CN106097271A - The desert areas Road Detection platform being positioned on unmanned plane - Google Patents
The desert areas Road Detection platform being positioned on unmanned plane Download PDFInfo
- Publication number
- CN106097271A CN106097271A CN201610413079.XA CN201610413079A CN106097271A CN 106097271 A CN106097271 A CN 106097271A CN 201610413079 A CN201610413079 A CN 201610413079A CN 106097271 A CN106097271 A CN 106097271A
- Authority
- CN
- China
- Prior art keywords
- road
- image
- equipment
- value
- desert areas
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000001914 filtration Methods 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 12
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 239000004576 sand Substances 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000013011 mating Effects 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims 1
- 238000003379 elimination reaction Methods 0.000 claims 1
- 239000003595 mist Substances 0.000 claims 1
- 239000000203 mixture Substances 0.000 abstract description 6
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- VOYADQIFGGIKAT-UHFFFAOYSA-N 1,3-dibutyl-4-hydroxy-2,6-dioxopyrimidine-5-carboximidamide Chemical compound CCCCn1c(O)c(C(N)=N)c(=O)n(CCCC)c1=O VOYADQIFGGIKAT-UHFFFAOYSA-N 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 150000003839 salts Chemical group 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
Abstract
The present invention relates to a kind of desert areas Road Detection platform being positioned on unmanned plane, equipment is positioned including GPS, pressure altitude sensing equipment, linear array digital aviation photographic equipment, image detecting apparatus and embedded processing equipment, embedded processing equipment positions equipment with GPS, pressure altitude sensing equipment, linear array digital aviation photographic equipment and image detecting apparatus connect respectively, real time positioning data based on the equipment output of GPS location and the real-time of air pressure highly sensing equipment output the most highly determine whether to start linear array digital aviation photographic equipment and image detecting apparatus to realize the Road Detection to desert areas.The present invention also uses sharpening processing equipment to eliminate the haze composition in aerial photographing image.By means of the invention it is possible under the desert haze weather of various complexity, the desert areas of complex landform is realized road Identification fast, accurately.
Description
The present invention is Application No. 201510163007.X, filing date on April 8th, 2015, invention entitled " is positioned at nothing
Desert areas Road Detection platform on man-machine " the divisional application of patent.
Technical field
The present invention relates to electronics survey field, particularly relate to a kind of desert areas Road Detection being positioned on unmanned plane and put down
Platform.
Background technology
Desert, refers to that ground is covered by sand completely, plant is the most rare, rainwater is rare, air dried uncultivated area.
" sand curtain ", i.e. drought and water shortage are also made in desert, the area that plant is rare.Region, desert is sandy beach or sand dune mostly, and husky lower rock is also
Often occur.Some desert is salt flat, entirely without vegetation.Desert is usually eolian landform.The rare resident in desert, Climate Dryness
Dry, compared with other landform, it is easier to produce haze weather.But, the resource in desert is abundanter, and appearance is also compared in development of resources
Easily, needing people to go to desert areas to carry out development of resources, at this moment, the road of desert areas is drawn the most important.
But, in road draws the daily road drawing of department, the location of relatively simple is urban road and
Route is drawn, because urban road has road and the obvious typical characteristic of urban background edge boundary, therefore uses satellite distant
Related roads information can be effectively extracted in sense, and the road for desert area is drawn, and due to a varied topography, road is carried on the back with desert
The edge boundary of scape obscures, and some roads Bu Shi road administration department builds, but the dirt road that local resident renovates, the most passing
The irregular route that vehicle rolls for a long time and formed, the mode at this moment re-using satellite remote sensing carries out road survey, and its precision is full
Foot the most not requirement, and go to carry out road survey by the means of on-site land survey, its real-time and efficiency is the poorest.
Accordingly, it would be desirable to the technical scheme of a kind of new desert areas Road Detection, it is possible to for the desert area of complex landform
Territory, formulates specific testing mechanism and detection platform targetedly, and various haze weather can be overcome testing result
Impact, thus quickly, accurately, reliably complete the measurement to desert areas road and location.
Summary of the invention
In order to solve the problems referred to above, the invention provides a kind of desert areas Road Detection platform being positioned on unmanned plane,
Utilize unmanned plane feature flexible, comprehensive, improve identification high efficiency and the real-time of identification system of the present invention, meanwhile, for essence
Really obtain the relevant information of desert areas road, to the processing sequence of each image processing equipment with in processing on recognition mechanism
Appearance is customized, to improve the accuracy of detection of the present invention, more it is essential that determine that haze is to image according to atmospheric attenuation model
Influence factor, and go hazeization to process the detection image gathered under foggy days, improve the reliability of detection platform.
According to an aspect of the present invention, it is provided that a kind of desert areas Road Detection platform being positioned on unmanned plane, described
Detection platform include GPS location equipment, pressure altitude sensing equipment, linear array digital aviation photographic equipment, image detecting apparatus and
Embedded processing equipment, described embedded processing equipment and described GPS location equipment, described pressure altitude sensing equipment, described
Linear array digital aviation photographic equipment and described image detecting apparatus connect respectively, based on the equipment output of described GPS location real-time
Location data and the real-time of described pressure altitude sensing equipment output highly determine whether to start the photography of described linear array digital aviation
Equipment and described image detecting apparatus are to realize the Road Detection to described desert areas.
More specifically, in the described desert areas Road Detection platform being positioned on unmanned plane, also include: power supply,
Including solar powered device, accumulator, switching switch and electric pressure converter, described switching switch and described solar energy electric supplier
Part and described accumulator connect respectively, according to accumulator dump energy decide whether to be switched to described solar powered device with by
Described solar powered device is powered, and described electric pressure converter is connected with described switching switch, will be inputted by switching switch
5V voltage be converted to 3.3V voltage；Static storage device, is used for prestoring desert areas road R channel range, desert area
Territory road G channel range, desert areas road channel B scope, described desert areas road R channel range, described desert areas
Road G channel range and described desert areas road channel B scope are for scheming the desert areas road in RGB image with RGB
As background separation；Wireless communication interface, draws service platform with the road of far-end and sets up two-way wireless communication link, be used for connecing
Receiving described road and draw the flight control instruction that service platform sends, described flight control instruction is just including described desert areas
Purpose gps data that top position is corresponding and purpose shooting height；Sharpening processing equipment, is positioned at described linear array digital aviation and takes the photograph
Between shadow equipment and described image detecting apparatus, receive the desert that desert areas is shot by described linear array digital aviation photographic equipment
Area image, goes described desert areas image haze to process and removes haze desert areas image to obtain, substitute described sand
Unconcerned area image, goes haze desert areas image to input described image detecting apparatus to realize described desert areas by described
Road Detection；Described sharpening processing equipment includes: haze Concentration Testing subset, is positioned in air, detects nothing in real time
The haze concentration of man-machine position, and determine that intensity removed by haze according to haze concentration, described haze removes intensity value 0
Between 1；Overall air light value obtains subset, is connected to obtain described desert area with described linear array digital aviation photographic equipment
Area image, calculates the gray value of each pixel in the image of described desert areas, using the gray value of pixel maximum for gray value as
Overall air light value；Atmospheric scattering light value obtains subset, with described linear array digital aviation photographic equipment and described haze concentration
Detection subset connects respectively, and each pixel to described desert areas image extracts its R, G, B tri-Color Channel pixel value
Middle minima, as target pixel value, uses the Gaussian filter EPGF (edge-preserving keeping edge
Gaussian filter) it is filtered processing to obtain filtered target pixel value, by target pixel value to described target pixel value
Deduct filtered target pixel value to obtain object pixel difference, use EPGF to be filtered object pixel difference processing to obtain
Filtered target pixel value difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes reference value, will
Intensity of removing haze is multiplied by haze removal reference value removes threshold value to obtain haze, takes haze and removes in threshold value and target pixel value
Minima as comparison reference, take the atmospheric scattering light value as each pixel of the maximum in comparison reference and 0；
Medium transmission rate obtains subset, obtains subset with described overall air light value and described atmospheric scattering light value obtains subset
Connect respectively, by the atmospheric scattering light value of each pixel divided by overall air light value to obtain except value, deduct 1 described except value
To obtain the medium transmission rate of each pixel；Sharpening Image Acquisition subset, with described linear array digital aviation photographic equipment,
Described overall air light value obtains subset and described medium transmission rate obtains subset and connects respectively, deducts each picture by 1
Described first difference, to obtain the first difference, is multiplied by overall air light value to obtain product value, by institute by the medium transmission rate of element
State the pixel value of each pixel in the image of desert areas and deduct described product value to obtain the second difference, by described second difference
Divided by the medium transmission rate of each pixel to obtain the sharpening pixel value of each pixel, every in the image of described desert areas
The pixel value of one pixel includes the R of each pixel in the image of described desert areas, G, B tri-Color Channel pixel value, accordingly
Ground, it is thus achieved that the sharpening pixel value of each pixel include the R of each pixel, G, B tri-Color Channel sharpening pixel value,
Haze desert areas image is removed described in the sharpening pixel value composition of all pixels；Described image detecting apparatus is deposited with described static state
Storage equipment and described sharpening processing equipment connect respectively, and described image detecting apparatus includes: histogram equalization subset, with
Described sharpening processing equipment connects, and goes haze desert areas image to perform image enhaucament based on histogram equalization to described
Process, to obtain the enhancing image that road strengthens with background contrasts；Image segregant equipment, with described static storage device and
Described histogram equalization subset connects respectively, calculates the R channel value of each pixel, G channel value in described enhancing image
With channel B value, when the R channel value of a certain pixel in the road R channel range of described desert areas, G channel value is in described desert
In area road G channel range and channel B value in the range of the road channel B of described desert areas time, be defined as road picture
All road pixel in described enhancing image are combined to form road subimage by element；Wavelet filtering subset, with described image
Segregant equipment connects, and based on Haar wavelet transform wave filter, described road subimage is performed Filtering Processing, filters noise to obtain
The filtering road subimage of pixel；Least square fitting subset, is connected, based on least square with described wavelet filtering subset
Fitting algorithm is to described filtering road subimage execution process of fitting treatment to determine road curve, and described road curve is and described filter
The square distance of all pixels and a minimum curve in radio frequency channel way image；Described embedded processing equipment is wireless with described
Communication interface, described GPS location equipment, described pressure altitude sensing equipment, described linear array digital aviation photographic equipment, described clearly
Clearization processing equipment and described image detecting apparatus connect respectively, and the flight receiving the forwarding of described wireless communication interface controls to refer to
Order, resolves described flight control instruction to obtain purpose gps data corresponding to described desert areas position directly above and purpose
Shooting height, mates with described purpose shooting height and described real time positioning data and described purpose GPS at described real-time height
During Data Matching, enter road recognition mode, described real-time height do not mate with described purpose shooting height or described in real time
When location data are not mated with described purpose gps data, enter desert areas searching modes；Wherein, described embedded processing sets
Standby in described road Identification pattern, start described linear array digital aviation photographic equipment, described sharpening processing equipment and described
Image detecting apparatus, removes haze desert areas image and described road curve described in reception, determines that described road curve is described
Go to the relative position in the image of haze desert areas, based on described relative position, described real time positioning data and described real-time height
Degree determines the location information of described road curve, and the location information of described road curve includes determining of the starting point of described road curve
The location information of the terminal of position information and described road curve.
More specifically, in the described desert areas Road Detection platform being positioned on unmanned plane: described wireless communication interface
Receive the location information of described road curve and described road curve, and by described road curve and described road curve
Location information is wirelessly sent to described road and draws service platform.
More specifically, in the described desert areas Road Detection platform being positioned on unmanned plane, also include: unmanned plane drives
Equipment, is connected with described embedded processing equipment, for driving described unmanned plane under the control of described embedded processing equipment
Fly to described desert areas position directly above.
More specifically, in the described desert areas Road Detection platform being positioned on unmanned plane: described embedded processing sets
Standby in the searching modes of described desert areas, close described linear array digital aviation photographic equipment, described sharpening processing equipment and
Described image detecting apparatus.
More specifically, in the described desert areas Road Detection platform being positioned on unmanned plane: described histogram equalization
Subset, described image segregant equipment, described wavelet filtering subset and described least square fitting subset are respectively adopted
The fpga chip of different model realizes.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the structure square frame of an embodiment of the desert areas Road Detection platform being positioned on unmanned plane of the present invention
Figure.
Fig. 2 is the structure side of the another embodiment of the desert areas Road Detection platform being positioned on unmanned plane of the present invention
Block diagram.
Detailed description of the invention
The embodiment of the desert areas Road Detection the platform below with reference to accompanying drawings present invention being positioned on unmanned plane
It is described in detail.
On the earth, the road Identification of regional is significant, not only can provide navigation letter for car and crowd
Breath, and can succour for natural disaster, emergency relief etc. provides valuable reference information, the effect of raising rescue and relief
Rate.But, different types of region, the difficulty of road Identification is different.Wherein, the more difficult desert complicated no more than landforms
Region.
Desert areas is typically in remote area, the less standard road occurring that road administration department is built, and is more to work as
The dirt road that ground resident renovates, even vehicular traffic roll and the irregular route that formed for a long time, due to a varied topography, road with
The edge boundary of desert background obscures, and conventional satellite remote sensing mode cannot accurately identify road, and the hands of manual site's exploration
Section is the most original, and meanwhile, the many haze weather of desert area also Road Detection to desert areas brings no small interference,
The weather that haze is serious, cannot be carried out Road Detection the most at all.
The present invention has built a kind of desert areas Road Detection platform being positioned on unmanned plane, with unmanned plane flexibly for surveying
Amount platform, customizes a set of image detecting apparatus being made up of multiple image procossing subset based on desert special geomorphology, it is achieved right
Effective, the road Identification fast and accurately of selected desert areas, meanwhile, also introduces haze processing equipment to remove detection
Haze composition in image, thus draw department for relevant road and road data accurate, reliable is provided.
Fig. 1 is the structure square frame of an embodiment of the desert areas Road Detection platform being positioned on unmanned plane of the present invention
Figure, described detection platform includes that GPS positions equipment 1, pressure altitude sensing equipment 2, linear array digital aviation photographic equipment 4, image
Detection equipment 5 and embedded processing equipment 3, described embedded processing equipment 3 positions equipment 1, described pressure altitude with described GPS
Sensing equipment 2, described linear array digital aviation photographic equipment 4 and described image detecting apparatus 5 connect respectively, fixed based on described GPS
The real time positioning data of position equipment 1 output and the real-time of described pressure altitude sensing equipment 2 output the most highly determine whether to start institute
State linear array digital aviation photographic equipment 4 and described image detecting apparatus 5 to realize the Road Detection to described desert areas.
Fig. 2 is the structure side of the another embodiment of the desert areas Road Detection platform being positioned on unmanned plane of the present invention
Block diagram, compared to Figure 1, adds sharpening processing equipment 6 and detects the haze composition in image with removal, to ensure detection platform
Various desert climates also are able to normally work.
Then, the concrete structure of the desert areas Road Detection platform that Fig. 2 is positioned on unmanned plane by continuation enters one
The explanation of step.
Described detection platform also includes: power supply, including solar powered device, accumulator, switching switch and voltage
Transducer, described switching switch is connected respectively with described solar powered device and described accumulator, according to accumulator residue electricity
Amount decides whether to be switched to described solar powered device to be powered by described solar powered device, described electric pressure converter with
Described switching switch connects, will be converted to 3.3V voltage by the 5V voltage of switching switch input.
Described detection platform also includes: static storage device, is used for prestoring desert areas road R channel range, sand
Unconcerned area road G channel range, desert areas road channel B scope, described desert areas road R channel range, described desert
Area road G channel range and described desert areas road channel B scope for by the desert areas road in RGB image with
RGB image background separation.
Described detection platform also includes: wireless communication interface, draws service platform with the road of far-end and sets up two-way nothing
Line communication link, draws the flight control instruction that service platform sends, in described flight control instruction for receiving described road
The purpose gps data corresponding including described desert areas position directly above and purpose shooting height.
Sharpening processing equipment 6, between described linear array digital aviation photographic equipment 4 and described image detecting apparatus 5,
Receive the desert areas image that desert areas is shot by described linear array digital aviation photographic equipment 4, to described desert areas image
Carry out haze process and remove haze desert areas image to obtain, substitute described desert areas image, go to haze desert by described
Area image inputs described image detecting apparatus 5 to realize the Road Detection to described desert areas.
Described sharpening processing equipment 6 includes with lower component:
Haze Concentration Testing subset, is positioned in air, for the haze concentration of detection unmanned plane position in real time, and
Determining that intensity removed by haze according to haze concentration, described haze removes intensity value between 0 to 1；
Overall air light value obtains subset, is connected to obtain described desert with described linear array digital aviation photographic equipment 4
Area image, calculates the gray value of each pixel in the image of described desert areas, is made by the gray value of pixel maximum for gray value
For overall air light value；
Atmospheric scattering light value obtains subset, with described linear array digital aviation photographic equipment 4 and described haze Concentration Testing
Subset connects respectively, each pixel to described desert areas image, extracts its R, G, B tri-in Color Channel pixel value
Little value, as target pixel value, uses Gaussian filter EPGF (the edge-preserving gaussian keeping edge
Filter) it is filtered described target pixel value processing to obtain filtered target pixel value, target pixel value is deducted filtering
Target pixel value, to obtain object pixel difference, uses EPGF to be filtered object pixel difference processing to obtain filtered target
Pixel value difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes reference value, removed by haze
Intensity is multiplied by haze removal reference value removes threshold value to obtain haze, takes haze and removes the minima in threshold value and target pixel value
As comparison reference, take the atmospheric scattering light value as each pixel of the maximum in comparison reference and 0；
Medium transmission rate obtains subset, obtains subset with described overall air light value and described atmospheric scattering light value obtains
Take subset to connect respectively, by the atmospheric scattering light value of each pixel divided by overall air light value to obtain except value, deduct 1
It is described except value is to obtain the medium transmission rate of each pixel；
Sharpening Image Acquisition subset, obtains with described linear array digital aviation photographic equipment 4, described overall air light value
Subset and described medium transmission rate obtain subset and connect respectively, deduct the medium transmission rate of each pixel by 1 to obtain
First difference, is multiplied by overall air light value to obtain product value, by each in the image of described desert areas by described first difference
The pixel value of individual pixel deducts described product value to obtain the second difference, by described second difference divided by the medium of each pixel
Transfer rate is to obtain the sharpening pixel value of each pixel, and in the image of described desert areas, the pixel value of each pixel includes
The R of each pixel in the image of described desert areas, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that each pixel
Sharpening pixel value includes the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel of all pixels
Haze desert areas image is removed described in value composition.
Described image detecting apparatus 5 is connected respectively with described static storage device and described sharpening processing equipment 6, described
Image detecting apparatus 5 includes with lower component:
Histogram equalization subset, is connected with described sharpening processing equipment 6, removes haze desert areas image to described
Perform image enhancement processing based on histogram equalization, to obtain the enhancing image that road strengthens with background contrasts；
Image segregant equipment, is connected respectively with described static storage device and described histogram equalization subset, meter
Calculate the R channel value of each pixel, G channel value and channel B value in described enhancing image, when the R channel value of a certain pixel is in institute
State in the road R channel range of desert areas, G channel value is in the road G channel range of described desert areas and channel B value is described
Time in the range of the road channel B of desert areas, it is defined as road pixel, all road pixel in described enhancing image are combined
To form road subimage；
Wavelet filtering subset, is connected, based on Haar wavelet transform wave filter to described road with described image segregant equipment
Subimage performs Filtering Processing, to obtain the filtering road subimage filtering noise pixel；
Least square fitting subset, is connected with described wavelet filtering subset, based on least square fitting algorithm to institute
State filtering road subimage perform process of fitting treatment to determine road curve, described road curve is and described filtering road subimage
In the square distance of all pixels and a minimum curve.
Described embedded processing equipment 3 passes with described wireless communication interface, described GPS location equipment 1, described pressure altitude
Sense equipment 2, described linear array digital aviation photographic equipment 4, described sharpening processing equipment 6 and described image detecting apparatus 5 are respectively
Connect, receive the flight control instruction that described wireless communication interface forwards, described flight control instruction is resolved to obtain described
Purpose gps data that desert areas position directly above is corresponding and purpose shooting height, clap with described purpose at described real-time height
Take the photograph matched and described real time positioning data when mating with described purpose gps data, enter road recognition mode, in described reality
When Shi Gaodu does not mates with described purpose shooting height or described real time positioning data does not mates with described purpose gps data, enter
Enter desert areas searching modes.
Wherein, described embedded processing equipment 3, in described road Identification pattern, starts the photography of described linear array digital aviation
Equipment 4, described sharpening processing equipment 6 and described image detecting apparatus 5, remove haze desert areas image and described described in reception
Road curve, determine described road curve in the described relative position gone in the image of haze desert areas, based on described phase para-position
Put, described real time positioning data and the described location information highly determining in real time described road curve, determining of described road curve
Position information includes the location information of the starting point of described road curve and the location information of the terminal of described road curve.
Alternatively, in described detection platform: described wireless communication interface receives described road curve and described road
The location information of curve, and the location information of described road curve and described road curve is wirelessly sent to described road paints
Service platform processed；Described detection platform can also include: unmanned plane drives equipment, is connected with described embedded processing equipment 3,
For driving described unmanned plane to fly to described desert areas position directly above under the control of described embedded processing equipment 3；Institute
State embedded processing equipment 3 in the searching modes of described desert areas, close described linear array digital aviation photographic equipment 4, described
Sharpening processing equipment 6 and described image detecting apparatus 5；And described histogram equalization subset, described image segregant
Equipment, described wavelet filtering subset and described least square fitting subset can be respectively adopted the fpga chip of different model
Realize.
It addition, haze image can remove haze by what a series of images processing equipment realized image, clear to obtain
The image changed, improves the visibility of image.These image processing equipments perform different image processing functions respectively, based on haze
The principle formed, reaches to remove the effect of haze.The sharpening of haze image processes all has pole for dual-use field
Big using value, military domain includes military and national defense, remote sensing navigation etc., civil area include road monitoring, target following and
Automatic Pilot etc..
The process that haze image is formed can be described by atmospheric attenuation process, the most clear in haze image and real image
Change the relation between image to state, i.e. at known haze figure by the medium transmission rate of overall air light value and each pixel
In the case of Xiang, according to overall air light value and the medium transmission rate of each pixel, sharpening image can be solved.
There are some effectively and through testing in the solving of medium transmission rate for overall air light value and each pixel
The means of card, such as, for the medium transmission rate of each pixel, the overall air light value of needs acquisition is big with each pixel
Gas scattering light value, and each pixel pixel value in haze image can carried out by the atmospheric scattering light value of each pixel
Keeping for twice the Gaussian smoothing filter at edge to obtain, therebetween, the intensity that haze is removed is adjustable；And the acquisition of entirety air light value
Mode has two kinds, and a kind of mode is, (i.e. can make some pixels in haze image by obtaining the black channel of haze image
Black channel value the lowest, black channel is R, G, the B tri-one in Color Channel), in haze image, black by finding
The pixel finding gray value maximum in multiple pixels that chrominance channel pixel value is bigger than normal obtains, and that will search out, gray value is
The gray value of big pixel, as overall air light value, participates in the sharpening of each pixel in haze image and processes；It addition, it is whole
Body atmosphere light value also can obtain in the following manner: calculates the gray value of each pixel in haze image, by gray value maximum
The gray value of pixel is as overall air light value.
Relation between concrete haze image and real image i.e. sharpening image, and the relation between parameters
Can be found in above content.
By the discussion to haze image formation basic theory, build the relation between haze image and sharpening image, used
Multiple parameters represent this relation, and multiple parameter values and haze image the most reducible acquisition definition by obtaining are higher subsequently
Image, owing to some statistical means and empirical means have been used in the acquisition of parameter, the higher image of the most described definition is not
May be fully equivalent to real image, but have and considerable degree of gone haze effect, for the every field under haze weather
Operation provides effective guarantee.
Use the desert areas Road Detection platform being positioned on unmanned plane of the present invention, for existing satellite remote sensing identification side
Formula measurement error measures compared with big, manual site's recognition method that efficiency is low and the technical problem of poor real, by using flexibly
Unmanned aerial vehicle platform, introduce more image processing equipment targetedly, planning image processing procedure more efficiently, introduce high-precision
Degree haze eliminating equipment with eliminate detection image in haze composition, thus define a set of can meet simultaneously high accuracy, height
The desert areas road Identification system of efficiency, high real-time and high reliability.
Although it is understood that the present invention discloses as above with preferred embodiment, but above-described embodiment being not used to
Limit the present invention.For any those of ordinary skill in the art, without departing under technical solution of the present invention ambit,
Technical solution of the present invention is made many possible variations and modification by the technology contents that all may utilize the disclosure above, or is revised as
Equivalent embodiments with change.Therefore, every content without departing from technical solution of the present invention, according to the technical spirit pair of the present invention
Any simple modification made for any of the above embodiments, equivalent variations and modification, all still fall within the scope of technical solution of the present invention protection
In.
Claims (2)
1. the desert areas Road Detection platform that a kind is positioned on unmanned plane, it is characterised in that described detection platform includes that GPS is fixed
Position equipment, pressure altitude sensing equipment, linear array digital aviation photographic equipment, image detecting apparatus and embedded processing equipment, institute
State embedded processing equipment to set with described GPS location equipment, described pressure altitude sensing equipment, the photography of described linear array digital aviation
Standby and described image detecting apparatus connects respectively, real time positioning data based on the equipment output of described GPS location and described air pressure
The real-time of highly sensing equipment output highly determines whether to start described linear array digital aviation photographic equipment and the detection of described image
Equipment is to realize the Road Detection to described desert areas.
The desert areas Road Detection platform being positioned at the most as claimed in claim 1 on unmanned plane, it is characterised in that described detection
Platform also includes:
Power supply, including solar powered device, accumulator, switching switch and electric pressure converter, described switching switch and institute
State solar powered device and described accumulator connects respectively, decide whether to be switched to the described sun according to accumulator dump energy
Energy power supply device is to be powered by described solar powered device, and described electric pressure converter is connected with described switching switch, leading to
The 5V voltage crossing switching switch input is converted to 3.3V voltage；
Static storage device, is used for prestoring desert areas road R channel range, desert areas road G channel range, desert
Area road channel B scope, described desert areas road R channel range, described desert areas road G channel range and described sand
Unconcerned area road channel B scope is for by the desert areas road in RGB image and RGB image background separation；
Wireless communication interface, draws service platform with the road of far-end and sets up two-way wireless communication link, is used for receiving described
Road draws the flight control instruction that service platform sends, and described flight control instruction includes position directly over described desert areas
Put purpose gps data and the purpose shooting height of correspondence；
Sharpening processing equipment, between described linear array digital aviation photographic equipment and described image detecting apparatus, receives institute
State the desert areas image that desert areas is shot by linear array digital aviation photographic equipment, described desert areas image is carried out mist elimination
Haze processes and removes haze desert areas image to obtain, and substitutes described desert areas image, removes haze desert areas image by described
Input described image detecting apparatus to realize the Road Detection to described desert areas；
Described sharpening processing equipment includes:
Haze Concentration Testing subset, is positioned in air, for the haze concentration of detection unmanned plane position in real time, and according to
Haze concentration determines that intensity removed by haze, and described haze removes intensity value between 0 to 1；
Overall air light value obtains subset, is connected with described linear array digital aviation photographic equipment to obtain described desert areas figure
Picture, calculates the gray value of each pixel in the image of described desert areas, using the gray value of pixel maximum for gray value as entirety
Air light value；
Atmospheric scattering light value obtains subset, with described linear array digital aviation photographic equipment and described haze Concentration Testing subset
Connect respectively, each pixel to described desert areas image, extract its R, G, B tri-in Color Channel pixel value minima make
For target pixel value, use and keep the Gaussian filter EPGF at edge to be filtered described target pixel value processing to obtain
Filtered target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, uses EPGF pair
Object pixel difference is filtered processing to obtain filtered target pixel value difference, and filtered target pixel value is deducted filtered target picture
Plain difference removes reference value to obtain haze, haze is removed intensity and is multiplied by haze removal reference value to obtain haze removal threshold
Value, takes haze and removes the minima in threshold value and target pixel value as comparison reference, take the maximum in comparison reference and 0
It is worth the atmospheric scattering light value as each pixel；
Medium transmission rate obtains subset, obtains subset with described overall air light value and described atmospheric scattering light value obtains son
Equipment connects respectively, by the atmospheric scattering light value of each pixel divided by overall air light value to obtain except value, deducts described by 1
Except value is to obtain the medium transmission rate of each pixel；
Sharpening Image Acquisition subset, obtains son set with described linear array digital aviation photographic equipment, described overall air light value
Standby and described medium transmission rate obtains subset and connects respectively, deducts the medium transmission rate of each pixel by 1 to obtain first
Difference, is multiplied by overall air light value to obtain product value, by each picture in the image of described desert areas by described first difference
The pixel value of element deducts described product value to obtain the second difference, by described second difference divided by the medium transmission of each pixel
Rate is to obtain the sharpening pixel value of each pixel, and in the image of described desert areas, the pixel value of each pixel includes described
The R of each pixel in the image of desert areas, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that each pixel clear
Change pixel value and include the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value group of all pixels
Haze desert areas image is removed described in one-tenth；
Described image detecting apparatus is connected respectively with described static storage device and described sharpening processing equipment, and described image is examined
Measurement equipment includes:
Histogram equalization subset, is connected with described sharpening processing equipment, goes haze desert areas image to perform to described
Image enhancement processing based on histogram equalization, to obtain the enhancing image that road strengthens with background contrasts；
Image segregant equipment, is connected respectively with described static storage device and described histogram equalization subset, calculates institute
State the R channel value of each pixel, G channel value and channel B value in enhancing image, when the R channel value of a certain pixel is at described sand
In unconcerned area road R channel range, G channel value is in the road G channel range of described desert areas and channel B value is in described desert
Time in the range of area road channel B, it is defined as road pixel, all road pixel in described enhancing image are combined with shape
Become road subimage；
Wavelet filtering subset, is connected with described image segregant equipment, based on Haar wavelet transform wave filter to described road subgraph
As performing Filtering Processing, to obtain the filtering road subimage filtering noise pixel；
Least square fitting subset, is connected with described wavelet filtering subset, based on least square fitting algorithm to described filter
Radio frequency channel way image perform process of fitting treatment to determine road curve, described road curve for institute in described filtering road subimage
There are the square distance of pixel and a minimum curve；
Described embedded processing equipment sets with described wireless communication interface, described GPS location equipment, described pressure altitude sensing
Linear array digital aviation photographic equipment standby, described, described sharpening processing equipment and described image detecting apparatus connect respectively, receive
The flight control instruction that described wireless communication interface forwards, resolves just obtaining described desert areas to described flight control instruction
Purpose gps data that top position is corresponding and purpose shooting height, mate with described purpose shooting height at described real-time height
And described real time positioning data is when mating with described purpose gps data, enter road recognition mode, in described real-time height and institute
State purpose shooting height not mate or time described real time positioning data does not mates with described purpose gps data, enter desert areas
Searching modes；
Wherein, described embedded processing equipment in described road Identification pattern, start described linear array digital aviation photographic equipment,
Described sharpening processing equipment and described image detecting apparatus, go described in reception haze desert areas image and described road bent
Line, determine described road curve in the described relative position gone in the image of haze desert areas, based on described relative position, described
Real time positioning data and the described location information highly determining described road curve in real time, the location information bag of described road curve
Include the location information of the starting point of described road curve and the location information of the terminal of described road curve；
Unmanned plane drives equipment, is connected with described embedded processing equipment, under the control of described embedded processing equipment
Described unmanned plane is driven to fly to described desert areas position directly above；
Described embedded processing equipment in the searching modes of described desert areas, close described linear array digital aviation photographic equipment,
Described sharpening processing equipment and described image detecting apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610413079.XA CN106097271A (en) | 2015-04-08 | 2015-04-08 | The desert areas Road Detection platform being positioned on unmanned plane |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510163007.XA CN104715462B (en) | 2015-04-08 | 2015-04-08 | Desert region road detection platform on unmanned aerial vehicle |
| CN201610413079.XA CN106097271A (en) | 2015-04-08 | 2015-04-08 | The desert areas Road Detection platform being positioned on unmanned plane |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510163007.XA Division CN104715462B (en) | 2015-04-08 | 2015-04-08 | Desert region road detection platform on unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106097271A true CN106097271A (en) | 2016-11-09 |
Family
ID=53414757
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610409547.6A Pending CN106097270A (en) | 2015-04-08 | 2015-04-08 | The desert areas Road Detection platform being positioned on unmanned plane |
| CN201510163007.XA Expired - Fee Related CN104715462B (en) | 2015-04-08 | 2015-04-08 | Desert region road detection platform on unmanned aerial vehicle |
| CN201610413079.XA Pending CN106097271A (en) | 2015-04-08 | 2015-04-08 | The desert areas Road Detection platform being positioned on unmanned plane |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610409547.6A Pending CN106097270A (en) | 2015-04-08 | 2015-04-08 | The desert areas Road Detection platform being positioned on unmanned plane |
| CN201510163007.XA Expired - Fee Related CN104715462B (en) | 2015-04-08 | 2015-04-08 | Desert region road detection platform on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN106097270A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108417041A (en) * | 2018-05-15 | 2018-08-17 | 江苏大学 | A kind of backroad monitoring system and method based on quadrotor and Cloud Server |
| CN109151413A (en) * | 2018-10-10 | 2019-01-04 | 泉州市敏匠智能科技有限公司 | A kind of unmanned plane image intelligent processing system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110636465B (en) * | 2019-04-03 | 2020-10-16 | 浙江艾克米信息科技有限公司 | Local area network information sending platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763512A (en) * | 2009-12-11 | 2010-06-30 | 西安电子科技大学 | Method for semi-automatically detecting road target in high-resolution remote sensing images |
| CN103186887A (en) * | 2011-12-30 | 2013-07-03 | 株式会社日立制作所 | Image demisting device and image demisting method |
| CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7298869B1 (en) * | 2003-07-21 | 2007-11-20 | Abernathy Donald A | Multispectral data acquisition system and method |
| CN103034982B (en) * | 2012-12-19 | 2015-07-08 | 南京大学 | Image super-resolution rebuilding method based on variable focal length video sequence |
-
2015
- 2015-04-08 CN CN201610409547.6A patent/CN106097270A/en active Pending
- 2015-04-08 CN CN201510163007.XA patent/CN104715462B/en not_active Expired - Fee Related
- 2015-04-08 CN CN201610413079.XA patent/CN106097271A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763512A (en) * | 2009-12-11 | 2010-06-30 | 西安电子科技大学 | Method for semi-automatically detecting road target in high-resolution remote sensing images |
| CN103186887A (en) * | 2011-12-30 | 2013-07-03 | 株式会社日立制作所 | Image demisting device and image demisting method |
| CN104240508A (en) * | 2014-09-20 | 2014-12-24 | 无锡北斗星通信息科技有限公司 | Unmanned plane detection system for road segment congestion alarming |
Non-Patent Citations (1)
| Title |
|---|
| 来彦栋: "单幅图像雾霾去除算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108417041A (en) * | 2018-05-15 | 2018-08-17 | 江苏大学 | A kind of backroad monitoring system and method based on quadrotor and Cloud Server |
| CN109151413A (en) * | 2018-10-10 | 2019-01-04 | 泉州市敏匠智能科技有限公司 | A kind of unmanned plane image intelligent processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106097270A (en) | 2016-11-09 |
| CN104715462B (en) | 2017-05-03 |
| CN104715462A (en) | 2015-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102609726B (en) | Method for classifying remote sensing images blended with high-space high-temporal-resolution data by object oriented technology | |
| CN104933708A (en) | Barrier detection method in vegetation environment based on multispectral and 3D feature fusion | |
| CN102435174A (en) | Method and device for detecting barrier based on hybrid binocular vision | |
| CN103822635A (en) | Visual information based real-time calculation method of spatial position of flying unmanned aircraft | |
| CN105300358B (en) | Foreign bodies on transmission lines species detection platform | |
| CN104735423B (en) | The transmission facility identification platform being positioned on unmanned plane | |
| CN105352480A (en) | Electric transmission line foreign matter kind detection method | |
| CN103035006A (en) | High-resolution aerial image partition method based on LEGION and under assisting of LiDAR | |
| CN105184279B (en) | Desert area road detection method for unmanned plane | |
| CN104715462B (en) | Desert region road detection platform on unmanned aerial vehicle | |
| Guldogan et al. | Automated tree detection and density calculation using unmanned aerial vehicles | |
| CN105208345B (en) | Transmission facility identification method based on unmanned plane | |
| Wang et al. | Building heights estimation using ZY3 data—A case study of Shanghai, China | |
| Broussard et al. | Unmanned Aircraft Systems (UAS) and satellite imagery collections in a coastal intermediate marsh to determine the land-water interface, vegetation types, and Normalized Difference Vegetation Index (NDVI) values | |
| Taherzadeh et al. | Using hyperspectral remote sensing data in urban mapping over Kuala Lumpur | |
| Gxumisa et al. | Evaluating pixel vs. segmentation based classifiers with height differentiation on SPOT 6 imagery for urban land cover mapping | |
| CN111192229A (en) | Airborne multi-mode video image enhancement display method and system | |
| Khadanga et al. | Use of OBIA for extraction of cadastral parcels | |
| Grigillo et al. | Classification based building detection from GeoEye-1 images | |
| Jin et al. | Automated road pavement marking detection from high resolution aerial images based on multi-resolution image analysis and anisotropic Gaussian filtering | |
| Zeng et al. | Urban land-use classification using integrated airborne laser scanning data and high resolution multi-spectral satellite imagery | |
| CN106354135A (en) | Lane keeping system and method based on Beidou high-precision positioning | |
| CN112308904A (en) | Vision-based drawing construction method and device and vehicle-mounted terminal | |
| Wang et al. | An algorithm of real-time vehicle detection with low altitude aerial video | |
| CN109141366A (en) | Big data acquisition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |
|
| RJ01 | Rejection of invention patent application after publication |