CN116029981A (en) | Embryo egg automatic detection system based on industrial Internet sample library |
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 |
Application publication date: 20190108 |
|
RJ01 | Rejection of invention patent application after publication |