CN117647806B - Point trace condensation and target tracking method based on millimeter wave radar - Google Patents
Point trace condensation and target tracking method based on millimeter wave radar Download PDFInfo
- Publication number
- CN117647806B CN117647806B CN202410123760.5A CN202410123760A CN117647806B CN 117647806 B CN117647806 B CN 117647806B CN 202410123760 A CN202410123760 A CN 202410123760A CN 117647806 B CN117647806 B CN 117647806B
- Authority
- CN
- China
- Prior art keywords
- condensation
- track
- radar
- point
- trace
- 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
- 238000009833 condensation Methods 0.000 title claims abstract description 139
- 230000005494 condensation Effects 0.000 title claims abstract description 139
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000013256 coordination polymer Substances 0.000 claims description 63
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 102220103881 rs201490575 Human genes 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000002131 composite material Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to target tracking, in particular to a method for condensing and tracking points based on millimeter wave radar, which collects radar point data of a ship and corrects the position of the radar point; performing trace condensation on the corrected radar trace data; calculating condensation point parameters based on the condensation result of the point trace; performing track-track association according to track states and condensation point parameters, and performing track management and track updating; the technical scheme provided by the invention is beneficial to improving the accuracy of the track associated condensation point and the stability of target tracking, and improving the accuracy of outputting the ship data.
Description
Technical Field
The invention relates to target tracking, in particular to a method for condensation of points and target tracking based on millimeter wave radar.
Background
In recent years, along with rapid development of millimeter wave radar technology, millimeter wave radar is gradually introduced into bridge collision-prevention early warning systems. In the bridge anti-collision early warning system, the millimeter wave radar can detect the information such as the position, the speed, the heading and the like of the ship in real time, and has the advantages of long detection distance and no influence of weather factors such as rain, snow, fog and the like.
However, the conventional data processing method of millimeter wave radar is mostly applied to the fields of security and traffic, but the motion characteristics of ships have great differences from targets such as people, vehicles and the like. Compared with people or vehicles, the ship has the characteristics of large volume and slow speed, if the traditional data processing method is adopted, the situation that a single ship corresponds to a plurality of condensation points often occurs due to poor condensation effect, and even the problem that the track cannot start up due to slow speed can be caused. In addition, even after forming the track, problems such as track object splitting and track association errors often occur.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a point trace condensation and target tracking method based on a millimeter wave radar, which can effectively overcome the defects existing in the prior art that the detection of a ship by the millimeter wave radar has poor point trace condensation and target tracking effect.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
a method for trace condensation and target tracking based on millimeter wave radar comprises the following steps:
s1, collecting radar trace data of a ship, and correcting the position of the radar trace;
s2, performing trace point condensation on the corrected radar trace point data;
s3, calculating condensation point parameters based on a point trace condensation result;
s4, performing track-track association according to the track state and the condensation point parameters, and performing track management and track updating.
Preferably, the collecting radar trace data of the ship in S1 includes:
s11, continuously storing N frames of radar trace data P= { P based on the receiving time of the radar trace data 1 ,P 2 ,P 3 ,…,P N N is a fixed value set in advance;
wherein, the nth frame radar trace data P n Comprises a plurality of points, namely P n ={,/>,/>,…,/>}，/>The number of radar points contained in the nth frame of radar point data is the number of radar points contained in the nth frame of radar point data;
nth frame radar trace data P n The mth trace of (a) contains the relevant trace information, namely={}，/>Representing the target distance->Indicating the target angle +.>Representing the target signal intensity, +.>Indicating the target speed.
Preferably, the performing position correction on the radar trace in S1 includes:
S12. will trace out the spots={/>Conversion of the polar coordinate system into a point trace in the Cartesian coordinate system>={/>}；
Wherein,point marks +.>The abscissa and ordinate values in the cartesian coordinate system,，/>；
s13, using the latest frame radar trace data P N As a time reference, based on stipplingSpeed of->And frame number n, trace points in Cartesian coordinate System +.>Corrected to；
Wherein,、/>the corrected marks +.>Abscissa and ordinate in Cartesian coordinate system, < >>，delT is the time difference between frames, which is a fixed value.
Preferably, the stitching will be performed in S12={/>Conversion of the polar coordinate system into a point trace in the Cartesian coordinate system>={/>-comprising:
for radar trace->The included angle between the radar normal, the radar normal is the positive direction of the Y axis, and the radar normal is taken as the point trace +.>Will +.>Marking as positive value, otherwise marking as negative value;
when the target is far from the radar,positive value, when the target is close to the radar, < > is>Is negative.
Preferably, the performing the trace condensation on the corrected radar trace data in S2 includes:
corrected N frames of radar trace dataP={/>P 1 ,/>P 2 ,/>P 3 ,…,/>P N Using the data as a frame of radar trace data, and jointly adopting a DBSCAN clustering algorithm to perform trace condensation;
wherein, the modified nth frame radar trace data AP n Comprises a plurality of points, namely AP n ={,/>,/>,…,/>Modified nth frame radar trace data AP n The mth trace of (a) contains the relevant trace information, namely}。
Preferably, the calculating the condensation point parameter based on the condensation result of the trace point in S3 includes:
based on the trace condensation result, respectively calculating the weighted average value, the maximum value, the minimum value and the weighted speed value of each condensation point in the X, Y direction, and marking the weighted average value, the maximum value, the minimum value and the weighted speed value as CP= { CP 1 ,P 2 ,CP 3 ,…,CP W }；
Wherein W is the number of condensation points, and the W th condensation point CP w Contains relevant condensation point parameters, CP w ={,,/>,/>,/>,/>,/>,/>}，/>、Respectively the condensation points CP w Weighted mean in direction X, Y, +.>、/>Respectively the condensation points CP w Maximum in direction X, Y, < >>,/>Respectively the condensation points CP w Minimum in X, Y direction, +.>、Respectively the condensation points CP w Weighted velocity values in direction X, Y.
Preferably, the calculating the weighted average, the maximum, the minimum and the weighted speed of each condensation point in the X, Y direction based on the condensation result of the point trace includes:
due to the condensation point CP w To obtain the K corrected radar points by weighted condensation, the condensation points CP are calculated by the following methods w Weighted mean, maximum, minimum and weighted velocity values in direction X, Y:
=/>//>；
=/>//>；
=MAX(/>,/>,/>,…/>)；
=MAX(/>,/>,/>,…/>)；
=MIN(/>,/>,/>,…A/>)；
=MIN(/>,/>,/>,…/>)；
=/>//>；
=/>//>。
preferably, in S4, the associating of the track and the track according to the track state and the condensation point parameter, and the track management and the track update include:
s41, considering track state and condensation point CP w ={,/>,/>,/>,,/>,/>,/>The relation between the tracks is carried out by adopting a weighted nearest neighbor association algorithm on the basis of the nearest neighbor association algorithm, the comprehensive score of the track state and the condensation point is calculated, and the target condensation point which is used as the next frame association of the track is determined based on the comprehensive score;
s42, track management and track updating are carried out based on the associated target condensation point.
Preferably, calculating a composite score of the track state and the condensation point in S41, determining a target condensation point as a correlation point of a next frame of the track based on the composite score includes:
s411, track state is T= {,/>,/>,/>,/>,/>,/>}，/>、/>Respectively are provided withFor the predicted position of the track in direction X, Y after Kalman filtering, +.>、/>Track prediction speed in X, Y direction after Jing Kaer Manfiltered, respectively, +.>、/>Respectively, ship width, ship length, +.>Is a heading;
s412, based on track and condensation point CP w Position difference in X, Y direction, track and condensation point CP are calculated w Weighted score for ship position、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction positions respectively;
s413, based on track and condensation point CP w Calculating the speed difference in X, Y direction and the track and condensation point CP w Weighted score for watercraft speed、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction speeds respectively;
s414, based on track and condensation point CP w Difference in ship width, ship length, meterCalculating track and condensation point CP w Weighted score for ship specification、/>：
=/>*fabs[/>]；
=/>*fabs[/>]；
Wherein,、/>the weight coefficient values are respectively the ship width and the ship length;
s415, calculating a comprehensive score S of the track state and the condensation point:
S=；
s416, taking the condensation point with the lowest comprehensive score S as a target condensation point CP of the next frame association point of the track g 。
Preferably, track management and track update based on the associated target condensation point in S42 includes:
based on the objectCondensation point CP g Calculation of track predicted position in X, Y direction using Kalman filtering、/>And track prediction speed in X, Y direction +.>、/>Calculating the ship width +.>And ship length->And update heading；
Wherein, the Kalman filtering adopts a classical Kalman filtering uniform-speed linear model, and the width of the shipLength of ship->The following formula is adopted for calculation:
=/>；
=/>；
、/>respectively the target condensation points CP g Maximum in direction X, Y, < >>、/>Respectively the target condensation points CP g Minimum in direction X, Y;
updating heading by adopting the following method：
。
Compared with the prior art, the method for condensing the trace points and tracking the target based on the millimeter wave radar has the following beneficial effects:
1) In view of the characteristics of large volume and slow speed of a ship, the technical scheme of the method adopts a multi-frame accumulation method of the point track, and the corrected multi-frame radar point track data are fused into one frame, so that the fused inter-frame radar point track position generates an obvious movement trend, and the problems that the ship target is split and the track cannot be batched are effectively solved;
2) In order to eliminate the difference of the movement of the ship caused by the inter-frame radar trace data, the technical scheme of the method and the device corrects the positions of radar traces based on the speed and the frame number of the traces, and carries out trace condensation on the corrected radar trace data by adopting a DBSCAN clustering algorithm, so that the condensed traces are more concentrated and can describe the outline of the ship, and the detection precision of the width and the length of the ship is improved;
3) According to the technical scheme, the correlation between the track and the point is carried out by adopting a weighted nearest neighbor correlation algorithm according to the track state and the condensation point parameters, so that the characteristics involved in the correlation are richer, and the accuracy of the correlation between the track and the condensation point and the stability of target tracking are improved.
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 evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic diagram of a radar trace in a radar coordinate system according to the present invention;
FIG. 3 is a schematic diagram of the present invention for performing trace condensation on corrected radar trace data;
FIG. 4 is a schematic diagram of correlating radar points with tracks in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A method for condensing and tracking the trace of the trace based on millimeter wave radar is shown in figure 1, S1, collecting the radar trace data of the ship and correcting the position of the radar trace.
1) Collecting radar trace data of a ship, comprising:
s11, continuously storing N frames of radar trace data P= { P based on the receiving time of the radar trace data 1 ,P 2 ,P 3 ,…,P N N is a fixed value set in advance (here N is set to 10）；
Wherein, the nth frame radar trace data P n Comprises a plurality of marks, namely，/>The number of radar points contained in the nth frame of radar point data is the number of radar points contained in the nth frame of radar point data;
nth frame radar trace data P n The mth trace (shown in figure 2) contains the relevant trace information, namely，/>Representing the target distance->Indicating the target angle +.>Representing the target signal intensity, +.>Indicating the target speed.
2) Performing position correction on the radar trace, including:
s12, trace-pointingConversion from polar coordinate system to point trace in Cartesian coordinate system>；
Wherein,point marks +.>The abscissa and ordinate values in the cartesian coordinate system,，/>；
s13, using the latest frame radar trace data P N As a time reference, based on stipplingSpeed of->And frame number n, trace points in Cartesian coordinate System +.>Corrected to}；
Wherein,、/>the corrected marks +.>Abscissa and ordinate in Cartesian coordinate system, < >>，delT is the time difference between frames, which is a fixed value.
Specifically, the spot is traced={/>Conversion of the polar coordinate system into a point trace in the Cartesian coordinate system>={/>-comprising:
for radar trace->The included angle between the radar normal, the radar normal is the positive direction of the Y axis, and the radar normal is taken as the point trace +.>Will +.>Marking as positive value, otherwise marking as negative value;
when the target is far from the radar,positive value, when the target is close to the radar, < > is>Is negative.
S2, performing trace condensation on the corrected radar trace data, as shown in FIG. 3, specifically including:
corrected N frames of radar trace dataAs a frame of radar trace data, a DBSCAN clustering algorithm is adopted together to perform trace condensation;
wherein, the modified nth frame radar trace data AP n Comprises a plurality of marks, namelyCorrected nth frame radar trace data AP n The mth trace of (a) contains the relevant trace information, i.e. +.>}。
S3, calculating condensation point parameters based on a point trace condensation result, wherein the method specifically comprises the following steps:
based on the condensation result of the point trace, respectively calculating the weighted average value, the maximum value, the minimum value and the weighted speed value of each condensation point in the X, Y direction, and marking as；
Wherein W is the number of condensation points, and the W th condensation point CP w Contains relevant condensation point parameters, CP w ={,,/>,/>,/>,/>,/>,/>}，/>、Respectively the condensation points CP w Weighted mean in direction X, Y, +.>、/>Respectively the condensation points CP w Maximum in direction X, Y, < >>,/>Respectively the condensation points CP w Minimum in X, Y direction, +.>、Respectively the condensation points CP w Weighted velocity values in direction X, Y.
Specifically, based on the trace condensation result, a weighted average value, a maximum value, a minimum value and a weighted speed value of each condensation point in the X, Y direction are calculated respectively, including:
due to the condensation point CP w To obtain the K corrected radar points by weighted condensation, the condensation points CP are calculated by the following methods w Weighted mean, maximum, minimum and weighted velocity values in direction X, Y:
=/>//>；
=/>//>；
=MAX(/>,/>,/>,…/>)；
=MAX(/>,/>,/>,…/>)；
=MIN(/>,/>,/>,…/>)；
=MIN(/>,/>,/>,…/>)；
=/>//>；
=/>//>。
s4, performing track-track association (shown in fig. 4) according to track states and condensation point parameters, and performing track management and track updating, wherein the method specifically comprises the following steps:
s41, considering track state and condensation point CP w ={,/>,/>,/>,,/>,/>,/>The relation between the tracks is carried out by adopting a weighted nearest neighbor association algorithm on the basis of the nearest neighbor association algorithm, the comprehensive score of the track state and the condensation point is calculated, and the target condensation point which is used as the next frame association of the track is determined based on the comprehensive score;
s42, track management and track updating are carried out based on the associated target condensation point.
1) Calculating a composite score of the track state and the condensation point, and determining a target condensation point serving as a next frame association point of the track based on the composite score, wherein the method comprises the following steps of:
s411, track state is T= {,/>,/>,/>,/>,/>,/>}，/>、/>Track prediction position in X, Y direction after Jing Kaer Manfiltered, respectively, +.>、/>Track prediction speed in X, Y direction after Jing Kaer Manfiltered, respectively, +.>、/>Respectively, ship width, ship length, +.>Is a heading;
s412, based on track and condensation point CP w Position difference in X, Y direction, track and condensation point CP are calculated w Weighted score for ship position、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction positions respectively;
s413, based on track and condensation point CP w Calculating the speed difference in X, Y direction and the track and condensation point CP w Weighted score for watercraft speed、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction speeds respectively;
s414, based on track and condensation point CP w Calculating the difference between the track and the condensation point CP in the aspects of the width and the length of the ship w Weighted score for ship specification、/>：
=/>*fabs[/>]；
=/>*fabs[/>]；
Wherein,、/>the weight coefficient values are respectively the ship width and the ship length;
s415, calculating a comprehensive score S of the track state and the condensation point:
S=；
s416, taking the condensation point with the lowest comprehensive score S as the next frame of the trackTarget condensation point CP of joint point g 。
2) Track management and track update based on the associated target condensation point, including:
CP based on target condensation point g Calculation of track predicted position in X, Y direction using Kalman filtering、/>And track prediction speed in X, Y direction +.>、/>Calculating the ship width +.>And ship length->And update heading；
Wherein, the Kalman filtering adopts a classical Kalman filtering uniform-speed linear model, and the width of the shipLength of ship->The following formula is adopted for calculation:
；
；
、/>respectively the target condensation points CP g Maximum in direction X, Y, < >>、/>Respectively the target condensation points CP g Minimum in direction X, Y;
updating heading by adopting the following method：
。
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A point trace condensation and target tracking method based on millimeter wave radar is characterized in that: the method comprises the following steps:
s1, collecting radar trace data of a ship, and correcting the position of the radar trace;
s2, performing trace point condensation on the corrected radar trace point data;
s3, calculating condensation point parameters based on a point trace condensation result;
s4, performing track-track association according to track states and condensation point parameters, and performing track management and track updating;
collecting radar trace data of a ship in S1, including:
s11, continuously storing N frames of radar trace data P= { P based on the receiving time of the radar trace data 1 ,P 2 ,P 3 ,…,P N N is a fixed value set in advance;
wherein, the nth frame radar trace data P n Comprises a plurality of points, namely P n ={,/>,/>,…,/>}，/>The number of radar points contained in the nth frame of radar point data is the number of radar points contained in the nth frame of radar point data;
nth frame radar trace data P n The mth trace of (a) contains the relevant trace information, namely={/>}，Representing the target distance->Indicating the target angle +.>Representing the target signal intensity, +.>Representing a target speed;
in S1, carrying out position correction on radar trace points, including:
s12, trace-pointing={/>Conversion of polar coordinate system into point trace in Cartesian coordinate system={/>}；
Wherein,point marks +.>The abscissa and ordinate values in the cartesian coordinate system,，/>；
s13, using the latest frame radar trace data P N As a time reference, based on stipplingSpeed of->And frame number n, trace points in Cartesian coordinate System +.>Corrected to}；
Wherein,、/>the corrected marks +.>The abscissa and ordinate values in the cartesian coordinate system,，delT is the time difference between frames, which is a fixed value.
2. The millimeter wave radar-based spot condensing and target tracking method according to claim 1, wherein: the spot is traced in S12={/>Conversion of the polar coordinate system into a point trace in the Cartesian coordinate system>={-comprising:
for radar trace->The included angle between the radar normal, the radar normal is the positive direction of the Y axis, and the radar normal is taken as the point trace +.>Will +.>Marking as positive value, otherwise marking as negative value;
when the target is far from the radar,positive value, when the target is close to the radar, < > is>Is negative.
3. The millimeter wave radar-based spot condensing and target tracking method according to claim 1, wherein: and S2, performing trace condensation on the corrected radar trace data, wherein the method comprises the following steps of:
corrected N frames of radar trace dataP={/>P 1 ,/>P 2 ,/>P 3 ,…,/>P N Using the data as a frame of radar trace data, and jointly adopting a DBSCAN clustering algorithm to perform trace condensation;
wherein, the modified nth frame radar trace data AP n Comprises a plurality of points, namely AP n ={,/>,/>,…,Modified nth frame radar trace data AP n The mth trace of (a) contains the relevant trace information, namely}。
4. The millimeter wave radar-based spot condensing and target tracking method according to claim 3, wherein: s3, calculating condensation point parameters based on the condensation result of the point trace, wherein the method comprises the following steps:
based on the trace condensation result, respectively calculating the weighted average value, the maximum value, the minimum value and the weighted speed value of each condensation point in the X, Y direction, and marking the weighted average value, the maximum value, the minimum value and the weighted speed value as CP= { CP 1 ,P 2 ,CP 3 ,…,CP W }；
Wherein W is the number of condensation points, and the W th condensation point CP w Contains relevant condensation point parameters, CP w ={,,/>,/>,/>,/>,/>,/>}，/>、Respectively the condensation points CP w Weighted mean in direction X, Y, +.>、/>Respectively the condensation points CP w Maximum in direction X, Y, < >>,/>Respectively the condensation points CP w Minimum in X, Y direction, +.>、Respectively the condensation points CP w Weighted velocity values in direction X, Y.
5. The millimeter wave radar-based spot condensing and target tracking method according to claim 4, wherein: based on the trace condensation result, respectively calculating a weighted average value, a maximum value, a minimum value and a weighted speed value of each condensation point in the X, Y direction, including:
due to the condensation point CP w To obtain the K corrected radar points by weighted condensation, the condensation points CP are calculated by the following methods w Weighted mean, maximum, minimum and weighted velocity values in direction X, Y:
=/>//>；
=/>//>；
=MAX(/>,/>,/>,…/>)；
=MAX(/>,/>,/>,…/>)；
=MIN(/>,/>,/>,…A/>)；
=MIN(/>,/>,/>,…/>)；
=/>//>；
=/>//>。
6. the millimeter wave radar-based spot condensing and target tracking method according to claim 5, wherein: s4, performing track-track association according to track states and condensation point parameters, performing track management and track updating, and comprising the following steps:
s41, considering track state and condensation point CP w ={,/>,/>,/>,/>,,/>,/>The relation between the tracks is carried out by adopting a weighted nearest neighbor association algorithm on the basis of the nearest neighbor association algorithm, the comprehensive score of the track state and the condensation point is calculated, and the target condensation point which is used as the next frame association of the track is determined based on the comprehensive score;
s42, track management and track updating are carried out based on the associated target condensation point.
7. The millimeter wave radar-based spot condensing and target tracking method according to claim 6, wherein: s41, calculating a comprehensive score of the track state and the condensation point, and determining a target condensation point serving as a next frame association point of the track based on the comprehensive score, wherein the method comprises the following steps of:
s411, track state is T= {,/>,/>,/>,/>,/>,/>}，/>、/>Track prediction position in X, Y direction after Jing Kaer Manfiltered, respectively, +.>、/>The predicted speeds of the tracks in the X, Y direction after Jing Kaer Manfiltered,、/>respectively, ship width, ship length, +.>Is a heading;
s412, based on track and condensation point CP w Position difference in X, Y direction, track and condensation point CP are calculated w Weighted score for ship position、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction positions respectively;
s413, based on track and condensation point CP w Calculating the speed difference in X, Y direction and the track and condensation point CP w Weighted score for watercraft speed、/>：
=/>*fabs(/>)；
=/>*fabs(/>)；
Wherein,、/>weighting coefficient values of X, Y direction speeds respectively;
s414, based on track and condensation point CP w Calculating the difference between the track and the condensation point CP in the aspects of the width and the length of the ship w Weighted score for ship specification、/>：
=/>*fabs[/>]；
=/>*fabs[/>]；
Wherein,、/>the weight coefficient values are respectively the ship width and the ship length;
s415, calculating a comprehensive score S of the track state and the condensation point:
S=；
s416, taking the condensation point with the lowest comprehensive score S as a target condensation point CP of the next frame association point of the track g 。
8. The millimeter wave radar-based spot condensing and target tracking method according to claim 7, wherein: track management and track update based on the associated target condensation point in S42, including:
CP based on target condensation point g Calculation of track predicted position in X, Y direction using Kalman filtering、/>And track prediction speed in X, Y direction +.>、/>Calculating the ship width +.>And ship length->And update heading->；
Wherein, the Kalman filtering adopts a classical Kalman filtering uniform-speed linear model, and the width of the shipLength of ship->The following formula is adopted for calculation:
=/>；
=/>；
、/>respectively the target condensation points CP g Maximum in direction X, Y, < >>、/>Respectively the target condensation points CP g Minimum in direction X, Y;
updating heading by adopting the following method：
=/>。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410123760.5A CN117647806B (en) | 2024-01-30 | 2024-01-30 | Point trace condensation and target tracking method based on millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410123760.5A CN117647806B (en) | 2024-01-30 | 2024-01-30 | Point trace condensation and target tracking method based on millimeter wave radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117647806A CN117647806A (en) | 2024-03-05 |
| CN117647806B true CN117647806B (en) | 2024-04-12 |
Family
ID=90049960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410123760.5A Active CN117647806B (en) | 2024-01-30 | 2024-01-30 | Point trace condensation and target tracking method based on millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117647806B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| WO2020133449A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳市大疆创新科技有限公司 | Target track determination method, target tracking system, and vehicle |
| CN112731296A (en) * | 2020-11-30 | 2021-04-30 | 惠州市德赛西威智能交通技术研究院有限公司 | Automobile millimeter wave radar point trace condensation method and system |
| CN112986971A (en) * | 2021-04-29 | 2021-06-18 | 北京海兰信数据科技股份有限公司 | Radar target measuring method and device |
| CN115754933A (en) * | 2022-10-02 | 2023-03-07 | 西安长远电子工程有限责任公司 | Method for reducing false tracks of sea detection radar |
| WO2023050567A1 (en) * | 2021-09-30 | 2023-04-06 | 南京市德赛西威汽车电子有限公司 | Dead correction method based on scenario recognition by millimeter-wave vehicle-mounted radar |
| WO2023097971A1 (en) * | 2021-12-03 | 2023-06-08 | 南京楚航科技有限公司 | 4d millimeter wave radar data processing method |
| CN116449329A (en) * | 2023-04-27 | 2023-07-18 | 深圳承泰科技有限公司 | Method, system, equipment and storage medium for disambiguating speed of millimeter wave radar |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116106864A (en) * | 2021-11-09 | 2023-05-12 | 深圳市速腾聚创科技有限公司 | Point cloud motion compensation method and device, storage medium and laser radar |
-
2024
- 2024-01-30 CN CN202410123760.5A patent/CN117647806B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| WO2020133449A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳市大疆创新科技有限公司 | Target track determination method, target tracking system, and vehicle |
| CN112731296A (en) * | 2020-11-30 | 2021-04-30 | 惠州市德赛西威智能交通技术研究院有限公司 | Automobile millimeter wave radar point trace condensation method and system |
| CN112986971A (en) * | 2021-04-29 | 2021-06-18 | 北京海兰信数据科技股份有限公司 | Radar target measuring method and device |
| WO2023050567A1 (en) * | 2021-09-30 | 2023-04-06 | 南京市德赛西威汽车电子有限公司 | Dead correction method based on scenario recognition by millimeter-wave vehicle-mounted radar |
| WO2023097971A1 (en) * | 2021-12-03 | 2023-06-08 | 南京楚航科技有限公司 | 4d millimeter wave radar data processing method |
| CN115754933A (en) * | 2022-10-02 | 2023-03-07 | 西安长远电子工程有限责任公司 | Method for reducing false tracks of sea detection radar |
| CN116449329A (en) * | 2023-04-27 | 2023-07-18 | 深圳承泰科技有限公司 | Method, system, equipment and storage medium for disambiguating speed of millimeter wave radar |
Non-Patent Citations (3)
| Title |
|---|
| "Comparison of CovarianceBased Track Association Approaches Using Simulated Radar Data";Keric Hill等;《The Journal of the Astronautical Sciences》;20121231;第59卷(第1- 2期);281-300 * |
| "基于实时优化的搜索雷达点迹提取方法";周昆正等;《现代导航》;20180228;第2卷(第1期);65-69 * |
| "基于车载毫米波雷达的目标跟踪滤波算法";宋玛君等;《2021年全国微波毫米波会议》;20180523;348-350 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117647806A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636829B (en) | Multi-target tracking method based on semantic information and scene information | |
| CN108280442B (en) | Multi-source target fusion method based on track matching | |
| CN103064086B (en) | Vehicle tracking method based on depth information | |
| CN111127518B (en) | Target tracking method and device based on unmanned aerial vehicle | |
| CN110361727A (en) | A kind of millimetre-wave radar multi-object tracking method | |
| CN109946671B (en) | Underwater maneuvering weak target detection and tracking method based on double-threshold judgment | |
| CN111781608B (en) | Moving target detection method and system based on FMCW laser radar | |
| CN111340855A (en) | Road moving target detection method based on track prediction | |
| CN112991391A (en) | Vehicle detection and tracking method based on radar signal and vision fusion | |
| CN105374049B (en) | Multi-corner point tracking method and device based on sparse optical flow method | |
| CN110796676A (en) | Target tracking method combining high-confidence updating strategy with SVM (support vector machine) re-detection technology | |
| CN115840221B (en) | Method for achieving target feature extraction and multi-target tracking based on 4D millimeter wave radar | |
| CN113671481B (en) | 3D multi-target tracking processing method based on millimeter wave radar | |
| CN112731296B (en) | Method and system for condensing points of millimeter wave radar of automobile | |
| CN113791414B (en) | Scene recognition method based on millimeter wave vehicle-mounted radar view | |
| CN114063056A (en) | Ship track fusion method, system, medium and equipment | |
| CN112810619A (en) | Radar-based method for identifying front target vehicle of assistant driving system | |
| CN106569214A (en) | Method and system for processing vehicle-mounted radar data of adaptive cruise vehicle in conjunction with navigation information | |
| CN111768430A (en) | Expressway outfield vehicle tracking method based on multi-feature cascade matching | |
| CN117647806B (en) | Point trace condensation and target tracking method based on millimeter wave radar | |
| CN116246232A (en) | Cross-border head and local feature strategy optimized vehicle multi-target tracking method | |
| CN111340846B (en) | Multi-feature fusion anti-occlusion target tracking method | |
| CN114019497B (en) | Target lane change identification method based on millimeter wave radar variance statistics | |
| CN103886292B (en) | Night vehicle target stable tracking method based on machine vision | |
| CN115471526A (en) | Automatic driving target detection and tracking method based on multi-source heterogeneous information fusion |
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 |