CN113030934B - Vehicle inspection radar data preprocessing method based on average distance nearest principle - Google Patents
Vehicle inspection radar data preprocessing method based on average distance nearest principle Download PDFInfo
- Publication number
- CN113030934B CN113030934B CN202110548861.3A CN202110548861A CN113030934B CN 113030934 B CN113030934 B CN 113030934B CN 202110548861 A CN202110548861 A CN 202110548861A CN 113030934 B CN113030934 B CN 113030934B
- Authority
- CN
- China
- Prior art keywords
- target
- targets
- simulated
- range
- simulation
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
-
- 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
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/91—Radar or analogous systems specially adapted for specific applications for traffic control
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
Abstract
The invention relates to a vehicle inspection radar data preprocessing method based on an average distance nearest principle, and belongs to the technical field of vehicle inspection radar data processing. Comprises the following steps of 1: waiting for the radar sensor to push the target, and filtering and selecting the required target from the targets pushed by the radar sensor; step 2: updating target information, judging whether a newly lost target needs to be simulated or not, if so, classifying the newly lost target as the target needing to be simulated, and entering the step 3; if no simulation is needed, it is classified as a target that needs to be released and then discarded; and step 3: preparing a newly lost target before simulation; and 4, step 4: simulating the newly lost target; and 5: and combining the updated target with the simulated target to generate a custom target. The invention can select proper targets from the targets of the sensor data, and adopts the principle of nearest average distance and the relay baton strategy to simulate the lost targets, thereby improving the statistical accuracy.
Description
Technical Field
The invention relates to a vehicle inspection radar data preprocessing method based on an average distance nearest principle, and belongs to the technical field of vehicle inspection radar data processing.
Background
The vehicle detection radar can measure the position and speed of a running vehicle in a road in real time, can provide lane-level traffic flow, average speed and the like, and has irreplaceable effects on traffic control and event detection. However, the number of output targets of the sensor module at the front end of the radar is limited, or problems such as target occlusion exist in an actual scene, and the like, so that the targets output by the sensor are easily lost. If the target output by the sensor is directly taken as the actual target to directly carry out statistical calculation, the accuracy and the precision of statistical data cannot be ensured.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provide a vehicle detection radar data preprocessing method based on the average distance nearest principle, which can select a proper target from targets of sensor data, and adopts the average distance nearest principle and a relay baton strategy to simulate a lost target, thereby improving the statistical accuracy.
The invention discloses a vehicle inspection radar data preprocessing method based on the principle of average distance nearest, which comprises the following steps of:
step 1: waiting for the radar sensor to push the target, and filtering and selecting the required target from the targets pushed by the radar sensor;
step 2: updating target information, judging whether a newly lost target needs to be simulated or not, if so, classifying the newly lost target as the target needing to be simulated, and entering the step 3; if no simulation is needed, it is classified as a target that needs to be released and then discarded;
and step 3: preparing a newly lost target before simulation;
and 4, step 4: simulating the newly lost target;
and 5: and combining the updated target with the simulated target to generate a custom target.
Further, the method also comprises the step 0: initializing relevant variables of a target vehicle, wherein the initialization sequentially comprises the following two substeps:
step 0.0: acquiring a target type and lane information, wherein the lane information is used for classifying the target into a corresponding lane;
step 0.1: the lane center line information is acquired as coordinates of the target.
Further, the filtering in step 1 includes the following two substeps:
step 1.0: selecting a required target according to target information given by the radar sensor and the target type and the coordinates;
step 1.1: and updating the lane where the target is located for simulation and queuing of the target.
Further, step 2 comprises the following substeps:
step 2.0: comparing the target given by the radar sensor with the updated target:
if the target given by the radar sensor is in the updated target, classifying the target as the newly updated target;
ii, if the target given by the radar sensor is not in the updated target, classifying the target as an unmatched target;
iii if the updated target does not appear in the target given by the radar sensor, classifying the updated target as a new lost target;
step 2.1: and judging whether the target needs to be simulated or not according to the position, the speed and the RCS value of the target.
Further, step 3 comprises the following substeps:
step 3.0: judging whether the unmatched target in the step 2.0 can be used as a simulation reference, if so, generating a target within the range, and if not, generating a newly added target;
step 3.1: comparing the targets within the range with reference targets, and classifying:
i if an object in range appears in the reference object, then it is classified as an old started object;
ii if an in-range target is not present in the reference target, then classifying it as a newly activated target;
iii if the reference target does not appear in the targets within range, classifying it as a departing reference target;
step 3.2: merging the newly started target and the old started target to be used as a reference target in the step 3.1 of the next period;
step 3.3: performing lane sequencing on all current targets including updated targets and targets needing simulation; then traversing each lane, and selecting a range of a target to be referenced by using the positions of the simulated real targets on the lane, wherein the range of the target to be referenced is a range between two discontinuous real targets;
step 3.4: sorting the unmatched targets: traversing each unmatched target, if the unmatched target appears in the range of the target to be referred to, storing the unmatched target in a corresponding variable, otherwise, changing the unmatched target into a newly updated target;
step 3.5: when the reference targets in a certain range needing the reference targets are more than the targets needing to be simulated, the targets used as the reference are selected by adopting the principle of average distance nearest, and the rest are converted into the newly updated targets.
Further, step 4 comprises the following substeps:
step 4.0: judging whether the target being simulated loses the reference target or not through the separated reference target in the step 3.1;
step 4.1: adopting a relay baton strategy to take a reference target as a reference target for simulating starting; if the relay range is reached, generating a real target;
step 4.2: simulating queuing and starting;
step 4.3: reverse pushing: when the simulated target does not find the reference target and is in a road where the real target runs, the real target is used for pushing the simulated target out of the range of the target to be referenced, and accumulation to the next period is avoided;
step 4.4: and judging whether the simulated target can be released or not, discarding the target which can be released, and generating the simulated target which cannot be released.
Further, step 5 specifically includes the following steps:
step 5.0: merging the newly updated target, the newly added target and the converted real target to generate an updated target for the step 2.0 of the next period;
step 5.1: merging the updated target and the simulated target to generate a user-defined target, and sorting according to the lane and the distance;
step 5.2: and updating the self-defined target information and the lane sequence to a subsequent radar data processing program.
Further, the specific method of selecting the target used as the reference in step 3.5 by using the principle of the closest mean distance is as follows:
step 3.51: traversing the simulation targets in the target-to-be-referenced range, and calculating the average longitudinal coordinate of the simulation targets, as shown in the following formula:
in the formula: dx _ AVE _ sim is the average vertical coordinate of all simulated targets in the range,nfor the number of targets to be simulated in this range, X i Is as followsiLongitudinal coordinates of each simulation target;
step 3.52: frommIn each reference target, according to the longitudinal coordinate from small to large, the continuous reference targets are selected in turnnThe reference targets, whose average longitudinal coordinates are calculated, are given by:
in the formula: dx _ AVE _ ref i Is shown asiIs connected in seriesnThe average longitudinal coordinate of the individual reference targets,mrepresenting the number of reference targets in the range, XX j Represents the firstjLongitudinal coordinates of the individual reference targets;
step 3.53: calculate Dx _ AVE _ ref in turn i And absolute value of difference of Dx _ AVE _ sim:
selecting the absolute value of the differenceDiff i Minimum sizeiThen select the firstiToi+n-1 reference target as the final adopted reference target; the other unselected targets are converted into newly updated targets.
Further, the step 4.1 comprises the following steps:
calculating a distance D12= X2-X1 between the reference target and the simulated target, wherein X1 is a longitudinal distance of the simulated target from the radar and X2 is a longitudinal distance of the reference target from the radar;
i when the reference target is behind the simulation target, the simulation target needs to be left as it is and waits for the reference target to arrive, and then the following formula is satisfied: d12< 0;
ii, when the reference target moves to or appears before the simulation target but does not exceed the preset distance Dis _ Limit, and the reference target is within the capture range of the simulation target, the simulation target is converted into a real target, and all the attributes of the reference target are assigned to the real target, and the following formula is satisfied: 0< = D12< = Dis _ Limit, Dis _ Limit is the maximum capture distance for the reference target to exceed the simulation target;
iii when the reference target appears in front of the simulated target and exceeds the preset distance, the simulated target needs to increase the speed to catch up with the reference target, and the following formula is satisfied: d12> Dis _ Limit.
The invention has the beneficial effects that: the method can select a proper target from the targets of the sensor data, and adopts the principle of closest average distance and the relay baton strategy to simulate the lost target, thereby improving the statistical accuracy and effectively avoiding the loss of target vehicles output by the sensor due to the limitation of the output target of the radar sensor or the shielding of the target in the actual scene.
Drawings
FIG. 1 is a flow chart of the algorithm of the present invention;
fig. 2 is a schematic diagram of the baton strategy in the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
As shown in fig. 1, the method for preprocessing the radar data of the vehicle inspection based on the principle of the closest average distance includes the following steps:
step 0: initializing relevant variables of a target vehicle, wherein the initialization sequentially comprises the following two substeps:
step 0.0: acquiring a target type and lane information, wherein the lane information is used for classifying the target into a corresponding lane;
step 0.1: acquiring lane center line information as coordinates of a target;
step 1: waiting for the radar sensor to push the target, and filtering and selecting the required target from the targets pushed by the radar sensor;
the filtering in step 1 comprises the following two substeps:
step 1.0: selecting a required target according to target information given by the radar sensor and the target type and the coordinates;
step 1.1: and updating the lane where the target is located for simulation and queuing of the target.
Step 2: updating target information, judging whether a newly lost target needs to be simulated or not, if so, classifying the newly lost target as the target needing to be simulated, and entering the step 3; if no simulation is needed, it is classified as a target that needs to be released and then discarded;
step 2.0: comparing the target given by the radar sensor with the updated target:
if the target given by the radar sensor is in the updated target, classifying the target as the newly updated target;
ii, if the target given by the radar sensor is not in the updated target, classifying the target as an unmatched target;
iii if the updated target does not appear in the target given by the radar sensor, classifying the updated target as a new lost target;
step 2.1: and judging whether the target needs to be simulated or not according to the position, the speed and the RCS value of the target.
And step 3: preparing a newly lost target before simulation; step 3 comprises the following substeps:
step 3.0: judging whether the unmatched target in the step 2.0 can be used as a simulation reference, if so, generating a target within the range, and if not, generating a newly added target;
step 3.1: comparing the targets within the range with reference targets, and classifying:
i if an object in range appears in the reference object, then it is classified as an old started object;
ii if an in-range target is not present in the reference target, then classifying it as a newly activated target;
iii if the reference target does not appear in the targets within range, classifying it as a departing reference target;
step 3.2: merging the newly started target and the old started target to be used as a reference target in the step 3.1 of the next period;
step 3.3: performing lane sequencing on all current targets including updated targets and targets needing simulation; then traversing each lane, and selecting a range needing a reference target by using the positions of the simulated real targets on the lane, wherein the range needing the reference target is a range between two discontinuous real targets;
step 3.4: sorting the unmatched targets: traversing each unmatched target, if the unmatched target appears in the range of the target to be referred to, storing the unmatched target in a corresponding variable, otherwise, changing the unmatched target into a newly updated target;
step 3.5: when the reference targets in a certain range needing the reference targets are more than the targets needing to be simulated, selecting the targets used as the reference by adopting the principle of the nearest average distance, and converting the rest of the targets into newly updated targets;
as shown in fig. 2, in the figure, the solid line is a vehicle simulation target, and the dashed line vehicle is a reference target; the specific method for selecting the target used as the reference by adopting the principle of the closest average distance in the step 3.5 is as follows:
step 3.51: traversing the simulation targets in the target-to-be-referenced range, and calculating the average longitudinal coordinate of the simulation targets, as shown in the following formula:
in the formula: dx _ AVE _ sim is the average vertical coordinate of all simulated targets in the range,nfor the number of targets to be simulated in this range, X i Is as followsiLongitudinal coordinates of each simulation target;
step 3.52: frommIn each reference target, according to the longitudinal coordinate from small to large, the continuous reference targets are selected in turnnThe reference targets, whose average longitudinal coordinates are calculated, are given by:
in the formula: dx _ AVE _ ref i Is shown asiIs connected in seriesnThe average longitudinal coordinate of the individual reference targets,mrepresenting the number of reference targets in the range, XX j Represents the firstjLongitudinal coordinates of the individual reference targets;
step 3.53: calculate Dx _ AVE _ ref in turn i And absolute value of difference of Dx _ AVE _ sim:
selecting the absolute value of the differenceDiff i Minimum sizeiThen select the firstiToi+n-1 reference target as the final adopted reference target; the other unselected targets are converted into newly updated targets.
And 4, step 4: simulating the newly lost target; step 4 comprises the following substeps:
step 4.0: judging whether the target being simulated loses the reference target or not through the reference target which leaves in the step 3.1;
step 4.1: adopting a relay baton strategy to take a reference target as a reference target for simulating starting; if the relay range is reached, generating a real target; step 4.1 the concrete steps are as follows:
calculating a distance D12= X2-X1 between the reference target and the simulated target, wherein X1 is a longitudinal distance of the simulated target from the radar and X2 is a longitudinal distance of the reference target from the radar;
i when the reference target is behind the simulation target, as in fig. 2, the simulation target needs to be saved and waits for the reference target to arrive, and then the following formula is satisfied: d12< 0;
ii, when the reference target moves to or appears before the simulation target but does not exceed the preset distance Dis _ Limit, as in the second embodiment of fig. 2, when the reference target is within the capture range of the simulation target, the simulation target is converted to a real target, and all the attributes of the reference target are assigned to the real target, when the following formula is satisfied: 0< = D12< = Dis _ Limit, Dis _ Limit is the maximum capture distance for the reference target to exceed the simulation target;
iii when the reference target appears in front of the simulated target and exceeds the preset distance, as in three in fig. 2, the simulated target needs to increase the speed to catch up with the reference target, and the following formula is satisfied: d12> Dis _ Limit.
Step 4.2: simulating queuing and starting;
step 4.3: reverse pushing: when the simulated target does not find the reference target and is in a road where the real target runs, the real target is used for pushing the simulated target out of the range of the target to be referenced, and accumulation to the next period is avoided;
step 4.4: and judging whether the simulated target can be released or not, discarding the target which can be released, and generating the simulated target which cannot be released.
And 5: merging the updated target and the simulated target to generate a user-defined target; the step 5 specifically comprises the following steps:
step 5.0: merging the newly updated target, the newly added target and the converted real target to generate an updated target for the step 2.0 of the next period;
step 5.1: merging the updated target and the simulated target to generate a user-defined target, and sorting according to the lane and the distance;
step 5.2: and updating the self-defined target information and the lane sequence to a subsequent radar data processing program.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (7)
1. A vehicle inspection radar data preprocessing method based on the principle of average distance nearest is characterized by comprising the following steps:
step 1: waiting for the radar sensor to push the target, and filtering and selecting the required target from the targets pushed by the radar sensor;
step 2: updating target information, judging whether a newly lost target needs to be simulated or not, if so, classifying the newly lost target as the target needing to be simulated, and entering the step 3; if no simulation is needed, it is classified as a target that needs to be released and then discarded;
step 2 comprises the following substeps:
step 2.0: comparing the target given by the radar sensor with the updated target:
if the target given by the radar sensor is in the updated target, classifying the target as the newly updated target;
ii, if the target given by the radar sensor is not in the updated target, classifying the target as an unmatched target;
iii if the updated target does not appear in the target given by the radar sensor, classifying the updated target as a new lost target;
step 2.1: judging a new lost target, and judging whether the target needs to be simulated or not according to the position, the speed and the RCS value of the target;
and step 3: preparing a newly lost target before simulation;
step 3 comprises the following substeps:
step 3.0: judging whether the unmatched target in the step 2.0 can be used as a simulation reference, if so, generating a target within the range, and if not, generating a newly added target;
step 3.1: comparing the targets within the range with reference targets, and classifying:
i if an object in range appears in the reference object, then it is classified as an old started object;
ii if an in-range target is not present in the reference target, then classifying it as a newly activated target;
iii if the reference target does not appear in the targets within range, classifying it as a departing reference target;
step 3.2: merging the newly started target and the old started target to be used as a reference target in the step 3.1 of the next period;
step 3.3: performing lane sequencing on all current targets including updated targets and targets needing simulation; then traversing each lane, and selecting a range of a target to be referenced by using the positions of the simulated real targets on the lane, wherein the range of the target to be referenced is a range between two discontinuous real targets; the lane is the one being visited in the process of traversing each lane;
step 3.4: sorting the unmatched targets: traversing each unmatched target, if the unmatched target appears in the range of the target to be referred to, storing the unmatched target in a corresponding variable, otherwise, changing the unmatched target into a newly updated target;
step 3.5: when the reference targets in a certain range needing the reference targets are more than the targets needing to be simulated, selecting the targets used as the reference by adopting the principle of the nearest average distance, and converting the rest of the targets into newly updated targets;
and 4, step 4: simulating the newly lost target;
and 5: and combining the updated target with the simulated target to generate a custom target.
2. The method for preprocessing the radar data of the vehicle inspection based on the principle of the average distance nearest in claim 1, further comprising the step 0 of: initializing relevant variables of a target vehicle, wherein the initialization sequentially comprises the following two substeps:
step 0.0: acquiring a target type and lane information, wherein the lane information is used for classifying the target into a corresponding lane;
step 0.1: the lane center line information is acquired as coordinates of the target.
3. The method for preprocessing the radar data for vehicle inspection based on the principle of average distance nearest in claim 2, wherein the filtering in the step 1 comprises the following two substeps:
step 1.0: selecting a required target according to target information given by the radar sensor and the target type and the coordinates;
step 1.1: and updating the lane where the target is located for simulation and queuing of the target.
4. The method for preprocessing the radar data of the vehicle inspection based on the principle of the nearest average distance in the claim 1, wherein the step 4 comprises the following sub-steps:
step 4.0: judging whether the target being simulated loses the reference target or not through the separated reference target in the step 3.1;
step 4.1: adopting a relay baton strategy to take a reference target as a reference target for simulating starting; if the relay range is reached, generating a real target;
step 4.2: simulating queuing and starting;
step 4.3: reverse pushing: when the simulated target does not find the reference target and is in a road where the real target runs, the real target is used for pushing the simulated target out of the range of the target to be referenced, and accumulation to the next period is avoided;
step 4.4: and judging whether the simulated target can be released or not, discarding the target which can be released, and generating the simulated target which cannot be released.
5. The vehicle inspection radar data preprocessing method based on the average distance nearest principle as claimed in claim 4, wherein the step 5 specifically comprises the following steps:
step 5.0: merging the newly updated target, the newly added target and the converted real target to generate an updated target for the step 2.0 of the next period;
step 5.1: merging the updated target and the simulated target to generate a user-defined target, and sorting according to the lane and the distance;
step 5.2: and updating the self-defined target information and the lane sequence to a subsequent radar data processing program.
6. The method for preprocessing the radar data of the vehicle inspection based on the principle of average distance nearest in claim 4, wherein the specific method for selecting the target used as the reference in step 3.5 by using the principle of average distance nearest is as follows:
step 3.51: traversing the simulation targets in the target-to-be-referenced range, and calculating the average longitudinal coordinate of the simulation targets, as shown in the following formula:
in the formula: dx _ AVE _ sim is the average vertical coordinate of all simulated targets in the range,nfor the number of targets to be simulated in this range, X i Is as followsiLongitudinal coordinates of each simulation target;
step 3.52: frommIn each reference target, according to the longitudinal coordinate from small to large, the continuous reference targets are selected in turnnThe reference targets, whose average longitudinal coordinates are calculated, are given by:
in the formula: dx _ AVE _ ref i Is shown asiIs connected in seriesnThe average longitudinal coordinate of the individual reference targets,mrepresenting the number of reference targets in the range, XX j Represents the firstjLongitudinal coordinates of the individual reference targets;
step 3.53: calculate Dx _ AVE _ ref in turn i And absolute value of difference of Dx _ AVE _ sim:
selecting the absolute value of the differenceDiff i Minimum sizeiThen select the firstiToi+n-1 reference target as the final adopted reference target; the other unselected targets are converted into newly updated targets.
7. The vehicle inspection radar data preprocessing method based on the average distance nearest principle as claimed in claim 4, wherein the step 4.1 comprises the following steps:
calculating a distance D12= X2-X1 between the reference target and the simulated target, wherein X1 is a longitudinal distance of the simulated target from the radar and X2 is a longitudinal distance of the reference target from the radar;
i when the reference target is behind the simulation target, the simulation target needs to be left as it is and waits for the reference target to arrive, and then the following formula is satisfied: d12< 0;
ii, when the reference target moves to or appears before the simulation target but does not exceed the preset distance Dis _ Limit, and the reference target is within the capture range of the simulation target, the simulation target is converted into a real target, and all the attributes of the reference target are assigned to the real target, and the following formula is satisfied: 0< = D12< = Dis _ Limit, Dis _ Limit is the maximum capture distance for the reference target to exceed the simulation target;
iii when the reference target appears in front of the simulated target and exceeds the preset distance, the simulated target needs to increase the speed to catch up with the reference target, and the following formula is satisfied: d12> Dis _ Limit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110548861.3A CN113030934B (en) | 2021-05-20 | 2021-05-20 | Vehicle inspection radar data preprocessing method based on average distance nearest principle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110548861.3A CN113030934B (en) | 2021-05-20 | 2021-05-20 | Vehicle inspection radar data preprocessing method based on average distance nearest principle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113030934A CN113030934A (en) | 2021-06-25 |
CN113030934B true CN113030934B (en) | 2021-08-20 |
Family
ID=76455392
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110548861.3A Active CN113030934B (en) | 2021-05-20 | 2021-05-20 | Vehicle inspection radar data preprocessing method based on average distance nearest principle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113030934B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111562581A (en) * | 2020-04-26 | 2020-08-21 | 南京慧尔视防务科技有限公司 | Traffic radar, target detection method and device thereof, electronic equipment and storage medium |
US10852733B1 (en) * | 2012-03-16 | 2020-12-01 | Waymo Llc | Approach for consolidating observed vehicle trajectories into a single representative trajectory |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108872955B (en) * | 2018-06-22 | 2021-11-23 | 成都聚利中宇科技有限公司 | Radar echo signal simulation method and system |
US10829121B1 (en) * | 2018-08-02 | 2020-11-10 | GM Global Technology Operations LLC | Controlling an autonomous vehicle based upon computed lane boundaries |
-
2021
- 2021-05-20 CN CN202110548861.3A patent/CN113030934B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10852733B1 (en) * | 2012-03-16 | 2020-12-01 | Waymo Llc | Approach for consolidating observed vehicle trajectories into a single representative trajectory |
CN111562581A (en) * | 2020-04-26 | 2020-08-21 | 南京慧尔视防务科技有限公司 | Traffic radar, target detection method and device thereof, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
基于RTMS数据的区域机动车积累量分析和可视化;胡玥;《中国优秀硕士学位论文全文数据库工程科技II辑》;20170815;论文第2章,第3章第3.2节 * |
Also Published As
Publication number | Publication date |
---|---|
CN113030934A (en) | 2021-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Pointlanenet: Efficient end-to-end cnns for accurate real-time lane detection | |
CN109087510B (en) | Traffic monitoring method and device | |
CN108986465B (en) | Method, system and terminal equipment for detecting traffic flow | |
CN111123920A (en) | Method and device for generating automatic driving simulation test scene | |
CN108519094B (en) | Local path planning method and cloud processing terminal | |
CN110659664B (en) | SSD-based high-precision small object identification method | |
CN113902897A (en) | Training of target detection model, target detection method, device, equipment and medium | |
CN114694123B (en) | Traffic signal lamp sensing method, device, equipment and storage medium | |
CN113392169A (en) | High-precision map updating method and device and server | |
CN110827326A (en) | Method, device, equipment and storage medium for generating simulation human-vehicle conflict scene model | |
CN110426714B (en) | Obstacle identification method | |
CN113887391A (en) | Method and device for recognizing road sign and automatic driving vehicle | |
CN113030934B (en) | Vehicle inspection radar data preprocessing method based on average distance nearest principle | |
CN113295176A (en) | Map updating method, map updating apparatus, and computer-readable storage medium | |
CN111695389B (en) | Lane line clustering method and device | |
CN115641359B (en) | Method, device, electronic equipment and medium for determining movement track of object | |
CN111325811B (en) | Lane line data processing method and processing device | |
CN111597986A (en) | Method, apparatus, device and storage medium for generating information | |
CN116794619A (en) | Radar debugging processing method and device, electronic equipment and storage medium | |
CN109472973B (en) | Real-time traffic display method based on voice recognition | |
CN113119999B (en) | Method, device, equipment, medium and program product for determining automatic driving characteristics | |
CN114842285A (en) | Roadside berth number identification method and device | |
CN113570727A (en) | Scene file generation method and device, electronic equipment and storage medium | |
CN113837222A (en) | Cloud-edge cooperative machine learning deployment application method and device for millimeter wave radar intersection traffic monitoring system | |
CN114219907B (en) | Three-dimensional map generation method, device, equipment and storage medium |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A data preprocessing method of vehicle inspection radar based on the principle of average distance nearest Effective date of registration: 20211220 Granted publication date: 20210820 Pledgee: Zheshang Bank Co.,Ltd. Nanjing Branch Pledgor: GENTURE ELECTRONICS Co.,Ltd. Registration number: Y2021320000397 |