CN108344992A - A kind of multi-object tracking method for vehicle-mounted millimeter wave radar - Google Patents

A kind of multi-object tracking method for vehicle-mounted millimeter wave radar Download PDF

Info

Publication number
CN108344992A
CN108344992A CN201711380531.8A CN201711380531A CN108344992A CN 108344992 A CN108344992 A CN 108344992A CN 201711380531 A CN201711380531 A CN 201711380531A CN 108344992 A CN108344992 A CN 108344992A
Authority
CN
China
Prior art keywords
flight path
frame
target
association
radar
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.)
Granted
Application number
CN201711380531.8A
Other languages
Chinese (zh)
Other versions
CN108344992B (en
Inventor
李舒悦
云峰
赵川
许振丰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Huahang Radio Measurement Research Institute
Original Assignee
Beijing Huahang Radio Measurement Research Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Huahang Radio Measurement Research Institute filed Critical Beijing Huahang Radio Measurement Research Institute
Priority to CN201711380531.8A priority Critical patent/CN108344992B/en
Publication of CN108344992A publication Critical patent/CN108344992A/en
Application granted granted Critical
Publication of CN108344992B publication Critical patent/CN108344992B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/66Radar-tracking systems; Analogous systems
    • G01S13/72Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
    • G01S13/723Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
    • G01S13/726Multiple target tracking

Landscapes

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

Abstract

Invention provides a kind of multi-object tracking method for vehicle-mounted millimeter wave radar, and after this method initializes multiple target tracking data, track initiation is carried out to the target of radar surveying;To the flight path after existing starting into line trace;The targetpath tracked is managed;And judge whether to meet and show output condition, it carries out output and shows.This method is applied under highway environment especially highway environment, and real-time tracking can be realized to multiple targets of appearance;It at least realizes the real-time tracking of 10 small maneuvering targets, and has the function of to reject nonmaneuvering target;Multiple target tracking success rate reaches 85% or more.

Description

A kind of multi-object tracking method for vehicle-mounted millimeter wave radar
Technical field
The present invention relates to Radar Technology field more particularly to a kind of multiple target tracking sides for vehicle-mounted millimeter wave radar Method.
Background technology
With the rapid development of auto industry and the raising of living standards of the people, automobile already becomes essential in life A part.However as being continuously increased for automobile quantity, automotive safety problem has become that today's society is very important to ask Topic.Vehicle-mounted millimeter wave radar is not easy to be influenced by target surface shape and color, and also not by big airflow influence, detection performance is steady It is fixed, influenced by weather such as rain, snow, hazes small, environmental suitability is strong, is the research hotspot of automotive safety technology.
Vehicle-mounted millimeter wave radar application scene is complicated, and jamming target is more, influences tracking and alarm to being concerned about target, existing The tracking of some vehicle-mounted millimeter wave radars, method are complicated, realize it is difficult, and only to determining target into line trace, when going out It, then can not be to it into line trace and alarm when now new target.
Invention content
In view of the above-mentioned problems, the present invention provides a kind of multi-object tracking method for vehicle-mounted millimeter wave radar, method exists To multiple targets into while line trace, solve the problems, such as to newly there is target following.
The technical solution adopted by the present invention is as follows:
A kind of multi-object tracking method for vehicle-mounted millimeter wave radar, which is characterized in that include the following steps:
Step 1, initialization multiple target tracking data, the multiple target including target range, speed and angle of input is believed After breath carries out finish message, flight path structure, the parameter of initialization multiple target tracking filtering are defined, and extract multiple target tracking ginseng Number;
Step 2 carries out track initiation to the target of radar surveying;
Step 3, basis have flight path, present frame target structure, Kalman filtering parameter and 3 frame isolated points, to There is flight path into line trace, obtains updated association flight path, Kalman filtering parameter and 3 frame isolated points;
Step 4 is managed the targetpath tracked, to the flight path after track initiation success into line label, by boat Mark starting successfully sequentially, gives flight path to mark flight path number successively;Flight path termination is carried out to the radar flight path arrived unmeasured for a long time;
Step 5 judges whether to meet display output condition, is that then carrying out output to the targetpath tracked shows, It is no, then the targetpath tracked is not shown, until showing output condition until meeting.
Further, described information arrangement is that multiple-object information is organized into structure format, the target structure Content includes the target number of present frame radar surveying, each target range, speed and angle, non-zero frame count;The non-zero Frame is measurement frame of the radar surveying to target;
The flight path structure includes flight path number, and distance, speed and the angle of every flight path, flight path number and flight path do not close Join frame number to count;
The multiple target tracking filtering uses Kalman filter;To including state vector, vector is measured, state shifts square Battle array, kalman gain, state covariance, measurement matrix measure the Kalman filter ginseng including covariance and new breath covariance Number is initialized;
The multiple target tracking parameter of the extraction is the radar state information including radar speed.
Further, the track initiation of target is carried out in step 2 using logical approach, specially uses 2/3 ratio and 3/4 The track initiation method that ratio combines.
Further, the specific implementation of the track initiation is:
1) target structure of the 4 frame non-zeros exported in continuous receiving step 1;
2) 2/3 ratio track initiation is carried out to first three frame target structure, if successfully originating internal flight path, be output to 3);If internal flight path cannot be originated, it is output to 5);
3) 3/4 ratio track initiation is carried out
A. the internal flight path being associated with the 4th frame target structure, correlating method is related wave door association, if It is successfully associated, is output to b, if association is unsuccessful, be output to c.
B. judge to be successfully associated whether flight path corresponds with internal flight path, be then to be output to 4), it is no, then it enters step c。
C. judging the internal flight path cannot be with the inside flight path for whether having 3/3 starting in the 4th associated part of frame, It is then added in flight path and is output to 4), it is no, then flight path inside residue is added in corresponding isolated point and is output to 4), The isolated point is to fail associated target structure.
4) it is successfully associated, initialized card Germania parameter, arranges and originate successful flight path and the progress of remaining 3 frame isolated point Output.
5) unsuccessful, 3 frame isolated points of output are associated with, flight path is empty.
Further, the specific implementation of the Track In Track in step 3 is:
1) position that frame is currently measured the flight path of input using linear Kalman filter method prediction radar, is updated simultaneously Predicted value and the target structure of input are associated by Kalman filtering parameter;
2) starting that 3 frame isolated points of remaining isolated point after association and input are carried out to new flight path, obtains new flight path With updated 3 frame isolated point;
3) updated flight path, 3 frame isolated points and Kalman filtering parameter in output 2);
4) 1) updated flight path, 3 frame isolated points and Kalman filtering parameter are input to, cycle is 1)~3), it realizes real When Track In Track and to entering the track initiation of fresh target occurred in radar coverage.
Further, the associated method is correlation Bo Menfa, according to the essence of the flight path information and radar of corresponding target The parameter of the related wave door of degree setting.
Further, the flight path termination is to the radar flight path progress finalization process arrived unmeasured for a long time, the boat Mark finish condition is that continuous 7 frame radar surveying value does not terminate flight path then with track association success, deletes the flight path number of the flight path.
Further, the display output condition is set according to whether the track of target output association frame number meets What the number of definite value limited.
Further, the method for counting of the association frame number of the targetpath is as follows:
1) if flight path is the flight path newly originated, it is associated with frame number and is assigned a value of 3;
2) flight path being successfully associated in association process, association frame number carry out adding 1;
3) the not associated success of only 1 frame in association process, association frame number remain unchanged;
4) continuous multiple frames are associated with and are associated with not successfully the flight path that frame number is more than 1 in association process, and association frame number subtracts 1, if closing Join frame number and be not more than 1, is then associated with frame number and is assigned a value of 1.
5) when judging that association frame number is greater than the set value, the track of target is exported.
Further, the setting value is 7.
The beneficial effects of the invention are as follows:
It applies under highway environment especially highway environment, real-time tracking can be realized to multiple targets of appearance; It at least realizes the real-time tracking of 10 small maneuvering targets, and has the function of to reject nonmaneuvering target;Multiple target tracking success rate reaches To 85% or more.
Description of the drawings
Fig. 1-multi-object tracking method flow chart;
3/4 ratio track initiation flow chart of Fig. 2-logical approach;
Fig. 3-multi-target path tracking flow chart;
The method of counting decision flow chart of Fig. 4-association frame number.
Specific implementation mode
The present invention is described further below in conjunction with the accompanying drawings.
A kind of multi-object tracking method for vehicle-mounted millimeter wave radar, as shown in Figure 1, including the following steps:
Step 1, initialization multiple target tracking data, the multiple target including target range, speed and angle of input is believed After breath carries out finish message, flight path structure, the parameter of initialization multiple target tracking filtering are defined, and extract multiple target tracking ginseng Number.
The multiple-object information including target range, speed and angle of the input is the target information of radar surveying;
Described information arrangement is that multiple-object information is organized into structure format, and the content of the target structure includes working as The target number of previous frame radar surveying, each target range, speed and angle, non-zero frame count;The non-zero frame is surveyed for radar Measure the measurement frame of target.
The flight path structure includes flight path number, and distance, speed and the angle of every flight path, flight path number and flight path do not close Join frame number to count;
The multiple target tracking filtering uses Kalman filter;To including state vector, vector is measured, state shifts square Battle array, kalman gain, state covariance, measurement matrix measure the Kalman filter ginseng including covariance and new breath covariance Number is initialized;
The multiple target tracking parameter of the extraction is the radar state information including radar speed.
Step 2 carries out track initiation to the target of radar surveying.
The present invention carries out the track initiation of target using logical approach, and 2/3 ratio and 3/4 ratio is specially used to combine Track initiation method;
In the method, the input data of track initiation is the target structure of continuous 4 frame non-zero, is exported as the new of starting Flight path and remaining 3 frame target structure, as shown in Fig. 2, the specific implementation of track initiation is:
1) target structure of the 4 frame non-zeros exported in continuous receiving step 1;
2) 2/3 ratio track initiation is carried out to first three frame target structure, if successfully originating internal flight path, be output to 3);If internal flight path cannot be originated, it is output to 5);
3) 3/4 ratio track initiation is carried out
A. the internal flight path being associated with the 4th frame target structure, correlating method is related wave door association, if It is successfully associated, is output to b, if association is unsuccessful, be output to c.
B. judge to be successfully associated whether flight path corresponds with internal flight path, be then to be output to 4), it is no, then it enters step c。
C. judging the internal flight path cannot be with the inside flight path for whether having 3/3 starting in the 4th associated part of frame, It is then added in flight path and is output to 4), it is no, then flight path inside residue is added in corresponding isolated point and is output to 4), The isolated point is to fail associated target structure.
4) it is successfully associated, initialized card Germania parameter, arranges flight path and isolated point is exported.
5) unsuccessful, 3 frame isolated points of output are associated with, flight path is empty.
Step 3, basis have flight path, present frame target structure, Kalman filtering parameter and 3 frame isolated points, to There is flight path into line trace, obtains updated association flight path, Kalman filtering parameter and 3 frame isolated points.
As shown in figure 3, the specific implementation of Track In Track is:
1) position that frame is currently measured the flight path of input using linear Kalman filter method prediction radar, is updated simultaneously Predicted value and the target structure of input are associated by Kalman filtering parameter;
Correlating method is correlation Bo Menfa, obtains association flight path and fails the isolated point with track association, wherein related wave The setting of door is related to the information of corresponding flight path and radar accuracy, the related wave of distance, speed and the angle chosen in the present invention Door is as shown in table 1.
2) starting that 3 frame isolated points of remaining isolated point after association and input are carried out to new flight path, obtains new flight path With updated 3 frame isolated point;
3) updated flight path, 3 frame isolated points and Kalman filtering parameter in output 2);
4) 1) updated flight path, 3 frame isolated points and Kalman filtering parameter are input to, cycle is 1)~3), it realizes real When Track In Track and to entering the track initiation of fresh target occurred in radar coverage.
The related wave door parameter of table 1
Step 4 is managed the targetpath tracked, to the flight path after track initiation success into line label, by boat Mark starting successfully sequentially, gives flight path to mark flight path number successively;Flight path termination is carried out to the radar flight path arrived unmeasured for a long time.
For the flight path termination to carry out finalization process to the radar flight path arrived unmeasured for a long time, the flight path in the present invention is whole Knot condition is that continuous 7 frame radar surveying value does not terminate flight path then with track association success, deletes the flight path number of the flight path.
Step 5 judges whether to meet display output condition, is that then carrying out output to the targetpath tracked shows, It is no, then the targetpath tracked is not shown
Display output condition is to export the number restriction whether association frame number meets setting according to the track of the target ,
The present embodiment is more than 7 as display output condition using the association frame number of targetpath.
As shown in figure 4, the method for counting of the association frame number of the targetpath is as follows:
1) if flight path is the flight path newly originated, it is associated with frame number and is assigned a value of 3;
2) flight path being successfully associated in association process, association frame number carry out adding 1;
3) the not associated success of only 1 frame in association process, association frame number remain unchanged;
4) continuous multiple frames are associated with and are associated with not successfully the flight path that frame number is more than 1 in association process, and association frame number subtracts 1, if closing Join frame number and be not more than 1, is then associated with frame number and is assigned a value of 1.
5) when judging that association frame number is more than 7, the track of target is exported.
Therefore on the whole, the multi-object tracking method for vehicle-mounted millimeter wave radar of the present embodiment can be applied Under highway environment especially highway environment, real-time tracking can be realized to multiple targets of appearance;It at least realizes 10 small The real-time tracking of maneuvering target, and have the function of to reject nonmaneuvering target;Multiple target tracking success rate reaches 85% or more.
Above-mentioned specific embodiment is only used for explanation and illustration technical scheme of the present invention, but can not constitute and be wanted to right The restriction for the protection domain asked.It will be apparent to those skilled in the art that doing based on the technical solution of the present invention any simple Deformation and replacement obtained from new technical solution, will fall under the scope of the present invention.

Claims (10)

1. a kind of multi-object tracking method for vehicle-mounted millimeter wave radar, which is characterized in that include the following steps:
Step 1, initialization multiple target tracking data, by the multiple-object information including target range, speed and angle of input into After row information arranges, flight path structure, the parameter of initialization multiple target tracking filtering are defined, and extract multiple target tracking parameter;
Step 2 carries out track initiation to the target of radar surveying;
Step 3, basis have flight path, present frame target structure, Kalman filtering parameter and 3 frame isolated points, to existing boat Mark obtains updated association flight path, Kalman filtering parameter and 3 frame isolated points into line trace;
Step 4 is managed the targetpath tracked, to the flight path after track initiation success into line label, is risen by flight path Begin successfully sequence, marks flight path number to flight path successively;Flight path termination is carried out to the radar flight path arrived unmeasured for a long time;
Step 5 judges whether to meet display output condition, is that then carrying out output to the targetpath tracked shows, no, then The targetpath tracked is not shown, until showing output condition until meeting.
2. multi-object tracking method according to claim 1, which is characterized in that described information arrangement is by multiple-object information Be organized into structure format, the content of the target structure includes the target number of present frame radar surveying, each target away from From, speed and angle, non-zero frame count;The non-zero frame is measurement frame of the radar surveying to target;
The flight path structure includes flight path number, distance, speed and the angle of every flight path, flight path number and the not associated frame of flight path Counting number;
The multiple target tracking filtering uses Kalman filter;To including state vector, measurement vector, state-transition matrix, Kalman gain, state covariance, measurement matrix, measure Kalman filter parameter including covariance and new breath covariance into Row initialization;
The multiple target tracking parameter of the extraction is the radar state information including radar speed.
3. multi-object tracking method according to claim 1, which is characterized in that carry out target using logical approach in step 2 Track initiation, the track initiation method for specially using 2/3 ratio and 3/4 ratio to combine.
4. multi-object tracking method according to claim 3, which is characterized in that the specific implementation of the track initiation For:
1) target structure of the 4 frame non-zeros exported in continuous receiving step 1;
2) 2/3 ratio track initiation is carried out to first three frame target structure, if successfully originating internal flight path, be output to 3); If internal flight path cannot be originated, it is output to 5);
3) 3/4 ratio track initiation is carried out;
A. the internal flight path is associated with the 4th frame target structure, correlating method is related wave door association, if association Success, is output to b, if association is unsuccessful, is output to c;
B. judge to be successfully associated whether flight path corresponds with internal flight path, be then to be output to 4), it is no, then enter step c;
C. judge that the internal flight path cannot then will with the inside flight path for whether having 3/3 starting in the 4th associated part of frame It is added in flight path and is output to 4), no, then flight path inside residue is added in corresponding isolated point and is output to 4), described Isolated point is to fail associated target structure;
4) it is successfully associated, initialized card Germania parameter, arranges the successful flight path of starting and remaining 3 frame isolated point is exported;
5) unsuccessful, 3 frame isolated points of output are associated with, flight path is empty.
5. multi-object tracking method according to claim 1, which is characterized in that the specific reality of the Track In Track in step 3 Now mode is:
1) position of frame is currently measured using linear Kalman filter method prediction radar to the flight path of input, while updates karr Predicted value and the target structure of input are associated by graceful filtering parameter;
2) remaining isolated point after association and 3 frame isolated points of input are subjected to the starting of new flight path, obtain new flight path and more 3 frame isolated points after new;
3) updated flight path, 3 frame isolated points and Kalman filtering parameter in output 2);
4) 1) updated flight path, 3 frame isolated points and Kalman filtering parameter are input to, cycle is 1)~3), realize boat in real time Mark tracks and the track initiation to entering the fresh target occurred in radar coverage.
6. multi-object tracking method according to claim 5, which is characterized in that the associated method is related wave door Method, according to the parameter of the flight path information wave door related to the precision setting of radar of corresponding target.
7. multi-object tracking method according to claim 1, which is characterized in that the flight path termination is to radar long-time The unmeasured flight path that arrives carries out finalization process, the flight path finish condition be continuous 7 frame radar surveying value not with track association at Work(then terminates flight path, deletes the flight path number of the flight path.
8. multi-object tracking method according to claim 1, which is characterized in that the display output condition is according to the mesh Whether target track output association frame number meets the number restriction of setting value.
9. multi-object tracking method according to claim 8, which is characterized in that the meter of the association frame number of the targetpath Counting method is as follows:
1) if flight path is the flight path newly originated, it is associated with frame number and is assigned a value of 3;
2) flight path being successfully associated in association process, association frame number carry out adding 1;
3) the not associated success of only 1 frame in association process, association frame number remain unchanged;
4) continuous multiple frames are associated with and are associated with not successfully the flight path that frame number is more than 1 in association process, and association frame number subtracts 1, if disassociation frame Number is not more than 1, then is associated with frame number and is assigned a value of 1.
5) when judging that association frame number is greater than the set value, the track of target is exported.
10. multi-object tracking method according to claim 8 or claim 9, which is characterized in that the setting value is 7.
CN201711380531.8A 2017-12-20 2017-12-20 Multi-target tracking method for vehicle-mounted millimeter wave radar Active CN108344992B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711380531.8A CN108344992B (en) 2017-12-20 2017-12-20 Multi-target tracking method for vehicle-mounted millimeter wave radar

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711380531.8A CN108344992B (en) 2017-12-20 2017-12-20 Multi-target tracking method for vehicle-mounted millimeter wave radar

Publications (2)

Publication Number Publication Date
CN108344992A true CN108344992A (en) 2018-07-31
CN108344992B CN108344992B (en) 2020-03-27

Family

ID=62962572

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711380531.8A Active CN108344992B (en) 2017-12-20 2017-12-20 Multi-target tracking method for vehicle-mounted millimeter wave radar

Country Status (1)

Country Link
CN (1) CN108344992B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110515041A (en) * 2019-08-30 2019-11-29 的卢技术有限公司 A kind of measuring vehicle distance control method and system based on Kalman filter technology
CN111274336A (en) * 2019-12-18 2020-06-12 浙江大华技术股份有限公司 Target track processing method and device, storage medium and electronic device
CN112379350A (en) * 2020-12-01 2021-02-19 吉林大学 Intelligent vehicle millimeter wave radar multi-target tracking method, device and equipment
CN112837887A (en) * 2019-11-25 2021-05-25 北京华航无线电测量研究所 Local alternating magnetic field generating device of time division multiplexing system
CN113176562A (en) * 2021-05-10 2021-07-27 北京邮电大学 Multi-target tracking method and device, electronic equipment and readable storage medium
CN114185034A (en) * 2020-09-15 2022-03-15 郑州宇通客车股份有限公司 Target tracking method and system for millimeter wave radar

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160078066A (en) * 2014-12-24 2016-07-04 (주)디지탈엣지 Multi target trace method of radar apparatus
CN106199583A (en) * 2016-06-30 2016-12-07 大连楼兰科技股份有限公司 Multi-target Data coupling and the method and system followed the tracks of
CN106249232A (en) * 2016-08-24 2016-12-21 中国电子科技集团公司第二十八研究所 Method for tracking target based on target travel situation information data association strategy
CN106980114A (en) * 2017-03-31 2017-07-25 电子科技大学 Target Track of Passive Radar method
CN107144837A (en) * 2017-04-24 2017-09-08 北京海兰信数据科技股份有限公司 The multi-object tracking method and system of a kind of navigation radar data interconnection

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160078066A (en) * 2014-12-24 2016-07-04 (주)디지탈엣지 Multi target trace method of radar apparatus
CN106199583A (en) * 2016-06-30 2016-12-07 大连楼兰科技股份有限公司 Multi-target Data coupling and the method and system followed the tracks of
CN106249232A (en) * 2016-08-24 2016-12-21 中国电子科技集团公司第二十八研究所 Method for tracking target based on target travel situation information data association strategy
CN106980114A (en) * 2017-03-31 2017-07-25 电子科技大学 Target Track of Passive Radar method
CN107144837A (en) * 2017-04-24 2017-09-08 北京海兰信数据科技股份有限公司 The multi-object tracking method and system of a kind of navigation radar data interconnection

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
贾岩松 等: "多目标跟踪中一种改进的航迹起始算法", 《现代计算机》 *
陈琼 等: "一种实用的多目标航迹跟踪算法", 《火控雷达技术》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110515041A (en) * 2019-08-30 2019-11-29 的卢技术有限公司 A kind of measuring vehicle distance control method and system based on Kalman filter technology
CN110515041B (en) * 2019-08-30 2023-12-01 的卢技术有限公司 Vehicle distance measurement control method and system based on Kalman filtering technology
CN112837887A (en) * 2019-11-25 2021-05-25 北京华航无线电测量研究所 Local alternating magnetic field generating device of time division multiplexing system
CN111274336A (en) * 2019-12-18 2020-06-12 浙江大华技术股份有限公司 Target track processing method and device, storage medium and electronic device
CN111274336B (en) * 2019-12-18 2023-05-09 浙江大华技术股份有限公司 Target track processing method and device, storage medium and electronic device
CN114185034A (en) * 2020-09-15 2022-03-15 郑州宇通客车股份有限公司 Target tracking method and system for millimeter wave radar
CN112379350A (en) * 2020-12-01 2021-02-19 吉林大学 Intelligent vehicle millimeter wave radar multi-target tracking method, device and equipment
CN113176562A (en) * 2021-05-10 2021-07-27 北京邮电大学 Multi-target tracking method and device, electronic equipment and readable storage medium
CN113176562B (en) * 2021-05-10 2023-08-29 北京邮电大学 Multi-target tracking method, device, electronic equipment and readable storage medium

Also Published As

Publication number Publication date
CN108344992B (en) 2020-03-27

Similar Documents

Publication Publication Date Title
CN108344992A (en) A kind of multi-object tracking method for vehicle-mounted millimeter wave radar
CN110187318B (en) Radar data processing method
CN110361727A (en) A kind of millimetre-wave radar multi-object tracking method
CN109919981A (en) A kind of multi-object tracking method of the multiple features fusion based on Kalman filtering auxiliary
CN107993245B (en) Aerospace background multi-target detection and tracking method
CN104237881B (en) FMCW anti-collision radar multi-target detecting and tracking system and method
CN103064086B (en) Vehicle tracking method based on depth information
CN108802722B (en) It is a kind of based on tracking before the Faint target detection virtually composed
CN105809126B (en) The intelligent vehicle Target Tracking System and method that DSRC is merged with onboard sensor
CN101577006B (en) Loitering detecting method and loitering detecting system in video monitoring
CN114299417A (en) Multi-target tracking method based on radar-vision fusion
CN109375177A (en) A kind of moving target detecting method for airport surface detection radar system
CN109633599B (en) Multi-target tracking method for airborne early warning radar
CN108765452A (en) A kind of detection of mobile target in complex background and tracking
CN109188430B (en) Target extraction method based on ground monitoring radar system
CN105093215A (en) Doppler information based method for tracking low-altitude low-speed small target through radar
CN110376581B (en) Explicit multi-target tracking method based on Gaussian mixture probability hypothesis density filter
CN109633590A (en) Extension method for tracking target based on GP-VSMM-JPDA
CN102915545A (en) OpenCV(open source computer vision library)-based video target tracking algorithm
CN108535713A (en) A kind of radar and the tracking of AIS joints and information fusion method
CN108344982A (en) Small drone target radar detection method based on long-time phase-coherent accumulation
CN106526559A (en) Maneuvering target passive coherent location method based on BCD-VSMM
CN107346020A (en) A kind of distribution for asynchronous multi-static radar system batch estimation fusion method
CN109117776A (en) Aircraft and meteorological clutter classifying identification method based on track information
CN108414992B (en) Target detection method based on phase information clutter map

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