CN111091148A - Vehicle-mounted radar target tracking method and device based on target prior information - Google Patents

Vehicle-mounted radar target tracking method and device based on target prior information Download PDF

Info

Publication number
CN111091148A
CN111091148A CN201911261278.3A CN201911261278A CN111091148A CN 111091148 A CN111091148 A CN 111091148A CN 201911261278 A CN201911261278 A CN 201911261278A CN 111091148 A CN111091148 A CN 111091148A
Authority
CN
China
Prior art keywords
target
tracking
vehicle
group
prior information
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
CN201911261278.3A
Other languages
Chinese (zh)
Other versions
CN111091148B (en
Inventor
车驰
张伟
谭梦瑶
何宁宇
王平
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.)
Chengdu Nalei Technology Co ltd
Original Assignee
Chengdu Nalei Technology Co ltd
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 Chengdu Nalei Technology Co ltd filed Critical Chengdu Nalei Technology Co ltd
Priority to CN201911261278.3A priority Critical patent/CN111091148B/en
Publication of CN111091148A publication Critical patent/CN111091148A/en
Application granted granted Critical
Publication of CN111091148B publication Critical patent/CN111091148B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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
    • G01S13/66—Radar-tracking systems; Analogous systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/28—Details of pulse systems
    • G01S7/285—Receivers
    • G01S7/295—Means for transforming co-ordinates or for evaluating data, e.g. using computers

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a vehicle-mounted radar target tracking method and device based on target prior information, wherein the method comprises the following steps: s1, obtaining an echo signal of a vehicle-mounted radar in a target vehicle to perform target detection tracking to obtain an initial target tracking result; s2, screening a target group to be fused from an initial target detection tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic; s3, fusing the target groups screened in the step S2 to obtain a final target tracking result and outputting the final target tracking result; the device comprises a target detection tracking module, a fusion target screening module and a target group fusion module. The invention can fully utilize the prior information of the target to realize the target tracking and improve the tracking effect of regularly arranged targets such as trees and the like, and has the advantages of simple realization method, low cost, good tracking precision and tracking effect and the like.

Description

Vehicle-mounted radar target tracking method and device based on target prior information
Technical Field
The invention relates to the technical field of vehicle-mounted radar target tracking, in particular to a vehicle-mounted radar target tracking method and device based on target prior information.
Background
Vehicle-mounted radars such as automobile forward obstacle avoidance radars can be used for assisting a vehicle to judge a forward obstacle so as to avoid collision and ensure driving safety, so that the radars currently become research hotspots. For example, as shown in fig. 1, in a relatively common practical application scenario of a forward obstacle avoidance radar of an automobile, when a vehicle runs on a road, regularly arranged targets, such as regularly arranged trees and telegraph poles, may exist on both sides of the road, and other running vehicles may exist in front of the automobile. In this type of application scenario, if the vehicle needs to avoid the obstacle, a prerequisite is to stably and accurately track the surrounding environment.
In the prior art, when a radar tracks a target, filtering and tracking are usually performed on the target directly after motion information of the target position is detected, but in an actual environment, interference of various noises exists, and it is almost impossible to accurately acquire real-time noise of the target, that is, the filtering result cannot completely filter the interference of the noises, so that the interference of the noises still exists in an output result, and therefore, various errors usually exist in an actual measurement value obtained by the radar. In the application scenario of the vehicle-mounted radar as shown in fig. 1, when regularly arranged targets such as trees, utility poles, etc. are tracked by using the above method, because various errors exist in actual measurement values obtained by the radar, the tracking effect obtained actually is usually not regularly arranged as expected, and the expected tracking effect cannot be achieved. Taking the tracking effect of the automobile forward obstacle avoidance radar on the trees beside the road as an example, the tracking effect actually obtained by adopting the above traditional target tracking mode is generally as shown in fig. 2, wherein a square frame in the figure represents other vehicles in front of the own vehicle, and it can be seen from the figure that a row of tracked trees are not inclined and are not in straight and orderly arrangement, that is, a large error exists between the actual tracking effect and the expected tracking effect.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems in the prior art, the invention provides the vehicle-mounted radar target tracking method and device based on the target prior information, which are simple in implementation method and low in cost, can fully utilize the target prior information to realize the target tracking of the vehicle-mounted radar, and improve the tracking effect of regularly arranged targets such as trees.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a vehicle-mounted radar target tracking method based on target prior information comprises the following steps:
s1, target detection and tracking: obtaining an echo signal of a vehicle-mounted radar in a target vehicle to carry out target detection tracking, and obtaining an initial target tracking result;
s2, fusion target screening: screening a target group to be fused from the initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic;
s3, target group fusion: and fusing the target groups screened in the step S2 to obtain a final target tracking result and output the final target tracking result.
Further, the step of step S2 includes:
s21, obtaining a movement speed interval of a target vehicle, and preliminarily screening a target group to be fused from the initial target tracking result according to the obtained movement speed interval of the vehicle;
and S22, finally screening the target group to be fused according to the position information of each target in the target group preliminarily screened in the step S21.
Further, in step S21, each target point with a speed within the vehicle movement speed interval is specifically screened from the initial target tracking result, and a target group to be fused is obtained through preliminary screening.
Further, the step of acquiring the moving speed of the target vehicle in step S21 includes: dividing the speed of the target into a plurality of speed intervals, counting the number of the targets in each speed interval in the initial target tracking result, and taking the speed interval with the maximum number of the targets as the vehicle movement speed interval.
Further, the specific step of step S22 includes: and (3) dividing all the targets of which the X coordinate values are greater than a first preset threshold value in the primarily screened target groups of the step (S21) into a right side fusion target group, dividing all the targets of which the X coordinate values are less than a second preset threshold value into a left side fusion target group, dividing all the targets of which the X coordinate values are within the range of the first preset threshold value and the second preset threshold value into vehicle front side targets, and finally screening out the target groups to be fused from the divided right side fusion target group and the left side fusion target.
Further, each target with the X coordinate difference value smaller than a third preset threshold is specifically removed from the divided right side fusion target group and left side fusion target, and finally the target group to be fused is obtained through screening.
Further, when performing the fusion in step S3, specifically, a statistical value of the X coordinate of the selected target group is calculated and used as the X coordinate of the target group, and the Y coordinate of each target is determined according to the X coordinate of the target group and the radial distance of each target in the target group.
Further, specifically, the mean value X of all X coordinates in the screened target group is taken1As the X coordinate of the target group, take
Figure BDA0002311663070000021
Is the Y coordinate of each object in the object group, wherein RiIs the radial distance of the ith tree in the target group.
An on-vehicle radar target tracking device based on target prior information comprises:
the target detection tracking module is used for acquiring an echo signal of a vehicle-mounted radar in a target vehicle to perform target detection tracking to obtain an initial target tracking result;
the fusion target screening module is used for screening a target group to be fused from the initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic of the target;
and the target group fusion module is used for fusing the target groups screened by the fused target screening module to obtain a final target tracking result and outputting the final target tracking result.
An on-board radar target tracking device based on target prior information comprises a processor, wherein an executable computer program is stored in the processor, and the processor is configured to execute the method.
Compared with the prior art, the invention has the advantages that:
1. according to the vehicle-mounted radar target tracking method and device based on the target prior information, after the radar carries out target detection tracking to obtain an initial target tracking result, the speed and the position characteristics of the tracked target are used as the prior information, a required target group is screened out from the initial target tracking result according to the prior information and then fusion is carried out, the target group to be tracked can be accurately screened out by fully utilizing the prior information of the target to carry out targeted fusion processing, the tracking precision and the tracking effect of the type targets such as trees and telegraph poles can be effectively improved, and the final tracking effect can be closer to the expected tracking effect.
2. According to the vehicle-mounted radar target tracking method and device based on the target prior information, the position and the speed characteristics of the tracked target are further used as prior information, the target group to be fused is preliminarily screened out from the initial target tracking result according to the speed characteristics and the vehicle movement speed interval, then the target group to be fused is finally screened out from the preliminarily screened target group by using the position characteristics, and all tracked targets can be screened out quickly and accurately.
3. The vehicle-mounted radar target tracking method and device based on the target prior information further divide the preliminarily screened target points by utilizing the X coordinate values of the targets according to the characteristics that the targets such as trees, telegraph poles and the like are positioned at the two sides of the road, finally screen out the target groups to be fused from the divided left and right fused target groups, and further eliminate the non-required tracking targets according to the difference value of the X coordinates of the targets, so that only the required targets such as trees, telegraph poles and the like which are regularly arranged can be selected as far as possible for fusion.
Drawings
Fig. 1 is a schematic diagram of a typical application scenario of an automobile forward obstacle avoidance radar.
Fig. 2 is a schematic diagram of tracking effect obtained by tracking a tree by using a conventional tracking method.
Fig. 3 is a schematic flow chart of an implementation of the vehicle-mounted radar target tracking method based on the target prior information in the embodiment.
Fig. 4 is a complete flow chart of the implementation of radar target tracking in the present embodiment.
Fig. 5 is a detailed flowchart illustrating the implementation of radar target tracking in this embodiment.
Detailed Description
The invention is further described below with reference to the drawings and specific preferred embodiments of the description, without thereby limiting the scope of protection of the invention.
As shown in fig. 3, the steps of the vehicle-mounted radar target tracking method based on the target prior information in this embodiment include:
s1, target detection and tracking: obtaining an echo signal of a vehicle-mounted radar in a target vehicle to carry out target detection tracking, and obtaining an initial target tracking result;
s2, fusion target screening: screening a target group to be fused from an initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic;
s3, target group fusion: and (4) fusing the target groups screened in the step (S2) to obtain a final target tracking result and outputting the final target tracking result.
For targets regularly arranged in a vehicle motion environment such as trees, telegraph poles and the like, the targets are usually regularly arranged on two sides of a road in a straight manner, so that the positions and the speeds of the targets in a radar tracking result have specific characteristics, and the position and the speed characteristics of the targets are firstly analyzed in the embodiment:
(1) position characteristics: because the regularly arranged targets such as trees and telegraph poles are usually straightly arranged on two sides of a road, the positions of the targets in the rectangular coordinate system are similar to the positions of the vehicle-mounted radars in the x-axis direction (namely, perpendicular to the vehicle advancing direction), namely, the distances between the targets in the x-axis direction and the vehicle-mounted radars in the radar tracking result are similar;
(2) speed characteristics: since the regularly arranged targets such as trees and telegraph poles are static, and the speed of the targets relative to the vehicle is caused by the motion of the vehicle, the motion speeds of the targets in the y direction, namely the forward direction of the vehicle, are the same, and are the motion speeds of the vehicle, namely the speed of the targets in the forward direction of the vehicle in the radar tracking result is the same.
For the targets regularly arranged, such as trees, telegraph poles, and the like, the embodiment utilizes the position and speed characteristics of the targets, obtains an initial target tracking result by performing target detection and tracking through a radar, uses the speed and position characteristics of the tracked target as prior information, screens out a required target group from the initial target tracking result according to the prior information, and performs fusion, so that the target group to be tracked can be accurately screened out by fully utilizing the prior information of the target to perform targeted fusion processing, thereby effectively improving the tracking precision and tracking effect of the targets, such as trees, telegraph poles, and the like, and enabling the final tracking effect to be closer to the expected tracking effect.
In step S1 of this embodiment, a tracking method in the prior art may be specifically used according to actual requirements to obtain a preliminary tracking result, as shown in fig. 4, after the tracking is finished, that is, after the target filtering is finished, the process goes to step S2 and step S3 to perform targeted screening and fusion processing on the tracked target, and the finally obtained tracked target is output and displayed.
In this embodiment, the specific step of step S2 includes:
s21, obtaining a movement speed interval of a target vehicle, and preliminarily screening a target group to be fused from an initial target tracking result according to the obtained movement speed interval of the vehicle;
and S22, finally screening the target group to be fused according to the position information of each target in the target group preliminarily screened in the step S21.
Because the distance between regularly arranged targets such as trees and telegraph poles and the vehicle-mounted radar is close in the x-axis direction, the speed of the targets is the same along the vehicle front direction and is the vehicle motion speed, the two characteristics of the targets are used as prior information, the target group needing to be fused is preliminarily screened out from the initial target tracking result according to the vehicle motion speed interval according to the speed characteristic, then the target group needing to be fused is finally screened out from the preliminarily screened target group by utilizing the position characteristic, and all the tracking targets of the type can be accurately screened out.
The step of acquiring the moving speed of the destination vehicle in step S21 of the present embodiment includes: dividing the speed of the target into a plurality of speed intervals, counting the number of the targets in each speed interval in the initial target tracking result, and taking the speed interval with the maximum number of the targets as a vehicle movement speed interval. Since the number of the stationary targets such as trees, telegraph poles and the like is usually the largest in the radar monitoring area, the present embodiment utilizes the characteristic to determine the movement speed interval of the vehicle itself, that is, the movement speed of the targets such as trees along the movement direction of the vehicle, by determining the speed interval with the largest number of targets, so that the speed of the vehicle can be accurately obtained without using additional speed detection equipment.
In a specific application embodiment, the number of targets in each speed interval is counted by taking a preset speed v (specifically, 10km/h) as a separation threshold, for example, the number of targets in speed intervals of 1-10km/h,10-20km/h and … are counted respectively, a speed interval with the largest number of targets is selected, all speed values in the interval are averaged (in a specific application, the most value can be removed and then averaged to improve the precision), the obtained average value is taken as the moving speed v of the vehicle, and the speed interval v is recordedth1～vth2And obtaining the required vehicle movement speed interval.
It can be understood that the vehicle movement speed can also be obtained by other methods according to actual requirements, for example, if information interaction can be performed with the vehicle itself, the speed of the vehicle itself can be directly obtained through the interface.
In step S21, in this embodiment, each target point with a speed within the vehicle movement speed interval is specifically screened from the initial target tracking result, and a target group to be fused is obtained through preliminary screening, that is, a target point group meeting the above speed characteristics (the speed is the same as the vehicle movement speed) is obtained through preliminary screening. In a determined speed interval vth1～vth2Then, the velocity interval v is usedth1～vth2And screening out target points to be fused, namely target points with the speed within the speed interval as an initial fusion target point group. And in specific application, the maximum value and the minimum value in the screened target point group can be removed so as to further improve the precision.
In this embodiment, the specific step of step S22 includes: and (4) dividing all the targets of which the X coordinate values are greater than a first preset threshold value in the primarily screened target groups of the step (S21) into a right side fusion target group, dividing all the targets of which the X coordinate values are less than a second preset threshold value into a left side fusion target group, dividing all the targets of which the X coordinate values are within the range of the first preset threshold value and the second preset threshold value into vehicle front side targets, and finally screening out target groups required to be fused from the divided right side fusion target group and the left side fusion target.
The implementation divides the preliminarily screened target points according to the X coordinate values of the targets, wherein the divided left and right side fusion target groups belong to the regularly arranged targets such as the trees, the telegraph poles and the like positioned on the two sides of the road, and finally screens out the target group to be fused from the left and right side fusion target groups.
In a specific application embodiment, when the left and right fusion target groups are distinguished according to the X coordinate, assuming that the radar normal position is set as a 0 point, the target X coordinate on the right side of the radar is positive, and the target X coordinate on the left side of the radar is negative, sequentially judging the X coordinate of each preliminarily screened target point, and if the X coordinate is greater than a first preset threshold (specifically, 20cm), judging the right fusion target group; when the X coordinate is smaller than a second preset threshold (specifically-20 cm), judging that the fusion target group on the left side is a fusion target group; if the X coordinate is between a first preset threshold and a second preset threshold (namely-20 cm), the front moving target of the vehicle body is judged, the target is not taken as a fusion target, and only the left and right fusion target groups are taken as fusion targets.
In this embodiment, the targets whose absolute values of the X coordinate differences are smaller than the third preset threshold are specifically removed from the divided right-side fusion target group and left-side fusion target, and the target group to be fused is finally obtained through screening. The selected left and right fusion target groups still have the undesired tracking targets, and the undesired tracking targets are further removed according to the target X coordinate difference value in the embodiment, so that only the desired targets regularly arranged such as trees, telegraph poles and the like are selected for fusion.
In a specific application embodiment, when the unnecessary tracking target is removed according to the target X coordinate difference, specifically, target points whose X coordinate difference absolute values are smaller than a third preset threshold (specifically, 0.5m) are sequentially screened from the left and right fusion target groups, if the number of the screened target points is smaller than a preset threshold (specifically, 3), that is, the number of the target points meeting the condition is too small, which indicates that the target is not the tracking target required by the type of tree, telegraph pole, or the like, the fusion is not performed, the unnecessary tracking target is removed, and the tracking accuracy can be further improved.
The preset threshold value can be configured according to actual requirements, radar measurement accuracy and the like.
Target groups (namely target point groups required to be tracked and regularly arranged such as trees, telegraph poles and the like) to be fused are screened out and then fused, so that the target tracking effect can be improved. In the fusion performed in step S3 of the present embodiment, the statistical value of the X coordinates of the screened target group is specifically calculated as the X coordinates of the target group, and the Y coordinates of each target are determined based on the X coordinates of the target group and the radial distance of each target in the target group. In a specific application embodiment, the mean value of all X coordinates in the screened target group is taken
Figure BDA0002311663070000061
As the X coordinate of the target group, take
Figure BDA0002311663070000062
Is the Y coordinate of each object in the object group, wherein RiIs the radial distance of the ith target in the target group, i.e. the distance of the target to the center of the radar.
By adopting the method of the embodiment, regularly arranged target groups of the targets to be tracked, such as trees, telegraph poles and the like, can be accurately screened out for targeted fusion, the influence caused by errors of radar measurement values is eliminated, and finally a straight and orderly tracking effect can be obtained, namely, the expected tracking effect is achieved.
The following takes the example of tracking trees by using a forward obstacle avoidance radar of an automobile in a specific application embodiment as an example, and as shown in fig. 5, the detailed steps include:
step 1, target detection and tracking
And obtaining an echo signal of a vehicle-mounted radar in the target vehicle, and detecting and tracking the target by adopting a tracking method in the prior art to obtain an initial target tracking result.
Step 2, fusion target group screening
Step 2.1 vehicle movement speed acquisition
Counting the number of targets in each speed interval by taking 10km/h as a separation threshold, for example, counting the number of targets in speed intervals of 1-10km/h,10-20km/h and … respectively, determining the speed interval with the maximum number of targets, and determining to obtain the movement speed interval v of the vehicleth1～vth2And averaging after removing the most values of all the speed values in the interval, and taking the average value v as the movement speed of the vehicle.
Step 2.2, primary screening of fusion target group according to vehicle speed
According to the velocity interval vth1～vth2The target points to be fused, namely the target points with the speed in the interval are screened out as the initial fused target point group, and the detection information of the screened target points is stored in an array VAnd V (i) represents the ith element in the array V, and the maximum value and the minimum value in the array V are removed.
Step 2.3, dividing the fusion target group according to the X coordinate
And (3) circularly judging the elements in the array V by taking the radar normal line position as a 0 point, the target X coordinate on the right side of the radar as a positive target X coordinate and the target X coordinate on the left side of the radar as a negative target X coordinate, if the X coordinate of the ith element is more than 20cm, judging that the element is a right fusion target group, and storing the element into the array VRight sidePerforming the following steps; if the X coordinate is less than-20, the fusion target group on the left side is judged and stored in the array VLeft side ofPerforming the following steps; if the X coordinate is between-20 and 20, the front moving target of the vehicle body is not taken as a fusion target.
Step 2.4, finally screening out tree target groups from the left and right fusion target groups
Non-tree targets exist in the targets selected after the step 2.3, and the targets are removed, namely only trees are selected for fusion. Specific pair array VRight sideAnd VLeft side ofRespectively implementing the following steps: and traversing the array for circulation, screening array elements with the X coordinate difference absolute value smaller than 0.5m, and if the number of the screened array elements is smaller than 3, indicating that no trees which are planted straightly exist on the left and right, not fusing.
Step 3, fusing the target group
The following steps are respectively carried out on the left and right side tree groups: averaging all X coordinates in the tree group, and recording the obtained mean value as
Figure BDA0002311663070000071
Will be provided with
Figure BDA0002311663070000072
As the X-coordinate of the tree crowd, the Y-coordinate of each tree in the tree crowd is
Figure BDA0002311663070000073
And obtaining the fused coordinate values.
And 4, step 4: target output display
And outputting and displaying the fused coordinate values.
The vehicle-mounted radar target tracking device based on the target prior information comprises:
the target detection tracking module is used for acquiring an echo signal of a vehicle-mounted radar in a target vehicle to perform target detection tracking to obtain an initial target tracking result;
the fusion target screening module is used for screening a target group to be fused from the initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic of the target;
and the target group fusion module is used for fusing the target groups screened by the fused target screening module to obtain a final target tracking result and outputting the final target tracking result.
In this embodiment, the fusion target screening module specifically includes:
the preliminary screening unit is used for acquiring a movement speed interval of a target vehicle and preliminarily screening a target group to be fused from an initial target tracking result according to the acquired movement speed interval of the vehicle;
and the secondary screening unit is used for finally screening the target group to be fused according to the position information of each target in the target group preliminarily screened by the preliminary screening unit.
In this embodiment, the vehicle-mounted radar target tracking device based on the target prior information corresponds to the vehicle-mounted radar target tracking method based on the target prior information one to one, and is not described herein any more.
In another embodiment, the vehicle-mounted radar target tracking device based on the target prior information may further include: the vehicle-mounted radar target tracking method based on the target prior information comprises a processor, wherein an executable computer program is stored in the processor, and the processor is configured to execute the vehicle-mounted radar target tracking method based on the target prior information.
The foregoing is considered as illustrative of the preferred embodiments of the invention and is not to be construed as limiting the invention in any way. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.

Claims (10)

1. A vehicle-mounted radar target tracking method based on target prior information is characterized by comprising the following steps:
s1, target detection and tracking: obtaining an echo signal of a vehicle-mounted radar in a target vehicle to carry out target detection tracking, and obtaining an initial target tracking result;
s2, fusion target screening: screening a target group to be fused from the initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic;
s3, target group fusion: and fusing the target groups screened in the step S2 to obtain a final target tracking result and output the final target tracking result.
2. The method for tracking the vehicle-mounted radar target based on the target prior information as claimed in claim 1, wherein the step S2 comprises:
s21, obtaining a movement speed interval of a target vehicle, and preliminarily screening a target group to be fused from the initial target tracking result according to the obtained movement speed interval of the vehicle;
and S22, finally screening the target group to be fused according to the position information of each target in the target group preliminarily screened in the step S21.
3. The method for tracking the vehicle-mounted radar target based on the target prior information as claimed in claim 2, wherein in step S21, each target point with a speed within the vehicle movement speed interval is specifically screened from the initial target tracking result, and a target group to be fused is obtained through preliminary screening.
4. The method for tracking the vehicle-mounted radar target based on the target prior information as claimed in claim 2, wherein the step of obtaining the movement speed of the target vehicle in step S21 comprises: dividing the speed of the target into a plurality of speed intervals, counting the number of the targets in each speed interval in the initial target tracking result, and taking the speed interval with the maximum number of the targets as the vehicle movement speed interval.
5. The method for tracking the vehicle-mounted radar target based on the target prior information according to claim 2, 3 or 4, wherein the specific step of the step S22 includes: and (3) dividing all the targets of which the X coordinate values are greater than a first preset threshold value in the primarily screened target groups of the step (S21) into a right side fusion target group, dividing all the targets of which the X coordinate values are less than a second preset threshold value into a left side fusion target group, dividing all the targets of which the X coordinate values are within the range of the first preset threshold value and the second preset threshold value into vehicle front side targets, and finally screening out the target groups to be fused from the divided right side fusion target group and the left side fusion target.
6. The method for tracking the vehicle-mounted radar target based on the target prior information as claimed in claim 5, wherein each target with an X coordinate difference value smaller than a third preset threshold is specifically removed from the divided right-side fusion target group and left-side fusion target, and finally the target group to be fused is obtained through screening.
7. The method for tracking the vehicle-mounted radar target based on the target prior information as claimed in any one of claims 1 to 4, wherein, during the fusion in the step S3, specifically, a statistical value of X coordinates of the screened target group is calculated and used as the X coordinates of the target group, and Y coordinates of each target are correspondingly determined according to the X coordinates of the target group and the radial distance of each target in the target group.
8. The method as claimed in claim 7, wherein the mean value of all X coordinates in the selected target group is taken
Figure FDA0002311663060000021
As the X coordinate of the target group, take
Figure FDA0002311663060000022
Is the Y coordinate of each object in the object group, where RiIs the radial distance of the ith tree in the target group.
9. The utility model provides a vehicle-mounted radar target tracking device based on target prior information which characterized in that includes:
the target detection tracking module is used for acquiring an echo signal of a vehicle-mounted radar in a target vehicle to perform target detection tracking to obtain an initial target tracking result;
the fusion target screening module is used for screening a target group to be fused from the initial target tracking result according to prior information of a tracked target, wherein the prior information comprises a speed characteristic and a position characteristic of the target;
and the target group fusion module is used for fusing the target groups screened by the fused target screening module to obtain a final target tracking result and outputting the final target tracking result.
10. An on-board radar target tracking device based on target prior information, comprising a processor having an executable computer program stored therein, wherein the processor is configured to perform the method of any one of claims 1 to 8.
CN201911261278.3A 2019-12-10 2019-12-10 Vehicle-mounted radar target tracking method and device based on target prior information Active CN111091148B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911261278.3A CN111091148B (en) 2019-12-10 2019-12-10 Vehicle-mounted radar target tracking method and device based on target prior information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911261278.3A CN111091148B (en) 2019-12-10 2019-12-10 Vehicle-mounted radar target tracking method and device based on target prior information

Publications (2)

Publication Number Publication Date
CN111091148A true CN111091148A (en) 2020-05-01
CN111091148B CN111091148B (en) 2021-07-27

Family

ID=70395498

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911261278.3A Active CN111091148B (en) 2019-12-10 2019-12-10 Vehicle-mounted radar target tracking method and device based on target prior information

Country Status (1)

Country Link
CN (1) CN111091148B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113093145A (en) * 2021-06-09 2021-07-09 深圳市万集科技有限公司 Target detection method and target detection device

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101290350A (en) * 2008-05-21 2008-10-22 覃征 Ground cluster object tracking method
CN101339243A (en) * 2008-08-15 2009-01-07 覃征 Ground cluster object tracking system
US20100033366A1 (en) * 2008-08-07 2010-02-11 Fujitsu Ten Limited Radar apparatus and control method of the same
JP2012238182A (en) * 2011-05-12 2012-12-06 Honda Motor Co Ltd Object detection device for vehicle
CN104502907A (en) * 2014-12-15 2015-04-08 西安电子工程研究所 Stable ground moving/static target tracking method for airborne radar
CN104793202A (en) * 2014-01-16 2015-07-22 通用汽车环球科技运作有限责任公司 Object fusion system of multiple radar imaging sensors
JP2018040642A (en) * 2016-09-06 2018-03-15 株式会社Ihi Device and method for recognizing moving objects
CN109031279A (en) * 2018-06-23 2018-12-18 中国人民解放军海军航空大学青岛校区 Multiple multiple targets trackings with shape information
CN109212514A (en) * 2018-09-29 2019-01-15 河北德冠隆电子科技有限公司 A kind of detections of radar equipment persistently tracks correlating method to movement and static target
CN109343049A (en) * 2017-11-10 2019-02-15 长城汽车股份有限公司 The method and apparatus for tracking movable object
CN109870680A (en) * 2018-10-26 2019-06-11 北京润科通用技术有限公司 A kind of objective classification method and device
CN110146865A (en) * 2019-05-31 2019-08-20 阿里巴巴集团控股有限公司 Target identification method and device for radar image
WO2019199349A2 (en) * 2017-09-14 2019-10-17 Raytheon Company Multi-static frequency diverse waveform (mfdw)

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101290350A (en) * 2008-05-21 2008-10-22 覃征 Ground cluster object tracking method
US20100033366A1 (en) * 2008-08-07 2010-02-11 Fujitsu Ten Limited Radar apparatus and control method of the same
CN101339243A (en) * 2008-08-15 2009-01-07 覃征 Ground cluster object tracking system
JP2012238182A (en) * 2011-05-12 2012-12-06 Honda Motor Co Ltd Object detection device for vehicle
CN104793202A (en) * 2014-01-16 2015-07-22 通用汽车环球科技运作有限责任公司 Object fusion system of multiple radar imaging sensors
CN104502907A (en) * 2014-12-15 2015-04-08 西安电子工程研究所 Stable ground moving/static target tracking method for airborne radar
JP2018040642A (en) * 2016-09-06 2018-03-15 株式会社Ihi Device and method for recognizing moving objects
WO2019199349A2 (en) * 2017-09-14 2019-10-17 Raytheon Company Multi-static frequency diverse waveform (mfdw)
CN109343049A (en) * 2017-11-10 2019-02-15 长城汽车股份有限公司 The method and apparatus for tracking movable object
CN109031279A (en) * 2018-06-23 2018-12-18 中国人民解放军海军航空大学青岛校区 Multiple multiple targets trackings with shape information
CN109212514A (en) * 2018-09-29 2019-01-15 河北德冠隆电子科技有限公司 A kind of detections of radar equipment persistently tracks correlating method to movement and static target
CN109870680A (en) * 2018-10-26 2019-06-11 北京润科通用技术有限公司 A kind of objective classification method and device
CN110146865A (en) * 2019-05-31 2019-08-20 阿里巴巴集团控股有限公司 Target identification method and device for radar image

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
SZE KIM PANG 等: "Detection and Tracking of Coordinated Groups", 《IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS》 *
李春霞: "宽带雷达空间目标及目标群跟踪方法研究", 《中国博士学位论文全文数据库信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113093145A (en) * 2021-06-09 2021-07-09 深圳市万集科技有限公司 Target detection method and target detection device
CN113093145B (en) * 2021-06-09 2021-10-01 深圳市万集科技有限公司 Target detection method and target detection device

Also Published As

Publication number Publication date
CN111091148B (en) 2021-07-27

Similar Documents

Publication Publication Date Title
CN110764108B (en) Obstacle detection method and device for port automatic driving scene
US9983306B2 (en) System and method for providing target threat assessment in a collision avoidance system on a vehicle
US10605896B2 (en) Radar-installation-angle calculating device, radar apparatus, and radar-installation-angle calculating method
CN106991389B (en) Device and method for determining road edge
CN110867132B (en) Environment sensing method, device, electronic equipment and computer readable storage medium
CN112526521B (en) Multi-target tracking method for automobile millimeter wave anti-collision radar
CN107103275B (en) Wheel-based vehicle detection and tracking using radar and vision
CN110516621B (en) Method and device for detecting barrier-free driving area, vehicle and storage medium
WO2022134510A1 (en) Vehicle-mounted bsd millimeter wave radar based method for obstacle recognition at low speed
US11753002B2 (en) Vehicular control system
CN113807168A (en) Vehicle driving environment sensing method, vehicle-mounted equipment and storage medium
CN111797701B (en) Road obstacle sensing method and system for vehicle multi-sensor fusion system
CN110940982B (en) Vehicle front destination identification method and corresponding device
CN115856872A (en) Vehicle motion track continuous tracking method
CN111091148B (en) Vehicle-mounted radar target tracking method and device based on target prior information
CN110426714B (en) Obstacle identification method
CN111959515B (en) Forward target selection method, device and system based on visual detection
CN114296095A (en) Method, device, vehicle and medium for extracting effective target of automatic driving vehicle
CN110940981B (en) Method for judging whether position of object in front of vehicle is in own lane
CN112277799A (en) Automobile blind area detection alarm method and system
US20050177336A1 (en) Method for identifying object constellations using distance signals
CN113879312B (en) Forward target selection method and device based on multi-sensor fusion and storage medium
CN117250595B (en) False alarm suppression method for vehicle-mounted millimeter wave radar metal well lid target
EP4266083A1 (en) Distribution fitting constant false alarm rate (cfar) detection
CN115775468A (en) High-risk vehicle driving safety intelligent management system based on data analysis

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