CN113900091B - Power line and electric wire tower identification method based on polarized radar - Google Patents

Power line and electric wire tower identification method based on polarized radar Download PDF

Info

Publication number
CN113900091B
CN113900091B CN202110977269.5A CN202110977269A CN113900091B CN 113900091 B CN113900091 B CN 113900091B CN 202110977269 A CN202110977269 A CN 202110977269A CN 113900091 B CN113900091 B CN 113900091B
Authority
CN
China
Prior art keywords
polarization
channel
power line
amplitude
channels
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110977269.5A
Other languages
Chinese (zh)
Other versions
CN113900091A (en
Inventor
陈伯孝
郎思呈
叶倾知
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xidian University
Original Assignee
Xidian University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xidian University filed Critical Xidian University
Priority to CN202110977269.5A priority Critical patent/CN113900091B/en
Publication of CN113900091A publication Critical patent/CN113900091A/en
Application granted granted Critical
Publication of CN113900091B publication Critical patent/CN113900091B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a polarized radar-based power line and electric wire tower identification method, which comprises the following steps: transmitting signals to be detected by using a linear polarization antenna of a polarization radar, and receiving echo signals by using a circular polarization antenna to obtain echo signals of 4 polarization channels; according to the echo signals of the 4 polarization channels, obtaining the amplitude of the echo signals of each polarization channel, the polarization amplitude angles, the polarization inclination angles and the polarization ellipticity angles of the left and right channels of the circularly polarized antenna, and determining ten-dimensional vectors formed by the obtained 10 data as target feature vectors to be detected; inputting the feature vector of the target to be tested into a target classification network which is trained in advance to obtain the identification result that the target to be tested belongs to the power line or the electric wire tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and power line towers with category identification in a training set. The invention can effectively solve the problems of too few characteristics and unreasonable characteristic selection, and improve the recognition accuracy of the power line and the power line tower.

Description

Power line and electric wire tower identification method based on polarized radar
Technical Field
The invention belongs to the technical field of radars, and particularly relates to a polarized radar-based power line and electric wire tower identification method.
Background
With the continuous development of aviation industry, low-altitude aircrafts such as helicopters are increasingly widely applied, but the identification capability of power lines and electric wire towers in the prior radar technology is seriously insufficient, so that the life safety of pilots in low-altitude flight is threatened.
Currently, identification of the electromagnetic wave characteristics of the power line and the electric wire tower by using polarization information is a major research direction. For example, the paper "method for identifying power lines based on radar echo polarization characteristics" uses distance information, doppler velocity, horizontal polarization channel amplitude, vertical polarization channel amplitude, and polarization inclination angle of a power line and a power line tower as 6-dimensional feature vectors, and uses a machine learning method to perform classification identification on the power line and the power line tower. However, the distance information and the Doppler speed in the feature vector used by the method are only related to the actual geographic position of the power line/electric wire tower, the power line and the electric wire tower are difficult to distinguish from ground clutter and unknown static targets in the identification process, and the method is poor in spatial separability and not suitable for serving as the feature vector, so that the identification effect of the method on the power line and the electric wire tower is limited.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the invention provides a polarized radar-based power line and wire tower identification method, a polarized radar-based power line and wire tower identification device, electronic equipment and a storage medium. The technical problems to be solved by the invention are realized by the following technical scheme:
In a first aspect, an embodiment of the present invention provides a method for identifying a power line and a power line tower based on a polarized radar, where the method includes:
transmitting signals to be detected by utilizing a linear polarization antenna of a polarization radar, and receiving echo signals by utilizing a circular polarization antenna to obtain echo signals of 4 polarization channels in total; wherein the 4 polarization channels include an HL channel, a VL channel, an HR channel, and a VR channel;
According to the echo signals of the 4 polarization channels, obtaining the amplitude of the echo signals of each polarization channel, the polarization amplitude angles, the polarization inclination angles and the polarization ellipticity angles of the left and right channels of the circular polarization antenna, and determining ten-dimensional vectors formed by the obtained 10 data as target feature vectors to be detected;
inputting the feature vector of the target to be tested into a target classification network which is trained in advance to obtain a recognition result that the target to be tested belongs to a power line or a power line tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
In a second aspect, an embodiment of the present invention provides a polarized radar-based power line and power line tower identification device, the device including:
The echo signal acquisition module is used for transmitting signals to be detected by utilizing a linear polarization antenna of the polarization radar, receiving echo signals by utilizing a circular polarization antenna, and obtaining echo signals of 4 polarization channels in total; wherein the 4 polarization channels include an HL channel, a VL channel, an HR channel, and a VR channel;
The target feature vector generation module to be tested is used for obtaining the echo signal amplitude of each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circular polarization antenna according to the echo signals of the 4 polarization channels, and determining a ten-dimensional vector formed by the obtained 10 data as the target feature vector to be tested;
The target classification module is used for inputting the feature vector of the target to be detected into a target classification network which is trained in advance to obtain the identification result of the target to be detected belonging to the power line or the power line tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, where,
The memory is used for storing a computer program;
The processor is used for implementing the steps of the power line and electric wire tower identification method based on the polarized radar provided by the embodiment of the invention when executing the program stored on the memory.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of the polarized radar based power line and power line tower identification method provided by the embodiments of the present invention.
In the scheme provided by the embodiment of the invention, a linear polarization antenna of a polarization radar is utilized to transmit signals to a target to be detected, and a circular polarization antenna is utilized to receive echo signals, so that echo signals of 4 polarization channels are obtained in total; according to the echo signals of the 4 polarization channels, obtaining the amplitude of the echo signals of each polarization channel, the polarization amplitude angles, the polarization inclination angles and the polarization ellipticity angles of the left and right channels of the circular polarization antenna, and determining ten-dimensional vectors formed by the obtained 10 data as target feature vectors to be detected; inputting the feature vector of the target to be tested into a pre-trained target classification network to obtain the identification result of the target to be tested belonging to the power line or the power line tower. The embodiment of the invention integrates the polarization difference of the power line and the electric wire tower, selects more characteristics with distinction in space, constructs a 10-dimensional characteristic vector by utilizing polarization multichannel information, and identifies the power line and the electric wire tower by utilizing a machine learning method. Compared with the prior art, the method effectively solves the problems of too few characteristics and unreasonable characteristic selection, and improves the recognition accuracy of the power line and the wire tower.
Drawings
Fig. 1 is a schematic flow chart of a power line and electric wire tower identification method based on a polarized radar according to an embodiment of the present invention;
FIG. 2 is a schematic view of a polarization ellipse in radar technology;
FIG. 3 is a graph showing contrast of the amplitude of return signals of an HL channel and a VL channel in measured data in a method for identifying a power line and a wire tower based on a polarized radar according to an embodiment of the present invention;
FIG. 4 is a graph showing contrast of the amplitudes of return signals of an HL channel and a VL channel in measured data in a power line and wire tower identification method based on a polarized radar according to an embodiment of the present invention;
fig. 5 is a comparison chart of echo signal amplitudes of HR channel and VR channel electric wire tower in measured data in a polarized radar-based electric wire and electric wire tower identification method according to an embodiment of the present invention;
fig. 6 is a comparison chart of the amplitude of echo signals of HR channel and VR channel in measured data in a method for identifying a power line and a wire tower based on a polarized radar according to an embodiment of the present invention;
fig. 7 is a graph showing comparison of polarization angles of an L-channel power line and a tower in measured data in a method for identifying a power line and a tower based on a polarization radar according to an embodiment of the present invention;
Fig. 8 is a graph showing the comparison of polarization angles of R-channel power lines and electric wire towers in measured data in a method for identifying power lines and electric wire towers based on a polarized radar according to an embodiment of the present invention;
fig. 9 is a graph showing a comparison of polarization inclination angles of an L-channel power line and a tower in measured data in a method for identifying a power line and a tower based on a polarization radar according to an embodiment of the present invention;
Fig. 10 is a graph showing the polarization inclination angle of R-channel power line and electric wire tower in the measured data in the method for identifying power line and electric wire tower based on the polarization radar according to the embodiment of the invention;
FIG. 11 is a graph showing comparison of ellipticity angles of polarization of an L-channel power line and a tower in measured data in a method for identifying a power line and a tower based on a polarized radar according to an embodiment of the present invention;
fig. 12 is a comparison chart of R-channel power line and tower polarization ellipticity angle in measured data in a method for identifying power line and tower based on a polarization radar according to an embodiment of the present invention;
Fig. 13 is a schematic flow chart of a training process of the target classification network in a polarized radar-based power line and electric wire tower identification method according to an embodiment of the present invention;
Fig. 14 is a schematic structural diagram of a polarized radar-based power line and electric wire tower identification device according to an embodiment of the present invention;
fig. 15 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to construct reasonable feature vectors and improve the recognition accuracy of the radar on the power line and the electric wire tower, the embodiment of the invention provides a power line and electric wire tower recognition method, device, electronic equipment and storage medium based on a polarized radar.
It should be noted that, the execution subject of the power line and electric wire tower identification method based on the polarized radar provided by the embodiment of the invention may be a power line and electric wire tower identification device based on the polarized radar, and the device may be operated in an electronic device, and the electronic device may be mounted in the polarized radar. The electronic device may be a server or a terminal device, but is not limited thereto.
In a first aspect, an embodiment of the present invention provides a method for identifying a power line and a power line tower based on a polarized radar. As shown in fig. 1, the steps may be included as follows:
S1, transmitting signals of a target to be detected by using a linear polarization antenna of a polarization radar, and receiving echo signals by using a circular polarization antenna to obtain echo signals of 4 polarization channels in total.
The radar beam has polarization (also known as polarization). When radar (electromagnetic wave) interacts with a target ground object, the polarization of the radar can rotate in different directions to generate horizontal and vertical components. The polarization direction is parallel to the ground and is called horizontal polarization, and is denoted by H; the polarization direction perpendicular to the ground (parallel to the plane of incidence) is referred to as the vertical polarization, denoted by V.
The embodiment of the invention adopts a polarized radar, which is to transmit H, V polarized wave pulses in a very short interval and simultaneously receive H, V echoes by using a left-hand circularly polarized antenna and a right-hand circularly polarized antenna. The polarized radar records both the amplitude variation of the coherent echo signal and the phase variation (phase difference) between the echoes of different polarizations.
It will be understood by those skilled in the art that in the present embodiment, the linearly polarized antenna refers to a horizontally-vertically polarized antenna (horizontal polarization is denoted by H, vertical polarization is denoted by V), and the circularly polarized antenna refers to a left-right circularly polarized antenna (left-hand circularly polarized is denoted by L, and right-hand circularly polarized is denoted by R). The 4 polarization channels include HL channel, VL channel, HR channel and VR channel; HL represents a horizontal polarization antenna transmitting signal, and a left-hand circular polarization antenna receives an echo signal; VL represents a vertical polarization antenna transmitting signal, and a left-hand circular polarization antenna receives an echo signal; HR represents a horizontal polarized antenna transmitting signal, and a right-hand circularly polarized antenna receiving an echo signal; VR indicates that the vertical polarized antenna transmits a signal and the right-hand circularly polarized antenna receives an echo signal. Therefore, for the target to be measured, the echo signals of the 4 polarization channels can be finally obtained.
S2, according to echo signals of 4 polarization channels, obtaining the amplitude of the echo signals of each polarization channel, the polarization amplitude angles, the polarization inclination angles and the polarization ellipticity angles of the left and right channels of the circularly polarized antenna, and determining ten-dimensional vectors formed by the obtained 10 data as target feature vectors to be detected.
Specifically, the process for obtaining the echo signal amplitude of each polarization channel includes:
for the echo signal of each polarization channel, the amplitude of the echo signal of the polarization channel is obtained through peak detection.
It will be appreciated by those skilled in the art that by detecting the amplitudes of the signal peaks by means of signal processing for the echo signals of the HL channel, the VL channel, the HR channel and the VR channel, respectively, the echo signal amplitudes of the corresponding polarization channels can be obtained. This process is of the prior art and will not be described in detail here.
Specifically, the process for obtaining the polarization amplitude angles of the left and right channels of the circularly polarized antenna comprises the following steps:
Calculating to obtain the polarization amplitude angle of the left-hand circularly polarized channel by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization amplitude angle calculation formula;
Calculating to obtain the polarization amplitude angles of the right-hand circularly polarized channels by using the echo signal amplitudes of the VR channels and the HR channels and a polarization amplitude angle calculation formula of the right-hand circularly polarized channels;
The calculation formulas of the polarization amplitude angles of the left-hand circular polarization channel and the right-hand circular polarization channel are respectively as follows:
The polarization amplitude angles of the left and right channels of the circular polarized antenna comprise a left-hand circular polarized channel polarization amplitude angle and a right-hand circular polarized channel polarization amplitude angle; gamma L represents the polarization amplitude angle of the left-hand circularly polarized channel; gamma R represents the polarization amplitude angle of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; arctan (·) represents the arctangent function.
It will be appreciated by those skilled in the art that the amplitude of the echo signal for each polarized channel can be obtained by the peak detection method described above, and therefore, the polarization angles of the left and right channels of the circularly polarized antenna can be obtained by the calculation described above.
Specifically, the process for obtaining the polarization inclination angles of the left and right channels of the circularly polarized antenna comprises the following steps:
Calculating to obtain the polarization inclination angle of the left-hand circular polarization channel by using the echo signal amplitudes of the VL channel and the HL channel and a polarization inclination angle calculation formula of the left-hand circular polarization channel;
Calculating to obtain the right-hand circularly polarized channel polarization inclination angle by utilizing echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization inclination angle calculation formula;
The calculation formulas of the polarization dip angles of the left-hand circular polarization channel and the right-hand circular polarization channel are respectively as follows:
Wherein:
The polarization dip angles of the left and right channels of the circular polarized antenna comprise a left-hand circular polarized channel polarization dip angle and a right-hand circular polarized channel polarization dip angle; τ L represents the polarization tilt of the left-hand circularly polarized channel; τ R represents the polarization tilt of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; tan (-) represents the tangent function; cos (·) represents a cosine function; arctan (·) represents the arctangent function.
It will be appreciated by those skilled in the art that the amplitude of the echo signal for each polarized channel can be obtained by the peak detection method described above, and therefore, the polarization tilt angles of the left and right channels of the circularly polarized antenna can be obtained by the calculation described above.
Specifically, the process for obtaining the ellipticity angle of the left and right channels of the circularly polarized antenna comprises the following steps:
calculating to obtain the left-hand circularly polarized channel polarization ellipticity angle by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization ellipticity angle calculation formula;
calculating to obtain the right-hand circularly polarized channel polarization ellipticity angle by using echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization ellipticity angle calculation formula;
The left-hand circular polarization channel polarization ellipticity angle calculation formula and the right-hand circular polarization channel polarization ellipticity angle calculation formula are respectively as follows:
Wherein:
The circular polarized antenna comprises a left circular polarized antenna, a right circular polarized antenna and a left circular polarized antenna, wherein the polarized ellipticity angles of the left and right channels of the circular polarized antenna comprise a left circular polarized channel polarized ellipticity angle and a right circular polarized channel polarized ellipticity angle; epsilon L represents the left-hand circularly polarized channel polarization ellipticity angle; epsilon R represents the right-hand circularly polarized channel polarization ellipticity angle; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; sin (·) represents a sine function; arctan (·) represents the arctangent function.
It will be appreciated by those skilled in the art that the amplitude of the echo signal for each polarized channel can be obtained by the peak detection method described above, and thus, the ellipticity angle of polarization for the left and right channels of the circularly polarized antenna can be obtained by the calculation described above.
For specific concepts of polarization argument, polarization tilt angle, and polarization ellipticity angle, please understand in conjunction with the related art, detailed description thereof will be omitted herein. The polarized ellipse is a description mode of completely polarized electromagnetic waves, referring specifically to fig. 2, and fig. 2 is a schematic diagram of polarized ellipse in radar technology. Wherein A represents an auxiliary angle; the i E x and the i E y represent the magnitudes of electromagnetic wave signals in the x and y directions, respectively; the polarization tilt angle tau and the polarization ellipticity angle epsilon are two geometric descriptors of the polarization ellipse, the polarization tilt angle tau takes a value in a [0, pi ] continuous interval, and the polarization ellipticity angle epsilon takes a value in a [ -pi/4, pi/4 ] continuous interval. In the foregoing calculation formulas of the polarization tilt angle and the polarization ellipticity angle, δ L represents the left-hand circularly polarized channel auxiliary angle, and δ R represents the right-hand circularly polarized channel auxiliary angle.
Therefore, for the object to be measured, the echo signal amplitude of each polarized channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circularly polarized antenna, and ten-dimensional vectors formed by the obtained 10 data are as follows: the ten-dimensional vector is a feature vector of a target to be measured, which is simply referred to as a feature vector of the target to be measured.
Compared with six-dimensional feature vectors in the prior art, the embodiment of the invention designs the 10 features as polarization feature discrimination according to polarization differences reflected by the power line and the wire tower in a multi-polarization channel, abandons unreasonable distance information and Doppler speed in the prior art, synthesizes the polarization differences of the power line and the wire tower, selects more features with distinction degree in space to construct feature vectors, and increases the features and simultaneously realizes the rationality of feature selection.
The rationality of the feature vector selected by the embodiment of the invention is described below by a certain helicopter radar measured data.
For the amplitude of the polarized channel echo signals, please refer to fig. 3-6. FIG. 3 is a graph showing contrast of the amplitude of return signals of an HL channel and a VL channel in measured data in a method for identifying a power line and a wire tower based on a polarized radar according to an embodiment of the present invention; FIG. 4 is a graph showing contrast of the amplitudes of return signals of an HL channel and a VL channel in measured data in a power line and wire tower identification method based on a polarized radar according to an embodiment of the present invention; fig. 5 is a comparison chart of echo signal amplitudes of HR channel and VR channel electric wire tower in measured data in a polarized radar-based electric wire and electric wire tower identification method according to an embodiment of the present invention; fig. 6 is a comparison chart of the amplitude of echo signals of HR channel and VR channel in measured data in a method for identifying a power line and a wire tower based on a polarized radar according to an embodiment of the present invention. As can be seen from fig. 3 to 6, the echo amplitude of the power line is larger in the horizontal polarization channels HL and HR than in the vertical polarization channels VL and VR, whereas the echo characteristics of the wire tower are opposite to the power line, and the echo amplitude is larger in the vertical polarization channels VL and VR. That is, the power line and the power line tower have a difference in terms of the echo signal amplitude of each polarization channel.
For polarization argument, please refer to fig. 7 and 8. Fig. 7 and fig. 8 are respectively an L-channel power line and electric wire tower polarization amplitude comparison chart and an R-channel power line and electric wire tower polarization amplitude comparison chart in measured data in the electric wire and electric wire tower identification method based on the polarized radar according to the embodiment of the invention, it can be seen that the polarization amplitude of the power line is concentrated at about 0.4rad and the polarization amplitude of the electric wire tower is concentrated at about 1.2rad no matter the power line is the L-channel or the R-channel. That is, the power line and the wire tower also have a difference in terms of polarization amplitude angle.
For polarization tilt, please refer to fig. 9 and 10. Fig. 9 and fig. 10 are respectively an L-channel power line and electric wire tower polarization inclination angle comparison chart and an R-channel power line and electric wire tower polarization inclination angle comparison chart in measured data in the power line and electric wire tower identification method based on the polarized radar according to the embodiment of the invention, and it can be seen that the polarization inclination angles of the power line are concentrated in the [ -20 °,20 ° ] interval, and the polarization inclination angles of the electric wire tower are concentrated in the vicinity of 75 ° and-75 °. That is, the power line and the power line tower also have a difference in terms of polarization inclination.
For the ellipticity angle, please refer to fig. 11 and 12. Fig. 11 and fig. 12 are respectively an L-channel power line and electric wire tower polarization ellipticity angle comparison chart and an R-channel power line and electric wire tower polarization ellipticity angle comparison chart in measured data in a power line and electric wire tower identification method based on a polarization radar according to an embodiment of the present invention; likewise, it can be seen from the figure that the power line and the tower also have a certain degree of differentiation.
In summary, according to the actual measurement data, the power line and the electric wire tower have polarization differences on 10 features selected in the embodiment of the invention, the 10 features selected in the embodiment of the invention have high spatial separability to the power line and the electric wire tower, and the ten-dimensional feature vector is used for classifying and identifying the power line and the electric wire tower effectively.
And S3, inputting the feature vector of the target to be tested into a pre-trained target classification network to obtain the identification result that the target to be tested belongs to the power line or the electric wire tower.
The target classification network of the embodiment of the invention can be constructed by adopting any existing neural network for target classification.
The object of the embodiment of the invention is a power line or a power line tower, namely the known object is one of the two, but the classification problem of the unknown specific class is a classification problem, and the SVM (support vector machines, support vector machine) is a typical classification model. Therefore, in order to achieve a quick and easy classification. In an alternative embodiment, the object classification network may include: and (5) SVM.
The target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
In an alternative embodiment, referring to fig. 13, the training process of the target classification network includes:
S01, transmitting signals to an actual measurement area containing a plurality of sample targets by using a linear polarization antenna of the polarized radar, and receiving echo signals by using a circular polarization antenna to obtain echo signals of 4 polarization channels in total.
Wherein the plurality of sample targets includes power lines and power line towers. That is to say for sample targets, it is a power line or a tower of wires.
It will be appreciated by those skilled in the art that the received echo signals for the 4 polarized channels are echo signals for a plurality of sample targets.
S02, obtaining a distance unit and a Doppler channel where each sample target is located by using known parameter information of the actually measured area.
It will be appreciated by those skilled in the art that the actual location of each power line and power line tower can be calculated from known parameter information that can be obtained by measurement, such as the speed of the radar in the measured area, the distance between the power line tower and the power line relative to the radar, and the parameter information set by the radar, to obtain the distance unit and doppler channel where each power line and power line tower is located. This process is of the prior art and will not be described in detail here.
S03, marking each sample target by using a distance unit and a Doppler channel where the sample target is located in the received echo signals of the 4 polarization channels.
As will be appreciated by those skilled in the art, the received echo signals for the 4 polarized channels are a matrix of data, with the horizontal axis representing the distance elements and the vertical axis representing the doppler channels. Because the received echo signals of the 4 polarization channels not only contain echo signals of the sample targets of the power line and the power line tower, but also contain echo signals of other objects, such as surface vegetation, boulders and the like, in order to distinguish the sample targets from the other targets, a distance unit and a Doppler channel where each sample target is located can be obtained by S02 calculation, the position of the sample target is marked in matrix data corresponding to the echo signals, and the distance-Doppler unit where the sample target is located corresponds to the echo signal of the sample target in the received echo signals of the 4 polarization channels.
S04, each sample target obtains the amplitude of echo signals of each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circularly polarized antenna by using the distance units and the Doppler channels marked in the echo signals of the 4 polarization channels of the sample target, and determines a ten-dimensional vector formed by the obtained 10 data as a sample target feature vector corresponding to the sample target, wherein each sample target feature vector has a category identification of the sample target.
For the amplitude of the echo signal of the sample object in each polarization channel, the amplitude of the range-doppler cell marked in the echo signal of each polarization channel by the sample object is used to obtain.
According to the echo signal amplitude of the sample target in each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circularly polarized antenna can be calculated, and the specific calculation formula is referred to the calculation formula of the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle and is not described herein.
S05, forming a training set by sample target feature vectors corresponding to a large number of sample targets.
In addition, besides the training set, the test set may be formed by sample object feature vectors corresponding to a plurality of sample objects, so as to test classification effects after the training of the object classification network is completed. It will be appreciated that each sample target feature vector in the training set and test set has a class identification of the sample target, that is, whether the class of each sample target feature vector is power line or power line tower known.
S06, training the obtained target classification network by using the training set until the target classification network converges, and obtaining the target classification network after training.
The specific training process may include the steps of:
1) And taking the class identifier corresponding to each sample target feature vector in the training set as the true value corresponding to the sample target feature vector, training the sample target feature vector and the corresponding true value through the built target classification network, and obtaining the training result of the sample target feature vector.
2) And comparing the training result of each sample target feature vector with the true value corresponding to the sample target feature vector to obtain the output result corresponding to the sample target feature vector.
3) And calculating the loss value of the target classification network according to the output result corresponding to each sample target feature vector.
4) And (3) according to the loss value, adjusting the parameters of the target classification network, and repeating the steps 1) to 3) until the loss value of the target classification network reaches a certain convergence condition, namely the loss value reaches the minimum. At this time, it means that the training result of each sample target feature vector is consistent with the true value corresponding to the sample target feature vector, so as to complete the network training and obtain the target classification network after the training is completed.
After S06, the test set may be used to verify the target classification network, specifically, the sample target feature vector in the test set may be input into the trained target classification network to obtain an output category, and the output category may be compared with the category identifier originally corresponding to the input sample target feature vector to verify the classification effect of the target classification network.
According to the embodiment, the actual measurement data of the certain helicopter radar are used for carrying out experiments by using the provided power line and electric wire tower identification method based on the polarized radar, the training set is used for training to complete the target classification network, the testing set is used for verifying the identification accuracy, and the table 1 is the target identification result of the actual measurement data. The training set contains 90 groups of eigenvectors, the power line corresponds to 30 groups, and the power line tower corresponds to 60 groups. The test set contains 150 sets of eigenvectors, 57 sets for power lines and 93 sets for wire towers.
Table 1 recognition results of measured data
In the experimental results of table 1, out of 57 sample targets classified as power lines in the test set, 55 were identified as power lines and 2 were identified as power line towers, and thus, the identification accuracy of the power lines was 96.49%. The test set class was 93 sample targets of the wire tower, all of which were correctly identified, so the identification accuracy of the wire tower was 100%.
In the scheme provided by the embodiment of the invention, a linear polarization antenna of a polarization radar is utilized to transmit signals to a target to be detected, and a circular polarization antenna is utilized to receive echo signals, so that echo signals of 4 polarization channels are obtained in total; according to the echo signals of the 4 polarization channels, obtaining the echo signal amplitude of each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circular polarization antenna, and determining a ten-dimensional vector formed by the obtained 10 data as a target feature vector to be detected; inputting the feature vector of the target to be tested into a target classification network which is trained in advance, and obtaining the identification result of the target to be tested belonging to the power line or the power line tower. The embodiment of the invention integrates the polarization difference of the power line and the electric wire tower, selects more characteristics with distinction in space, constructs a 10-dimensional characteristic vector by utilizing polarization multichannel information, and identifies the power line and the electric wire tower by utilizing a machine learning method. Compared with the prior art, the method effectively solves the problems of too few characteristics and unreasonable characteristic selection, and improves the recognition accuracy of the power line and the wire tower.
In a second aspect, corresponding to the above method embodiment, the embodiment of the present invention further provides a polarized radar-based power line and power line tower identification device, as shown in fig. 14, including:
An echo signal obtaining module 1401, configured to utilize a linear polarized antenna of a polarized radar to emit a signal to be measured, and utilize a circular polarized antenna to receive the echo signal, so as to obtain echo signals of 4 polarized channels in total; wherein the 4 polarization channels include an HL channel, a VL channel, an HR channel, and a VR channel;
The target feature vector to be measured generating module 1402 is configured to obtain, according to echo signals of the 4 polarization channels, an echo signal amplitude of each polarization channel, a polarization amplitude angle, a polarization inclination angle, and a polarization ellipticity angle of the left and right channels of the circularly polarized antenna, and determine a ten-dimensional vector formed by the obtained 10 data as a target feature vector to be measured;
The target classification module 1403 is configured to input a feature vector of a target to be tested into a target classification network that is trained in advance, so as to obtain a recognition result that the target to be tested belongs to a power line or a power line tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
Further, the process for obtaining the echo signal amplitude of each polarization channel includes:
for the echo signal of each polarization channel, the amplitude of the echo signal of the polarization channel is obtained through peak detection.
Further, the process for obtaining the polarization amplitude angles of the left and right channels of the circularly polarized antenna comprises the following steps:
Calculating to obtain the polarization amplitude angle of the left-hand circularly polarized channel by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization amplitude angle calculation formula;
Calculating to obtain the polarization amplitude angles of the right-hand circularly polarized channels by using the echo signal amplitudes of the VR channels and the HR channels and a polarization amplitude angle calculation formula of the right-hand circularly polarized channels;
The calculation formulas of the polarization amplitude angles of the left-hand circular polarization channel and the right-hand circular polarization channel are respectively as follows:
The polarization amplitude angles of the left and right channels of the circular polarized antenna comprise a left-hand circular polarized channel polarization amplitude angle and a right-hand circular polarized channel polarization amplitude angle; gamma L represents the polarization amplitude angle of the left-hand circularly polarized channel; gamma R represents the polarization amplitude angle of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; arctan (·) represents the arctangent function.
Further, the process for obtaining the polarization inclination angles of the left and right channels of the circularly polarized antenna comprises the following steps:
Calculating to obtain the polarization inclination angle of the left-hand circular polarization channel by using the echo signal amplitudes of the VL channel and the HL channel and a polarization inclination angle calculation formula of the left-hand circular polarization channel;
Calculating to obtain the right-hand circularly polarized channel polarization inclination angle by utilizing echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization inclination angle calculation formula;
The calculation formulas of the polarization dip angles of the left-hand circular polarization channel and the right-hand circular polarization channel are respectively as follows:
Wherein:
The polarization dip angles of the left and right channels of the circular polarized antenna comprise a left-hand circular polarized channel polarization dip angle and a right-hand circular polarized channel polarization dip angle; τ L represents the polarization tilt of the left-hand circularly polarized channel; τ R represents the polarization tilt of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; tan (-) represents the tangent function; cos (·) represents a cosine function; arctan (·) represents the arctangent function.
Further, the process for obtaining the polarization ellipticity angle of the left and right channels of the circularly polarized antenna comprises the following steps:
calculating to obtain the left-hand circularly polarized channel polarization ellipticity angle by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization ellipticity angle calculation formula;
calculating to obtain the right-hand circularly polarized channel polarization ellipticity angle by using echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization ellipticity angle calculation formula;
The left-hand circular polarization channel polarization ellipticity angle calculation formula and the right-hand circular polarization channel polarization ellipticity angle calculation formula are respectively as follows:
Wherein:
The circular polarized antenna comprises a left circular polarized antenna, a right circular polarized antenna and a left circular polarized antenna, wherein the polarized ellipticity angles of the left and right channels of the circular polarized antenna comprise a left circular polarized channel polarized ellipticity angle and a right circular polarized channel polarized ellipticity angle; epsilon L represents the left-hand circularly polarized channel polarization ellipticity angle; epsilon R represents the right-hand circularly polarized channel polarization ellipticity angle; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; sin (·) represents a sine function; arctan (·) represents the arctangent function.
Further, the object classification network includes: and (5) SVM.
Further, the training process of the target classification network includes:
transmitting signals to an actual measurement area containing a plurality of sample targets by using a linear polarization antenna of the polarized radar, and receiving echo signals by using a circular polarization antenna to obtain echo signals of 4 polarization channels in total; wherein the plurality of sample targets includes a power line and a power line tower;
Obtaining a distance unit and a Doppler channel where each sample target is located by utilizing known parameter information of an actual measurement area;
marking each sample target by using a distance unit and a Doppler channel where the sample target is located in the received echo signals of the 4 polarization channels;
Each sample target utilizes a distance unit and Doppler channels marked in echo signals of 4 polarization channels of the sample target to obtain echo signal amplitude of each polarization channel, polarization amplitude angles, polarization inclination angles and polarization ellipticity angles of left and right channels of a circular polarization antenna, and a ten-dimensional vector formed by the obtained 10 data is determined as a sample target feature vector corresponding to the sample target, and each sample target feature vector has a category identification of the sample target;
forming a training set by sample target feature vectors corresponding to a large number of sample targets;
And training the obtained target classification network by using the training set until the target classification network reaches convergence, so as to obtain the target classification network after training.
For details, please refer to the method section of the first aspect, and details are not described herein.
In the scheme provided by the embodiment of the invention, a linear polarization antenna of a polarization radar is utilized to transmit signals to a target to be detected, and a circular polarization antenna is utilized to receive echo signals, so that echo signals of 4 polarization channels are obtained in total; according to the echo signals of the 4 polarization channels, obtaining the echo signal amplitude of each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circular polarization antenna, and determining a ten-dimensional vector formed by the obtained 10 data as a target feature vector to be detected; inputting the feature vector of the target to be tested into a target classification network which is trained in advance, and obtaining the identification result of the target to be tested belonging to the power line or the power line tower. The embodiment of the invention integrates the polarization difference of the power line and the electric wire tower, selects more characteristics with distinction in space, constructs a 10-dimensional characteristic vector by utilizing polarization multichannel information, and identifies the power line and the electric wire tower by utilizing a machine learning method. Compared with the prior art, the method effectively solves the problems of too few characteristics and unreasonable characteristic selection, and improves the recognition accuracy of the power line and the wire tower.
In a third aspect, an embodiment of the present invention further provides an electronic device, as shown in fig. 15, including a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504, where the processor 1501, the communication interface 1502, and the memory 1503 complete communication between each other through the communication bus 1504,
A memory 1503 for storing a computer program;
a processor 1501 for implementing the steps of the polarized radar-based power line and tower identification method as described in the first aspect, when executing the program stored on the memory 1503.
The electronic device may be: desktop computers, portable computers, intelligent mobile terminals, servers, etc. Any electronic device capable of implementing the present invention is not limited herein, and falls within the scope of the present invention.
The communication bus mentioned above for the electronic device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
Through the electronic equipment, the following steps can be realized: the problems of too few characteristics and unreasonable characteristic selection are effectively solved, and the recognition accuracy of the power line and the electric wire tower is improved.
In a fourth aspect, corresponding to the method for identifying a power line and a power line tower based on a polarized radar provided in the first aspect, an embodiment of the present invention further provides a computer readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying a power line and a power line tower based on a polarized radar provided in the embodiment of the present invention are implemented.
For the apparatus/electronic device/storage medium embodiments, the description is relatively simple as it is substantially similar to the method embodiments, as relevant see the section description of the method embodiments.
The foregoing is merely illustrative of the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims (10)

1. A polarized radar-based power line and tower identification method, comprising:
transmitting signals to be detected by utilizing a linear polarization antenna of a polarization radar, and receiving echo signals by utilizing a circular polarization antenna to obtain echo signals of 4 polarization channels in total; wherein the 4 polarization channels include an HL channel, a VL channel, an HR channel, and a VR channel;
According to the echo signals of the 4 polarization channels, obtaining the amplitude of the echo signals of each polarization channel, the polarization amplitude angles, the polarization inclination angles and the polarization ellipticity angles of the left and right channels of the circular polarization antenna, and determining ten-dimensional vectors formed by the obtained 10 data as target feature vectors to be detected;
inputting the feature vector of the target to be tested into a target classification network which is trained in advance to obtain a recognition result that the target to be tested belongs to a power line or a power line tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
2. The polarized radar-based power line and power line tower identification method according to claim 1, wherein the obtaining process of the echo signal amplitude of each polarized channel comprises:
for the echo signal of each polarization channel, the amplitude of the echo signal of the polarization channel is obtained through peak detection.
3. The polarized radar-based power line and power line tower identification method according to claim 2, wherein the obtaining process of the polarization argument of the right and left channels of the circularly polarized antenna comprises:
Calculating to obtain the polarization amplitude angle of the left-hand circularly polarized channel by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization amplitude angle calculation formula;
Calculating to obtain the polarization amplitude angles of the right-hand circularly polarized channels by using the echo signal amplitudes of the VR channels and the HR channels and a polarization amplitude angle calculation formula of the right-hand circularly polarized channels;
the left-hand circular polarization channel polarization amplitude angle calculation formula and the right-hand circular polarization channel polarization amplitude angle calculation formula are respectively as follows:
The polarization amplitude angles of the left and right channels of the circularly polarized antenna comprise a left-hand circularly polarized channel polarization amplitude angle and a right-hand circularly polarized channel polarization amplitude angle; gamma L represents the polarization amplitude angle of the left-hand circularly polarized channel; gamma R represents the polarization amplitude angle of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; arctan (·) represents the arctangent function.
4. The polarized radar-based power line and power line tower identification method according to claim 2, wherein the process of obtaining the polarization tilt angles of the right and left channels of the circularly polarized antenna comprises:
Calculating to obtain the polarization inclination angle of the left-hand circular polarization channel by using the echo signal amplitudes of the VL channel and the HL channel and a polarization inclination angle calculation formula of the left-hand circular polarization channel;
Calculating to obtain the right-hand circularly polarized channel polarization inclination angle by utilizing echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization inclination angle calculation formula;
The left-hand circular polarization channel polarization dip angle calculation formula and the right-hand circular polarization channel polarization dip angle calculation formula are respectively as follows:
Wherein:
The polarization dip angles of the left and right channels of the circularly polarized antenna comprise a left-hand circularly polarized channel polarization dip angle and a right-hand circularly polarized channel polarization dip angle; τ L represents the polarization tilt of the left-hand circularly polarized channel; τ R represents the polarization tilt of the right-hand circularly polarized channel; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; tan (-) represents the tangent function; cos (·) represents a cosine function; arctan (·) represents the arctangent function.
5. The polarized radar-based power line and power line tower identification method according to claim 2, wherein the process of obtaining the ellipticity angle of the right and left channels of the circularly polarized antenna comprises:
calculating to obtain the left-hand circularly polarized channel polarization ellipticity angle by using the echo signal amplitudes of the VL channel and the HL channel and a left-hand circularly polarized channel polarization ellipticity angle calculation formula;
calculating to obtain the right-hand circularly polarized channel polarization ellipticity angle by using echo signal amplitudes of the VR channel and the HR channel and a right-hand circularly polarized channel polarization ellipticity angle calculation formula;
the left-hand circular polarization channel polarization ellipticity angle calculation formula and the right-hand circular polarization channel polarization ellipticity angle calculation formula are respectively as follows:
Wherein:
The circular polarized antenna comprises a left circular polarized antenna, a right circular polarized antenna and a left circular polarized antenna, wherein the polarized ellipticity angles of the left and right channels of the circular polarized antenna comprise a left circular polarized channel polarized ellipticity angle and a right circular polarized channel polarized ellipticity angle; epsilon L represents the left-hand circularly polarized channel polarization ellipticity angle; epsilon R represents the right-hand circularly polarized channel polarization ellipticity angle; e VL represents the echo signal amplitude of the VL channel; e HL represents the echo signal amplitude of the HL channel; e VR represents the echo signal amplitude of the VR channel; e HR represents the echo signal amplitude of the HR channel; sin (·) represents a sine function; arctan (·) represents the arctangent function.
6. The polarized radar-based power line and power tower identification method according to claim 1, wherein the target classification network comprises:
SVM。
7. the polarized radar-based power line and power tower identification method according to claim 1 or 6, wherein the training process of the target classification network comprises:
Transmitting signals to an actual measurement area containing a plurality of sample targets by using a linear polarization antenna of the polarized radar, and receiving echo signals by using a circular polarization antenna to obtain echo signals of 4 polarization channels in total; wherein the plurality of sample targets includes a power line and a power line tower;
obtaining a distance unit and a Doppler channel where each sample target is located by utilizing the known parameter information of the actually measured area;
marking each sample target by using a distance unit and a Doppler channel where the sample target is located in the received echo signals of the 4 polarization channels;
Each sample target utilizes a distance unit and Doppler channels marked in echo signals of 4 polarization channels of the sample target to obtain echo signal amplitude of each polarization channel, polarization amplitude angles, polarization inclination angles and polarization ellipticity angles of left and right channels of a circular polarization antenna, and a ten-dimensional vector formed by the obtained 10 data is determined as a sample target feature vector corresponding to the sample target, and each sample target feature vector has a category identification of the sample target;
forming a training set by sample target feature vectors corresponding to a large number of sample targets;
And training the obtained target classification network by using the training set until the target classification network converges, so as to obtain the target classification network after training.
8. A polarized radar-based power line and power line tower identification device, comprising:
The echo signal acquisition module is used for transmitting signals to be detected by utilizing a linear polarization antenna of the polarization radar, receiving echo signals by utilizing a circular polarization antenna, and obtaining echo signals of 4 polarization channels in total; wherein the 4 polarization channels include an HL channel, a VL channel, an HR channel, and a VR channel;
The target feature vector generation module to be tested is used for obtaining the echo signal amplitude of each polarization channel, the polarization amplitude angle, the polarization inclination angle and the polarization ellipticity angle of the left and right channels of the circular polarization antenna according to the echo signals of the 4 polarization channels, and determining a ten-dimensional vector formed by the obtained 10 data as the target feature vector to be tested;
The target classification module is used for inputting the feature vector of the target to be detected into a target classification network which is trained in advance to obtain the identification result of the target to be detected belonging to the power line or the power line tower; the target classification network is trained by using a plurality of sample target feature vectors of power lines and wire towers with category identifications in a training set.
9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
The memory is used for storing a computer program;
The processor is configured to implement the method steps of any of claims 1-7 when executing a program stored on the memory.
10. A computer-readable storage medium comprising,
The computer readable storage medium has stored therein a computer program which, when executed by a processor, carries out the method steps of any of claims 1-7.
CN202110977269.5A 2021-08-24 2021-08-24 Power line and electric wire tower identification method based on polarized radar Active CN113900091B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110977269.5A CN113900091B (en) 2021-08-24 2021-08-24 Power line and electric wire tower identification method based on polarized radar

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110977269.5A CN113900091B (en) 2021-08-24 2021-08-24 Power line and electric wire tower identification method based on polarized radar

Publications (2)

Publication Number Publication Date
CN113900091A CN113900091A (en) 2022-01-07
CN113900091B true CN113900091B (en) 2024-06-14

Family

ID=79187936

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110977269.5A Active CN113900091B (en) 2021-08-24 2021-08-24 Power line and electric wire tower identification method based on polarized radar

Country Status (1)

Country Link
CN (1) CN113900091B (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IL123626A0 (en) * 1998-03-11 1998-12-06 Marc Zuta Wire detection system and method
US10054667B2 (en) * 2015-07-22 2018-08-21 Rodradar Ltd. Obstacle detection radar using a polarization test
CN107561509B (en) * 2017-08-28 2021-04-30 电子科技大学 Airborne millimeter wave radar power line detection method
CN111045009B (en) * 2019-08-21 2022-02-22 国网浙江省电力有限公司 Power line detection and identification method based on L-band dual-polarization radar

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于雷达回波极化特征的电力线识别方法;伍政华等;《雷达科学与技术》;20200229;第63-68页 *
毫米波雷达高压线检测技术的研究进展;罗旌胜等;《电讯技术》;20161031;第1174-1182页 *

Also Published As

Publication number Publication date
CN113900091A (en) 2022-01-07

Similar Documents

Publication Publication Date Title
CN107076832A (en) For decoupling determine the angle of pitch and azimuthal MIMO radar equipment of object and the method for running MIMO radar equipment
Ezuma et al. Radar cross section based statistical recognition of UAVs at microwave frequencies
CN108761419A (en) Low level wind shear velocity estimation method based on combination main channel self-adaptive processing when empty
WO2022116008A1 (en) Method for estimating number of sources, apparatus, and storage medium
CN106959437B (en) A kind of external illuminators-based radar object localization method and device based on multiple-input multiple-output
CN115061113B (en) Target detection model training method and device for radar and storage medium
CN102998660A (en) Robustness multi-beam forming method in near field scope
CN113900091B (en) Power line and electric wire tower identification method based on polarized radar
Mathews et al. Learning multi-static contextual target signatures
Oispuu et al. Multiple emitter localization using a realistic airborne array sensor
Wang et al. A practical calibration method of linear UHF Yagi arrays for ship target detection application
Wang et al. Accurate Direction Finding for Shipborne HFSWR Through Platform Motion Compensation
Pang et al. Polarization Monopulse Forward-Looking Imaging Algorithm Based on BADS Optimization
CN114355280B (en) Multi-sensor composite array antenna arraying and multi-information fusion sorting angle measuring method
CN113759325B (en) Sea surface corner reflector interference identification method based on polarization invariant and polarization decomposition
Guay The dynamic measurement of unmanned aerial vehicle radar cross section
CN114791588B (en) Underwater acoustic pulse positioning method and system
CN116008944B (en) Method and device for judging space dimension information source number of millimeter wave FMCW radar
CN116383717B (en) Intelligent comprehensive unmanned aerial vehicle recognition system and method
CN116539643B (en) Method and system for identifying coal rock data by using radar
US12028150B2 (en) Communication control apparatus and method of artificial satellite
Bialer et al. A Multi-radar Joint Beamforming Method
Nel et al. Detecting 3-D rotational motion and extracting target information from the principal component analysis of scatterer range histories
CN109342995B (en) Acoustic vector sensor direction finding method
Jiang et al. DOA estimation performance simulations and analysis with velocity errors for a passive synthetic array using single moving sensor

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant