Summary of the invention
In order to solve the problem, according to an aspect of the present invention, the invention provides a kind of transmission facility identification method based on unmanned plane, it comprises: utilize aerial camera to take ground transmission facility, to obtain transmission facility image; Equipment recognition system is utilized to carry out image procossing to described transmission facility image, to identify the kind of transmission facility in described transmission facility image; Freescale IMX6 processor is utilized the kind of described transmission facility to be wirelessly transmitted to the power supply unit management platform of far-end by wireless transceiver device.Wherein said aerial camera, equipment recognition system, wireless transceiver device and Freescale IMX6 processor form transmission facility identification platform, and it is positioned on unmanned plane.
Preferably, transmission facility identification method of the present invention comprises the mist elimination haze treatment facility of utilization between described aerial camera and described equipment recognition system further and receives described transmission facility image, carries out the process of mist elimination haze to obtain the step of mist elimination haze transmission facility image to described transmission facility image.
According to another aspect of the present invention, present invention also offers a kind of transmission facility identification platform be positioned on unmanned plane, comprise aerial camera, equipment recognition system, wireless transceiver device and Freescale IMX6 processor, wherein said aerial camera is taken ground transmission facility, to obtain transmission facility image; Described equipment recognition system carries out image procossing to described transmission facility image, to identify the kind of transmission facility in described transmission facility image; Described Freescale IMX6 processor is connected respectively with described equipment recognition system and described wireless transceiver device, the kind of described transmission facility is wirelessly transmitted to the power supply unit management platform of far-end by described wireless transceiver device.
More specifically, described platform also comprises:
Power supply, comprise solar powered device, storage battery, diverter switch and electric pressure converter, described diverter switch is connected respectively with described solar powered device and described storage battery, determine whether be switched to described solar powered device to be powered by described solar powered device according to storage battery dump energy, described electric pressure converter is connected with described diverter switch, with the 5V voltage transitions will inputted by diverter switch for 3.3V voltage;
Portable hard drive, for prestoring preset height scope, preset pressure elevation weight and preset radio elevation weight, also for prestoring one deck wavelet systems manifold of the transmission facility of various species, one deck wavelet systems manifold of the transmission facility of each kind is made up of the coefficient of wavelet decomposition benchmark transmission facility image of each kind being carried out to 4 decomposition subgraphs that one deck Harr wavelet decomposition obtains, the benchmark transmission facility image of each kind described is for taking obtained image in advance to the benchmark transmission facility of each kind, the coefficient of wavelet decomposition of described 4 decomposition subgraphs is respectively the coefficient of wavelet decomposition of a level and smooth subgraph, the coefficient of wavelet decomposition of a horizontal subgraph, the coefficient of wavelet decomposition of the coefficient of wavelet decomposition of a vertical subgraph and an oblique subgraph, the coefficient of wavelet decomposition of level and smooth subgraph is general picture coefficient, the coefficient of wavelet decomposition that its excess-three decomposes subgraph is all detail coefficients,
GPS locator, is connected with GPS navigation satellite, for receiving the real time positioning data of unmanned plane position;
Highly sensing equipment, is connected with described portable hard drive, comprises pressure-altitude sensor, radio altitude transducer and microcontroller; Described pressure-altitude sensor is used for according to the air pressure change near unmanned plane, detects the real-time pressure altitude of unmanned plane position; Described radio altitude transducer comprises radio transmitter, radio receiver and single-chip microcomputer, described single-chip microcomputer is connected respectively with described radio transmitter and described radio receiver, described radio transmitter launches radio wave earthward, described radio receiver receives the radio wave of ground return, described single-chip microcomputer calculates the real-time radio electrical height of unmanned plane according to the launch time of described radio transmitter, the time of reception of described radio receiver and velocity of radio wave, and described velocity of radio wave is the light velocity; Described microcontroller is connected respectively with described pressure-altitude sensor, described radio altitude transducer and described portable hard drive, when the difference of described real-time pressure altitude and described real-time radio electrical height is in described preset height scope, calculate based on described preset pressure elevation weight, described preset radio elevation weight, described real-time pressure altitude and described real-time radio electrical height and export described real-time height, when the difference of described real-time pressure altitude and described real-time radio electrical height is not in described preset height scope, export height detection failure signal;
Mist elimination haze treatment facility, between described aerial camera and described equipment recognition system, for receiving described transmission facility image, the process of mist elimination haze is carried out to obtain mist elimination haze transmission facility image to described transmission facility image, replace described transmission facility image, described mist elimination haze transmission facility image is inputted described equipment recognition system to carry out image procossing to identify the kind of transmission facility in described mist elimination haze transmission facility image.
More specifically, described mist elimination haze treatment facility comprises:
Haze Concentration Testing subset, is arranged in air, for the haze concentration of real-time unmanned plane position, and removes intensity according to haze concentration determination haze, and described haze removes intensity value between 0 to 1;
Overall air light value obtains subset, is connected to obtain described transmission facility image, calculates the gray value of each pixel in described transmission facility image, by the gray value of pixel maximum for gray value air light value as a whole with described aerial camera;
Atmospheric scattering light value obtains subset, be connected respectively with described aerial camera and described haze Concentration Testing subset, to each pixel of described transmission facility image, extract its R, G, in B tri-Color Channel pixel value, minimum value is as target pixel value, use and keep the Gaussian filter EPGF (edge-preservinggaussianfilter) at edge to carry out filtering process to obtain filtered target pixel value to described target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, EPGF is used to carry out filtering process to obtain filtered target pixel value difference to object pixel difference, filtered target pixel value is deducted filtered target pixel value difference and remove fiducial value to obtain haze, haze is removed intensity and be multiplied by haze removal fiducial value to obtain haze removal threshold value, get haze and remove minimum value in threshold value and target pixel value as comparison reference, get the atmospheric scattering light value of the maximum in comparison reference and 0 as each pixel,
Medium transmission rate obtains subset, obtain subset and described atmospheric scattering light value with described overall air light value to obtain subset and be connected respectively, the atmospheric scattering light value of each pixel is removed value divided by overall air light value to obtain, deducts 1 described except value is to obtain the medium transmission rate of each pixel;
Sharpening image acquisition subset, with described aerial camera, described overall air light value obtains subset and is connected respectively with described medium transmission rate acquisition subset, the medium transmission rate of each pixel is deducted to obtain the first difference by 1, described first difference is multiplied by overall air light value to obtain product value, the pixel value of each pixel in described transmission facility image is deducted 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, in described transmission facility image, the pixel value of each pixel comprises the R of each pixel in described transmission facility image, G, B tri-Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel obtained comprises the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination haze transmission facility image of all pixels.
More specifically, described equipment recognition system is connected respectively with mist elimination haze treatment facility and portable hard drive, comprises contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment, described contrast strengthen equipment is connected with described mist elimination haze treatment facility, for carrying out contrast enhancement processing to described mist elimination haze transmission facility image, obtaining and strengthening image, described gray processing treatment facility and described contrast strengthen equipment connection, for carrying out gray processing process to described enhancing image, obtain gray level image, described medium filtering equipment is connected with described gray processing treatment facility, for carrying out medium filtering to described gray level image, to remove the noise spot in gray level image, obtains filtering image, described Image erosion expansion process equipment and described medium filtering equipment connection, for carrying out Image erosion process and image expansion process successively to described filtering image, to remove in filtering image because the bright spot that formed of light the border of transmission facility in smothing filtering image, obtain the image after corrosion expansion process, described wavelet decomposition equipment is connected respectively with described Image erosion expansion process equipment and described portable hard drive, one deck Harr wavelet decomposition is carried out to the image after corrosion expansion process, the coefficient of wavelet decomposition that 4 that obtain are decomposed subgraph is formed real-time one deck wavelet systems manifold, real-time one deck wavelet systems manifold is mated one by one with one deck wavelet systems manifold of the transmission facility of various species, it fails to match then exports without transmission facility signal, the match is successful then export there is transmission facility signal and the kind of the kind of the transmission facility matched as transmission facility in described mist elimination haze transmission facility image exported.
More specifically, described wireless transceiver device comprises the first wireless network card and the second wireless network card, first wireless network card is used for the control command that wireless receiving power supply unit management platform sends, described control command comprises object gps data and the object shooting height of the ground transmission facility position being about to shooting, and the second wireless network card is used for markd for band image wireless to be sent to power supply unit management platform;
Described Freescale IMX6 processor and described aerial camera, described mist elimination haze treatment facility, described GPS locator, described highly sensing equipment, described equipment recognition system is connected respectively with described wireless transceiver device, by described real time positioning data, in described real-time height and described mist elimination haze transmission facility image, the kind of transmission facility all marks on described mist elimination haze transmission facility image to obtain the markd image of band, the markd image of band is sent to the second wireless network card of described wireless transceiver device, described Freescale IMX6 processor is when receiving height detection failure signal or without transmission facility signal, the first wireless network card of described wireless transceiver device is sent to so that described first wireless network card is forwarded to power supply unit management platform by height detection failure signal or without transmission facility signal, described Freescale IMX6 processor is sent to the drive singal of unmanned plane driving mechanism according to the adjustment of described real time positioning data, described real-time height, described object gps data and described object shooting height, so that described unmanned plane driving mechanism is according to the flight attitude of described drive singal adjustment unmanned plane, described first wireless network card adopts TCP transmission agreement, and described second wireless network card adopts UDP host-host protocol.
More specifically, in described identification platform, contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment adopt different fpga chips to realize respectively.
More specifically, in described identification platform, contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition integration of equipments are on one piece of surface-mounted integrated circuit.
More specifically, in described identification platform, the type selecting of the fpga chip that contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment adopt is all the Artix-7 series of Xilinx company.
More specifically, in described identification platform, contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition integration of equipments are in same fpga chip.
More specifically, in described identification platform, the transmission facility of described various species comprises the power transmission tower of each model, the insulator of each model and the stockbridge damper of each model.
Transmission facility identification method based on unmanned plane of the present invention, employing comprises contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, the multiple image processing section of Image erosion expansion process equipment and wavelet decomposition equipment carries out high-precision type identification to the transmission facility image that unmanned plane is taken, and use two radio communication network interface cards disturbed with the data avoiding unmanned plane to receive and dispatch, wherein transmission facility identification platform can be integrated in the electronic equipment of unmanned plane, more crucially, can according to atmospheric attenuation model determination haze to the influencing factor of image, the process of mist elimination haze is carried out to the transmission facility image gathered under haze weather, obtain transmission facility image clearly, thus ensure the accurate identification also carrying out transmission facility kind in inclement weather
Embodiment
Below with reference to accompanying drawings the embodiment of the identification platform implementing the transmission facility identification method based on unmanned plane of the present invention is described in detail.
Drone is called for short " unmanned plane ", and english abbreviation is " UAV ", is the not manned aircraft utilizing radio robot to handle with the presetting apparatus provided for oneself.Unmanned plane is actually the general designation of unmanned vehicle, can be divided into: this several large class of depopulated helicopter, unmanned fixed-wing aircraft, unmanned multi-rotor aerocraft, unmanned airship, unmanned parasol from technical standpoint definition.Without driving cabin on unmanned plane, but the equipment such as automatic pilot, presetting apparatus is installed.On ground, naval vessels or machine tool remote control station personnel by equipment such as radars, it is followed the tracks of, locates, remote control, remote measurement and Digital Transmission.
The attention that unmanned plane is flexible, motor-driven, the feature of low cost has also attracted power monitoring department.For power monitoring department, each transmission facility of the electric power transmission network of its subordinate is distributed in the extensive area of different terrain, if by the mode of hand inspection, certainly will take time and effort, and use the mode that unmanned plane checks instead in the air, just can improve the efficiency checked, the cost of reduction inspection.
In order to find that the transmission facility of outward appearance defect is so that the timely maintenance in later stage, first the type identifying transmission facility is needed, then with the type of transmission facility for starting point, judge that whether the transmission facility of current check consistent, inconsistent with benchmark transmission facility outward appearance, need timely maintenance.Here, the determination of transmission facility type is a difficult problem, and because unmanned plane has passed a large amount of transmission facility images back, then operating efficiency is not high for the mode of employing hand inspection, and the problem of accuracy of identification difference also appears in electronic recognition patterns more of the prior art.
In addition, electronic recognition pattern of the prior art cannot overcome the adverse effect of haze weather to image, like this, easily when haze weather is serious, cannot be accurately identified transmission facility type wherein to ambiguous transmission facility image.
For this reason, the present invention establishes a kind of transmission facility based on unmanned plane identification platform, and built the transmission facility identification platform be positioned on unmanned plane, based on the feature of transmission facility, customize and comprised contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, the multiple image processing section of Image erosion expansion process equipment and wavelet decomposition equipment carries out high-precision type identification to the transmission facility image that unmanned plane is taken, core is different based on the wavelet character value of dissimilar transmission facility and pattern that is that have employed wavelet character value coupling carries out the identification of transmission facility type, add mist elimination haze treatment facility effectively to realize the sharpening process to transmission facility image under haze weather simultaneously.
Under fair weather, the block diagram being positioned at the transmission facility identification platform on unmanned plane can design as follows, described platform comprises aerial camera, equipment recognition system, wireless transceiver device and Freescale IMX6 processor, described aerial camera is taken ground transmission facility, to obtain transmission facility image, described equipment recognition system carries out image procossing to described transmission facility image, to identify the kind of transmission facility in described transmission facility image, described Freescale IMX6 processor is connected respectively with described equipment recognition system and described wireless transceiver device, the kind of described transmission facility is wirelessly transmitted to the power supply unit management platform of far-end by described wireless transceiver device.
Under haze weather, the block diagram being positioned at the transmission facility identification platform on unmanned plane can design as shown in Figure 1, is further detailed below to the concrete structure of the transmission facility identification platform be positioned on unmanned plane designed under haze weather.
Relative to the platform under fair weather, platform shown in Fig. 1 also comprises: power supply, comprise solar powered device, storage battery, diverter switch and electric pressure converter, described diverter switch is connected respectively with described solar powered device and described storage battery, determine whether be switched to described solar powered device to be powered by described solar powered device according to storage battery dump energy, described electric pressure converter is connected with described diverter switch, with the 5V voltage transitions will inputted by diverter switch for 3.3V voltage.
Platform shown in Fig. 1 also comprises: portable hard drive, for prestoring preset height scope, preset pressure elevation weight and preset radio elevation weight, also for prestoring one deck wavelet systems manifold of the transmission facility of various species, one deck wavelet systems manifold of the transmission facility of each kind is made up of the coefficient of wavelet decomposition benchmark transmission facility image of each kind being carried out to 4 decomposition subgraphs that one deck Harr wavelet decomposition obtains, the benchmark transmission facility image of each kind described is for taking obtained image in advance to the benchmark transmission facility of each kind, the coefficient of wavelet decomposition of described 4 decomposition subgraphs is respectively the coefficient of wavelet decomposition of a level and smooth subgraph, the coefficient of wavelet decomposition of a horizontal subgraph, the coefficient of wavelet decomposition of the coefficient of wavelet decomposition of a vertical subgraph and an oblique subgraph, the coefficient of wavelet decomposition of level and smooth subgraph is general picture coefficient, the coefficient of wavelet decomposition that its excess-three decomposes subgraph is all detail coefficients.
Platform shown in Fig. 1 also comprises: GPS locator, is connected with GPS navigation satellite, for receiving the real time positioning data of unmanned plane position.
Platform shown in Fig. 1 also comprises: highly sensing equipment, is connected with described portable hard drive, comprises pressure-altitude sensor, radio altitude transducer and microcontroller; Described pressure-altitude sensor is used for according to the air pressure change near unmanned plane, detects the real-time pressure altitude of unmanned plane position; Described radio altitude transducer comprises radio transmitter, radio receiver and single-chip microcomputer, described single-chip microcomputer is connected respectively with described radio transmitter and described radio receiver, described radio transmitter launches radio wave earthward, described radio receiver receives the radio wave of ground return, described single-chip microcomputer calculates the real-time radio electrical height of unmanned plane according to the launch time of described radio transmitter, the time of reception of described radio receiver and velocity of radio wave, and described velocity of radio wave is the light velocity; Described microcontroller is connected respectively with described pressure-altitude sensor, described radio altitude transducer and described portable hard drive, when the difference of described real-time pressure altitude and described real-time radio electrical height is in described preset height scope, calculate based on described preset pressure elevation weight, described preset radio elevation weight, described real-time pressure altitude and described real-time radio electrical height and export described real-time height, when the difference of described real-time pressure altitude and described real-time radio electrical height is not in described preset height scope, export height detection failure signal.
Platform shown in Fig. 1 also comprises: mist elimination haze treatment facility 5, between described aerial camera 1 and described equipment recognition system 2, for receiving described transmission facility image, the process of mist elimination haze is carried out to obtain mist elimination haze transmission facility image to described transmission facility image, replace described transmission facility image, described mist elimination haze transmission facility image is inputted described equipment recognition system to carry out image procossing to identify the kind of transmission facility in described mist elimination haze transmission facility image.
Described mist elimination haze treatment facility 5 comprises: haze Concentration Testing subset, is arranged in air, for the haze concentration of real-time unmanned plane position, and removes intensity according to haze concentration determination haze, and described haze removes intensity value between 0 to 1.
Described mist elimination haze treatment facility 5 comprises: overall air light value obtains subset, be connected to obtain described transmission facility image with described aerial camera 1, calculate the gray value of each pixel in described transmission facility image, by the gray value of pixel maximum for gray value air light value as a whole.
Described mist elimination haze treatment facility 5 comprises: atmospheric scattering light value obtains subset, be connected respectively with described aerial camera 1 and described haze Concentration Testing subset, to each pixel of described transmission facility image, extract its R, G, in B tri-Color Channel pixel value, minimum value is as target pixel value, use and keep the Gaussian filter EPGF (edge-preservinggaussianfilter) at edge to carry out filtering process to obtain filtered target pixel value to described target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, EPGF is used to carry out filtering process to obtain filtered target pixel value difference to object pixel difference, filtered target pixel value is deducted filtered target pixel value difference and remove fiducial value to obtain haze, haze is removed intensity and be multiplied by haze removal fiducial value to obtain haze removal threshold value, get haze and remove minimum value in threshold value and target pixel value as comparison reference, get the atmospheric scattering light value of the maximum in comparison reference and 0 as each pixel.
Described mist elimination haze treatment facility 5 comprises: medium transmission rate obtains subset, obtain subset and described atmospheric scattering light value with described overall air light value to obtain subset and be connected respectively, the atmospheric scattering light value of each pixel is removed value divided by overall air light value to obtain, deducts 1 described except value is to obtain the medium transmission rate of each pixel.
Described mist elimination haze treatment facility 5 comprises: sharpening image acquisition subset, with described aerial camera 1, described overall air light value obtains subset and is connected respectively with described medium transmission rate acquisition subset, the medium transmission rate of each pixel is deducted to obtain the first difference by 1, described first difference is multiplied by overall air light value to obtain product value, the pixel value of each pixel in described transmission facility image is deducted 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, in described transmission facility image, the pixel value of each pixel comprises the R of each pixel in described transmission facility image, G, B tri-Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel obtained comprises the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination haze transmission facility image of all pixels.
Described equipment recognition system 2 is connected respectively with described mist elimination haze treatment facility 5 and described portable hard drive, comprises contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment, described contrast strengthen equipment is connected with described mist elimination haze treatment facility 5, for carrying out contrast enhancement processing to described mist elimination haze transmission facility image, obtaining and strengthening image, described gray processing treatment facility and described contrast strengthen equipment connection, for carrying out gray processing process to described enhancing image, obtain gray level image, described medium filtering equipment is connected with described gray processing treatment facility, for carrying out medium filtering to described gray level image, to remove the noise spot in gray level image, obtains filtering image, described Image erosion expansion process equipment and described medium filtering equipment connection, for carrying out Image erosion process and image expansion process successively to described filtering image, to remove in filtering image because the bright spot that formed of light the border of transmission facility in smothing filtering image, obtain the image after corrosion expansion process, described wavelet decomposition equipment is connected respectively with described Image erosion expansion process equipment and described portable hard drive, one deck Harr wavelet decomposition is carried out to the image after corrosion expansion process, the coefficient of wavelet decomposition that 4 that obtain are decomposed subgraph is formed real-time one deck wavelet systems manifold, real-time one deck wavelet systems manifold is mated one by one with one deck wavelet systems manifold of the transmission facility of various species, it fails to match then exports without transmission facility signal, the match is successful then export there is transmission facility signal and the kind of the kind of the transmission facility matched as transmission facility in described mist elimination haze transmission facility image exported.
Described wireless transceiver device 3 comprises the first wireless network card and the second wireless network card, first wireless network card is used for the control command that wireless receiving power supply unit management platform sends, described control command comprises object gps data and the object shooting height of the ground transmission facility position being about to shooting, and the second wireless network card is used for markd for band image wireless to be sent to power supply unit management platform.
Described Freescale IMX6 processor 4 and described aerial camera 1, described mist elimination haze treatment facility 5, described GPS locator, described highly sensing equipment, described equipment recognition system 2 is connected respectively with described wireless transceiver device 3, by described real time positioning data, in described real-time height and described mist elimination haze transmission facility image, the kind of transmission facility all marks on described mist elimination haze transmission facility image to obtain the markd image of band, the markd image of band is sent to the second wireless network card of described wireless transceiver device 3, described Freescale IMX6 processor 4 is when receiving height detection failure signal or without transmission facility signal, the first wireless network card of described wireless transceiver device 3 is sent to so that described first wireless network card is forwarded to power supply unit management platform by height detection failure signal or without transmission facility signal.
Wherein, described Freescale IMX6 processor 4 is sent to the drive singal of unmanned plane driving mechanism according to the adjustment of described real time positioning data, described real-time height, described object gps data and described object shooting height, so that described unmanned plane driving mechanism is according to the flight attitude of described drive singal adjustment unmanned plane; Described first wireless network card adopts TCP transmission agreement, and described second wireless network card adopts UDP host-host protocol.
Wherein, alternatively, at the described transmission facility identification platform be arranged on unmanned plane, contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment are adopted different fpga chips to realize respectively; By contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition integration of equipments on one piece of surface-mounted integrated circuit; The type selecting of the fpga chip that contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition equipment adopt is all the Artix-7 series of Xilinx company; By contrast strengthen equipment, gray processing treatment facility, medium filtering equipment, Image erosion expansion process equipment and wavelet decomposition integration of equipments in same fpga chip; And the transmission facility of described various species can comprise the stockbridge damper of the power transmission tower of each model, the insulator of each model and each model.
In addition, haze image can realize the mist elimination haze of image by a series of images treatment facility, to obtain the image of sharpening, improves the visibility of image.These image processing equipments perform different image processing functions respectively, based on the principle that haze is formed, reach the effect removing haze.The sharpening process of haze image all has great using value for dual-use field, and military domain comprises military and national defense, remote sensing navigation etc., and civil area comprises road monitoring, target following and automatic Pilot etc.
The process that haze image is formed can be described by atmospheric attenuation process, relation between haze image and real image and sharpening image can be stated by the medium transmission rate of overall air light value and each pixel, namely when known haze image, according to the medium transmission rate of overall air light value with each pixel, sharpening image can be solved.
There are some effective and through verifying means in the solving of medium transmission rate for overall air light value and each pixel, such as, for the medium transmission rate of each pixel, need the atmospheric scattering light value obtaining overall air light value and each pixel, and the atmospheric scattering light value of each pixel can obtain carrying out the Gaussian smoothing filter at twice maintenance edge to the pixel value of each pixel in haze image, therebetween, the intensity of haze removal is adjustable; And the acquisition pattern of overall air light value has two kinds, a kind of mode is, black channel by obtaining haze image (namely makes the black channel value of some pixels very low in haze image, black channel is R, G, one in B tri-Color Channel), in haze image, obtain by finding the maximum pixel of gray value in multiple pixels that searching black channel pixel value is bigger than normal, be about to the gray value air light value as a whole of that search out, that gray value is maximum pixel, participate in the sharpening process of each pixel in haze image; In addition, overall air light value is also by obtaining with under type: the gray value calculating each pixel in haze image, by the gray value of pixel maximum for gray value air light value as a whole.
Relation between concrete haze image and real image and sharpening image, and the relation between parameters can see above content.
By the discussion to haze image formation basic theory, build the relation between haze image and sharpening image, by this relation of multiple Parametric Representation, subsequently by the multiple parameter values that obtain and haze image and the higher image of reducible acquisition definition, some statistical means and empirical means have been used in acquisition due to parameter, therefore the image that described definition is higher can not be equal to real image completely, but there is the mist elimination haze effect of certain degree, for the every field operation under haze weather provides effective guarantee.
Adopt the transmission facility identification method based on unmanned plane of the present invention, for existing unmanned plane transmission facility recognition mechanism inefficiency, precision not high and cannot overcome haze weather impact technical problem, have developed a kind of is the transmission facility type identification pattern of core based on transmission facility wavelet character value coupling, a transmission facility identification platform be made up of the image processing section of multiple customization has been built around this recognition mode, also in transmission facility identification platform, add double netcard communication interface, the electronic units such as high accuracy height sensor, the more important thing is, the introducing of high accuracy mist elimination haze treatment facility ensures that this platform also can normally work under the weather that haze is serious, thus improve the reliability of transmission facility unmanned plane identification comprehensively.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.