CN115047419A - Constant false alarm rate detection method and device for millimeter wave radar - Google Patents
Constant false alarm rate detection method and device for millimeter wave radar Download PDFInfo
- Publication number
- CN115047419A CN115047419A CN202110250191.7A CN202110250191A CN115047419A CN 115047419 A CN115047419 A CN 115047419A CN 202110250191 A CN202110250191 A CN 202110250191A CN 115047419 A CN115047419 A CN 115047419A
- Authority
- CN
- China
- Prior art keywords
- detection
- point
- dimension
- distance
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/418—Theoretical aspects
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The embodiment of the invention provides a method and a device for detecting constant false alarm rate of a millimeter wave radar, which are used for receiving a signal of a frequency modulation continuous wave FMCW signal transmitted by the millimeter wave radar after the signal is reflected by a detection target, performing preset signal processing on the received signal to obtain a range-Doppler matrix, and calculating the average noise power of a two-dimensional plane of a detection point according to the range-Doppler matrix; calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution; according to a noise screening threshold, carrying out noise point screening on the distance-Doppler matrix to obtain a candidate target point set; and determining a target point by adopting two-dimensional windowed constant false alarm detection, and determining a detection result aiming at the detection target based on the target point. The complexity of target detection is reduced, and the target detection accuracy is improved.
Description
Technical Field
The invention relates to the technical field of radar detection, in particular to a constant false alarm rate detection method and device for a millimeter wave radar.
Background
Frequency Modulated Continuous Wave (FMCW) is widely used in various short-range radars, anti-collision radars, and the like. Constant False Alarm Rate (CFAR) algorithm is a common technique for detecting whether target signals exist in a radar system, and is always the focus of research in the field of radar. At present, in the field of FMCW millimeter wave radar measurement, a one-dimensional CFAR detection algorithm is mainly adopted for target detection on an obtained echo signal containing a target and interference. Specifically, a Range Doppler Map (RDM) containing target information is first traversed and searched in a Range dimension to obtain a preliminary detection result, and then, based on the result obtained in the previous step, a velocity dimension is traversed to finally obtain the Range and velocity information of the detected target. However, the target detection algorithm needs to perform a one-dimensional CFAR detection algorithm on RDM with different dimensions for multiple traversal searches to determine the distance and speed information of the target, and when the method is applied to an actual scene, the complexity of the algorithm is high, and the real-time requirement of radar detection cannot be met. And, as the number of sampling points for the transmitted signal increases, the dimension of the obtained RDM is continuously increasing, which results in the detection complexity increasing by multiple times.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for detecting constant false alarm rate of a millimeter wave radar, so as to reduce the complexity of target detection and improve the accuracy of target detection.
In order to achieve the above object, an embodiment of the present invention provides a method for detecting a constant false alarm rate of a millimeter wave radar, where the method includes:
receiving a signal of a frequency modulation continuous wave FMCW signal transmitted by a millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a range-Doppler matrix, wherein the range-Doppler matrix represents the signal intensity at detection points with different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
calculating the average noise power of a two-dimensional plane of the detection points according to the distance-Doppler matrix;
calculating a noise screening threshold under the average noise power of the two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution;
according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set;
and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
Optionally, the step of calculating the two-dimensional plane average noise power of the detection points according to the range-doppler matrix includes:
calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension;
determining the minimum value of the average value of the signal intensity of the distance dimension in each window as the average noise power of the distance dimension;
calculating the average value of the distance-Doppler matrix in the velocity dimension, and calculating the signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of the preset velocity dimension;
determining the minimum value of the signal intensity average value of the speed dimension in each window as the average noise power of the speed dimension;
and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
Optionally, the step of screening noise points of the range-doppler matrix according to the noise screening threshold to obtain a candidate target point set includes:
and screening out detection points with the signal intensity smaller than the noise screening threshold in the distance-Doppler matrix, and determining the remaining detection points as candidate target points.
Optionally, the step of determining a target point by using two-dimensional windowed constant false alarm detection for the candidate target point set includes:
determining a detection area taking the detection point as a center according to a preset two-dimensional detection window aiming at each detection point in the candidate target point set;
determining clutter average power of a distance dimension and a speed dimension of a detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value of the distance dimension and a detection threshold value of the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient;
averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point;
determining whether the detection point is a target point according to the magnitude relation between the signal strength of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
In order to achieve the above object, an embodiment of the present invention further provides a millimeter wave radar constant false alarm rate detection apparatus, where the apparatus includes:
the processing module is used for receiving a signal of a frequency modulated continuous wave FMCW signal transmitted by the millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a distance-Doppler matrix, wherein the distance-Doppler matrix represents the signal intensity at detection points with different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
the first calculation module is used for calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix;
the second calculation module is used for calculating a noise screening threshold under the average noise power of the two-dimensional plane by adopting an N-P (N-P) criterion based on preset false alarm probability, noise probability distribution, clutter interference probability distribution and detection target probability distribution;
the screening module is used for screening noise points of the distance-Doppler matrix according to the noise screening threshold to obtain a candidate target point set;
and the detection module is used for determining a target point by adopting two-dimensional windowing constant false alarm detection aiming at the candidate target point set and determining a detection result aiming at the detection target based on the target point.
Optionally, the first calculating module is specifically configured to:
calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension;
determining the minimum value of the average value of the signal intensity of the distance dimension in each window as the average noise power of the distance dimension;
calculating the average value of the distance-Doppler matrix in the velocity dimension, and calculating the signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of the preset velocity dimension;
determining the minimum value of the signal strength average value of the speed dimension in each window as the average noise power of the speed dimension;
and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
Optionally, the screening module is specifically configured to:
and screening out detection points with the signal intensity smaller than the noise screening threshold in the distance-Doppler matrix, and determining the remaining detection points as candidate target points.
Optionally, the detection module is specifically configured to:
determining a detection area taking the detection point as a center according to a preset two-dimensional detection window aiming at each detection point in the candidate target point set;
determining clutter average power of a distance dimension and a speed dimension of a detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value of the distance dimension and a detection threshold value of the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient;
averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point;
determining whether the detection point is a target point according to the magnitude relation between the signal strength of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
In order to achieve the above object, an embodiment of the present application further provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing any method step when executing the program stored in the memory.
To achieve the above object, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements any of the above method steps.
The embodiment of the invention has the following beneficial effects:
the method and the device for detecting the constant false alarm rate of the millimeter wave radar receive the signal of the frequency modulation continuous wave FMCW signal transmitted by the millimeter wave radar after the signal is reflected by a detection target and carry out the detection on the received signalProcessing the preset signal to obtain a distance-Doppler matrix X MN distance-Doppler matrix X MN Representing signal strength at detection points of different distances and different velocities; the detection points comprise noise points, target points and clutter interference points; calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix; calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution; according to a noise screening threshold, carrying out noise point screening on the distance-Doppler matrix to obtain a candidate target point set; and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
It can be seen that, in the embodiment of the present invention, the following characteristics in the millimeter wave radar target detection field are considered: firstly, the interval between frames of an FMCW millimeter wave detection radar receiver is extremely short, and the noise power in a range-Doppler matrix obtained by processing each frame of received signals is almost unchanged; second, the high resolution characteristics of millimeter wave radars in the range and velocity dimensions result in a vast majority of noise points in the resulting range-doppler matrix. Therefore, a noise point screening plane is constructed, unnecessary noise points detected in the range-Doppler matrix are removed, and compared with a mode that the existing algorithm detects useless noise points in the range and speed dimensions, the complexity of target detection is greatly reduced. In addition, the embodiment of the invention adopts two-dimensional windowed constant false alarm detection, simultaneously analyzes clutter interference conditions in the detection areas of the distance dimension and the speed dimension of the detection points and comprehensively determines a final judgment threshold, and compared with one-dimensional constant false alarm rate detection, the target detection accuracy is effectively improved.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting a constant false alarm rate of a millimeter wave radar according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of calculating the average noise power of a two-dimensional plane of a detection point according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of two-dimensional windowed constant false alarm detection according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a millimeter wave radar constant false alarm rate detection apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the technical problem of high computational complexity of existing radar detection, the embodiment of the invention provides a method and a device for detecting a constant false alarm rate of a millimeter wave radar, an electronic device and a computer readable storage medium.
Referring to fig. 1, fig. 1 is a schematic flow chart of a millimeter wave radar constant false alarm rate detection method provided in an embodiment of the present invention, where the method includes:
s101: receiving a signal of a frequency modulation continuous wave FMCW signal transmitted by a millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a range-Doppler matrix, wherein the range-Doppler matrix represents the signal intensity of detection points at different distances and different speeds; the detection points include noise points, target points and clutter interference points.
In the embodiment of the invention, in order to detect a target, namely to acquire the distance between the target and the millimeter wave radar and the speed information of the target, the millimeter wave radar can send a frequency modulation continuous wave FMCW signal to the detected target, then receive a signal of the FMCW signal reflected by the detected target, and perform preset signal processing on the received signal to obtain a distance-Doppler matrix X MN distance-Doppler matrix X MN Indicating the signal strength at detection points of different distances and different velocities, including noise points, target points, and interference points.
In the embodiment of the present invention, the preset signal processing performed by the millimeter wave radar on the received reflected signal may include frequency mixing filtering, sampling discrete processing, and two-dimensional fourier transform processing.
The method specifically comprises the following steps: the method comprises the steps of firstly carrying out frequency mixing filtering processing on a received signal to obtain an intermediate frequency signal containing distance and speed information of a detection target, carrying out sampling dispersion on the intermediate frequency signal to obtain a discrete signal, carrying out two-dimensional Fourier transform on the sampled intermediate frequency discrete signal in a distance dimension and a speed dimension to convert time domain information into a frequency domain, and further obtaining a distance Doppler spectrogram containing the distance information and the speed information of the detection target, wherein the distance Doppler spectrogram is in a two-dimensional matrix form and contains signal intensities of detection points at different distances and different speeds, and the detection points comprise noise points, target points and clutter interference points. For convenience of description, in the embodiment of the present invention, the range-doppler spectrogram is recorded as a range-doppler matrix, and the symbol X is used MN And (4) showing. distance-Doppler matrix X MN Element x in (1) ij The signal intensity of a detected point corresponding to the ith distance and the jth speed is shown.
S102: and calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix.
In the embodiment of the invention, in order to reduce the complexity of target detection, a noise screening plane can be constructed to screen the detection points in the range-Doppler matrix.
Specifically, the following characteristics in the millimeter wave radar target detection field are considered: firstly, the interval between frames of an FMCW millimeter wave detection radar receiver is extremely short, and the noise power in a range-Doppler matrix obtained by processing a received signal of each frame is almost unchanged; second, the high resolution characteristics of millimeter wave radars in the range and velocity dimensions result in a vast majority of noise points in the resulting range-doppler matrix. Therefore, a noise screening plane can be constructed to screen out noise points so as to reduce the complexity of subsequent target detection.
Before constructing the noise screening plane, the average noise power of the two-dimensional plane of the detection points, that is, the average noise power of the velocity dimension and the distance dimension, needs to be calculated.
In an embodiment of the present invention, step S102 may specifically include the following refinement steps:
s201: and (3) calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension.
S202: the minimum of the average of the signal strengths of the distance dimensions within each window is determined as the average noise power of the distance dimension.
In the embodiment of the invention, the distance-Doppler matrix X MN The method is in a two-dimensional matrix form, the horizontal axis represents a distance dimension and the length is M, the vertical axis represents a speed dimension and the length is N.
In the embodiment of the invention, X can be treated MN Averaging in the distance dimension to obtain a curve relation of the average signal intensity of the detection points along with the change of the distance, windowing the curve relation to obtain the average value of the data signal intensity in the window, and taking the lowest value as the average noise power N of the distance dimension under the current measurement condition R 。
S203: calculating an average value of the distance-Doppler matrix in the velocity dimension, and calculating a signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of the preset velocity dimension;
s204: the minimum of the average of the signal strengths for the velocity dimension in each window is determined as the average noise power for the velocity dimension.
Similarly, can be to X MN Averaging in speed dimension to obtain curve relation of average signal intensity of detection points along with speed variation, windowing the curve relation to obtain average data signal intensity in window, and taking the lowest value as average noise power N in speed dimension under current measurement condition D 。
S205: and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
Average noise power N over a distance dimension R Sum velocity dimension average noise power N D Averaging to obtain the average noise power N of the two-dimensional plane O 。
S103: and calculating a noise screening threshold under the average noise power of the two-dimensional plane based on an N-P criterion based on preset false alarm probability, noise probability distribution, clutter interference probability distribution and target signal probability distribution.
In the embodiment of the invention, the false alarm probability can be set according to requirements.
Those skilled in the art will appreciate that noise and clutter interference are subject to a certain distribution, for example, noise is subject to a gaussian distribution and clutter interference is subject to a gaussian or Weibull distribution. On the basis, the average noise power N of the two-dimensional plane can be calculated by utilizing an N-P criterion when the constant false alarm probability is met O And (4) a lower noise screening threshold. Among them, the N-P criterion, the Neyman-Pearson criterion, is widely used in hypothesis testing.
Specifically, in the process of calculating the noise screening threshold, a hypothesis test model of the target noise screening may be established:
wherein H 0 Indicating that the detected value is noise only, H 1 Indicating that the current detection value contains not only noise but also a target or clutter signal.
In the case where noise, clutter and target signals are subject to deterministic distributionsUnder the condition, the optimal noise screening threshold F under the average noise power of the two-dimensional plane can be obtained according to the N-P criterion, wherein F is alpha N O And alpha is the obtained threshold coefficient.
Wherein, the false alarm probability, i.e. the probability that the current detection point is mistaken for the target point, is expressed as
Wherein f represents a probability density function, and the preset constant false alarm rate is P fa Then according to
The corresponding threshold coefficient alpha can be obtained.
As just one example, the method for calculating the threshold coefficient by using the N-P criterion based on the probability density function and the preset constant false alarm rate may also be referred to in the related art.
S104: and according to the noise screening threshold, carrying out noise point screening on the distance-Doppler matrix to obtain a candidate target point set.
In the embodiment of the invention, after the noise screening threshold is obtained, the noise point screening can be carried out on the distance-Doppler matrix.
In one embodiment of the invention, the detection points with the signal strength smaller than the noise screening threshold in the range-doppler matrix are screened out, and the remaining detection points are determined as candidate target points.
Specifically, when the signal intensity of a detection point in the range-doppler matrix is smaller than a noise screening threshold, the detection point is determined to be a noise point, and the noise point is screened out; when the signal intensity of the detection points in the range-Doppler matrix is not less than the noise screening threshold, the detection points are judged to be possible target points, the detection points are reserved, and the reserved detection points are all candidate target points to form a candidate target point set.
S105: and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
In an embodiment of the present invention, referring to fig. 3, fig. 3 is a schematic flow chart of two-dimensional windowed constant false alarm detection provided in the embodiment of the present invention, where the step S105 may specifically include the following detailed steps:
s301: and aiming at each detection point in the candidate target point set, determining a detection area taking the detection point as a center according to a preset two-dimensional detection window.
In the embodiment of the present invention, if the number of the remaining candidate target points is greatly reduced compared to the total number of the detection points before the noise point screening, the steps S301 to S304 may be performed for each candidate target point to determine whether the candidate target point is the target point or the clutter interference point.
For convenience of illustration, taking one of the candidate target points as an example, the detection area for the detection point may be determined. The two-dimensional detection window can be preset, the size of the two-dimensional detection window can be set according to requirements, and then a detection area with the detection point as the center can be determined.
S302: and determining clutter average power of a distance dimension and a speed dimension of the detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value aiming at the distance dimension and a detection threshold value aiming at the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient.
In the embodiment of the invention, the following hypothesis testing model can be established for the current detection point:
wherein H 0 Indicating the current detection point as a clutter interference point, H 1 Indicating that the current detection value is the target point. The clutter interference power is random and has large fluctuation, so that the interference power around the current detection point is obtained by adopting a two-dimensional window during detection to serve as the clutter interference power.
Under the condition that the clutter and the target signal obey the determined distribution, the current detection can be determined by adopting a constant false alarm rate detection algorithm according to the signal intensity of a detection point in a detection areaClutter average power of distance dimension of points
Clutter average power in the sum-velocity dimension
Further, a threshold coefficient alpha is obtained according to false alarm probabilities established on the distance dimension and the speed dimension 1 And alpha 2 Whereby the detection threshold values in the distance and speed dimensions of the detection unit are calculated as
And
wherein the threshold coefficient alpha 1 And alpha 2 Or the signal may be calculated by using an N-P criterion based on a probability density function and a preset constant false alarm rate, which is not described in detail.
S303: and averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point.
S304: determining whether the detection point is a target point according to the magnitude relation between the signal strength of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
In the embodiment of the invention, the average value of the detection thresholds calculated in the distance and speed dimensions can be taken as the final judgment threshold of the current detection point and judgment is carried out.
If the signal intensity of the detection point is greater than or equal to the corresponding judgment threshold value, the detection point is judged as a target point; and if the signal intensity of the detection point is smaller than the corresponding judgment threshold value, judging the detection point as a clutter interference point.
Through the above steps, a plurality of target points in the range-doppler matrix can be detected, the abscissa of the target points represents distance information, and the ordinate represents velocity information, and the distance information and the velocity information of the target points can represent the detection result for the detection target.
In the related art, a corresponding detection result diagram may be drawn based on distance information and velocity information of a plurality of target points to more intuitively represent a detection result for a target.
The constant false alarm rate detection method of the millimeter wave radar provided by the embodiment of the invention receives the signal of the frequency modulation continuous wave FMCW signal transmitted by the millimeter wave radar after the signal is reflected by a detection target, and performs preset signal processing on the received signal to obtain a distance-Doppler matrix X MN distance-Doppler matrix X MN Representing signal strength at detection points of different distances and different velocities; the detection points comprise noise points, target points and clutter interference points; calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix; calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution; according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set; and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
As can be seen, in the embodiment of the present invention, the following characteristics in the millimeter wave radar target detection field are considered: firstly, the interval between frames of an FMCW millimeter wave detection radar receiver is extremely short, and the noise power in a range-Doppler matrix obtained by processing a received signal of each frame is almost unchanged; second, the high resolution characteristics of millimeter wave radars in the range and velocity dimensions result in a vast majority of noise points in the resulting range-doppler matrix. Therefore, a noise point screening plane is constructed, unnecessary noise points detected in the range-Doppler matrix are removed, and compared with a mode that the existing algorithm detects useless noise points in the range dimension and the speed dimension, the complexity of target detection is greatly reduced. In addition, the embodiment of the invention adopts two-dimensional windowed constant false alarm detection, simultaneously analyzes clutter interference conditions in the detection areas of the distance dimension and the speed dimension of the detection points and comprehensively determines a final judgment threshold, and compared with one-dimensional constant false alarm rate detection, the detection precision is effectively improved.
Corresponding to the embodiment of the method for detecting the constant false alarm rate of the millimeter wave radar provided by the embodiment of the invention, the embodiment of the invention also provides a device for detecting the constant false alarm rate of the millimeter wave radar, and referring to fig. 4, the device can comprise the following modules:
the processing module 401 is configured to receive a signal, which is obtained by reflecting a frequency modulated continuous wave FMCW signal transmitted by a millimeter wave radar by a detection target, and perform preset signal processing on the received signal to obtain a range-doppler matrix, where the range-doppler matrix represents signal strengths at detection points at different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
a first calculating module 402, configured to calculate a two-dimensional plane average noise power of a detection point according to the range-doppler matrix;
a second calculating module 403, configured to calculate a noise screening threshold under the two-dimensional plane average noise power by using an N-P criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution, and a detection target probability distribution;
a screening module 404, configured to perform noise point screening on the range-doppler matrix according to a noise screening threshold to obtain a candidate target point set;
and a detection module 405, configured to determine a target point by using two-dimensional windowed constant false alarm detection for the candidate target point set, and determine a detection result for the detection target based on the target point.
In an embodiment of the present invention, the first calculating module 402 may specifically be configured to:
calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension;
determining the minimum value of the average value of the signal intensity of the distance dimension in each window as the average noise power of the distance dimension;
calculating an average value of the distance-Doppler matrix in a velocity dimension, and calculating a signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of a preset velocity dimension;
determining the minimum value of the signal intensity average value of the speed dimension in each window as the average noise power of the speed dimension;
and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
In an embodiment of the present invention, the screening module 404 may specifically be configured to:
and screening out detection points with the signal intensity smaller than the noise screening threshold in the distance-Doppler matrix, and determining the remaining detection points as candidate target points.
In an embodiment of the present invention, the detecting module 405 may specifically be configured to:
aiming at each detection point in the candidate target point set, determining a detection area taking the detection point as a center according to a preset two-dimensional detection window;
determining clutter average power of a distance dimension and a speed dimension of a detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value of the distance dimension and a detection threshold value of the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient;
averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point;
determining whether the detection point is a target point according to the magnitude relation between the signal intensity of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
The millimeter wave radar constant false alarm rate detection device provided by the embodiment of the invention receives the signal of the frequency modulation continuous wave FMCW signal transmitted by the millimeter wave radar after being reflected by the detection target, and performs preset signal processing on the received signal to obtain the distance-Doppler matrix X MN distance-Doppler matrix X MN Representing signal strength at detection points of different distances and different velocities; the detection points comprise noise points, target points and clutter interference points; calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix; calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution; according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set; and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
It can be seen that, in the embodiment of the present invention, the following characteristics in the millimeter wave radar target detection field are considered: firstly, the interval between frames of an FMCW millimeter wave detection radar receiver is extremely short, and the noise power in a range-Doppler matrix obtained by processing each frame of received signals is almost unchanged; second, the high resolution characteristics of millimeter wave radars in the range and velocity dimensions result in a vast majority of noise points in the resulting range-doppler matrix. Therefore, a noise point screening plane is constructed, unnecessary noise points detected in the range-Doppler matrix are removed, and compared with a mode that the existing algorithm detects useless noise points in the range dimension and the speed dimension, the complexity of target detection is greatly reduced. In addition, the embodiment of the invention adopts two-dimensional windowed constant false alarm detection, simultaneously analyzes the clutter interference situation in the detection area of the distance dimension and the speed dimension of the detection point and comprehensively determines the final judgment threshold, and compared with one-dimensional constant false alarm rate detection, the target detection accuracy is effectively improved.
The method and the device are based on the same application concept, and because the principles of solving the problems of the method and the device are similar, the implementation of the device and the method can be mutually referred, and repeated parts are not repeated.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, which includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504,
a memory 503 for storing a computer program;
the processor 501 is configured to implement the following steps when executing the program stored in the memory 503:
receiving a signal of a frequency modulation continuous wave FMCW signal transmitted by a millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a range-Doppler matrix, wherein the range-Doppler matrix represents the signal intensity of detection points at different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix;
calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution;
according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set;
and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a 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 processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The electronic equipment provided by the embodiment of the invention receives the signal of the frequency modulation continuous wave FMCW signal transmitted by the millimeter wave radar after being reflected by the detection target, and performs preset signal processing on the received signal to obtain the distance-Doppler matrix X MN distance-Doppler matrix X MN Representing signal strength at detection points of different distances and different velocities; the detection points comprise noise points, target points and clutter interference points; calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix; calculating a noise screening threshold under the average noise power of a two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution; according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set; and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
As can be seen, in the embodiment of the present invention, the following characteristics in the millimeter wave radar target detection field are considered: firstly, the interval between frames of an FMCW millimeter wave detection radar receiver is extremely short, and the noise power in a range-Doppler matrix obtained by processing a received signal of each frame is almost unchanged; second, the high resolution characteristics of millimeter wave radars in the range and velocity dimensions result in the range-doppler matrix being mostly noisy points. Therefore, a noise point screening plane is constructed, unnecessary noise points detected in the range-Doppler matrix are removed, and compared with a mode that the existing algorithm detects useless noise points in the range dimension and the speed dimension, the complexity of target detection is greatly reduced. In addition, the embodiment of the invention adopts two-dimensional windowed constant false alarm detection, simultaneously analyzes the clutter interference situation in the detection area of the distance dimension and the speed dimension of the detection point and comprehensively determines the final judgment threshold, and compared with one-dimensional constant false alarm rate detection, the target detection accuracy is effectively improved.
In another embodiment of the present invention, a computer-readable storage medium is further provided, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above methods for detecting a constant false alarm rate of a millimeter wave radar are implemented.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above described millimeter wave radar constant false alarm rate detection methods.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the millimeter wave radar constant false alarm rate detection apparatus, the electronic device, the computer readable storage medium, and the computer program product, since they are substantially similar to the embodiments of the millimeter wave radar constant false alarm rate detection method, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the embodiments of the millimeter wave radar constant false alarm rate detection method.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A constant false alarm rate detection method for a millimeter wave radar is characterized by comprising the following steps:
receiving a signal of a frequency modulation continuous wave FMCW signal transmitted by a millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a range-Doppler matrix, wherein the range-Doppler matrix represents the signal intensity at detection points with different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix;
calculating a noise screening threshold under the average noise power of the two-dimensional plane by adopting an N-P (N-P) criterion based on a preset false alarm probability, a noise probability distribution, a clutter interference probability distribution and a detection target probability distribution;
according to the noise screening threshold, performing noise point screening on the distance-Doppler matrix to obtain a candidate target point set;
and aiming at the candidate target point set, determining a target point by adopting two-dimensional windowing constant false alarm detection, and determining a detection result aiming at the detection target based on the target point.
2. The method of claim 1, wherein the step of calculating a two-dimensional plane average noise power of detection points from the range-doppler matrix comprises:
calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension;
determining the minimum value of the average value of the signal intensity of the distance dimension in each window as the average noise power of the distance dimension;
calculating the average value of the distance-Doppler matrix in the velocity dimension, and calculating the signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of the preset velocity dimension;
determining the minimum value of the signal intensity average value of the speed dimension in each window as the average noise power of the speed dimension;
and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
3. The method of claim 1, wherein the step of performing noise point screening on the range-doppler matrix according to the noise screening threshold to obtain a candidate target point set comprises:
and screening out detection points with the signal intensity smaller than the noise screening threshold in the distance-Doppler matrix, and determining the remaining detection points as candidate target points.
4. The method of claim 1, wherein the step of determining target points using two-dimensional windowed constant false alarm detection for the set of candidate target points comprises:
determining a detection area taking the detection point as a center according to a preset two-dimensional detection window aiming at each detection point in the candidate target point set;
determining clutter average power of a distance dimension and a speed dimension of a detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value aiming at the distance dimension and a detection threshold value aiming at the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient;
averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point;
determining whether the detection point is a target point according to the magnitude relation between the signal intensity of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
5. A millimeter wave radar constant false alarm rate detection device, characterized in that, the device includes:
the processing module is used for receiving a signal of a frequency modulated continuous wave FMCW signal transmitted by the millimeter wave radar after the signal is reflected by a detection target, and performing preset signal processing on the received signal to obtain a distance-Doppler matrix, wherein the distance-Doppler matrix represents the signal intensity at detection points with different distances and different speeds; the detection points comprise noise points, target points and clutter interference points;
the first calculation module is used for calculating the average noise power of the two-dimensional plane of the detection points according to the distance-Doppler matrix;
the second calculation module is used for calculating a noise screening threshold under the average noise power of the two-dimensional plane by adopting an N-P (N-P) criterion based on preset false alarm probability, noise probability distribution, clutter interference probability distribution and detection target probability distribution;
the screening module is used for screening noise points of the distance-Doppler matrix according to the noise screening threshold to obtain a candidate target point set;
and the detection module is used for determining a target point by adopting two-dimensional windowing constant false alarm detection aiming at the candidate target point set and determining a detection result aiming at the detection target based on the target point.
6. The apparatus of claim 5, wherein the first computing module is specifically configured to:
calculating the average value of the distance-Doppler matrix in the distance dimension, and calculating the signal intensity average value of the distance dimension in each window by adopting a windowing method according to the windowing length of the preset distance dimension;
determining the minimum value of the average value of the signal intensity of the distance dimension in each window as the average noise power of the distance dimension;
calculating the average value of the distance-Doppler matrix in the velocity dimension, and calculating the signal intensity average value of the velocity dimension in each window by adopting a windowing method according to the windowing length of the preset velocity dimension;
determining the minimum value of the signal intensity average value of the speed dimension in each window as the average noise power of the speed dimension;
and averaging the average noise power of the distance dimension and the average noise power of the speed dimension to obtain the average noise power of the two-dimensional plane.
7. The apparatus of claim 5, wherein the screening module is specifically configured to:
and screening out detection points with the signal intensity smaller than the noise screening threshold in the distance-Doppler matrix, and determining the remaining detection points as candidate target points.
8. The apparatus according to claim 5, wherein the detection module is specifically configured to:
determining a detection area taking the detection point as a center according to a preset two-dimensional detection window aiming at each detection point in the candidate target point set;
determining clutter average power of a distance dimension and a speed dimension of a detection point by adopting a constant false alarm rate detection algorithm according to the signal intensity of the detection point in the detection area, and respectively determining a detection threshold value of the distance dimension and a detection threshold value of the speed dimension of the detection point according to a predetermined distance dimension threshold coefficient and a predetermined speed dimension threshold coefficient;
averaging the detection threshold value of the distance dimension and the detection threshold value of the speed dimension aiming at the detection point to obtain a judgment threshold value aiming at the detection point;
determining whether the detection point is a target point according to the magnitude relation between the signal strength of the detection point and a judgment threshold value aiming at the detection point; when the signal intensity of the detection point is not less than the judgment threshold value aiming at the detection point, the detection point is a target point; and when the signal intensity of the detection point is smaller than the judgment threshold value aiming at the detection point, the detection point is a clutter interference point.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 4 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110250191.7A CN115047419A (en) | 2021-03-08 | 2021-03-08 | Constant false alarm rate detection method and device for millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110250191.7A CN115047419A (en) | 2021-03-08 | 2021-03-08 | Constant false alarm rate detection method and device for millimeter wave radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115047419A true CN115047419A (en) | 2022-09-13 |
Family
ID=83156275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110250191.7A Pending CN115047419A (en) | 2021-03-08 | 2021-03-08 | Constant false alarm rate detection method and device for millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115047419A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224280A (en) * | 2023-05-10 | 2023-06-06 | 南京隼眼电子科技有限公司 | Radar target detection method, radar target detection device, radar equipment and storage medium |
-
2021
- 2021-03-08 CN CN202110250191.7A patent/CN115047419A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224280A (en) * | 2023-05-10 | 2023-06-06 | 南京隼眼电子科技有限公司 | Radar target detection method, radar target detection device, radar equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220252712A1 (en) | Human Detection Method and Device, Electronic Apparatus and Storage Medium | |
| CN113376613B (en) | Constant false alarm detection method and device for radar detection and electronic equipment | |
| CN112731307B (en) | RATM-CFAR detector based on distance-angle joint estimation and detection method | |
| CN113009442B (en) | Method and device for identifying multipath target of radar static reflecting surface | |
| US20240134001A1 (en) | Method and apparatus for determining noise floor estimated value, target detection method and apparatus, and electronic device | |
| CN113486961A (en) | Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment | |
| Ai et al. | AIS data aided Rayleigh CFAR ship detection algorithm of multiple-target environment in SAR images | |
| CN115047419A (en) | Constant false alarm rate detection method and device for millimeter wave radar | |
| CN112327286B (en) | Method, device, equipment and storage medium for classifying daily activities under low complexity | |
| CN108399391B (en) | Unmanned aerial vehicle signal identification method and device based on signal bandwidth characteristics | |
| CN116299401B (en) | Constant false alarm method and device based on target scattering point position and storage medium thereof | |
| CN116299291A (en) | Radar target identification method, device, equipment and storage medium | |
| CN112034464A (en) | Target classification method | |
| US20200408881A1 (en) | Method and apparatus for radar signal processing using recurrent neural network | |
| CN115932773A (en) | Target angle detection method, device, equipment and medium based on spectrum shape characteristics | |
| CN116027288A (en) | Method and device for generating data, electronic equipment and storage medium | |
| CN109283507B (en) | Radar target identification method and system based on time-frequency domain characteristics | |
| US20200408880A1 (en) | Method and apparatus for radar signal processing using convolutional neural network | |
| CN116699590B (en) | FMCW multi-target ranging method and system based on 5.8G microwave radar | |
| CN113050057B (en) | Personnel detection method and device and terminal equipment | |
| CN116224280B (en) | Radar target detection method, radar target detection device, radar equipment and storage medium | |
| Quan et al. | A miss-detection probability based thresholding algorithm for an IR-UWB radar sensor | |
| CN116953655B (en) | Forward scattering radar moving target detection method and device based on Durbin test | |
| CN113189557B (en) | Sea radar target detection refinement processing method and device | |
| CN115061111A (en) | Sea surface target detection method based on combination of three characteristics and deep learning |
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 |