CN113064164B - Vehicle-mounted radar data association method and device - Google Patents
Vehicle-mounted radar data association method and device Download PDFInfo
- Publication number
- CN113064164B CN113064164B CN202110289728.0A CN202110289728A CN113064164B CN 113064164 B CN113064164 B CN 113064164B CN 202110289728 A CN202110289728 A CN 202110289728A CN 113064164 B CN113064164 B CN 113064164B
- Authority
- CN
- China
- Prior art keywords
- data
- threshold
- data association
- track prediction
- measured value
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005259 measurement Methods 0.000 claims abstract description 119
- 238000012545 processing Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 9
- 230000001629 suppression Effects 0.000 claims description 5
- 239000006185 dispersion Substances 0.000 abstract description 4
- 230000002401 inhibitory effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
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
- 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
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a vehicle-mounted radar data association method and a device, wherein the method comprises the steps of setting two sets of data association thresholds for each track prediction point, namely a first data association threshold and a second data association threshold; for each track prediction point, determining whether the measurement value is a candidate measurement value of the track prediction point through a first data association threshold and the accumulated times of the data association thresholds of the measurement values falling into other track prediction points; and weighting all the candidate measurement values of the track prediction points to be used as the final association data of the track prediction points for updating the track, thereby reducing the phenomenon of false association. And marking the measured values which fall into the second data correlation threshold and do not fall into the first data correlation threshold, so that the measured values cannot be used as a new track start, further inhibiting false alarms of the same target caused by large dispersion of the measured values, and improving the track continuity and stability.
Description
Technical Field
The invention relates to the technical field of vehicle-mounted radar data processing, in particular to a vehicle-mounted radar data association method and device.
Background
Under the single-target clutter-free environment, only one target measurement value exists in the detection range of the radar, and at the moment, data processing does not have a data association link and only relates to the tracking problem. Under the conditions of multiple targets on an actual road and complex scenes, the measured values of the targets are in the detection range of the radar, and the number of the measured values is uncertain, so that the data association problem is involved. The problem of data association is to establish a correct relation between a radar measured value and an existing tracking track at a certain moment so as to determine whether the measured values come from the same target, and finally correct pairing between the measured value and the tracking track is realized; meanwhile, the phenomenon that the same target tracks and outputs a plurality of tracks can be reduced through data association, namely false alarm suppression.
Data correlation is one of key problems in radar data processing, if the data correlation is incorrect, an incorrect measured value is correlated to a tracking track through incorrect data correlation, and for a vehicle-mounted radar, incorrect target measured value matching may cause estimation errors of a motion track or a heading of a target vehicle, so that a decision with serious deviation is made.
For example, in an intelligent driving sensor system, a millimeter wave radar has a good speed measurement capability on a target and a good penetration capability on environmental interference such as rain, fog and the like, and thus, the millimeter wave radar becomes an irreplaceable sensor choice in an intelligent driving scheme; however, considering the influence of the resolution, the angle measurement precision and the target size of the millimeter wave radar sensor, a plurality of measured values detected by the same target inevitably appear in the target detection process; in addition, the scattering of a plurality of measured values of the same target may be relatively dispersed, so in subsequent target tracking and other data processing links, if the measured values of the same target with larger scattering cannot be effectively scattered and the data association processing cannot be accurately performed to form a flight path, the same target is easily tracked to output a plurality of flight paths, and further, the increase of the radar false alarm is directly caused.
FIG. 1 is a schematic diagram of a point cloud of radar measurements, where { z } i I =1,2, \8230;, 7} is a set of radar measurements, also called point cloud measurements, the key information in the measurements being generally the spatial position of the target and the relative radar velocity, i.e. { x } zi ,y zi ,v zi I =1,2, \8230;, 7. The data association is to establish correct matching association between the flight path and the measured value in the point cloud measurement data, and correct flight path updating and correct optimization of the target state are naturally brought based on the correct data association.
Conventional Data Association algorithms include Nearest Neighbor (NN) algorithms, probabilistic Data Association (PDA) algorithms, joint Probabilistic Data Association (JPDA) algorithms, and the like. In order to express the traditional multi-target tracking data association algorithm more simply and intuitively, a common data association under a typical scene is assumed here, as shown in fig. 2; the point cloud measurement data in the graph is recorded as{z i I =1,2, \ 8230;, 7}; two track prediction points p exist in the graph i I =1,2} and a track prediction point p 1 Has a priority greater than the track prediction point p 2 I.e. track prediction points p 1 Preferentially remove point cloud measurement data { z i I =1,2, \8230;, 7} the measured values that satisfy the association policy are screened. The spatial location of the predicted point of the flight path and the velocity of the relative radar are labeled { x pi ,y pi ,v pi I =1,2. Track prediction point p 1 Has a data association threshold of S 1 Track prediction point p 2 Has a data association threshold of S 2 . Further assume that z in the measured values 2 、z 4 Is the track prediction point p 1 The correct correlation value of (a); z is a radical of 3 Is a track prediction point p 2 The correct correlation value of. Thus, the so-called data association algorithm is required to establish a correct data association pair through processing of the algorithm, i.e.
The nearest neighbor algorithm firstly sets a data association threshold, and measured values obtained by preliminary screening of the data association threshold become candidate measured values so as to limit the number of the measured values participating in data association. The data association threshold is a subspace in the tracking space, the center of the data association threshold falls into the predicted position of the tracked target, the size of the data association threshold is designed to ensure that a correct measured value is received with a certain probability, the measured value falling into the data association threshold is a potential associable measured value, and if only one measured value falls into the data association threshold, the measured value can be used as final associated data and can be directly used for track updating; however, if at least two measured values fall within the data correlation threshold of the tracked target, the measured value with the minimum statistical distance is taken as the final correlation data. Based on the basic principle of the nearest neighbor algorithm, for the assumed scene of fig. 2, the final data association result is
I.e. flight path prediction point p 1 Erroneously with the measured value z 3 Associated, and track-predicted point p 2 Due to the measured value z 3 Predicted point p of flight path 1 Preferential occupation, hence track prediction point p 2 The data association is unsuccessful. Although the nearest neighbor algorithm is simple to implement, for the condition that the measured value distribution of the same target is large, only the candidate measured value closest to the predicted position of the target is selected as final associated data, and the phenomenon that the same target outputs a plurality of tracking tracks is easily caused; and for the measured values of two targets which are close to each other, the phenomenon of false correlation is easy to occur, so the algorithm is only suitable for scenes with sparse target distribution and little measurement spread.
The probability data association algorithm considers all the measured values falling into the data association threshold, calculates the probability value of each measured value from the target according to different relevant conditions, weights different measured values in the data association threshold by using the probability values, uses the weighted sum of the measured values as an equivalent measured value, and updates the track of the target by using the equivalent measured value. The probability data association algorithm is a suboptimal data association method and is commonly used for solving the problem of single target tracking in a clutter environment. For multiple targets, especially scenes with targets close to each other, the measured values of the targets close to each other are easily taken into a data association threshold for weighting processing, so that target tracking errors are caused.
The joint probability data association algorithm is similar to the probability data association algorithm, and is also used for calculating a weighted equivalent measured value for the data association threshold based on all measured values in the data association threshold for track updating, the difference is that when the measured value falls into the overlapping area of the data association thresholds of different targets, the target source condition of each measured value is comprehensively considered, competition of a plurality of tracks on the measured value needs to be considered when the joint probability is calculated, and the competitive weighted value needs to be reduced to reflect competition of other targets on the measured value. Compared with other algorithms, the joint probability data association algorithm has stronger anti-interference capability for an environment containing a large number of clutter and is more suitable for an environment with dense target clutter, but when the target is too dense and concentrated and contains a large number of clutter, the joint probability data association algorithm often has a problem of combined explosion, namely, the calculation amount is multiplied exponentially along with the linear increase of the target, and finally the real-time performance and the stability of the tracking algorithm are greatly reduced.
Based on the basic principles of the probability data association algorithm and the joint probability data association algorithm, for the scene shown in FIG. 2, the point p is predicted according to the calculated track 1 Data association threshold S of 1 And track prediction point p 2 Data correlation threshold S of 2 Although the track prediction point p 1 And p 2 All data correlation can be achieved, but the measured value z 3 Belonging to a track prediction point p 1 And p 2 Sharing, measured value z 3 Do not belong to the track prediction point p at all 1 Finally, the threshold S is associated with the entering data 1 Measured value of (z) 3 And z 4 Weighted as a track prediction point p 1 The correlation value of (a); but obviously z 3 Will influence the track prediction point p 1 The processing accuracy of (2). And more seriously, the original point p belongs to the track prediction point 1 Measured value z of 2 No path prediction point p is entered at all 1 Data correlation threshold S of 1 Thus measuring the value z 2 Will start as an independent track and thus will result in a track prediction point p 1 A false alarm occurs nearby.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for associating vehicle radar data, which are intended to suppress false alarms caused by a large spread of measured values of the same target, and improve track continuity and stability.
In order to achieve the above object, the following solutions are proposed:
in a first aspect, a vehicle-mounted radar data association method is provided, including:
acquiring point cloud measurement data and track prediction points;
calculating to obtain a data association threshold of the jth track prediction point, wherein the data association threshold comprises a first data association threshold and a second data association threshold;
determining the measured value of the jth track prediction point as a candidate measured value of the jth track prediction point, wherein the measured value of the point cloud measured data, which falls into the first data association threshold and the accumulated times of the data association thresholds of other track prediction points are less than N times; n is more than or equal to 2;
if the jth track prediction point has the candidate measurement value, performing weighting processing on all the candidate measurement values of the jth track prediction point to obtain final associated data of the jth track prediction point;
marking the measured values which fall into the second data correlation threshold and do not fall into the first data correlation threshold in the point cloud measured data, so that the measured values cannot be used as a new track start, and j sequentially takes the value of 1,2, \ 8230;,/l; l is the total number of track prediction points.
Optionally, the transverse distance difference threshold of the second data association threshold is greater than the transverse distance difference threshold of the first data association threshold, the longitudinal distance difference threshold of the second data association threshold is smaller than the longitudinal distance difference threshold of the first data association threshold, and the relative speed difference threshold of the second data association threshold is smaller than the relative speed difference threshold of the first data association threshold.
Optionally, the weighting all the candidate measurement values of the jth track prediction point to obtain the final associated data of the jth track prediction point includes:
and taking the average value of all candidate measured values of the jth track prediction point as final associated data of the jth track prediction point.
Optionally, N =2, determining a measurement value, in the point cloud measurement data, of which the accumulated number of times of the data association thresholds falling into the first data association threshold and the data association thresholds falling into the other track prediction points is less than N times, as a candidate measurement value of the jth track prediction point, includes:
judging whether each measured value in the point cloud measured data falls into the first data association threshold or not;
for the measured value which falls into the first data association threshold and the identification position of which is the first identification, determining that the accumulated times of the data association thresholds of the measured value which falls into other track prediction points are less than two times, and updating the identification position of the measured value to be the second identification; the first identification is an initialization identification bit of each measured value in the point cloud measurement data;
for the measured value which falls into the first data association threshold and the identification position of which is the second identification, determining that the accumulated times of the measured value falling into the data association thresholds of other track prediction points is less than two times, and updating the identification position of the measured value to be the third identification;
for the measured value which falls into the first data association threshold and the identification position of which is the third identification, determining that the accumulated times of the data association thresholds of the measured value which falls into other track prediction points are not less than two times;
judging whether each measured value which does not fall into the first data association threshold in the point cloud measured data falls into the second data association threshold;
for the measured value which falls into the second data correlation threshold and the identification bit of which is the first identification, updating the identification bit of the measured value to be the second identification;
and updating the identifier bit of the measured value as a third identifier for the measured value which falls into the second data association threshold and has the identifier bit as a second identifier.
Optionally, the vehicle-mounted radar data association method further includes:
initializing the accumulated number of the candidate measurement values of each track prediction point to zero;
for each track prediction point, after determining a certain measurement value as a candidate measurement value of the track prediction point each time, the method further comprises the following steps:
and adding 1 to the accumulated number of the candidate measurement values of the track prediction point.
In a second aspect, an in-vehicle radar data correlation apparatus includes:
the data acquisition unit is used for acquiring point cloud measurement data and track prediction points;
the threshold calculation unit is used for calculating and obtaining a data association threshold of the jth track prediction point, wherein the data association threshold comprises a first data association threshold and a second data association threshold;
a candidate measurement value determining unit, configured to determine, as a candidate measurement value of the jth track prediction point, a measurement value in the point cloud measurement data that falls within the first data association threshold and falls within the data association thresholds of other track prediction points for which the cumulative number of times of the data association thresholds is less than N times; n is more than or equal to 2;
the final associated data calculation unit is used for carrying out weighting processing on all candidate measured values of the jth track prediction point if the jth track prediction point has the candidate measured values so as to obtain final associated data of the jth track prediction point;
a false alarm suppression unit, configured to label, in the point cloud measurement data, a measurement value that falls within the second data association threshold and does not fall within the first data association threshold, so that the measurement value cannot serve as a new track start, and j sequentially takes a value of 1,2, \ 8230;, l; l is the total number of track prediction points.
Optionally, the transverse distance difference threshold of the second data association threshold is greater than the transverse distance difference threshold of the first data association threshold, the longitudinal distance difference threshold of the second data association threshold is smaller than the longitudinal distance difference threshold of the first data association threshold, and the relative speed difference threshold of the second data association threshold is smaller than the relative speed difference threshold of the first data association threshold.
Optionally, the final associated data calculating unit is specifically configured to:
and taking the average value of all candidate measured values of the jth track prediction point as the final associated data of the jth track prediction point.
Optionally, N =2, the candidate measurement value determining unit includes:
the first judgment subunit is used for judging whether each measured value in the point cloud measured data falls into the first data association threshold or not;
the first updating and determining subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times for the measured value falling into the first data association threshold and the identification position of the measured value is a first identification, and updating the identification position of the measured value to be a second identification; the first identification is an initialization identification bit of each measured value in the point cloud measurement data;
the second updating determination subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times and updating the identification bit of the measured value to be a third identification for the measured value falling into the first data association threshold and the identification bit of the second identification;
the determining subunit is used for determining that the cumulative times of the data association thresholds of the measured value falling into other track prediction points are not less than two times for the measured value falling into the first data association threshold and the identification position of the measured value being the third identification;
a second judging subunit, configured to judge whether each measured value in the point cloud measurement data that does not fall within the first data association threshold falls within the second data association threshold;
a first updating subunit, configured to update, for a measurement value that falls within the second data association threshold and has an identifier bit that is a first identifier, the identifier bit of the measurement value to be a second identifier;
and the second updating subunit is used for updating the identifier bit of the measured value to be a third identifier for the measured value which falls into the second data association threshold and has the identifier bit being the second identifier.
Optionally, the candidate measured value determining unit further includes:
the initialization subunit is used for initializing the accumulated number of the candidate measurement values of each track prediction point to zero;
and the counting subunit is used for adding 1 to the accumulated number of the candidate measured values of the track prediction points after determining that a certain measured value is the candidate measured value of the track prediction point every time for each track prediction point.
Compared with the prior art, the technical scheme of the invention has the following advantages:
the technical scheme provides a vehicle-mounted radar data association method and a device, and the method comprises the steps of setting two sets of data association thresholds for each track prediction point, namely a first data association threshold and a second data association threshold; for each track prediction point, determining whether the measurement value is a candidate measurement value of the track prediction point through a first data association threshold and the accumulated times of the data association thresholds of the measurement values falling into other track prediction points; and weighting all candidate measured values of the track prediction points to be used as final associated data of the track prediction points for updating the track, so that the phenomenon of false association is reduced. And marking the measured values which fall into the second data correlation threshold and do not fall into the first data correlation threshold, so that the measured values cannot be used as a new track starting point, further inhibiting false alarms of the same target caused by large dispersion of the measured values, and improving the track continuity and stability.
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 description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of point cloud measurement data for a radar;
FIG. 2 is a diagram of a conventional data correlation algorithm;
fig. 3 is a flowchart of a data association method for a vehicle-mounted radar according to an embodiment of the present invention;
fig. 4 is an implementation schematic diagram of a vehicle-mounted radar data association method provided by an embodiment of the invention;
fig. 5 is an effect comparison diagram of the vehicle-mounted radar data association method provided by the embodiment of the invention and a conventional data association algorithm;
fig. 6 is a schematic logical structure diagram of a vehicle-mounted radar data association apparatus 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.
Referring to fig. 3, the vehicle-mounted radar data association method provided in this embodiment includes the following steps:
s31: and acquiring point cloud measurement data and track prediction points.
And the track prediction points are effective track prediction points in the current scene. The track prediction points include data such as spatial position and relative speed, and the method for acquiring the track prediction points of each track can adopt the prior art, and is not described herein again. The point cloud measurement data also includes spatial position and relative velocity data. Relative velocity refers to the velocity relative to the radar. The spatial position refers to the abscissa and ordinate in the radar coordinate system. The point cloud measurement data is obtained by measuring a target in a detection range by a radar.
S32: and calculating to obtain a data association threshold of the jth track prediction point, wherein the data association threshold comprises a first data association threshold and a second data association threshold.
In this embodiment, two sets of data association thresholds, that is, a first data association threshold and a second data association threshold, are set for each track prediction point. The first data association threshold is obtained by calculating the data association threshold based on the traditional data association algorithm such as a nearest neighbor algorithm, a probability data association algorithm or a joint probability data association algorithm. The first data correlation threshold is mainly used for searching for a measured value which ensures that the measured value is really a track prediction point. And calculating to obtain a second data association threshold based on the first data association threshold.
S33: determining a measured value, of which the accumulated times of the first data association threshold falling into the jth track prediction point and the data association thresholds falling into other track prediction points are less than N times, in the point cloud measured data as a candidate measured value of the jth track prediction point; n is more than or equal to 2.
Satisfying the ith measurement value in the point cloud measurement data shown in the following formula, namely considering that the ith measurement value falls into the first data association threshold of the jth track prediction point:
in the formula, D xj1 、D yj1 And D vj1 A transverse distance difference threshold, a longitudinal distance difference threshold and a relative speed difference threshold, x, each representing a first data-associated threshold pj 、y pj And v pj Respectively representing the abscissa, ordinate and relative speed, x, of the jth track prediction point among all the track prediction points acquired in step S31 zi 、y zi And v zi Respectively representing the abscissa, the ordinate and the relative speed of the ith measurement value in the point cloud measurement data.
Similarly, the ith measured value in the point cloud measured data which meets the following formula is considered to fall into the second data association threshold of the jth track prediction point:
in the formula D xj2 、D yj2 And D vj2 A lateral distance difference threshold, a longitudinal difference threshold, and a relative velocity difference threshold, each representing a second data association threshold.
It should be noted that other track prediction points falling in the accumulated times of the data association thresholds of other track prediction points refer to track prediction points for which candidate measurement values have been determined; that is to say, when a candidate measured value of a certain track prediction point is determined, the accumulated number of times that a certain measured value falls in the data association threshold of other track prediction points does not refer to the accumulated number of times that the measured value falls in the data association thresholds of the other l-1 track prediction points, but refers to the accumulated number of times that the measured value falls in the data association thresholds of the track prediction points for which the candidate measured value has been determined. When judging whether the measured value falls into the data association threshold of a certain track prediction point, judging whether the measured value falls into the first data association threshold of the track prediction point, if so, judging whether the measured value falls into the second data association threshold of the track prediction point, and if not, judging whether the measured value falls into the second data association threshold of the track prediction point. When the number of times of counting the number of times of the data association threshold of the measured value falling into the track prediction point is counted, whether the measured value falls into the first data association threshold of the track prediction point or the second data association threshold of the track prediction point is recorded to fall into one time.
S34: and if the jth track prediction point has the candidate measurement value, performing weighting processing on all the candidate measurement values of the jth track prediction point to obtain final associated data of the jth track prediction point.
If only one candidate measured value exists at the jth track prediction point, weighting all the candidate measured values of the jth track prediction point to obtain final associated data of the track prediction point, namely taking the candidate measured value as the final associated data of the jth track prediction point to update the track.
If there are at least two candidate measured values of the jth track prediction point, weighting processing can be performed on all candidate measured values of the jth track prediction point based on a weighting processing method in a traditional data association algorithm such as a probability data association algorithm, so as to obtain final association data of the jth track prediction point. The average value of all the candidate measured values of the jth track prediction point can be further calculated
The final associated data of the flight path prediction points are used, wherein c represents the number of candidate measured values of the jth flight path prediction point; namely, the average values of the abscissa, the ordinate and the relative speed of all the candidate measured values of the jth track prediction point are respectively calculated to be used as the final associated data of the jth track prediction point.
If the jth track prediction point does not exist in the candidate measured values, the final association data of the jth track prediction point is (0, 0), namely the association is unsuccessful.
S35: and marking the measured value of the second data association threshold which falls into the jth track prediction point and the measured value of the first data association threshold which does not fall into the jth track prediction point in the point cloud measured data, so that the measured value can not be used as the start of a new track.
j is sequentially valued at 1,2, \ 8230,. L, steps S32 to S35 are executed for each value of j; namely, the situation of each track prediction point is sequentially judged, and l is the total number of the track prediction points.
In some embodiments, the transverse distance difference threshold of the second data association threshold is greater than the transverse distance difference threshold of the first data association threshold, the longitudinal distance difference threshold of the second data association threshold is less than the longitudinal distance difference threshold of the first data association threshold, and the relative speed difference threshold of the second data association threshold is less than the relative speed difference threshold of the first data association threshold. The second data correlation threshold is relative to the first data correlation threshold, the constraint condition in the transverse space is looser, and the constraint condition in the longitudinal space and the relative speed are stricter. The difference value between the transverse distance difference threshold value, the longitudinal distance difference threshold value and the relative speed difference threshold value of the first correlation threshold and the transverse distance difference threshold value, the longitudinal distance difference threshold value and the relative speed difference threshold value of the second correlation threshold is obtained according to experience or calibration.
And the measured value of the second data association threshold falling into the jth track prediction point is not used as the candidate measured value of the jth track prediction point, namely is not used for track updating. Usually, the measured values of the second data association threshold entering the jth track prediction point are relatively dispersed in transverse position, and if the measured values falling into the first data association threshold are weighted and processed together with the measured values falling into the jth track prediction point to be used as the final association data of the jth track prediction point, the measured values entering the second data association threshold often cause unstable transverse tracking of the track, so that the measured values entering the second data association threshold are only labeled, so that a new track start is not performed, and the method is used for inhibiting false alarms caused by relatively large transverse dispersion.
As shown in FIG. 4, S 11 Representing the track prediction point p 1 Is associated with a threshold, S 21 Representing the track prediction point p 2 Is associated with a threshold, S 12 Representing the track prediction point p 1 Second data association threshold of (2)，z 2 P being actually track predicted point 1 Measuring values; using the second data association threshold S with more loose horizontal space constraint and more strict longitudinal space and speed constraint 12 Successfully measured value z 2 Processing as a track prediction point p 1 Measured value of (a) is z 2 Not as a new track start, effectively inhibits the track prediction point p 1 The false alarm of (3).
In a specific embodiment, the second data association threshold may be set to
The method is used for searching a large-scale transverse space range for measurement values which originally belong to the same target but have large dispersion due to angle measurement errors. The second data association threshold is not limited to this, and the actual values of the transverse distance difference threshold, the longitudinal distance difference threshold, and the relative speed difference threshold of the second association threshold may also be in other corresponding relationships with the transverse distance difference threshold, the longitudinal distance difference threshold, and the relative speed difference threshold of the first association threshold, and are obtained specifically according to experience or calibration.
In some embodiments, N =2, an identification Flag is added to each measured value in the point cloud measurement data to indicate the cumulative number of times that the measured value falls within the data association threshold of the track prediction point for which the candidate measured value has been determined. Flag =0 indicates that the measured value has fallen at least twice into the data association threshold of the track prediction point; flag =1 indicates that the measured value has not fallen into the data association threshold of any track prediction point; flag =2 indicates that the measurement has occurred once at a data association threshold that falls within a certain track prediction point. It should be noted that 0, 1, and 2 are exemplary illustrations of values of the flag bit, and the flag bit may also be represented by other different values for different accumulated times. It is understood that N may take other values, such as N =3, in other embodiments.
The following describes in detail a process of determining, in combination with an identification bit, a first data association threshold that falls into a jth track prediction point in point cloud measurement data, and a measurement value for which the cumulative number of times of data association thresholds that fall into other track prediction points is less than two times, as a candidate measurement value for the jth track prediction point:
(1) And judging whether each measured value in the point cloud measured data falls into a first data association threshold of the jth track prediction point. If a certain measured value falls into the first data association threshold of the jth track prediction point, whether the measured value falls into the second data association threshold of the jth track prediction point is not judged; if a certain measured value does not fall into the first data association threshold of the jth track prediction point, whether the measured value falls into the second data association threshold of the jth track prediction point or not is judged subsequently.
(2) And for the first data association threshold falling into the jth track prediction point, and the identification position is the measured value of the first identification, determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times, and updating the identification position of the measured value to be the second identification. And determining that the measured value is a candidate measured value of the jth track prediction point after the accumulated times of the data association thresholds of the measured value falling into other track prediction points are determined to be less than two times. The second signature represents a data association threshold where the measured value has occurred once and falls within a certain track prediction point. The first identifier is an initialization identifier of each measured value in the point cloud measurement data. The first indicator represents a data association threshold where the measured value has not fallen into any flight path prediction point.
(3) And for the first data association threshold falling into the jth track prediction point and the measured value of which the identification position is the second identification, determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times, and updating the identification position of the measured value to be the third identification. And determining that the measured value is a candidate measured value of the jth track prediction point after the accumulated times of the data association thresholds of the measured value falling into other track prediction points are determined to be less than two times. The third indicator represents a data correlation threshold where the measured value has fallen at least twice into the track prediction point.
(4) And determining the accumulated times of the data association thresholds of the measured value falling into other track prediction points to be not less than twice for the measured value of the first data association threshold falling into the jth track prediction point and the identification position being the third identification. Namely, for the measured value of the first data association threshold which falls into the jth track prediction point, if the identification bit is the third identification, the value of the identification bit is kept unchanged.
(5) And judging whether each measured value of the first data association threshold of the jth track prediction point in the point cloud measured data does not fall into the second data association threshold of the jth track prediction point.
(6) And for the second data which falls into the jth track prediction point, associating a threshold, wherein the identification bit is the measurement value of the first identification, and updating the identification bit of the measurement value to be the second identification. Namely, when the measured value falls into the second data association threshold of the jth track prediction point, even if the accumulated times of the data association thresholds falling into other track prediction points are less than two times, the measured value is not taken as the candidate measured value of the jth track prediction point.
(7) For the second data which falls into the jth track prediction point is associated with a threshold, and the identification position is the measured value of the second identification, and the identification position of the measured value is updated to be the third identification; and when the identification bit of the measured value is the third identification, keeping the value of the identification bit of the measured value unchanged. Namely, when the measured value falls into the second data association threshold of the jth track prediction point, even if the accumulated times of the data association thresholds falling into other track prediction points are less than two times, the measured value is not taken as the candidate measured value of the jth track prediction point.
As shown in FIG. 4, an identification bit is added to each measurement, i.e., measurement z 3 Predicted point p of the first-to-be-track 1 Use, but by setting the flag, z can be guaranteed 3 Can also be predicted by flight path point p 2 By using the method, the track prediction point p is effectively avoided 1 Priority occupancy measurement z 3 Resulting in a track prediction point p 2 The association is unsuccessful.
In some embodiments, a counter is further allocated to each track prediction point for recording the number of candidate measurement values of the track prediction point, i.e. the cumulative number of candidate measurement values. When the identification bit of each measured value in the point cloud measurement data is initialized to be a first identification, the accumulated number of the candidate measured values of each track prediction point is initialized to be zero, namely the counting result of the corresponding counter is reset to be zero; then, aiming at each track prediction point, after the measured value is determined to be the candidate measured value of the track prediction point every time, adding 1 to the accumulated number of the candidate measured values of the track prediction point, and realizing the statistics of the number of the candidate measured values.
By sets M j And storing the candidate measured value of the jth track prediction point. By using
And final associated data representing each track prediction point. When the cumulative number of candidate measurements for each track prediction point is initialized to zero, the set of stored candidate measurements for each track prediction point is also initialized to null and the final correlation data is initialized to (0, 0).
Referring to fig. 5, the effect of the vehicle-mounted radar data association method provided by the embodiment is compared with that of the conventional data association method. As shown in fig. 5, in which the black dots are the point cloud measurement data, and the triangular connecting lines (i.e., ID =14, ID =10, and ID = 31) in the graph are the results of the conventional data association algorithm processing, it can be seen that the track of ID =14 is the main track, but in the processing process, false alarms due to the relatively large lateral spread of the measurement values, i.e., the tracks of ID =10 and ID =31, occur. In the figure, a square connecting line (i.e., ID = 25) is a processing result of the vehicle-mounted radar data association method according to the present invention. By contrast, the ID =25 track is free of false alarms in the conventional data association algorithm process. Obviously, the vehicle-mounted radar data correlation method effectively inhibits false alarms of the flight path. By comparing the two main tracks with the ID =14 and the ID =25, the track processed by the vehicle-mounted radar data association method is smoother and continuous than the track processed by the traditional data association algorithm.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present invention is not limited by the illustrated ordering of acts, as some steps may occur in other orders or concurrently with other steps in accordance with the invention.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 6, the vehicle-mounted radar data association apparatus provided in this embodiment includes: a data acquisition unit 61, a threshold calculation unit 62, a candidate measurement determination unit 63, a final correlation data calculation unit 64 and a false alarm suppression unit 65.
And the data acquisition unit 61 is used for acquiring point cloud measurement data and track prediction points.
And the threshold calculation unit 62 is configured to calculate a data association threshold of the jth track prediction point, where the data association threshold includes a first data association threshold and a second data association threshold.
A candidate measurement value determining unit 63, configured to determine, as a candidate measurement value of the jth track prediction point, a measurement value in which an accumulated number of times of data association thresholds falling in the jth track prediction point in the point cloud measurement data is less than N times, and the first data association threshold falling in the jth track prediction point; n is more than or equal to 2.
And the final associated data calculating unit 64 is used for performing weighting processing on all the candidate measured values of the jth track prediction point to obtain the final associated data of the jth track prediction point if the jth track prediction point has the candidate measured values.
The false alarm suppression unit 65 is used for marking the measured values of the second data association threshold which falls into the jth track prediction point and the first data association threshold which does not fall into the jth track prediction point in the point cloud measured data, so that the measured values cannot be used as a new track start, and j sequentially takes the value of 1,2, \ 8230;, l; l is the total number of track prediction points.
In some embodiments, the lateral distance difference threshold of the second data association threshold is greater than the lateral distance difference threshold of the first data association threshold; the longitudinal distance difference threshold of the second data association threshold is smaller than the longitudinal distance difference threshold of the first data association threshold; the relative velocity difference threshold of the second data association threshold is less than the relative velocity difference threshold of the first data threshold.
In some embodiments, the final associated data calculating unit is specifically configured to use an average value of all candidate measured values of the jth track prediction point as the final associated data of the jth track prediction point.
In some embodiments, the candidate measurement value determination unit includes: the device comprises a first judgment subunit, a first update confirmation subunit, a second update confirmation subunit, a second judgment subunit, a first update subunit and a second update subunit.
And the judging subunit is used for judging whether each measured value in the point cloud measured data falls into a first data association threshold of the jth track prediction point.
The first updating and determining subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times and updating the identification position of the measured value to be a second identification for the first data association threshold falling into the jth track prediction point and the identification position of the first identification is the measured value of the first identification; the first identifier is an initialization identifier of each measured value in the point cloud measurement data.
And the second updating determining subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times and updating the identification position of the measured value to be a third identification for the first data association threshold falling into the jth track prediction point and the identification position of the second identification.
And the determining subunit is used for determining the accumulated times of the data association thresholds of the measured value falling into other track prediction points to be not less than two times for the first data association threshold falling into the jth track prediction point and the measured value of which the identification position is the third identification.
A second judging subunit, configured to judge whether each measured value of the first data association threshold, which does not fall into the jth track prediction point, in the point cloud measured data falls into a second data association threshold of the jth track prediction point
And the first updating subunit is used for associating a threshold with the second data falling into the jth track prediction point, wherein the identification bit of the second data is the measurement value of the first identification, and the identification bit of the measurement value is updated to be the second identification.
And the second updating subunit is used for associating a threshold with second data which falls into the jth track prediction point, wherein the identification bit is a measured value of the second identification, and the identification bit for updating the measured value is a third identification.
In some embodiments, the candidate measurement value determining unit further includes: an initialization subunit and a counting subunit.
And the second initialization subunit is used for initializing the accumulated number of the candidate measurement values of each track prediction point to zero.
A counting subunit, configured to, for each track prediction point, add 1 to the cumulative number of candidate measurement values of the track prediction point after determining that a certain measurement value is a candidate measurement value of the track prediction point each time
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may fall into one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
In this document, relational terms such as first and second, and the like may be 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 phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are mainly described as different from other embodiments, the same and similar parts in the embodiments may be referred to each other, and the features described in the embodiments in the present description may be replaced with each other or combined with each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A vehicle-mounted radar data association method is characterized by comprising the following steps:
acquiring point cloud measurement data and track prediction points;
calculating to obtain a data association threshold of the jth track prediction point, wherein the data association threshold comprises a first data association threshold and a second data association threshold;
determining the measured value of the jth track prediction point as a candidate measured value of the jth track prediction point, wherein the measured value of the point cloud measured data, which falls into the first data association threshold and the accumulated times of the data association thresholds of other track prediction points are less than N times; n is more than or equal to 2;
if the jth track prediction point has the candidate measurement value, performing weighting processing on all the candidate measurement values of the jth track prediction point to obtain final associated data of the jth track prediction point;
marking the measured values which fall into the second data association threshold and do not fall into the first data association threshold in the point cloud measured data, so that the measured values cannot be used as a new track start, and j sequentially takes the value of 1,2, \8230;,; l is the total number of track prediction points.
2. The vehicle radar data correlation method of claim 1, wherein a lateral distance difference threshold of the second data correlation threshold is greater than a lateral distance difference threshold of the first data correlation threshold, a longitudinal distance difference threshold of the second data correlation threshold is less than a longitudinal distance difference threshold of the first data correlation threshold, and a relative velocity difference threshold of the second data correlation threshold is less than a relative velocity difference threshold of the first data correlation threshold.
3. The vehicle-mounted radar data association method according to claim 1, wherein the step of performing weighting processing on all candidate measurement values of the jth track prediction point to obtain final association data of the jth track prediction point comprises the following steps:
and taking the average value of all candidate measured values of the jth track prediction point as the final associated data of the jth track prediction point.
4. The vehicle-mounted radar data association method according to claim 1, wherein N =2, and the step of determining the measurement value, which falls in the first data association threshold and falls in the data association thresholds of the other track prediction points for which the accumulated number of times of the data association thresholds is less than N, of the point cloud measurement data as the candidate measurement value of the jth track prediction point comprises the steps of:
judging whether each measured value in the point cloud measured data falls into the first data association threshold or not;
for the measured value which falls into the first data association threshold and the identification position of which is the first identification, determining that the accumulated times of the data association thresholds of the measured value which falls into other track prediction points are less than two times, and updating the identification position of the measured value to be the second identification; the first identification is an initialization identification bit of each measured value in the point cloud measurement data;
for the measured value which falls into the first data association threshold and the identification position of which is the second identification, determining that the accumulated times of the measured value falling into the data association thresholds of other track prediction points is less than two times, and updating the identification position of the measured value to be the third identification;
for the measured value which falls into the first data association threshold and the identification position of which is the third identification, determining that the accumulated times of the data association threshold of the measured value falling into other track prediction points is not less than twice;
judging whether each measured value which does not fall into the first data association threshold in the point cloud measured data falls into the second data association threshold;
for the measured value which falls into the second data association threshold and the identification bit of which is the first identification, updating the identification bit of the measured value to be the second identification;
and updating the identifier bit of the measured value to be a third identifier for the measured value which falls into the second data association threshold and has the identifier bit of the second identifier.
5. The vehicle radar data correlation method of claim 4, further comprising:
initializing the accumulated number of the candidate measurement values of each track prediction point to zero;
for each track prediction point, after determining a certain measurement value as a candidate measurement value of the track prediction point each time, the method further comprises the following steps:
and adding 1 to the accumulated number of the candidate measured values of the track prediction points.
6. An in-vehicle radar data correlation apparatus, characterized by comprising:
the data acquisition unit is used for acquiring point cloud measurement data and track prediction points;
the threshold calculation unit is used for calculating and obtaining a data association threshold of the jth track prediction point, wherein the data association threshold comprises a first data association threshold and a second data association threshold;
a candidate measurement value determining unit, configured to determine, as a candidate measurement value of the jth track prediction point, a measurement value in the point cloud measurement data that falls within the first data association threshold and falls within the data association thresholds of other track prediction points for which the cumulative number of times of the data association thresholds is less than N times; n is more than or equal to 2;
the final association data calculation unit is used for weighting all the candidate measurement values of the jth track prediction point if the jth track prediction point has the candidate measurement values so as to obtain final association data of the jth track prediction point;
a false alarm suppression unit, configured to label, in the point cloud measurement data, a measurement value that falls within the second data association threshold and does not fall within the first data association threshold, so that the measurement value cannot serve as a new track start, and j sequentially takes a value of 1,2, \ 8230;, l; l is the total number of track prediction points.
7. The vehicle-mounted radar data correlation apparatus of claim 6, wherein a lateral distance difference threshold of the second data correlation threshold is greater than a lateral distance difference threshold of the first data correlation threshold, a longitudinal distance difference threshold of the second data correlation threshold is less than a longitudinal distance difference threshold of the first data correlation threshold, and a relative velocity difference threshold of the second data correlation threshold is less than a relative velocity difference threshold of the first data correlation threshold.
8. The vehicle-mounted radar data correlation apparatus according to claim 6, wherein the final correlation data calculation unit is specifically configured to:
and taking the average value of all candidate measured values of the jth track prediction point as final associated data of the jth track prediction point.
9. The on-vehicle radar data correlation device according to claim 6, wherein N =2, the candidate measurement value determination unit includes:
the first judgment subunit is used for judging whether each measured value in the point cloud measured data falls into the first data association threshold or not;
the first updating and determining subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times for the measured value falling into the first data association threshold and the identification position of the measured value is a first identification, and updating the identification position of the measured value to be a second identification; the first identification is an initialization identification bit of each measured value in the point cloud measurement data;
the second updating determination subunit is used for determining that the accumulated times of the data association thresholds of the measured value falling into other track prediction points are less than two times and updating the identification bit of the measured value to be a third identification for the measured value falling into the first data association threshold and the identification bit of the second identification;
the determining subunit is configured to determine, for the measured value that falls into the first data association threshold and the identification position of which is the third identification, that the cumulative number of times that the measured value falls into the data association thresholds of the other track prediction points is not less than two times;
a second judging subunit, configured to judge whether each measured value in the point cloud measurement data that does not fall within the first data association threshold falls within the second data association threshold;
the first updating subunit is used for updating the identifier bit of the measurement value to be a second identifier for the measurement value which falls into the second data association threshold and has the identifier bit to be the first identifier;
and the second updating subunit is used for updating the identifier bit of the measured value to be a third identifier for the measured value which falls into the second data association threshold and has the identifier bit being the second identifier.
10. The vehicle-mounted radar data correlation apparatus according to claim 9, wherein the candidate measurement value determination unit further includes:
the initialization subunit is used for initializing the accumulated number of the candidate measurement values of each track prediction point to zero;
and the counting subunit is used for adding 1 to the accumulated number of the candidate measured values of the track prediction points after determining that a certain measured value is the candidate measured value of the track prediction point every time for each track prediction point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110289728.0A CN113064164B (en) | 2021-03-16 | 2021-03-16 | Vehicle-mounted radar data association method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110289728.0A CN113064164B (en) | 2021-03-16 | 2021-03-16 | Vehicle-mounted radar data association method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113064164A CN113064164A (en) | 2021-07-02 |
| CN113064164B true CN113064164B (en) | 2022-11-22 |
Family
ID=76561532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110289728.0A Active CN113064164B (en) | 2021-03-16 | 2021-03-16 | Vehicle-mounted radar data association method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113064164B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852756A (en) * | 2012-11-30 | 2014-06-11 | 中国科学院沈阳自动化研究所 | Target detecting and tracking method by utilization of continuous wave radar |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN106226751A (en) * | 2016-07-08 | 2016-12-14 | 西安电子科技大学 | Maneu-vering target detection based on DP TBD and tracking |
| CN108535713A (en) * | 2018-05-09 | 2018-09-14 | 深圳市华讯方舟雷达技术装备有限公司 | A kind of radar and the tracking of AIS joints and information fusion method |
| CN109655822A (en) * | 2018-11-09 | 2019-04-19 | 上海无线电设备研究所 | A kind of improved track initiation method |
| CN109782267A (en) * | 2019-01-25 | 2019-05-21 | 北京润科通用技术有限公司 | Data Association and trailer-mounted radar |
| CN109946671A (en) * | 2019-04-12 | 2019-06-28 | 哈尔滨工程大学 | A kind of underwater manoeuvre Faint target detection tracking based on dual-threshold judgement |
| CN111458702A (en) * | 2020-03-13 | 2020-07-28 | 四川九洲防控科技有限责任公司 | Maneuvering target tracking method, system, electronic equipment and storage medium |
| CN111751816A (en) * | 2020-07-07 | 2020-10-09 | 北京无线电测量研究所 | Radar track starting method based on trace point characteristic information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9613537B2 (en) * | 2015-07-29 | 2017-04-04 | The Boeing Company | Multiple landing threshold aircraft arrival system |
-
2021
- 2021-03-16 CN CN202110289728.0A patent/CN113064164B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852756A (en) * | 2012-11-30 | 2014-06-11 | 中国科学院沈阳自动化研究所 | Target detecting and tracking method by utilization of continuous wave radar |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN106226751A (en) * | 2016-07-08 | 2016-12-14 | 西安电子科技大学 | Maneu-vering target detection based on DP TBD and tracking |
| CN108535713A (en) * | 2018-05-09 | 2018-09-14 | 深圳市华讯方舟雷达技术装备有限公司 | A kind of radar and the tracking of AIS joints and information fusion method |
| CN109655822A (en) * | 2018-11-09 | 2019-04-19 | 上海无线电设备研究所 | A kind of improved track initiation method |
| CN109782267A (en) * | 2019-01-25 | 2019-05-21 | 北京润科通用技术有限公司 | Data Association and trailer-mounted radar |
| CN109946671A (en) * | 2019-04-12 | 2019-06-28 | 哈尔滨工程大学 | A kind of underwater manoeuvre Faint target detection tracking based on dual-threshold judgement |
| CN111458702A (en) * | 2020-03-13 | 2020-07-28 | 四川九洲防控科技有限责任公司 | Maneuvering target tracking method, system, electronic equipment and storage medium |
| CN111751816A (en) * | 2020-07-07 | 2020-10-09 | 北京无线电测量研究所 | Radar track starting method based on trace point characteristic information |
Non-Patent Citations (2)
| Title |
|---|
| 几种典型情况下的航迹关联研究;黄晓冬等;《***仿真学报》;20050920(第09期);正文第2085-2088页 * |
| 基于AIS的对海雷达多目标融合跟踪方法;贺丰收等;《雷达科学与技术》;20170415(第02期);正文第153-158页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113064164A (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597061B (en) | Method and system for judging motion state of target | |
| CN110596694B (en) | Complex environment radar multi-target tracking and road driving environment prediction method | |
| CN109087510B (en) | Traffic monitoring method and device | |
| Roecker et al. | Suboptimal joint probabilistic data association | |
| CN110542885B (en) | Millimeter wave radar target tracking method in complex traffic environment | |
| CN109581353B (en) | Multi-target tracking method and system based on automobile radar | |
| CN112526521B (en) | Multi-target tracking method for automobile millimeter wave anti-collision radar | |
| CN110040134B (en) | Vehicle collision time calculation method considering environmental factors | |
| CN110673130B (en) | Moving target track tracking method based on track association | |
| EP3671272A1 (en) | Vehicle sensor fusion based on fuzzy sets | |
| CN107464256A (en) | A kind of target detection differentiates the correlating method of amendment with possibility | |
| CN104237890B (en) | The heavy rain identification that one is caused by " train effect " and forecasting procedure | |
| CN110889862B (en) | Combined measurement method for multi-target tracking in network transmission attack environment | |
| CN108859952A (en) | Vehicle lane change method for early warning, device and radar | |
| CN102253375A (en) | Radar multi-target data interconnection method | |
| CN112233416A (en) | Traffic flow detection method and device | |
| CN114966591A (en) | Large target detection method, large target detection device and electronic equipment | |
| CN113064164B (en) | Vehicle-mounted radar data association method and device | |
| CN112748735B (en) | Extended target tracking method introducing color features | |
| CN114114242A (en) | Radar target tracking method based on point-selected flight path and flight path extrapolation | |
| CN117805805A (en) | Millimeter wave radar multi-vehicle tracking method based on traffic scene | |
| CN115220002B (en) | Multi-target data association tracking method and related device for fixed single station | |
| CN116184386A (en) | Target tracking method, device and storage medium | |
| CN113219425B (en) | Test method and system for radar target detection performance | |
| CN115327525A (en) | Method and device for evaluating track confidence and electronic equipment |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230608 Address after: 4 / F, building 1, No.14 Jiuxianqiao Road, Chaoyang District, Beijing 100020 Patentee after: Beijing Jingwei Hirain Technologies Co.,Inc. Address before: 100192 5th floor, Zhizhen building, 7 Zhichun Road, Haidian District, Beijing Patentee before: BEIJING RUNKE GENERAL TECHNOLOGY Co.,Ltd. |