CN104735423B - Power transmission equipment identification platform on UAV - Google Patents

Abstract

The invention relates to a power transmission equipment recognition platform on an unmanned aerial vehicle, which comprises an aerial camera, an equipment recognition system, a wireless transceiver and a Feichal IMX6 processor, wherein the aerial camera shoots power transmission equipment on the ground to obtain a power transmission equipment image, the equipment recognition system performs image processing on the power transmission equipment image to recognize the type of the power transmission equipment in the power transmission equipment image, and the Feichal IMX6 processor is respectively connected with the equipment recognition system and the wireless transceiver and wirelessly transmits the type of the power transmission equipment to a remote power supply unit management platform through the wireless transceiver. The invention also uses the haze-removing treatment equipment to overcome the influence of haze weather on the image. By the method and the device, the types of various power transmission equipment can be accurately, quickly and real-timely identified from the air even in haze weather.

Description

Power transmission equipment identification platform on UAV

technical field

The invention relates to the field of power transmission equipment management, in particular to a power transmission equipment identification platform located on an unmanned aerial vehicle.

Background technique

With the maturity of drone technology and the further expansion of aerial photography technology, in the field of military drone applications, drones are often used in forms of combat support such as reconnaissance and surveillance. More importantly, the application of civilian drones The fields are also becoming more and more extensive, including: photogrammetry, emergency relief, public safety, resource exploration, environmental monitoring, natural disaster monitoring and assessment, urban planning and municipal management, forest fire pest protection and monitoring, etc.

UAVs are used to inspect various transmission equipment for power transmission, so that the power supply unit can find problems and maintain them in time to ensure the normal operation of the transmission network. The drone inspection method has the advantages of high efficiency, fast, reliable, low cost, and not affected by the region. However, in the existing technology, the images of the power transmission equipment captured by the drone are usually sent to the power supply unit management platform of the power supervision department in real time. It is expected that the power regulatory department will manually observe and judge the received images of power transmission equipment frame by frame to determine the type of power transmission equipment and provide a data basis for subsequent judgments on whether the appearance of power transmission equipment is defective and whether maintenance is required. This kind of power transmission equipment identification The method needs to manually process a large amount of video images, with low work efficiency and poor real-time performance. Even if there are some electronic identification methods for power transmission equipment types, the recognition mode is relatively backward and the effect is not good. The image is blurred in severe fog and haze, making it difficult to identify the type of power transmission equipment.

Therefore, a new identification platform for power transmission equipment is needed, which can carry out targeted type inspection on the images of power transmission equipment taken by UAVs. This new identification platform can be integrated into the electronic equipment of UAVs. At the same time, it can Overcoming the adverse effects on the images of power transmission equipment in various haze weathers, so as to improve the integrity of the UAV while ensuring the efficiency and accuracy of UAV power transmission equipment inspection.

Contents of the invention

In order to solve the above problems, the present invention provides a power transmission equipment identification platform located on a UAV, which uses a variety of equipment including contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment. The image processing component performs high-precision type recognition on the image of the power transmission equipment captured by the UAV, and uses two wireless communication network cards to avoid interference with the data sent and received by the UAV. This power transmission equipment identification platform can be integrated into the UAV’s In electronic equipment, the more critical thing is to be able to determine the influence factors of fog and haze on images according to the atmospheric attenuation model, and to perform defogging processing on the images of power transmission equipment collected in haze weather to obtain clear images of power transmission equipment, thereby ensuring that in severe weather It can also accurately identify the type of power transmission equipment.

According to one aspect of the present invention, there is provided a power transmission equipment identification platform located on an unmanned aerial vehicle, including an aerial camera, an equipment identification system, a wireless transceiver device, and a Freescale IMX6 processor, and the aerial camera has a direct view of the power transmission equipment on the ground Shooting to obtain an image of the power transmission equipment, the equipment identification system performs image processing on the image of the power transmission equipment to identify the type of power transmission equipment in the image of the power transmission equipment, the Freescale IMX6 processor and the equipment identification The system is connected to the wireless transceiver device separately, and the type of the power transmission equipment is wirelessly sent to the management platform of the remote power supply unit through the wireless transceiver device.

More specifically, in the power transmission equipment identification platform located on the UAV, it also includes: a power supply, including a solar power supply device, a storage battery, a switch and a voltage converter, and the switch is connected to the solar power supply device and the The storage batteries are respectively connected, and whether to switch to the solar power supply device to be powered by the solar power supply device is determined according to the remaining power of the storage battery. The voltage converter is connected to the switch to convert the 5V voltage input through the switch to 3.3V voltage; mobile hard disk, used to pre-store the preset altitude range, preset air pressure altitude weight and preset radio altitude weight, and also used to pre-store a layer of wavelet coefficient sets of various types of power transmission equipment, each type of power transmission The wavelet coefficient set of one layer of equipment is composed of wavelet decomposition coefficients of four decomposition subgraphs obtained by performing a layer of Harr wavelet decomposition on each type of reference power transmission equipment image, and each type of reference power transmission equipment image is for each The image obtained by pre-shooting the type of reference power transmission equipment, the wavelet decomposition coefficients of the four decomposition sub-images are respectively the wavelet decomposition coefficient of a smooth sub-image, the wavelet decomposition coefficient of a horizontal sub-image, and the wavelet decomposition coefficient of a vertical sub-image. The decomposition coefficient and the wavelet decomposition coefficient of an oblique subgraph, the wavelet decomposition coefficient of the smooth subgraph are overview coefficients, and the wavelet decomposition coefficients of the other three decomposition subgraphs are all detail coefficients; the GPS locator is connected with the GPS navigation satellite, using To receive the real-time positioning data of the position of the drone; the altitude sensing device is connected with the mobile hard disk, including a barometric altitude sensor, a radio altitude sensor and a microcontroller; the barometric altitude sensor is used to Air pressure changes, detecting the real-time air pressure altitude of the position of the drone; the radio altitude sensor includes a radio transmitter, a radio receiver and a single-chip microcomputer, and the single-chip microcomputer is connected with the radio transmitter and the radio receiver respectively, and the The radio transmitter transmits radio waves to the ground, and the radio receiver receives the radio waves reflected by the ground. The single-chip microcomputer calculates no one according to the transmission time of the radio transmitter, the reception time of the radio receiver and the propagation speed of radio waves. The real-time radio altitude of the machine, the propagation speed of the radio wave is the speed of light; the microcontroller is connected with the air pressure altitude sensor, the radio altitude sensor and the mobile hard disk respectively, When the radio altitude difference is within the preset altitude range, the real-time altitude is calculated and output based on the preset barometric altitude weight, the preset radio altitude weight, the real-time barometric altitude and the real-time radio altitude, when When the difference between the real-time barometric altitude and the real-time radio altitude is not within the preset altitude range, an altitude detection failure signal is output; the haze removal processing equipment is located between the aerial photography camera and the equipment identification system for receiving the image of the power transmission equipment, performing defogging processing on the image of the power transmission equipment to obtain a defogged image of the power transmission equipment, replacing the image of the power transmission equipment, and inputting the image of the defogged power transmission equipment into the The equipment recognition system is used to perform image processing to identify the type of power transmission equipment in the image of the defogging power transmission equipment; the defogging processing equipment includes: haze concentration detection sub-equipment, located in the air, for real-time UAV location haze concentration, and determine the haze removal intensity according to the haze concentration, the value of the haze removal intensity is between 0 and 1; the overall atmospheric light value acquisition sub-equipment is connected with the aerial camera to obtain the power transmission Equipment image, calculating the gray value of each pixel in the image of the power transmission equipment, using the gray value of the pixel with the largest gray value as the overall atmospheric light value; the sub-equipment for obtaining atmospheric scattered light value is connected with the aerial camera and the The haze concentration detection sub-equipment is connected respectively, and for each pixel of the power transmission equipment image, extract its R, G, and B three-color channel pixel values as the minimum value as the target pixel value, and use the edge-keeping Gaussian smoothing filter EPGF (edge-preserving gaussian filter) filter the target pixel value to obtain the filtered target pixel value, subtract the target pixel value from the filtered target pixel value to obtain the target pixel difference, and use EPGF to filter the target pixel difference To obtain the filter target pixel difference, subtract the filter target pixel value from the filter target pixel difference to obtain the haze removal reference value, multiply the haze removal intensity by the haze removal reference value to obtain the haze removal threshold, and take the haze Remove the minimum value of the threshold value and the target pixel value as a comparison reference value, take the maximum value of the comparison reference value and 0 as the atmospheric scattered light value of each pixel; the medium transmission rate acquisition sub-equipment, and the acquisition of the overall atmospheric light value The sub-device and the atmospheric scattered light value acquisition sub-device are respectively connected, the atmospheric scattered light value of each pixel is divided by the overall atmospheric light value to obtain a division value, and the division value is subtracted from 1 to obtain the medium of each pixel Transmission rate; the clear image acquisition sub-equipment is respectively connected with the aerial photography camera, the overall atmospheric light value acquisition sub-equipment and the medium transmission rate acquisition sub-equipment, and the medium transmission rate of each pixel is subtracted from 1 to obtain The first difference value, multiplying the first difference value by the overall atmospheric light value to obtain a product value, subtracting the product value from the pixel value of each pixel in the power transmission device image to obtain a second difference value, and The second difference is divided by the medium transmission rate of each pixel to obtain a sharpened pixel value of each pixel, and the pixel value of each pixel in the power transmission equipment image includes R of each pixel in the power transmission equipment image , G, B three-color channel pixel value, correspondingly, the clear pixel value of each pixel obtained includes each pixel R, G, B three-color channel clear pixel value, and the clear pixel value of all pixels is composed of Fog power transmission equipment image; the equipment identification system is connected to the defogging processing equipment and the mobile hard disk respectively, including contrast enhancement equipment, gray scale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment ; The contrast enhancement device is connected to the defogging processing device, and is used to perform contrast enhancement processing on the image of the defogging power transmission device process to obtain an enhanced image; the grayscale processing device is connected to the contrast enhancement device for performing grayscale processing on the enhanced image to obtain a grayscale image; the median filtering device is connected to the grayscale The image processing device is connected to perform median filtering on the grayscale image to remove noise points in the grayscale image to obtain a filtered image; the image erosion and expansion processing device is connected to the median filtering device for Performing image erosion processing and image expansion processing on the filtered image in order to remove the bright spots formed by light in the filtered image and smooth the boundary of the power transmission equipment in the filtered image to obtain an image after erosion and expansion processing; the wavelet decomposition device and the The image erosion and expansion processing equipment is respectively connected with the mobile hard disk, and one layer of Harr wavelet decomposition is performed on the image after the erosion and expansion process, and the wavelet decomposition coefficients of the four decomposition subgraphs obtained form a real-time layer of wavelet coefficient set, and the real-time A layer of wavelet coefficient sets is matched with a layer of wavelet coefficient sets of various types of power transmission equipment one by one. If the matching fails, the signal of no power transmission equipment is output. The type output of the power transmission equipment in the image of the fog power transmission equipment; the wireless transceiver device includes a first wireless network card and a second wireless network card, and the first wireless network card is used to wirelessly receive the control instructions sent by the management platform of the power supply unit, and the control instructions include The purpose GPS data and the purpose shooting height of the power transmission equipment position on the ground to be photographed, the second wireless network card is used to wirelessly send the image with the mark to the power supply unit management platform; the Freescale IMX6 processor and the described The aerial camera, the defogging processing equipment, the GPS locator, the altitude sensing equipment, the equipment identification system and the wireless transceiver device are respectively connected, and the real-time positioning data, the real-time altitude and the The types of power transmission equipment in the image of the defogging power transmission equipment are all marked on the image of the defogging power transmission equipment to obtain a marked image, and the marked image is sent to the second wireless network card of the wireless transceiver device, so When the Freescale IMX6 processor receives the height detection failure signal or no power transmission equipment signal, the height detection failure signal or no power transmission equipment signal is sent to the first wireless network card of the wireless transceiver device so that the first wireless The network card is forwarded to the management platform of the power supply unit; wherein, the Freescale IMX6 processor is sent to the UAV driving mechanism according to the real-time positioning data, the real-time height, the GPS data of the purpose and the height adjustment of the purpose of shooting driving signal, so that the UAV driving mechanism adjusts the flying attitude of the UAV according to the driving signal; the first wireless network card adopts the TCP transmission protocol, and the second wireless network card adopts the UDP transmission protocol.

More specifically, in the power transmission equipment identification platform located on the UAV: the contrast enhancement equipment, grayscale processing equipment, median filter equipment, image erosion and expansion processing equipment, and wavelet decomposition equipment are respectively implemented using different FPGA chips. accomplish.

More specifically, in the power transmission equipment identification platform located on the UAV: the contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment are integrated on one integrated circuit board .

More specifically, in the power transmission equipment identification platform located on the UAV: the selection of FPGA chips used in contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment, and wavelet decomposition equipment Both are Artix-7 series of Xilinx Company.

More specifically, in the power transmission equipment identification platform located on the UAV: the contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment are integrated in the same FPGA chip .

More specifically, in the power transmission equipment identification platform located on the UAV: the various types of power transmission equipment include various types of transmission towers, various types of insulators, and various types of anti-vibration hammers.

Description of drawings

Embodiments of the present invention will be described below in conjunction with the accompanying drawings, wherein:

Fig. 1 is a structural block diagram of a power transmission equipment identification platform located on a drone according to an embodiment of the present invention.

detailed description

The following will describe in detail the implementation of the power transmission equipment identification platform on the drone according to the present invention with reference to the accompanying drawings.

Unmanned aircraft, referred to as "drone" for short, and "UAV" for English abbreviation, is an unmanned aircraft controlled by radio remote control equipment and its own program control device. UAVs are actually a general term for unmanned aerial vehicles. From a technical point of view, they can be divided into: unmanned helicopters, unmanned fixed-wing aircraft, unmanned multi-rotor aircraft, unmanned airships, and unmanned parawing aircraft. . There is no cockpit on the UAV, but it is equipped with autopilot, program control device and other equipment. The personnel on the ground, on the ship, or at the remote control station of the parent aircraft track, locate, remotely control, telemeter and digitally transmit it through radar and other equipment.

The flexible, maneuverable, and low-cost characteristics of drones have also attracted the attention of power regulators. For the power regulatory department, the transmission equipment of its subordinate power transmission network is distributed in a large area with different terrains. If it is manually inspected, it will be time-consuming and labor-intensive. Instead, the aerial inspection of drones will be used. It can improve the efficiency of inspection and reduce the cost of inspection.

In order to find the power transmission equipment with defective appearance for timely maintenance in the later stage, it is first necessary to identify the type of power transmission equipment, and then use the type of power transmission equipment as a starting point to judge whether the currently inspected power transmission equipment is consistent with the appearance of the reference power transmission equipment. If it is not consistent, timely maintenance is required . Here, the determination of the type of power transmission equipment is a difficult problem. Since the unmanned aerial vehicle sends back a large number of images of power transmission equipment, manual inspection is not efficient, and some electronic recognition modes in the prior art also have poor recognition accuracy. question.

In addition, the electronic identification mode in the prior art cannot overcome the adverse effects of fog and haze on the image, so it is easy to accurately identify the type of power transmission equipment in the blurred image of power transmission equipment in the case of severe fog and haze .

For this reason, the present invention builds a power transmission equipment identification platform located on the UAV. Based on the characteristics of power transmission equipment, it customizes a platform including contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet The various image processing components of the decomposition equipment perform high-precision type identification on the images of power transmission equipment captured by drones. The core is based on the different wavelet eigenvalues of different types of power transmission equipment, and the wavelet eigenvalue matching mode is used to identify the type of power transmission equipment. Recognition, at the same time, increase the defog processing equipment to effectively realize the clear processing of the image of the power transmission equipment in the haze weather.

In clear weather, the structural block diagram of the power transmission equipment identification platform located on the drone can be designed as follows, the platform includes an aerial camera, an equipment identification system, a wireless transceiver and a Freescale IMX6 processor, and the aerial camera is opposite to the ground. The power transmission equipment is photographed to obtain an image of the power transmission equipment, and the equipment identification system performs image processing on the image of the power transmission equipment to identify the type of the power transmission equipment in the image of the power transmission equipment. The Freescale IMX6 processor and the The equipment identification system is connected to the wireless transceiver device respectively, and the type of the power transmission equipment is wirelessly sent to the management platform of the remote power supply unit through the wireless transceiver device.

In hazy weather, the structural block diagram of the power transmission equipment identification platform on the UAV can be designed as shown in Figure 1. In the following, the specific structure of the power transmission equipment identification platform designed on the UAV under the haze weather is further described instruction of.

With respect to the platform under sunny weather, the platform shown in Figure 1 also includes: a power supply, including a solar power supply device, a storage battery, a switch and a voltage converter, the switch and the solar power supply device and the storage battery are respectively Connect, decide whether to switch to the solar power supply device to be powered by the solar power supply device according to the remaining power of the battery, and the voltage converter is connected to the switch to convert the 5V voltage input through the switch to 3.3V voltage .

The platform shown in Figure 1 also includes: a mobile hard disk, which is used to pre-store the preset altitude range, preset air pressure altitude weight and preset radio altitude weight, and is also used to pre-store a layer of wavelet coefficient sets of various types of power transmission equipment, The one-layer wavelet coefficient set of each type of power transmission equipment is composed of wavelet decomposition coefficients of four decomposition subgraphs obtained by performing a layer of Harr wavelet decomposition on each type of reference power transmission equipment image, and each type of reference power transmission equipment The image is an image obtained by pre-shooting each type of reference power transmission equipment. The wavelet decomposition coefficients of the four decomposition subgraphs are respectively a wavelet decomposition coefficient of a smooth subgraph, a wavelet decomposition coefficient of a horizontal subgraph, and a wavelet decomposition coefficient of a horizontal subgraph. The wavelet decomposition coefficients of the vertical subgraph and an oblique subgraph are the wavelet decomposition coefficients, the wavelet decomposition coefficients of the smooth subgraph are overview coefficients, and the wavelet decomposition coefficients of the other three decomposition subgraphs are detail coefficients.

The platform shown in Figure 1 also includes: a GPS locator, connected to GPS navigation satellites, for receiving real-time positioning data of the location of the drone.

The platform shown in Fig. 1 also includes: height sensing equipment, is connected with described mobile hard disk, comprises air pressure altitude sensor, radio altitude sensor and microcontroller; Detect the real-time barometric altitude of the position of the drone; the radio altitude sensor includes a radio transmitter, a radio receiver and a single-chip microcomputer, and the single-chip microcomputer is connected with the radio transmitter and the radio receiver respectively, and the radio transmitter Transmitting radio waves to the ground, the radio receiver receives the radio waves reflected by the ground, and the single-chip microcomputer calculates the real time radio altitude, the propagation speed of the radio waves is the speed of light; the microcontroller is connected with the air pressure altitude sensor, the radio altitude sensor and the mobile hard disk respectively, when the real-time air pressure altitude and the real-time radio altitude When the difference is within the preset altitude range, calculate and output the real-time altitude based on the preset barometric altitude weight, the preset radio altitude weight, the real-time barometric altitude and the real-time radio altitude, when the real-time When the difference between the barometric altitude and the real-time radio altitude is not within the preset altitude range, an altitude detection failure signal is output.

The platform shown in FIG. 1 also includes: a haze removal processing device 5, located between the aerial camera 1 and the device identification system 2, for receiving the image of the power transmission device, and performing dehazing on the image of the power transmission device Processing to obtain a defogged power transmission equipment image, replacing the power transmission equipment image, inputting the defogged power transmission equipment image into the equipment identification system for image processing to identify the type of power transmission equipment in the defogged power transmission equipment image.

Described defogging processing equipment 5 comprises: haze concentration detection sub-equipment, is positioned in the air, is used for the haze concentration of real-time unmanned aerial vehicle position, and determines haze removal strength according to haze concentration, and described haze removal strength The value is between 0 and 1.

The defogging processing device 5 includes: an overall atmospheric light value acquisition sub-device, which is connected with the aerial camera 1 to obtain the image of the power transmission equipment, calculates the gray value of each pixel in the image of the power transmission equipment, and converts the gray value The gray value of the pixel with the largest value is taken as the overall atmospheric light value.

The defogging processing device 5 includes: an atmospheric scattered light value acquisition sub-device, which is respectively connected to the aerial camera 1 and the haze concentration detection sub-device, and extracts its R for each pixel of the image of the power transmission device, The minimum value among the pixel values of the G and B three-color channels is used as the target pixel value, and the target pixel value is filtered using an edge-preserving gaussian filter EPGF (edge-preserving gaussian filter) to obtain the filtered target pixel value. Subtract the filtered target pixel value from the pixel value to obtain the target pixel difference, use EPGF to filter the target pixel difference to obtain the filtered target pixel difference, subtract the filtered target pixel value from the filtered target pixel difference to obtain haze removal Base value, multiply the haze removal intensity by the haze removal reference value to obtain the haze removal threshold, take the minimum value of the haze removal threshold and the target pixel value as a comparison reference value, and take the maximum value of the comparison reference value and 0 Atmospheric scattered light value as each pixel.

The defogging processing device 5 includes: a medium transmission rate acquisition sub-device, which is respectively connected with the overall atmospheric light value acquisition sub-device and the atmospheric scattered light value acquisition sub-device, and divides the atmospheric scattered light value of each pixel by The overall atmospheric light value to obtain the division value, which is subtracted from 1 to obtain the medium transmission rate of each pixel.

The defogging processing device 5 includes: a clear image acquisition sub-device, which is respectively connected with the aerial camera 1, the overall atmospheric light value acquisition sub-device and the medium transmission rate acquisition sub-device, and subtracts each The medium transmission rate of the pixel to obtain a first difference, multiply the first difference by the overall atmospheric light value to obtain a product value, and subtract the product value from the pixel value of each pixel in the power transmission device image to obtain Obtaining a second difference value, dividing the second difference value by the medium transmission rate of each pixel to obtain a sharpened pixel value of each pixel, the pixel value of each pixel in the power transmission device image includes the power transmission device The R, G, and B three-color channel pixel values of each pixel in the image. Correspondingly, the obtained sharpened pixel value of each pixel includes the R, G, and B three-color channel cleared pixel values of each pixel. All pixels The sharpened pixel values of the defogged power transmission equipment image.

The device identification system 2 is respectively connected to the defogging processing device 5 and the mobile hard disk, including contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment, and wavelet decomposition equipment; The contrast enhancement device is connected to the defogging processing device 5, and is used to perform contrast enhancement processing on the image of the defogging power transmission device to obtain an enhanced image; the grayscale processing device is connected to the contrast enhancement device, and is used to performing grayscale processing on the enhanced image to obtain a grayscale image; the median filtering device is connected to the grayscale processing device for performing median filtering on the grayscale image to remove Noise points to obtain a filtered image; the image erosion and expansion processing device is connected to the median filtering device, and is used to sequentially perform image erosion processing and image expansion processing on the filtered image, so as to remove the image formed by light in the filtered image Bright spots and smooth filter the boundary of the power transmission equipment in the image to obtain the image after corrosion and expansion processing; the wavelet decomposition device is connected to the image corrosion and expansion processing equipment and the mobile hard disk respectively, and performs a layer-by-layer process on the image after the corrosion and expansion processing Harr wavelet decomposition, the wavelet decomposition coefficients of the four decomposition subgraphs obtained form a real-time one-layer wavelet coefficient set, and the real-time one-layer wavelet coefficient set is matched with the one-layer wavelet coefficient set of each type of transmission equipment one by one. If the matching fails, output If there is no signal of the power transmission equipment, if the matching is successful, the signal of the existence of the power transmission equipment is output, and the type of the matched power transmission equipment is output as the type of the power transmission equipment in the defogged power transmission equipment image.

The wireless transceiver device 3 includes a first wireless network card and a second wireless network card, the first wireless network card is used to wirelessly receive the control instruction sent by the management platform of the power supply unit, and the control instruction includes the location of the power transmission equipment on the ground to be photographed The target GPS data and the target shooting height, the second wireless network card is used to wirelessly send the marked image to the management platform of the power supply unit.

The Freescale IMX6 processor 4 and the aerial camera 1, the defogging processing device 5, the GPS locator, the height sensing device, the device identification system 2 and the wireless transceiver device 3 Connect respectively, mark the real-time positioning data, the real-time height and the type of power transmission equipment in the image of the defogged power transmission equipment on the image of the defogged power transmission equipment to obtain a marked image, which will be marked The image of the image is sent to the second wireless network card of the wireless transceiver device 3, and the Freescale IMX6 processor 4 sends the height detection failure signal or the no power transmission equipment signal when receiving the height detection failure signal or the no power transmission equipment signal to the first wireless network card of the wireless transceiver device 3 so that the first wireless network card forwards to the management platform of the power supply unit.

Wherein, the Freescale IMX6 processor 4 adjusts the driving signal sent to the UAV driving mechanism according to the real-time positioning data, the real-time height, the GPS data of the purpose and the shooting height of the purpose, so that the The driving mechanism of the UAV adjusts the flying attitude of the UAV according to the driving signal; the first wireless network card adopts the TCP transmission protocol, and the second wireless network card adopts the UDP transmission protocol.

Wherein, optionally, in the power transmission equipment identification platform located on the UAV, the contrast enhancement equipment, the gray scale processing equipment, the median filtering equipment, the image erosion and expansion processing equipment and the wavelet decomposition equipment respectively adopt different FPGA chips; integrate contrast enhancement equipment, grayscale processing equipment, median filter equipment, image erosion and expansion processing equipment and wavelet decomposition equipment on one integrated circuit board; contrast enhancement equipment, grayscale processing equipment, median filter Equipment, image erosion and dilation processing equipment, and wavelet decomposition equipment use the FPGA chips of Xilinx's Artix-7 series; contrast enhancement equipment, grayscale processing equipment, median filter equipment, and image erosion and dilation processing equipment and the wavelet decomposition device are integrated in the same FPGA chip; and the various types of power transmission equipment may include various types of transmission towers, various types of insulators, and various types of anti-vibration hammers.

In addition, haze images can be dehazed through a series of image processing equipment to obtain clear images and improve the visibility of images. These image processing devices perform different image processing functions, based on the principle of haze formation, to achieve the effect of removing haze. The clear processing of smog images has great application value for both military and civilian fields. Military fields include military defense, remote sensing navigation, etc., and civilian fields include road monitoring, target tracking, and automatic driving.

The process of haze image formation can be described by the atmospheric attenuation process. The relationship between the haze image and the actual image, that is, the clear image can be expressed by the overall atmospheric light value and the medium transmission rate of each pixel, that is, in the known fog In the case of a haze image, according to the overall atmospheric light value and the medium transmission rate of each pixel, a clear image can be obtained.

There are some effective and proven methods for solving the overall atmospheric light value and the medium transmission rate of each pixel. For example, for the medium transmission rate of each pixel, it is necessary to obtain the overall atmospheric light value and the atmospheric scattered light of each pixel value, and the atmospheric scattered light value of each pixel can be obtained by performing two Gaussian smoothing filters on the pixel value of each pixel in the haze image, during which the intensity of haze removal is adjustable; and the overall atmospheric There are two ways to obtain the light value. One way is to obtain the black channel of the haze image (that is, in the haze image, the black channel value of some pixels is very low, and the black channel is R, G, B three colors One of the channels), in the haze image, it is obtained by looking for the pixel with the largest gray value among the pixels with a larger black channel pixel value, and the gray value of the pixel with the largest gray value that is about to be found As the overall atmospheric light value, it participates in the clearing process of each pixel in the haze image; in addition, the overall atmospheric light value can also be obtained by the following method: calculate the gray value of each pixel in the haze image, and convert the gray value The grayscale value of the largest pixel is used as the overall atmospheric light value.

For the relationship between the specific haze image and the actual image, that is, the clear image, and the relationship between various parameters, please refer to the above content.

Through the discussion of the formation principle of the haze image, the relationship between the haze image and the clear image is established, and multiple parameters are used to represent this relationship, and then the clarity can be obtained by restoring the obtained multiple parameter values and the haze image For images with higher resolution, because the parameters are obtained using some statistical and empirical means, the image with higher resolution cannot be completely equivalent to the actual image, but it already has a considerable degree of haze removal effect, which is called haze Provide effective protection for operations in various fields under weather conditions.

Using the power transmission equipment identification platform on the UAV of the present invention, aiming at the technical problems of low efficiency, low precision and inability to overcome the influence of fog and haze weather in the existing UAV power transmission equipment identification mechanism, a wavelet feature based on power transmission equipment has been developed. Value matching is the core of the transmission equipment type identification mode. Around this identification mode, a transmission equipment identification platform composed of a variety of customized image processing components is built. In the transmission equipment identification platform, dual network card communication interfaces and high-precision height are added. Sensors and other electronic components, and more importantly, the introduction of high-precision defogging processing equipment ensures that the platform can work normally even in severe haze weather, thus comprehensively improving the reliability of drone identification for power transmission equipment.

It can be understood that although the present invention has been disclosed above with preferred embodiments, the above embodiments are not intended to limit the present invention. For any person skilled in the art, without departing from the scope of the technical solution of the present invention, the technical content disclosed above can be used to make many possible changes and modifications to the technical solution of the present invention, or be modified into equivalent changes, etc. effective example. Therefore, any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention, which do not deviate from the technical solution of the present invention, still fall within the protection scope of the technical solution of the present invention.

Claims (1)

1. A power transmission equipment identification platform positioned on an unmanned aerial vehicle, it is characterized in that the platform includes an aerial camera, an equipment identification system, a wireless transceiver and a Freescale IMX6 processor, and the aerial camera is to the power transmission equipment on the ground Shooting to obtain an image of the power transmission equipment, the equipment identification system performs image processing on the image of the power transmission equipment to identify the type of power transmission equipment in the image of the power transmission equipment, the Freescale IMX6 processor and the equipment identification The system is connected to the wireless transceiver device respectively, and the type of the power transmission equipment is wirelessly sent to the management platform of the remote power supply unit through the wireless transceiver device; The platform also includes: The power supply includes a solar power supply device, a storage battery, a switch and a voltage converter. The switch is connected to the solar power supply device and the storage battery respectively, and it is determined whether to switch to the solar power supply device according to the remaining power of the storage battery to be used by the solar power supply device. The solar power supply device is powered, and the voltage converter is connected with the switch to convert the 5V voltage input through the switch to 3.3V voltage; The mobile hard disk is used to pre-store the preset altitude range, preset air pressure altitude weight and preset radio altitude weight, and is also used to pre-store a layer of wavelet coefficient sets of various types of power transmission equipment, and a layer of each type of power transmission equipment The wavelet coefficient set is composed of the wavelet decomposition coefficients of four decomposition subgraphs obtained by performing a layer of Harr wavelet decomposition on each type of reference power transmission equipment image. The image obtained by pre-shooting by the device, the wavelet decomposition coefficients of the four decomposition sub-images are respectively a wavelet decomposition coefficient of a smooth sub-image, a wavelet decomposition coefficient of a horizontal sub-image, a wavelet decomposition coefficient of a vertical sub-image and a The wavelet decomposition coefficients of the oblique subgraph, the wavelet decomposition coefficients of the smooth subgraph are overview coefficients, and the wavelet decomposition coefficients of the other three decomposed subgraphs are detail coefficients; GPS locator, connected with GPS navigation satellites, used to receive real-time positioning data of the location of the drone; The altitude sensing device is connected with the mobile hard disk, including an air pressure altitude sensor, a radio altitude sensor and a microcontroller; the air pressure altitude sensor is used to detect the real-time air pressure at the position of the drone according to the air pressure change near the drone Height; the radio altitude sensor includes a radio transmitter, a radio receiver and a single-chip microcomputer, and the single-chip microcomputer is connected with the radio transmitter and the radio receiver respectively, and the radio transmitter transmits radio waves to the ground, and the radio transmitter The receiver receives the radio waves reflected by the ground, and the single-chip microcomputer calculates the real-time radio altitude of the drone according to the transmitting time of the radio transmitter, the receiving time of the radio receiver and the radio wave propagation speed, and the radio wave propagation speed is the speed of light; the microcontroller is connected to the barometric altitude sensor, the radio altitude sensor and the mobile hard disk respectively, when the difference between the real-time barometric altitude and the real-time radio altitude is within the preset altitude range , calculating and outputting the real-time altitude based on the preset barometric altitude weight, the preset radio altitude weight, the real-time barometric altitude and the real-time radio altitude, when the real-time barometric altitude and the real-time radio altitude When the difference is not within the preset height range, a height detection failure signal is output; The haze removal processing device is located between the aerial camera and the device identification system, and is used to receive the image of the power transmission device, and perform defogging processing on the image of the power transmission device to obtain a defogged image of the power transmission device, replacing the An image of the power transmission equipment, inputting the image of the defogged power transmission equipment into the equipment identification system to perform image processing to identify the type of the power transmission equipment in the image of the defogged power transmission equipment; The defogging treatment equipment includes: The smog concentration detection sub-equipment is located in the air and is used for the smog concentration at the location of the drone in real time, and determines the smog removal intensity according to the smog concentration, and the value of the smog removal intensity is between 0 and 1; The overall atmospheric light value acquisition sub-equipment is connected with the aerial camera to obtain the image of the power transmission equipment, calculates the gray value of each pixel in the image of the power transmission equipment, and takes the gray value of the pixel with the largest gray value as a whole atmospheric light value; Atmospheric scattered light value acquisition sub-equipment is respectively connected with the aerial camera and the haze concentration detection sub-equipment, and for each pixel of the image of the power transmission equipment, extracts the minimum pixel value of the R, G, and B three-color channels value is used as the target pixel value, and the target pixel value is filtered using the edge-preserving Gaussian smoothing filter EPGF to obtain the filtered target pixel value, and the target pixel value is subtracted from the filtered target pixel value to obtain the target pixel difference value, using EPGF The target pixel difference is filtered to obtain the filtered target pixel difference, the filtered target pixel value is subtracted from the filtered target pixel difference to obtain the haze removal reference value, and the haze removal intensity is multiplied by the haze removal reference value to obtain Haze removal threshold, take the minimum value of the haze removal threshold and the target pixel value as a comparison reference value, and take the maximum value of the comparison reference value and 0 as the atmospheric scattered light value of each pixel; The medium transmission rate acquisition sub-device is respectively connected with the sub-device for obtaining the overall atmospheric light value and the sub-device for obtaining the atmospheric scattered light value, and divides the atmospheric scattered light value of each pixel by the overall atmospheric light value to obtain a division value, Subtracting the division value from 1 to obtain the medium transmission rate of each pixel; The clear image acquisition sub-device is respectively connected with the aerial camera, the overall atmospheric light value acquisition sub-device and the medium transmission rate acquisition sub-device, and the medium transmission rate of each pixel is subtracted from 1 to obtain the first difference value, the first difference is multiplied by the overall atmospheric light value to obtain a product value, the pixel value of each pixel in the power transmission equipment image is subtracted from the product value to obtain a second difference value, and the first Dividing the two difference values by the medium transmission rate of each pixel to obtain the cleared pixel value of each pixel, the pixel value of each pixel in the power transmission equipment image includes R, G, and R of each pixel in the power transmission equipment image B three-color channel pixel value, correspondingly, the obtained sharpened pixel value of each pixel includes the cleared pixel value of each pixel's R, G, and B three-color channels, and the cleared pixel values of all pixels form the defogging power transmission device image; The device identification system is connected to the defogging processing device and the mobile hard disk respectively, including contrast enhancement equipment, gray scale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment; the contrast enhancement The device is connected to the defogging processing device for performing contrast enhancement processing on the image of the defogging power transmission device to obtain an enhanced image; the grayscale processing device is connected to the contrast enhancement device for processing the enhanced Perform grayscale processing on the image to obtain a grayscale image; the median filtering device is connected to the grayscale processing device for performing median filtering on the grayscale image to remove noise points in the grayscale image , to obtain a filtered image; the image erosion and expansion processing device is connected to the median filtering device, and is used to sequentially perform image erosion processing and image expansion processing on the filtered image, so as to remove and smooth the bright spots formed by light in the filtered image Filtering the boundary of the power transmission equipment in the image to obtain the image after corrosion and expansion processing; the wavelet decomposition device is connected to the image corrosion and expansion processing device and the mobile hard disk respectively, and performs a layer of Harr wavelet decomposition on the image after the corrosion and expansion processing , the wavelet decomposition coefficients of the four decomposition subgraphs obtained form a real-time one-layer wavelet coefficient set, and match the real-time one-layer wavelet coefficient set with the one-layer wavelet coefficient set of each type of transmission equipment one by one. If the matching fails, no transmission equipment is output signal, if the matching is successful, the signal of the power transmission equipment exists and the type of the matched power transmission equipment is output as the type of the power transmission equipment in the defogging power transmission equipment image; The wireless transceiver device includes a first wireless network card and a second wireless network card. The first wireless network card is used to wirelessly receive control instructions sent by the management platform of the power supply unit. The control instructions include the location of the power transmission equipment on the ground to be photographed. Target GPS data and target shooting height, the second wireless network card is used to wirelessly send the marked image to the management platform of the power supply unit; The Freescale IMX6 processor is respectively connected with the aerial camera, the defogging processing equipment, the GPS locator, the height sensing equipment, the equipment identification system and the wireless transceiver device, and the The real-time positioning data, the real-time height and the type of power transmission equipment in the defogged power transmission equipment image are all marked on the defogged power transmission equipment image to obtain a marked image, and the marked image is sent to the defogged power transmission equipment image. The second wireless network card of the wireless transceiver device, when the Freescale IMX6 processor receives the height detection failure signal or no power transmission equipment signal, the height detection failure signal or no power transmission equipment signal is sent to the wireless transceiver device The first wireless network card is used to forward the first wireless network card to the management platform of the power supply unit; Wherein, the Freescale IMX6 processor adjusts the driving signal sent to the UAV driving mechanism according to the real-time positioning data, the real-time height, the target GPS data and the target shooting height, so that the drone can The man-machine drive mechanism adjusts the flight attitude of the drone according to the drive signal; Wherein, the first wireless network card adopts the TCP transmission protocol, and the second wireless network card adopts the UDP transmission protocol; The contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment are respectively implemented with different FPGA chips; Integrate contrast enhancement equipment, gray scale processing equipment, median filtering equipment, image erosion and expansion processing equipment and wavelet decomposition equipment on one integrated circuit board; The types of FPGA chips used in contrast enhancement equipment, gray scale processing equipment, median filter equipment, image erosion and dilation processing equipment and wavelet decomposition equipment are Artix-7 series of Xilinx Company; Integrate contrast enhancement equipment, grayscale processing equipment, median filtering equipment, image erosion and dilation processing equipment and wavelet decomposition equipment in the same FPGA chip; The various types of power transmission equipment include various types of transmission towers, various types of insulators and various types of anti-vibration hammers.