CN111098890B - Train collision avoidance method and device based on millimeter wave radar - Google Patents
Train collision avoidance method and device based on millimeter wave radar Download PDFInfo
- Publication number
- CN111098890B CN111098890B CN201911309157.1A CN201911309157A CN111098890B CN 111098890 B CN111098890 B CN 111098890B CN 201911309157 A CN201911309157 A CN 201911309157A CN 111098890 B CN111098890 B CN 111098890B
- Authority
- CN
- China
- Prior art keywords
- target
- radar
- train
- collision
- signals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000003137 locomotive effect Effects 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 29
- 239000013598 vector Substances 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to a train anti-collision method and a train anti-collision device based on a millimeter wave radar, which belong to the technical field of radars and solve the anti-collision problem of subway trains, wherein the method comprises the steps of preprocessing radar echo signals reflected in front of a subway locomotive head to obtain target echo signals; classifying the target echo signals by adopting a trained SVM model, and filtering false target echo signals to obtain real target echo signals; and calculating the relative distance and speed between the subway locomotive head and the target object according to the real target echo signal, judging whether the relative distance and speed exceed an anti-collision threshold value, and performing train anti-collision early warning if the relative distance and speed exceed the anti-collision threshold value. The invention can solve the problem of receiving and processing radar signals in the special environment of the subway tunnel and give early warning to obstacles in front of the subway train; interference signals and false targets are removed, and the influence of false alarms on the advancing of the train is avoided; besides, trackside equipment is not required to be arranged, the cost is low, and the maintenance is convenient.
Description
Technical Field
The invention relates to the technical field of radars, in particular to a train collision avoidance method and device based on a millimeter wave radar.
Background
The existing distance measuring and positioning technology for subway trains mainly depends on an Automatic Train Protection (ATP) subsystem, an Automatic Train Operation (ATO) subsystem and an Automatic Train Supervision (ATS) subsystem in a Communication Based Train Control System (CBTC) System.
Current CBTC systems are expensive, requiring many active beacons to be placed, which means high fitment and maintenance costs; and the system communication is closed, and the emergent obstacles outside the system can not be identified and measured and can not send out early warning.
In actual operation, the CBTC system inevitably has some faults. When the ATP system meets the condition that the ATP system needs to be cut off, the safety guarantee of the train mainly depends on train dispatching at a station, observation of a driver and execution of degradation regulations, a safety protection means at an equipment level is lacked, risks exist, and a rear-end collision event of the train under the condition that the ATP is cut off easily occurs.
Disclosure of Invention
In view of the above analysis, the present invention aims to provide a train collision avoidance method and apparatus based on millimeter wave radar, which solves the collision avoidance problem of subway trains.
The purpose of the invention is mainly realized by the following technical scheme:
the invention discloses a train collision avoidance method based on a millimeter wave radar, which comprises the following steps:
preprocessing a radar echo signal reflected in front of a subway locomotive head to obtain a target echo signal;
classifying the target echo signals by adopting a trained SVM model, and filtering false target echo signals to obtain real target echo signals;
and calculating the relative distance and speed between the subway locomotive head and the target object according to the real target echo signal, judging whether the relative distance and speed exceed an anti-collision threshold value, and if so, performing train anti-collision early warning.
Further, the pretreatment method comprises the following steps:
performing data primary screening on the radar echo signals, and eliminating transverse interference signals;
estimating a clutter power value of the position where the target is located;
and comparing the clutter power value serving as a threshold value with the power of the radar echo signal after preliminary screening, and rejecting a target unit only comprising the clutter signal in the radar echo signal to obtain a target echo signal.
Further, in the data preliminary screening, a transverse distance threshold value is set, and radar echo signals with transverse distances exceeding the transverse distance threshold value are removed.
Further, the lateral distance threshold is matched with the width of the subway tunnel.
Further, the estimated clutter power of the position where the target is located is an arithmetic average of the powers of all target units included in the current echo signal.
Further, the training method of the SVM model comprises the following steps:
constructing a training data set, wherein the training data is a radar echo signal;
constructing an SVM classifier;
preprocessing a training data set to obtain a target echo signal;
processing a target echo signal, and extracting a characteristic vector group; sticking a data label of a false target in the target echo signal to be +1, and sticking a data label of a real obstacle to be-1;
and sending the extracted feature vector group and the corresponding data label as input into an SVM trainer for model training.
Further, the SVM classifier adopts a linear kernel function.
Further, the training data set includes radar return signals collected while the train is running without an obstacle, and radar return signals collected while a specific obstacle is placed in front of the train travel.
Further, the set of feature vectors includes range, velocity, and target echo power data for the target.
The invention also discloses a train anti-collision device based on the millimeter wave radar, which comprises a radar transmitter, a radar receiver and an anti-collision processor;
the radar transmitter is arranged at the locomotive of the train locomotive and used for transmitting radar signals to the front of the locomotive;
the radar receiver is arranged at the locomotive of the locomotive and used for receiving radar echo signals reflected in front of the locomotive;
the anti-collision processor is respectively connected with the radar transmitter and the radar receiver, and processes the radar echo signal by adopting the train anti-collision method, finds out obstacles and performs train anti-collision early warning.
The invention has the following beneficial effects:
the method solves the problem of receiving and processing the radar signals in the special environment of the subway tunnel, eliminates interference signals and false targets, and avoids false alarm from influencing train advancing.
The invention does not need to arrange trackside equipment, has low cost and convenient maintenance, can measure the distance between the subway train and the object in front, makes early warning and prevents the train from colliding with obstacles.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a flowchart of a train collision avoidance method according to a first embodiment;
FIG. 2 is a flowchart illustrating a preprocessing method according to one embodiment of the present invention;
FIG. 3 is a flowchart of a training method of an SVM model according to the first embodiment;
fig. 4 is a connection schematic diagram of the train anti-collision device in the second embodiment;
fig. 5 is a schematic diagram of train deployment of the train collision avoidance device in the second embodiment.
Detailed Description
The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and which together with the embodiments of the invention serve to explain the principles of the invention.
The first embodiment,
The embodiment discloses a train collision avoidance method based on millimeter wave radar, as shown in fig. 1, comprising the following steps:
s1, preprocessing a radar echo signal reflected in front of a locomotive of a subway locomotive to obtain a target echo signal;
s2, classifying the target echo signals by adopting a trained SVM model, and filtering false target echo signals to obtain real target echo signals;
and S3, calculating the relative distance and speed between the subway locomotive head and the target object according to the real target echo signal, judging whether the relative distance and speed exceed an anti-collision threshold value, and performing train anti-collision early warning if the relative distance and speed exceed the anti-collision threshold value.
As shown in fig. 2, the preprocessing method in step S1 includes:
s101, performing data primary screening on the radar echo signals, and eliminating transverse interference signals;
specifically, in the data preliminary screening, a transverse distance threshold value is set, and radar echo signals with transverse distances exceeding the transverse distance threshold value are rejected.
Preferably, the transverse distance threshold is matched with the width of the subway tunnel, for example, when the width of the subway tunnel is greater than 5 meters, a millimeter wave radar is installed with the center of the train as the origin, and the transverse distance threshold is set to be 2.5 meters, so that radar signals reflected by the wall of the subway tunnel with the abscissa greater than 2.5 meters can be eliminated.
S102, estimating clutter power of a position where a target is located;
the millimeter wave radar is used in a subway tunnel environment, the environment is complex, a radar echo signal comprises a plurality of target units, and the target units comprise target units only containing clutter and target units containing both clutter and target information; estimating clutter power in an echo signal to judge a target unit containing target information, namely estimating the clutter power of a position where a target is located; and when the train travels in the tunnel, the environment is time-varying, so the clutter power is also time-varying.
Specifically, the power of all target units included in the current echo signal is arithmetically averaged to be used as the clutter power of the position where the target is located. Since the arithmetic average is the arithmetic average of the target unit with higher power, which contains both clutter and target information, and the target unit with lower power, which contains only clutter, the clutter power can be used as a power threshold to distinguish whether the target unit contains target information.
And S103, comparing the clutter power value serving as a threshold with the power of the preliminarily screened radar echo signal, and eliminating a target unit only comprising the clutter signal in the radar echo signal to obtain a target echo signal.
Specifically, if the power value of a target unit in the radar echo signal is greater than a threshold value, it is indicated that the target unit of the radar echo contains not only clutter but also target information, and at this time, the amplitude of the target echo signal in the target unit is the square root of the power value; if the power value is smaller than the threshold value, the unit only contains the clutter signals, and the amplitude value of the target unit is set to be 0.
The SVM model adopted in step S2 is a trained SVM model, and as shown in fig. 3, the training method includes the following steps:
1) Constructing a training data set, wherein the training data is a radar echo signal;
specifically, the constructed training data set includes radar return signals collected when the train is running without an obstacle, and radar return signals collected when a specific obstacle is placed in front of the travel of the train.
2) Constructing an SVM classifier;
specifically, the SVM classifier adopts a linear kernel function.
For a given training sample set D = { (x) 1 ,y 1 ),(x 2 ,y 2 ),…,(x m ,y m )},y i ∈{-1,+1};
The classification learning of the embodiment finds a partition hyperplane in the sample space based on the training set D, and separates samples of different classes. In sample space, the hyperplane can be partitioned by the following linear equation w T x + b =0 to describe: wherein ω = (ω) 1 ;ω 2 ;…;ω d ) The direction of the hyperplane is determined for the normal vector, and the distance between the hyperplane and the origin is determined for the displacement term b. The hypothesis hyperplane (ω, b) can correctly classify the training samples, i.e., for (x) i ,y i ) E.g. D, if y i = 1, then there is ω T x i +b>0; if y i If = 1, then there is ω T x i +b<0. Order to
When the following conditions are met:the dividing hyperplane with the maximum interval can be found for classification processing.
3) Preprocessing a training data set to obtain a target echo signal;
specifically, the preprocessing method in step S1 is adopted to process the training data set to obtain the target echo signal included in the training data set.
4) Processing a target echo signal, and extracting a characteristic vector group; sticking a data label of a false target in the target echo signal to be +1, and sticking a data label of a real obstacle to be-1;
specifically, the extracted feature vector group x i Including the relative distance, velocity, and target echo power data of the target.
Wherein, LFMCW (Linear Frequency Modulated Continuous Wave) method can be adopted to extract the distance of the target,
specifically, triangular transformation is performed according to the calculated continuously transmitted millimeter waves to obtain the radar transmission signal and the radar receiving signal, except for a lag time Δ t, the characteristics are the same, and the relation between the lag time Δ t and the relative distance R is as follows: Δ T =2R/c, where c denotes the speed of light, Δ F is the frequency difference of the mixing output, T is the radar scan period, Δ F is the signal bandwidth, so the relative distance is:
the difference of the relative distances measured continuously can obtain the relative speed of the target;
the target echo power data is obtained according to the method in the preprocessing.
5) Extracting the feature vector group x i And corresponding data tag y i Sending the input into an SVM trainer to carry out model training to obtainTrained model parameter normal vector ω = (ω =) 1 ;ω 2 ;…;ω d ) And a displacement term b.
Classifying the real-time acquired target echo signals by the SVM model trained by the method, and filtering false target echo signals to obtain real target echo signals;
and then calculating the relative distance and speed between the subway locomotive head and the target object according to the real target echo signal, judging whether the relative distance and speed exceed an anti-collision threshold value, and if so, performing train anti-collision early warning.
The anti-collision threshold value can be a relative distance threshold value or/and a relative speed threshold value, and when the relative distance between the locomotive head of the train and the obstacle measured by the radar is smaller than the distance threshold value or/and the relative speed is larger than the relative speed threshold value, an early warning is sent out.
Listing that the operation has certain speed requirement, so that the relative distance reflects the time of collision with the target object; meanwhile, because the millimeter wave radar has a certain detection distance, the time of collision with the target object can be judged according to the relative speed; therefore, the condition that the collision occurs in the preset time can be effectively warned by setting the relative distance threshold value or/and the relative speed threshold value.
Compared with the prior art, the train collision avoidance method based on the millimeter wave radar can solve the problem of receiving and processing radar signals in the special environment of the subway tunnel, and can give early warning to obstacles in front of the subway train; interference signals and false targets are removed, and the influence of false alarms on the advancing of the train is avoided; besides, trackside equipment is not required to be arranged, the cost is low, and the maintenance is convenient.
Example II,
The embodiment also discloses a train anti-collision device based on the millimeter wave radar, which comprises a radar transmitter, a radar receiver and an anti-collision processor, as shown in fig. 4;
the radar transmitter is arranged at the locomotive of the train locomotive and used for transmitting millimeter wave radar signals to the front of the locomotive;
the radar receiver is arranged at the locomotive of the locomotive and used for receiving radar echo signals reflected in front of the locomotive;
the anti-collision processor is respectively connected with the radar transmitter and the radar receiver, and the train anti-collision method of the embodiment I is adopted to process the radar echo signals, find out obstacles and start train anti-collision measures.
The anti-collision processor can adopt a structure of a millimeter wave radar ranging processing module and an upper computer, the millimeter wave radar ranging processing module is connected with the radar receiver, receives radar echo signals and directly transmits the radar echo signals to the upper computer for processing, the relative distance and the relative speed between the radar and a barrier are calculated through echoes, and a train anti-collision measure is started; or the millimeter wave radar ranging processing module locally completes calculation and then uploads the related data to the upper computer. The connection between the millimeter wave radar ranging processing module and the upper computer can be wired, and data and instruction interaction can also be carried out in a wireless communication mode.
As shown in fig. 5, a train deployment schematic diagram of a train collision avoidance device is shown, wherein a train runs in a tunnel along a track direction, a millimeter wave radar transmitter located at a train head is installed at the train head and transmits a millimeter wave beam forward, the millimeter wave beam is reflected by a barrier to form an echo, the millimeter wave radar receives the echo, a millimeter wave radar ranging processing module analyzes and processes the echo, a false target is removed, a real target is calculated, the relative distance, the relative speed and the relative angle between the millimeter wave radar and a target object are calculated, results are packaged and sent to an upper computer through a CAN bus, and the upper computer sends out an early warning if the relative distance is too small or the relative speed is too large.
Compared with the prior art, the beneficial effects of the train anticollision device based on millimeter wave radar that this embodiment provided are the same basically with the beneficial effects that embodiment one provided, and it is not repeated here.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (2)
1. A train collision avoidance method based on millimeter wave radar is characterized by comprising the following steps:
preprocessing a radar echo signal reflected in front of a subway locomotive head to obtain a target echo signal;
the pretreatment method comprises the following steps:
performing data primary screening on the radar echo signals, and eliminating transverse interference signals;
in the data preliminary screening, setting a transverse distance threshold value, and rejecting radar echo signals of which the transverse distance exceeds the transverse distance threshold value;
the transverse distance threshold is matched with the width of the subway tunnel;
estimating a clutter power value of the position where the target is located;
the radar echo signal comprises a plurality of target units, wherein the target units comprise target units only containing clutter and target units containing both the clutter and target information; when the clutter power of the position where the target is located is estimated, the arithmetic mean value of the power of all target units included in the current echo signal is taken as the clutter power of the position where the target is located;
comparing the clutter power value serving as a threshold value with the power of the radar echo signal after preliminary screening, and eliminating target units only comprising clutter signals in the radar echo signal to obtain a target echo signal;
if the power value of the target unit in the radar echo signal is larger than the threshold value, the target unit of the radar echo is indicated to contain not only the clutter but also target information, and the amplitude of the target echo signal in the target unit is the square root of the power value; if the power value is smaller than the threshold value, the unit only contains the clutter signals, and the amplitude value of the target unit is set to be 0; the target information comprises real obstacle information and false target information;
classifying the target echo signals by adopting a trained SVM model, and filtering false target echo signals to obtain real target echo signals;
the SVM model training method comprises the following steps:
1) Constructing a training data set, wherein the training data is a radar echo signal;
the constructed training data set comprises radar echo signals collected when a train runs under the condition that no obstacle exists, and radar echo signals collected when a specific obstacle is placed in front of the running train;
2) Constructing an SVM classifier;
the SVM classifier adopts a linear kernel function;
d = { (x) for a given training sample set 1 ,y 1 ),(x 2 ,y 2 ),…,(x m ,y m )},y i ∈{-1,+1};
The classification learning finds a division hyperplane in a sample space based on a training set D, and samples of different classes are separated; in sample space, the hyperplane can be partitioned by the following linear equation w T x + b =0 to describe: wherein ω = (ω) 1 ;ω 2 ;…;ω d ) The direction of the hyperplane is determined for the normal vector, the distance between the hyperplane and the origin is determined for the displacement item b, and obviously, the division of the hyperplane can be determined by the normal vector and the displacement; the hypothesis hyperplane (ω, b) can correctly classify the training samples, i.e., for (x) i ,y i ) E is D, if y i = 1, then there is ω T x i +b>0; if y i If = 1, then there is ω T x i +b<0. Order to
When the following conditions are met:the division hyperplane with the maximum interval can be found for classification processing;
3) Preprocessing a training data set to obtain a target echo signal;
specifically, the preprocessing method is adopted to process the training data set to obtain a target echo signal included in the training data set;
4) Processing a target echo signal, and extracting a characteristic vector group; the data label of the false target in the target echo signal is pasted as +1, and the data label of the real barrier is pasted as-1;
the extracted feature vector group comprises the relative distance and speed of the target and target echo power data;
specifically, triangular transformation is performed according to the calculated continuously transmitted millimeter waves to obtain radar transmission signals and radar reception signals, except for a lag time Δ t, the characteristics are the same, and the relation between the lag time Δ t and the relative distance R is as follows: Δ T =2R/c, where c denotes the speed of light, Δ F is the frequency difference of the mixing output, T is the radar scan period, Δ F is the signal bandwidth, so the relative distance is:
continuously measuring the difference of the relative distances to obtain the relative speed of the target;
obtaining target echo power data according to a method in preprocessing;
5) The extracted feature vector group and the corresponding data labels are used as input and sent to an SVM trainer for model training; obtaining a trained model parameter normal vector omega = (omega) 1 ;ω 2 ;…;ω d ) And a displacement term b;
classifying the target echo signals acquired in real time by adopting a trained SVM model, and filtering false target echo signals to obtain real target echo signals;
calculating the relative distance and speed between the subway locomotive head and the target object according to the real target echo signal, judging whether the relative distance and speed exceed an anti-collision threshold value, and if so, performing train anti-collision early warning;
the anti-collision threshold value is a relative distance threshold value and a relative speed threshold value, and when the relative distance between the locomotive head of the train and the obstacle measured by the radar is smaller than the distance threshold value and the relative speed is larger than the relative speed threshold value, an early warning is sent out.
2. A train anti-collision device based on a millimeter wave radar is characterized by comprising a radar transmitter, a radar receiver and an anti-collision processor;
the radar transmitter is arranged at the locomotive of the train locomotive and used for transmitting radar signals to the front of the locomotive;
the radar receiver is arranged at the locomotive of the locomotive and used for receiving radar echo signals reflected in front of the locomotive;
the anti-collision processor is respectively connected with the radar transmitter and the radar receiver, and the train anti-collision method according to claim 1 is adopted to process the radar echo signals, find obstacles and perform train anti-collision early warning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911309157.1A CN111098890B (en) | 2019-12-18 | 2019-12-18 | Train collision avoidance method and device based on millimeter wave radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911309157.1A CN111098890B (en) | 2019-12-18 | 2019-12-18 | Train collision avoidance method and device based on millimeter wave radar |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111098890A CN111098890A (en) | 2020-05-05 |
CN111098890B true CN111098890B (en) | 2023-04-07 |
Family
ID=70423611
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911309157.1A Active CN111098890B (en) | 2019-12-18 | 2019-12-18 | Train collision avoidance method and device based on millimeter wave radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111098890B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112793628B (en) * | 2021-02-05 | 2023-04-21 | 北京千驷驭电气有限公司 | Train operation safety assessment method and device |
CN114802354B (en) * | 2022-05-30 | 2024-08-30 | 中铁电气化局集团第三工程有限公司 | Intrusion detection system, method and early warning system for track construction section |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5764162A (en) * | 1995-07-20 | 1998-06-09 | Union Switch & Signal Inc. | Micropower impulse radar based wheel detector |
CN109633652A (en) * | 2019-01-14 | 2019-04-16 | 长沙莫之比智能科技有限公司 | Robot obstacle-avoiding system and its application method based on millimetre-wave radar |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101533092B (en) * | 2009-01-09 | 2012-12-05 | 中国人民解放军空军雷达学院 | Method for synchronously inhibiting radar clutter and multiple interferences based on power distinction |
CN101872014A (en) * | 2010-06-18 | 2010-10-27 | 深圳麒景雷信科技有限公司 | Target signal detection method based on improved COSGO (Average Order Statistics Greatest of)-CFAR (Constant False Alarm Rate) |
CN102707285A (en) * | 2012-05-28 | 2012-10-03 | 河海大学 | Method for detecting frequency domain constant false alarm of vehicle-mounted millimeter-wave anti-collision radar system |
CN103235310B (en) * | 2013-03-26 | 2014-11-05 | 北京理工雷科电子信息技术有限公司 | Vehicular millimeter-wave train collision avoidance radar system |
CN104345305A (en) * | 2013-07-30 | 2015-02-11 | 北京敏视达雷达有限公司 | Ground clutter residual filtering method |
CN103576155A (en) * | 2013-11-12 | 2014-02-12 | 河海大学 | Microwave radar type automobile anti-collision early warning system |
CN103809161B (en) * | 2014-01-09 | 2018-09-28 | 中国人民解放军海军航空大学 | Anti- range gate deception+SOJ composite interferences the method for radar fence |
CN104076362B (en) * | 2014-07-07 | 2016-08-24 | 芜湖航飞科技股份有限公司 | A kind of railroad train runs security radar |
CN104199007B (en) * | 2014-09-09 | 2016-10-12 | 西安电子科技大学 | Radar Area Objects discrimination method in a distributed manner based on arest neighbors oneclass classification device |
SE1551370A1 (en) * | 2015-10-22 | 2017-02-07 | Uniquesec Ab | Testing method with virtual radar signatures for an automotive safety radar system |
CN107064894A (en) * | 2017-01-11 | 2017-08-18 | 南京御达电信息技术有限公司 | A kind of clutter suppression method based on deep learning |
CN107024682B (en) * | 2017-03-30 | 2020-06-23 | 安徽工程大学 | Target detection method based on adaptive elimination algorithm |
CN107300698B (en) * | 2017-08-21 | 2020-04-24 | 哈尔滨工业大学 | Radar target track starting method based on support vector machine |
CN107807355A (en) * | 2017-10-18 | 2018-03-16 | 轩辕智驾科技(深圳)有限公司 | It is a kind of based on infrared and millimetre-wave radar technology vehicle obstacle-avoidance early warning system |
CN109633653A (en) * | 2019-01-28 | 2019-04-16 | 上海通轩电子科技有限公司 | A kind of radar anti-interference method, device, unjammable radar and storage medium |
CN110362077B (en) * | 2019-07-03 | 2020-09-04 | 上海交通大学 | Unmanned vehicle emergency hedge decision making system, method and medium |
CN110443138B (en) * | 2019-07-05 | 2021-10-19 | 东南大学 | Joint SVM and CNN multi-target classification method based on vehicle-mounted millimeter wave radar |
CN110320509A (en) * | 2019-07-29 | 2019-10-11 | 江苏必得科技股份有限公司 | A kind of millimetre-wave radar object detection method and system |
-
2019
- 2019-12-18 CN CN201911309157.1A patent/CN111098890B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5764162A (en) * | 1995-07-20 | 1998-06-09 | Union Switch & Signal Inc. | Micropower impulse radar based wheel detector |
CN109633652A (en) * | 2019-01-14 | 2019-04-16 | 长沙莫之比智能科技有限公司 | Robot obstacle-avoiding system and its application method based on millimetre-wave radar |
Non-Patent Citations (1)
Title |
---|
多传感器数据融合在飞机地面防撞中的应用;郭晓静;《测控技术》(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111098890A (en) | 2020-05-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106706334B (en) | Method and field for testing capability of automatic driving vehicle to avoid approaching vehicle | |
CN102439644B (en) | Vehicle surrounding monitor device and method for monitoring surroundings used for vehicle | |
CN110969855A (en) | Traffic flow monitoring system based on millimeter wave radar | |
KR102013224B1 (en) | Autonomous Emergencyy Braking System and Controlling Method Thereof | |
CN111098890B (en) | Train collision avoidance method and device based on millimeter wave radar | |
US9812008B2 (en) | Vehicle detection and tracking based on wheels using radar and vision | |
CN110596731A (en) | Active obstacle detection system and method for metro vehicle | |
US6356228B1 (en) | Automatic airport information transmitting apparatus | |
JP3520326B2 (en) | Running vehicle detection method using millimeter wave radar | |
CN109367529B (en) | Millimeter wave radar combined installation structure and virtual tunnel construction and obstacle judgment method | |
CN115257784A (en) | Vehicle-road cooperative system based on 4D millimeter wave radar | |
CN112660279A (en) | Electric vehicle driving warning system and method, millimeter wave radar system and electric vehicle | |
CN117706557A (en) | Ship collision avoidance early warning system based on navigation radar | |
EP3176603A1 (en) | A vehicle radar system | |
CN114212045A (en) | Method and system for detecting passengers in vehicle | |
US20210215821A1 (en) | Method and apparatus for radar infrastructure | |
EP3422046B1 (en) | A system for enhanced object tracking | |
CN109398367A (en) | A kind of Vehicular intelligent anti-collision early warning system based on ultrasound | |
CN113221638A (en) | Vehicle target sensing method and system | |
WO2020154962A1 (en) | Target credibility determination method, target recognition method and system, vehicle, and storage medium | |
CN214028970U (en) | Electric vehicle driving warning system and electric vehicle | |
KR102622937B1 (en) | Pedestrian Accident Prevention System and Method | |
US11300660B2 (en) | Determining relative velocity in a vehicle radar system | |
CN112114590A (en) | Unmanned aerial vehicle automated inspection system of dodging obstacle | |
Nair et al. | Dual Radar System for Predicting Collisions at Uncontrolled Intersections |
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 |