CN106325288A - Real-time identification method and real-time identification system for pesticide spraying sector angle of unmanned aerial vehicle - Google Patents
Real-time identification method and real-time identification system for pesticide spraying sector angle of unmanned aerial vehicle Download PDFInfo
- Publication number
- CN106325288A CN106325288A CN201610694478.8A CN201610694478A CN106325288A CN 106325288 A CN106325288 A CN 106325288A CN 201610694478 A CN201610694478 A CN 201610694478A CN 106325288 A CN106325288 A CN 106325288A
- Authority
- CN
- China
- Prior art keywords
- side separation
- pixel
- point
- pixel column
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000005507 spraying Methods 0.000 title abstract description 8
- 239000000575 pesticide Substances 0.000 title abstract description 7
- 238000000926 separation method Methods 0.000 claims description 131
- 239000007921 spray Substances 0.000 claims description 37
- 239000003814 drug Substances 0.000 claims description 32
- 238000005070 sampling Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 27
- 238000003384 imaging method Methods 0.000 claims description 19
- 238000002347 injection Methods 0.000 claims description 17
- 239000007924 injection Substances 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 230000009466 transformation Effects 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
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Catching Or Destruction (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a real-time identification method and a real-time identification system for a pesticide spraying sector angle of an unmanned aerial vehicle. The method comprises the steps of acquiring a real-time image which comprises a pesticide applying nozzle and a pesticide applying spraying sector; extracting a green component in the real-time image, and using the green component as an objective image; acquiring a central pixel of the objective image; according to the central pixel, acquiring a pixel a and a pixel b which are separated from the central pixel by m pixel distances in a vertical line which passes through the central pixel; acquiring a first horizontal line which passes through the pixel a and a second horizontal line that passes through the pixel b; acquiring a right upper side boundary point, a right lower side boundary point, a left upper boundary point and a left lower side boundary point; and acquiring the sector angle of the pesticide spraying sector according to the right upper boundary point, the right lower side boundary point, the left upper boundary point and the left lower side boundary point. The real-time identification method and the real-time identification system can realize quick identification for the pesticide spraying sector angle and furthermore satisfy a requirement for real-time performance.
Description
Technical field
The present invention relates to field of agricultural production technologies, be specifically related to a kind of unmanned plane spray medicine sector angle real-time identification method and
System.
Background technology
Obtain the size of sector angle of operation aviation plant protection unmanned plane shower nozzle ejection exactly for assessment herbal sprinkling width
Wide and working performance has important impact.Present stage obtains sector angle size multiple method.Such as by camera system to spraying
Device has carried out image acquisition, and image carries out denoising smooth, histogram equalization, optimal threshold extraction, binaryzation, rim detection
And marginalisation fine rule processes, use method of least square to calculate spray-cone angle on the spray edge line detected, obtain spray cone
Angle.Deng Wei et al. uses the method for digital camera shooting still photo to obtain pesticide spray in for the performance study of spreading nozzle
Mist coloured image, uses wavelet transformation to carry out denoising, is then converted into bianry image, and design Boundary extracting algorithm is extracted
Marginal information, carries out least square fitting finally according to the spray edge straight line obtained and obtains spreading of spray.
The shortcoming of existing sector angle recognition methods is: calculate the most time-consuming, it is impossible to meet the demand of real-time.Due to nothing
Man-machine when operation flight speed be generally higher than 3 meter per seconds, this speed caused calculating accurately sprinkling fabric width needs at 1 second
In, the path of minimum 3 meters obtains sufficient amount of sector angle image (being typically no less than 1.5 meters /), is otherwise calculated
Sprinkling fabric width precision can not arrive requirement.If by minimum 1.5 meters/, flight speed is 3 meter per seconds, and this means this reality to be carried out
Time calculating, needing to calculate the sector angle of every image the time spent is not more than 500 milliseconds.But this time restriction
More difficult in existing recognition methods accomplish.
Summary of the invention
For defect of the prior art, the present invention provides a kind of unmanned plane spray medicine sector angle real-time identification method and is
System, it is possible to realize the quick identification of spray medicine sector angle, meet the requirement of real-time.
For solving the problems referred to above, the invention provides techniques below scheme:
As shown from the above technical solution, unmanned plane of the present invention spray medicine sector angle real-time identification method, according to unmanned
Machine spray medicine and the feature of actual imaging, have employed the recognition methods such as step S4-S8, relative to traditional first acquisition spray medicine covering of the fan
Marginal information calculates the method for sector angle the most again, and the present invention has obvious speed advantage, it is possible to obtain sector angle in real time, full
The demand processed time full.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to
These accompanying drawings obtain other accompanying drawing.
Fig. 1 is the flow chart of the unmanned plane spray medicine sector angle real-time identification method that the embodiment of the present invention one provides；
Fig. 2 be image acquisition device comprise dispenser shower nozzle and dispenser injection covering of the fan real time imaging；
Fig. 3 is a kind of structural representation of the unmanned plane spray medicine sector angle real-time identifying system that the embodiment of the present invention two provides
Figure；
Fig. 4 is the another kind of structural representation of the unmanned plane spray medicine sector angle real-time identifying system that the embodiment of the present invention two provides
Figure.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is carried out clear, complete description, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
Below by accompanying drawing, the principle of the invention is described in further detail.The fan that the present invention proposes with previous investigators
The difference of angle, face recognition methods main reason is that at the shower nozzle spraying unmanned plane and the image capturing dress being loaded on unmanned plane
The position put is relatively-stationary, this make image obtain position be constant relative to shower nozzle.On the other hand, by obtaining
Body angle of inclination γ, and the image obtained is rotated, so make the image level obtained during imaging in ground level.Have
After the two prerequisite, the calculating of angle can not use the sector angle recognition methods that previous researcher provides, but logical
Cross the recognition methods quick obtaining sector angle that this method provides.The recognition methods that the present invention provides is made without histogram equalization
Change, optimal threshold extraction, binaryzation, rim detection etc. process, and therefore can be substantially reduced handling duration, improve processing speed,
Therefore the requirement of real-time can be met.
The embodiment of the present invention one provides a kind of unmanned plane spray medicine sector angle real-time identification method, sees Fig. 1, the method bag
Include following steps:
Step 101: obtain image acquisition device comprises dispenser shower nozzle and the real time imaging of dispenser injection covering of the fan, its
In, described image collecting device is arranged on unmanned plane.
Seeing Fig. 2, in this step, the image shown in Fig. 2 is the image acquisition device being arranged on unmanned plane
Comprise dispenser shower nozzle and dispenser injection covering of the fan real time imaging.
Step 102: extract the green component in described real time imaging, and using this green component as target image.
In this step, select green channel component as the target image of the extraction of separation, to a certain extent may be used
To avoid the interference of background at a distance.
Step 103: obtain the body inclination angle of described inorganic people during real time imaging described in described image acquisition device
Degree γ, if γ is more than or equal to first threshold, then rotates γ angle by described target image, so that described target image and level
Face is parallel.
In this step, obtain body angle of inclination γ during this video imaging according to the airbone gyro instrument, if when γ is more than
Or rotate γ angle equal to the target image that then step 102 obtained during first threshold so that image when imaging vertically downward,
I.e. make described target image and plane-parallel.
For example, it is possible to obtain body angle of inclination γ during this video imaging according to the airbone gyro instrument, such as γ ＞ 3 °
Time target image that step 102 is obtained rotate γ angle so that target image and plane-parallel.
Step 104: obtain described target image central pixel point C (x, y).
See Fig. 2, in this step, obtain target image central pixel point C (x, y).
Step 105: according to central pixel point, obtains on the vertical curve through described central pixel point, the most respectively away from
Pixel a and b from described central pixel point m pixel distance.
In this step, seeing Fig. 2, (m takes according to practical situation to obtain distance center pixel upper and lower orientation m pixel
Value, such as take 10), and with central pixel point pixel a and b on same vertical curve.
Step 106: obtain the first horizontal line through described pixel a, and the second level through described pixel b
Line.
In this step, see Fig. 2, obtain the first horizontal line 11 through described pixel a, and through described pixel
Second horizontal line 22 of some b.
Step 107: between the first horizontal line and the second horizontal line, by central pixel point, calculating the most to the right should
The second dervative of the pixel column on the right side of central pixel point, when the second dervative calculated a zero cross point occurs for the first time, then
Will appear from zero cross point current pixel row a upper pixel column and the first horizontal intersection point as upper right side separation Tr(x,
Y), continue to process to the right next pixel column, when zero cross point for the first time the most not in the presence of, working as of zero cross point will be occurred without for the first time
A upper pixel column of preceding pixel row and the second horizontal intersection point are as lower right side separation Br(x,y)；
Between the first horizontal line and the second horizontal line, by central pixel point, calculate this center pixel the most to the left
The second dervative of the pixel column on the left of Dian, when the second dervative calculated a zero cross point occurs for the first time, will appear from zero friendship
A upper pixel column of the current pixel row of crunode and the first horizontal intersection point are as upper left side separation Tl(x y), and continues
Process to the right next pixel column, when zero cross point for the first time the most not in the presence of, the current pixel of zero cross point will be occurred without for the first time
A upper pixel column of row and the second horizontal intersection point are as lower left side separation Bl(x,y)。
In this step, by central pixel point direction to both sides calculate each pixel column (between horizontal line a and b
Pixel) second dervative, during movement, to every string pixel, if the second dervative calculated occurs in that one for the first time
Zero cross point, the pixel of previous column and straight line (the first horizontal line 11) joining through a are designated as separation, and (point on right side is
Tr(x, y), the point in left side is Tl(x, y)), continues with next column pixel, when zero cross point for the first time the most not in the presence of, then by upper
The point that the pixel of one row intersects with the straight line (the second horizontal line 22) through b is labeled as separation, and (point on right side is Br(x,
Y), the point in left side is Bl(x,y))。
Further, in order to improve processing speed, by central pixel point, calculate the most to the right this central pixel point
Right side pixel column second dervative during, according to every k row sampling obtain corresponding pixel column, and calculate sampling obtain
The second dervative of pixel column；
Correspondingly, by central pixel point, calculate the second order of pixel column on the left of this central pixel point the most to the left
During derivative, obtain corresponding pixel column according to every k row sampling, and the second order calculating the pixel column that sampling obtains is led
Number.
Further, in order to avoid losing or missing lower right side separation and lower left side separation, upper right side is being obtained
Separation Tr(x, y), and continue process to the right next pixel column during, according to every h row sampling obtain corresponding pixel
Row, and calculate the second dervative of the pixel column that sampling obtains, wherein h is less than k；Such as, k=3, h=1.
Correspondingly, upper left side separation T is being obtainedl(x, y), and continue process next pixel column to the left during,
Obtain corresponding pixel column according to every h row sampling, and calculate the second dervative of the pixel column that sampling obtains.
Step 108: according to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side
Separation Tl(x, y) with described lower left side separation Bl(x y), obtains the sector angle θ of described dispenser injection covering of the fan.
In this step, after getting four separations, owing to target image being processed horizontal position by step 103
Put, therefore according to the principle on triangular parallel limit, i.e. calculate the sector angle θ of dispenser injection covering of the fan.
The unmanned plane spray medicine sector angle real-time identification method that the embodiment of the present invention provides, becomes with reality according to unmanned plane spray medicine
The feature of picture, have employed the recognition methods such as step 104-108, relative to traditional first acquisition spray medicine covering of the fan marginal information then
The method calculating sector angle again, the present invention has obvious speed advantage, it is possible to obtain sector angle in real time, meets process in real time
Demand.
Further, above-mentioned steps 108 specifically includes:
According to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl
(x, y) with described lower left side separation Bl(x, y), acquisition angle α and β:
According to angle α and the sector angle θ of β acquisition described dispenser injection covering of the fan:
θ=360-alpha-beta.
Wherein, Tr(y), Br(y), Tr(x), BrX () is respectively upper right side separation Tr(x, y), lower right side separation Br(x,
Y) y on target image, y, x, x coordinate；Tl(y), Bl(y), Tl(x), BlX () is respectively upper left side separation Tl(x, y) and
Lower left side separation Bl(x, y) y on target image, y, x, x coordinate.
Additionally, in actual spraying operation, sector angle water smoke is easily by unmanned plane rotor downwash wind field and outside natural wind
Frequently form suspension water smoke under the effect of field, and this water smoke is usually in sustained height with sector angle, may eventually form one
Irregular water smoke face, strengthens extraction edge line difficulty and even causes None-identified angle.
For solving the problems referred to above, further, can by central pixel point upwards after obtaining separation failure for the first time
Mobile n (n ＞ 0) individual pixel, so is conducive to more quickly obtaining separation, and the impact reducing sector angle water smoke causes covering of the fan
The probability of angle recognition failures.
Therefore, above-mentioned unmanned plane spray medicine sector angle real-time identification method also includes following processing procedure:
If step 107 cannot completely obtain described upper right side separation Tr(x, y), described lower right side separation Br(x,y)、
Described upper left side separation Tl(x, y) with described lower left side separation Bl(x, y), then by described central pixel point C (x, y) vertical
Move up n pixel, obtain new central pixel point C ' (x, y+n), then repeated execution of steps 105～107, if this energy
The described upper right side separation T of enough complete acquisitionsr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl
(x, y) with described lower left side separation Bl(x y), then performs step 108, otherwise continues new central pixel point C ' (x, y+
N), move n pixel straight up, and repeated execution of steps 105～107 is until described upper right side separation can all be obtained
Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x, y) with described lower left side separation Bl(x,
y)。
Here, by central pixel point C, (x, y) moves n pixel straight up, on the one hand moves upwardly so that required process
Pixel count tail off, on the other hand from shower nozzle more close to sector angle pixel affected by wind the least, so may insure that acquisition
The precision of separation and efficiency will not be affected substantially.
Visible, the embodiment of the present invention provide unmanned plane spray medicine sector angle real-time identification method, according to unmanned plane spray medicine and
The feature of actual imaging, it is possible to real-time acquisition sector angle, and can reduce to be affected by sector angle water smoke and cause sector angle identification
Failed probability.
In actual contrast, the unmanned plane spray medicine sector angle real-time identification method that the embodiment of the present invention provides is the most than ever
Recognition methods can reduce by process time of 10 times, the unmanned plane spray medicine sector angle real-time identification method that the present invention provides processes
The sector angle of one image about spends time 400ms, and conventional method is about 4～5s, and sector angle the most of the present invention extracts
Mortality can reduce by 10%.The computer configuration that experiment uses is CPU I3 4170, and 8G internal memory does not use multithreading, C++ and
OpenCV realizes.
The embodiment of the present invention two provides a kind of unmanned plane spray medicine sector angle real-time identifying system, sees Fig. 3, including:
First acquiring unit 31, comprises dispenser shower nozzle and dispenser injection covering of the fan for obtain image acquisition device
Real time imaging, wherein, described image collecting device is arranged on unmanned plane；
Extraction unit 32, for extracting the green component in described real time imaging, and using this green component as target figure
Picture；
Second acquisition unit 33, for obtaining described inorganic people during real time imaging described in described image acquisition device
Body angle of inclination γ, if γ is more than or equal to first threshold, then rotates γ angle by described target image, so that described target
Image and plane-parallel；
3rd acquiring unit 34, for obtain described target image central pixel point C (x, y)；
4th acquiring unit 35, for according to central pixel point, obtains on the vertical curve through described central pixel point,
The most respectively apart from pixel a and b of described central pixel point m pixel distance；
5th acquiring unit 36, for obtaining the first horizontal line through described pixel a, and through described pixel
Second horizontal line of b；
6th acquiring unit 37, is used between the first horizontal line and the second horizontal line, by central pixel point, successively
Calculate to the right the second dervative of pixel column on the right side of this central pixel point, when the second dervative calculated occurs one zero friendship for the first time
During crunode, the upper pixel column and the first horizontal intersection point that will appear from the current pixel row of zero cross point are demarcated as upper right side
Point Tr(x, y), and continues to process to the right next pixel column, when zero cross point for the first time the most not in the presence of, zero will be occurred without for the first time
A upper pixel column of the current pixel row in cross point and the second horizontal intersection point are as lower right side separation Br(x,y)；
And, between the first horizontal line and the second horizontal line, by central pixel point, calculate this center the most to the left
The second dervative of the pixel column on the left of pixel, when the second dervative calculated a zero cross point occurs for the first time, then will go out
A upper pixel column of the current pixel row of existing zero cross point and the first horizontal intersection point are as upper left side separation Tl(x, y),
Continue to process to the right next pixel column, when zero cross point for the first time the most not in the presence of, the current of zero cross point will be occurred without for the first time
A upper pixel column of pixel column and the second horizontal intersection point are as lower left side separation Bl(x,y)；
7th acquiring unit 38, for according to described upper right side separation Tr(x, y), described lower right side separation Br(x,
Y), described upper left side separation Tl(x, y) with described lower left side separation Bl(x y), obtains the covering of the fan of described dispenser injection covering of the fan
Angle θ.
Further, described 7th acquiring unit 38 specifically for:
According to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl
(x, y) with described lower left side separation Bl(x, y), acquisition angle α and β:
And according to angle α and the sector angle θ of β acquisition described dispenser injection covering of the fan:
θ=360-alpha-beta.
Further, seeing Fig. 4, said system also includes processing unit 39；
Correspondingly, if described 6th acquiring unit 37 cannot completely obtain described upper right side separation Tr(x, y), the described right side
Downside separation Br(x, y), described upper left side separation Tl(x, y) with described lower left side separation Bl(x, y), the most described process
Unit for by described central pixel point C (x y) moves n pixel straight up, obtains new central pixel point C ' (x, y+
n)；
Correspondingly, described 4th acquiring unit 35 performs to operate accordingly to the 6th acquiring unit 37, if this order six obtains
Take unit 37 and can completely obtain described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side
Separation Tl(x, y) with described lower left side separation Bl(x, y), the most correspondingly the 7th acquiring unit 38 is according to the 6th acquiring unit
The 37 described upper right side separation T obtainedr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x,
Y) with described lower left side separation Bl(x, y) obtains the sector angle θ of described dispenser injection covering of the fan, and the most described processing unit 39 is used
In continuing new central pixel point C ' (x, y+n) move n pixel straight up, obtains another central pixel point until the 6th
Acquiring unit can completely obtain described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side
Separation Tl(x, y) with described lower left side separation Bl(x,y)。
Further, described 6th acquiring unit 37, by central pixel point, calculates the most to the right this center pixel
During the second dervative of the pixel column on the right side of Dian, specifically for obtaining corresponding pixel column according to every k row sampling, and count
Calculate the second dervative of the pixel column that sampling obtains；
Correspondingly, described 6th acquiring unit 37, by central pixel point, calculates this central pixel point the most to the left
Left side pixel column second dervative during, according to every k row sampling obtain corresponding pixel column, and calculate sampling obtain
The second dervative of pixel column.
Further, described 6th acquiring unit 37 is obtaining upper right side separation Tr(x y), and continues to process to the right
During next pixel column, obtain corresponding pixel column according to every h row sampling, and calculate the two of the pixel column that sampling obtains
Order derivative, wherein h is less than k；
Correspondingly, described 6th acquiring unit 37 is obtaining upper left side separation Tl(x y), and continues under process to the left
During one pixel column, obtain corresponding pixel column according to every h row sampling, and calculate the second order of the pixel column that sampling obtains
Derivative.
The unmanned plane spray medicine sector angle real-time identifying system that the present embodiment provides may be used for performing described in above-described embodiment
Unmanned plane spray medicine sector angle real-time identification method, its concrete principle is similar with technique effect, the most no longer describes in detail.
In describing the invention, it should be noted that in this article, the relational terms of such as first and second or the like
It is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires or imply these
Relation or the order of any this reality is there is between entity or operation.And, term " includes ", " comprising " or it is any
Other variants are intended to comprising of nonexcludability, so that include the process of a series of key element, method, article or equipment
Not only include those key elements, but also include other key elements being not expressly set out, or also include for this process, side
The key element that method, article or equipment are intrinsic.In the case of there is no more restriction, statement " including ... " limit
Key element, it is not excluded that there is also other identical element in including the process of described key element, method, article or equipment.
Above example is merely to illustrate technical scheme, is not intended to limit；Although with reference to previous embodiment
The present invention is described in detail, it will be understood by those within the art that: it still can be to aforementioned each enforcement
Technical scheme described in example is modified, or wherein portion of techniques feature is carried out equivalent；And these are revised or replace
Change, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a unmanned plane spray medicine sector angle real-time identification method, it is characterised in that including:
S1, obtain image acquisition device comprise dispenser shower nozzle and dispenser injection covering of the fan real time imaging, wherein, described figure
As harvester is arranged on unmanned plane；
S2, the green component extracted in described real time imaging, and using this green component as target image；
S3, obtain the body angle of inclination γ of described inorganic people during real time imaging described in described image acquisition device, if γ
More than or equal to first threshold, then described target image is rotated γ angle, so that described target image and plane-parallel；
S4, obtain described target image central pixel point C (x, y)；
S5, according to central pixel point, obtain on the vertical curve through described central pixel point, the most respectively apart from described center
Pixel a and b of m pixel distance of pixel；
S6, obtain through first horizontal line of described pixel a, and the second horizontal line through described pixel b；
S7, between the first horizontal line and the second horizontal line, by central pixel point, calculate the most to the right this central pixel point
The second dervative of the pixel column on right side, when the second dervative calculated a zero cross point occurs for the first time, then will appear from zero friendship
A upper pixel column of the current pixel row of crunode and the first horizontal intersection point are as upper right side separation Tr(x, y), continue to
Next pixel column of right process, when zero cross point for the first time the most not in the presence of, the current pixel row of zero cross point will be occurred without for the first time
A upper pixel column and the second horizontal intersection point as lower right side separation Br(x,y)；
Between the first horizontal line and the second horizontal line, by central pixel point, calculate this central pixel point the most to the left left
The second dervative of the pixel column of side, when the second dervative calculated a zero cross point occurs for the first time, will appear from zero cross point
Current pixel row a upper pixel column and the first horizontal intersection point as upper left side separation Tl(x y), and continues to the right
Process next pixel column, when zero cross point for the first time the most not in the presence of, the current pixel row of zero cross point will be occurred without for the first time
A upper pixel column and the second horizontal intersection point are as lower left side separation Bl(x,y)；
S8, according to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl
(x, y) with described lower left side separation Bl(x y), obtains the sector angle θ of described dispenser injection covering of the fan.
Unmanned plane the most according to claim 1 spray medicine sector angle real-time identification method, it is characterised in that described S8 includes:
According to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x,
Y) with described lower left side separation Bl(x, y), acquisition angle α and β:
According to angle α and the sector angle θ of β acquisition described dispenser injection covering of the fan:
θ=360-alpha-beta；
Wherein, Tr(y), Br(y), Tr(x), BrX () is respectively upper right side separation Tr(x, y), lower right side separation Br(x y) exists
Y on target image, y, x, x coordinate；Tl(y), Bl(y), Tl(x), BlX () is respectively upper left side separation Tl(x, y) and lower-left
Side separation Bl(x, y) at the y of target image, y, x, x coordinate.
Unmanned plane the most according to claim 1 spray medicine sector angle real-time identification method, it is characterised in that described method is also wrapped
Include:
If S7 cannot completely obtain described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side
Separation Tl(x, y) with described lower left side separation Bl(x, y), then by described central pixel point C, (x y) moves n straight up
Pixel, obtains new central pixel point C ' (x, y+n), then repeat S5～S7, if this can completely obtain the described right side
Upside separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x, y) with described lower left side
Separation Bl(x y), then performs S8, otherwise continues new central pixel point C ' (x, y+n), move n pixel straight up,
And repeat S5～S7 until described upper right side separation T can completely be obtainedr(x, y), described lower right side separation Br(x,
Y), described upper left side separation Tl(x, y) with described lower left side separation Bl(x,y)。
Unmanned plane the most according to claim 1 spray medicine sector angle real-time identification method, it is characterised in that by center pixel
Point starts, during calculating the most to the right the second dervative of pixel column on the right side of this central pixel point, according to every k row sampling
Obtain corresponding pixel column, and calculate the second dervative of the pixel column that sampling obtains；
Correspondingly, by central pixel point, calculate the second dervative of pixel column on the left of this central pixel point the most to the left
During, obtain corresponding pixel column according to every k row sampling, and calculate the second dervative of the pixel column that sampling obtains.
Unmanned plane the most according to claim 4 spray medicine sector angle real-time identification method, it is characterised in that obtaining upper right
Side separation Tr(x, y), and continue process to the right next pixel column during, according to every h row sampling obtain corresponding picture
Element row, and calculate the second dervative of the pixel column that sampling obtains, wherein h is less than k；
Correspondingly, upper left side separation T is being obtainedl(x, y), and continue process next pixel column to the left during, according to often
Obtain corresponding pixel column every h row sampling, and calculate the second dervative of the pixel column that sampling obtains.
6. a unmanned plane spray medicine sector angle real-time identifying system, it is characterised in that including:
First acquiring unit, comprises dispenser shower nozzle and the real-time figure of dispenser injection covering of the fan for obtain image acquisition device
Picture, wherein, described image collecting device is arranged on unmanned plane；
Extraction unit, for extracting the green component in described real time imaging, and using this green component as target image；
Second acquisition unit, in time obtaining real time imaging described in described image acquisition device, the body of described inorganic people inclines
Rake angle γ, if γ is more than or equal to first threshold, then rotates γ angle by described target image so that described target image with
Plane-parallel；
3rd acquiring unit, for obtain described target image central pixel point C (x, y)；
4th acquiring unit, for according to central pixel point, obtains on the vertical curve through described central pixel point, divides up and down
Not apart from pixel a and b of described central pixel point m pixel distance；
5th acquiring unit, for obtaining through first horizontal line of described pixel a, and through the of described pixel b
Two horizontal lines；
6th acquiring unit, between the first horizontal line and the second horizontal line, by central pixel point, counts the most to the right
Calculate the second dervative of pixel column on the right side of this central pixel point, when the second dervative calculated occurs a zero cross point for the first time
Time, will appear from zero cross point current pixel row a upper pixel column and the first horizontal intersection point as upper right side separation Tr
(x, y), and continues to process to the right next pixel column, when zero cross point for the first time the most not in the presence of, zero crossing will be occurred without for the first time
A upper pixel column of the current pixel row of point and the second horizontal intersection point are as lower right side separation Br(x,y)；
And, between the first horizontal line and the second horizontal line, by central pixel point, calculate this center pixel the most to the left
The second dervative of the pixel column on the left of Dian, when the second dervative calculated a zero cross point occurs for the first time, then will appear from zero
A upper pixel column of the current pixel row in cross point and the first horizontal intersection point are as upper left side separation Tl(x y), continues
Process to the right next pixel column, when zero cross point for the first time the most not in the presence of, the current pixel of zero cross point will be occurred without for the first time
A upper pixel column of row and the second horizontal intersection point are as lower left side separation Bl(x,y)；
7th acquiring unit, for according to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described
Upper left side separation Tl(x, y) with described lower left side separation Bl(x y), obtains the sector angle θ of described dispenser injection covering of the fan.
Unmanned plane the most according to claim 6 spray medicine sector angle real-time identifying system, it is characterised in that the described 7th obtains
Unit specifically for:
According to described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x,
Y) with described lower left side separation Bl(x, y), acquisition angle α and β:
And according to angle α and the sector angle θ of β acquisition described dispenser injection covering of the fan:
θ=360-alpha-beta；
Wherein, Tr(y), Br(y), Tr(x), BrX () is respectively upper right side separation Tr(x, y), lower right side separation Br(x y) exists
Y on target image, y, x, x coordinate；Tl(y), Bl(y), Tl(x), BlX () is respectively upper left side separation Tl(x, y) and lower-left
Side separation Bl(x, y) at the y of target image, y, x, x coordinate.
Unmanned plane the most according to claim 6 spray medicine sector angle real-time identifying system, it is characterised in that also include processing list
Unit；
Correspondingly, if described 6th acquiring unit cannot completely obtain described upper right side separation Tr(x, y), described lower right side divides
Boundary point Br(x, y), described upper left side separation Tl(x, y) with described lower left side separation Bl(x, y), the most described processing unit is used
In by described central pixel point C (x y) moves n pixel straight up, obtains new central pixel point C ' (x, y+n)；
Correspondingly, described 4th acquiring unit to the 6th acquiring unit performs corresponding operation, if this order six acquiring unit energy
The described upper right side separation T of enough complete acquisitionsr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl
(x, y) with described lower left side separation Bl(x, y), the most correspondingly the 7th acquiring unit is according to described in the 6th acquiring unit acquisition
Upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x, y) with described lower-left
Side separation Bl(x, y) obtains the sector angle θ of described dispenser injection covering of the fan, and the most described processing unit is for continuing in new
Imago vegetarian refreshments C ' (x, y+n) moves n pixel straight up, obtains another central pixel point until the 6th acquiring unit can be complete
Whole acquisition described upper right side separation Tr(x, y), described lower right side separation Br(x, y), described upper left side separation Tl(x,y)
With described lower left side separation Bl(x,y)。
Unmanned plane the most according to claim 6 spray medicine sector angle real-time identifying system, it is characterised in that the described 6th obtains
Unit by central pixel point, calculates the most to the right the process of the second dervative of pixel column on the right side of this central pixel point
In, specifically for obtaining corresponding pixel column according to every k row sampling, and calculate the second dervative of the pixel column that sampling obtains；
Correspondingly, described 6th acquiring unit, by central pixel point, calculates on the left of this central pixel point the most to the left
During the second dervative of pixel column, obtain corresponding pixel column according to every k row sampling, and calculate the pixel that sampling obtains
The second dervative of row.
Unmanned plane the most according to claim 9 spray medicine sector angle real-time identifying system, it is characterised in that the described 6th obtains
Take unit and obtain upper right side separation Tr(x, y), and continue process to the right next pixel column during, according to every h
The row sampling corresponding pixel column of acquisition, and calculate the second dervative of the pixel column that sampling obtains, wherein h is less than k；
Correspondingly, described 6th acquiring unit is obtaining upper left side separation Tl(x y), and continues to process next pixel to the left
During row, obtain corresponding pixel column according to every h row sampling, and calculate the second dervative of the pixel column that sampling obtains.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610694478.8A CN106325288B (en) | 2016-08-19 | 2016-08-19 | Unmanned aerial vehicle pesticide spraying fan angle real-time identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610694478.8A CN106325288B (en) | 2016-08-19 | 2016-08-19 | Unmanned aerial vehicle pesticide spraying fan angle real-time identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106325288A true CN106325288A (en) | 2017-01-11 |
| CN106325288B CN106325288B (en) | 2020-05-22 |
Family
ID=57744792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610694478.8A Active CN106325288B (en) | 2016-08-19 | 2016-08-19 | Unmanned aerial vehicle pesticide spraying fan angle real-time identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106325288B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112731964A (en) * | 2020-12-16 | 2021-04-30 | 彩虹无人机科技有限公司 | Attack area off-line planning method for low-speed unmanned aerial vehicle bomb launching sector angle condition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203946276U (en) * | 2014-07-01 | 2014-11-19 | 中国农业大学 | Single rotor plant protection unmanned plane pesticide spraying system |
| CN105173085A (en) * | 2015-09-18 | 2015-12-23 | 山东农业大学 | Automatic control system and method for variable pesticide spraying of unmanned aerial vehicle |
-
2016
- 2016-08-19 CN CN201610694478.8A patent/CN106325288B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203946276U (en) * | 2014-07-01 | 2014-11-19 | 中国农业大学 | Single rotor plant protection unmanned plane pesticide spraying system |
| CN105173085A (en) * | 2015-09-18 | 2015-12-23 | 山东农业大学 | Automatic control system and method for variable pesticide spraying of unmanned aerial vehicle |
Non-Patent Citations (6)
| Title |
|---|
| 史春建: "植保机械雾化性能的图像检测方法研究", 《中国优秀硕士学位论文全文数据库农业科技辑》 * |
| 史春建等: "基于机器视觉的常温烟雾机喷雾角测量系统", 《农业机械学报》 * |
| 孙家抦等: "《遥感原理与应用》", 30 June 2013, 武汉大学出版社 * |
| 杨金中等: "《矿山遥感检测理论方法与实践》", 30 September 2011, 测绘出版社 * |
| 胡传胜等: "喷嘴液滴雾化细度和喷雾角测量装置的研究", 《能源研究与信息》 * |
| 龚声蓉等: "《数字图像处理与分析》", 31 May 2014, 清华大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112731964A (en) * | 2020-12-16 | 2021-04-30 | 彩虹无人机科技有限公司 | Attack area off-line planning method for low-speed unmanned aerial vehicle bomb launching sector angle condition |
| CN112731964B (en) * | 2020-12-16 | 2022-10-21 | 彩虹无人机科技有限公司 | Attack area off-line planning method for low-speed unmanned aerial vehicle bomb launching sector angle condition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106325288B (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145545B (en) | Road traffic behavior unmanned aerial vehicle monitoring system and method based on deep learning | |
| CN106203265B (en) | A kind of Construction Fugitive Dust Pollution source monitors automatically and coverage forecasting system and method | |
| CN103164706B (en) | Object counting method and device based on video signal analysis | |
| CN104751486B (en) | A kind of moving target relay tracking algorithm of many ptz cameras | |
| CN110348445A (en) | A kind of example dividing method merging empty convolution sum marginal information | |
| WO2016106955A1 (en) | Laser infrared composite ground building recognition and navigation method | |
| CN105910583B (en) | A kind of space junk based on spaceborne Visible Light Camera quickly detects localization method | |
| CN104574365B (en) | Obstacle detector and method | |
| CN109670503A (en) | Label detection method, apparatus and electronic system | |
| CN107450590A (en) | A kind of unmanned plane auxiliary landing method | |
| CN108229407A (en) | A kind of behavioral value method and system in video analysis | |
| CN105122303A (en) | Camera calibration using feature identification | |
| CN109949229A (en) | A kind of target cooperative detection method under multi-platform multi-angle of view | |
| CN107139666A (en) | Obstacle detouring identifying system and method | |
| CN104899894B (en) | A kind of method that use multiple cameras carries out motion target tracking | |
| CN102073846A (en) | Method for acquiring traffic information based on aerial images | |
| CN106897681A (en) | A kind of remote sensing images comparative analysis method and system | |
| CN107146239A (en) | Satellite video moving target detecting method and system | |
| CN102945554A (en) | Target tracking method based on learning and speeded-up robust features (SURFs) | |
| CN107527037A (en) | Blue-green algae identification and analysis system based on unmanned aerial vehicle remote sensing data | |
| CN107808524A (en) | A kind of intersection vehicle checking method based on unmanned plane | |
| CN110472628A (en) | A kind of improvement Faster R-CNN network detection floating material method based on video features | |
| CN106548131A (en) | A kind of workmen's safety helmet real-time detection method based on pedestrian detection | |
| Al-Sheary et al. | Crowd monitoring system using unmanned aerial vehicle (UAV) | |
| CN107220992A (en) | With reference to machine vision and the escalator floor plates video frequency monitoring method of infrared array |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |