CN109541601A - Differentiating obstacle and its detection method based on millimeter wave - Google Patents
Differentiating obstacle and its detection method based on millimeter wave Download PDFInfo
- Publication number
- CN109541601A CN109541601A CN201811372342.0A CN201811372342A CN109541601A CN 109541601 A CN109541601 A CN 109541601A CN 201811372342 A CN201811372342 A CN 201811372342A CN 109541601 A CN109541601 A CN 109541601A
- Authority
- CN
- China
- Prior art keywords
- data
- obstacle
- target
- module
- barrier
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 230000004888 barrier function Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000000523 sample Substances 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 abstract description 2
- 235000013350 formula milk Nutrition 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- G01S13/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S13/60—Velocity or trajectory determination systems; Sense-of-movement determination systems wherein the transmitter and receiver are mounted on the moving object, e.g. for determining ground speed, drift angle, ground track
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a kind of differentiating obstacle and its detection method based on millimeter wave, the system is by Subscriber Interface Module SIM, data reception module, data preprocessing module, obstacle probe module composition, automobile general control system is connected by Subscriber Interface Module SIM, by data reception module receive front-end collection to data information, then it adjusts the distance by data preprocessing module, the information such as position are filtered out and are converted, extract validity feature, corresponding model is matched after identifying to the data fuzziness after processing, and then judge barrier, obstacle identity is finally sent to automotive control system, early warning is made to the target;The present invention can not only filter out false target, and the barrier of potential danger also can be efficiently detected under complex environment, can accomplish data fusion with other sensors;The stability that algorithm calculates the system that improves is carried out to multiple features, the high product advantage of miniaturization, low-power consumption, integrated level facilitates the system design of pilotless automobile.
Description
Technical field
The invention belongs to intelligent vehicles to assist driving technology field, and in particular to a kind of barrier knowledge based on millimeter wave
Other system and its detection method further relate to a kind of detection method of differentiating obstacle based on millimeter wave.
Background technique
Obstacle recognition is the important content that intelligent vehicle auxiliary drives research field, can be improved automobile perception environment
Ability, be directly related to intelligent network connection automobile validity and personnel safety.Current main detection mode has based on thunder
It is detected up to sensor with the obstacle recognition based on machine vision.Wherein millimetre-wave radar has excellent detection performance, to ring
The advantages such as the adaptable, strong antijamming capability in border, the letters such as angle, distance, speed based on this technical principle detection objects ahead
Breath, analyzes reflected signal, and disturbance in judgement object form is to effectively avoid collision.
There is the following in existing obstacle recognition detection system:
1, the detection of obstacles of view-based access control model is that the matching by obtaining road scene image, between image is more complicated, real
When property is poor;Due to the requirement of real-time of detection of obstacles, classical matching algorithm pixel-by-pixel is difficult to meet the requirements;
It 2, is that the detection of barrier, laser are realized by mobile lidar based on the detection of obstacles of laser radar
Radar Technology has bulky and heavy, need often to debug in use, the disadvantages of equipment is expensive, and laser radar issues
Laser beam has higher-energy, using being difficult to popularize on automobile;
Thus it is proposed that a kind of differentiating obstacle and its detection method based on millimeter wave.
Summary of the invention
The purpose of the present invention is to provide a kind of differentiating obstacle and its detection method based on millimeter wave, with solution
Matching between image certainly mentioned above in the background art is more complicated, real-time is poor;Since the real-time of detection of obstacles is wanted
It asks, classical matching algorithm pixel-by-pixel is difficult to meet the requirements;Laser radar technique have it is bulky and heavy, needed in use
The laser beam that often debugging, the disadvantages of equipment is expensive, and laser radar issue has higher-energy, using being difficult on automobile
Universal problem a kind of can real-time and accurately the pedestrian to front side, vehicle and other possible barriers be carried out with providing
The system effectively identified.
To achieve the above object, the invention provides the following technical scheme: the differentiating obstacle based on millimeter wave, is somebody's turn to do
System is made of Subscriber Interface Module SIM, data reception module, data preprocessing module, obstacle probe module, and feature exists
In:
Subscriber Interface Module SIM: connection automobile general control system;
Data reception module: the data information that front-end collection arrives is received;
Data preprocessing module: adjusting the distance, the front-end informations such as position are filtered out and converted, and validity feature is extracted, right
Corresponding model is matched after data fuzziness identification after processing;
Obstacle probe module: judging barrier, and the obstacle identity of judgement is finally sent to automotive control system,
Early warning is made to the target.
The invention also discloses a kind of detection methods of differentiating obstacle based on millimeter wave, comprise the following steps:
Step 1: detection zone is arranged in information collection in front of system, will test scope limitation in specific region,
Target except detection zone without computational discrimination,;
Step 2: filtering processing, millimetre-wave radar is in effective detection zone, and wave beam carries out periodic scan, return
Data are distance, speed, the angle of corresponding each target cycle point, are realized using cluster algorithm by same object
Point mark be attributed to one kind, and then the target detection that will likely become barrier identifies;
Step 3: extracting target component, carries out preresearch estimates for the size of barrier.
Step 4: fuzziness identification realizes the estimation to target by triangle fuzziness recognizer.
Step 5: barrier determines, by the target discrimination to estimate obstacle identity after barrier, thus will
As a result it is transferred to automotive control system.
As a preferred technical solution of the invention, in the step 1, data reception module receives number of echoes
According to including speed, distance, angle, RCS value.
As a preferred technical solution of the invention, in the step 1, the scan period frequency of radar is
50Hz。
As a preferred technical solution of the invention, in the step 2, calculation formula are as follows:
Compared with prior art, the beneficial effects of the present invention are:
(1) the present invention is based on the differentiating obstacle of millimeter wave and detection methods, can not only filter out false target,
And the barrier of potential danger also can be efficiently detected under complex environment, it can accomplish data fusion with other sensors;
(2) present invention carries out the stability that algorithm calculates the system that improves to multiple features, and miniaturization, integrates low-power consumption
Spending high product advantage facilitates the system design of pilotless automobile.
Detailed description of the invention
Fig. 1 is system block diagram of the invention;
Fig. 2 is flow chart of the invention;
Fig. 3 is the flow chart of cluster algorithm of the present invention;
Fig. 4 is the flow chart of step three of the invention;
Fig. 5 is the coordinate diagram of step four of the invention;
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
Fig. 1 and Fig. 2 are please referred to, the present invention provides a kind of technical solution: the differentiating obstacle based on millimeter wave, it should
System is made of Subscriber Interface Module SIM, data reception module, data preprocessing module, obstacle probe module, and feature exists
In:
Subscriber Interface Module SIM: connection automobile general control system;
Data reception module: the data information that front-end collection arrives is received;
Data preprocessing module: adjusting the distance, the front-end informations such as position are filtered out and converted, and validity feature is extracted, right
Corresponding model is matched after data fuzziness identification after processing;
Obstacle probe module: judging barrier, and the obstacle identity of judgement is finally sent to automotive control system,
Early warning is made to the target.
A kind of detection method of the differentiating obstacle based on millimeter wave, comprises the following steps:
Step 1: detection zone is arranged in information collection in front of system, will test scope limitation in specific region,
Target except detection zone is without computational discrimination.The scan period frequency of radar is 50Hz, i.e., does not stop for antenna 20 times per second
Scanning, data reception module receive echo data include speed, distance, angle, RCS value;
Step 2: filtering processing, millimetre-wave radar is in effective detection zone, and wave beam carries out periodic scan, return
Data are distance, speed, the angle of corresponding each target cycle point, are realized using cluster algorithm by same object
Point mark be attributed to one kind, and then the target detection that will likely become barrier identifies.
By the distance parameter in same frame radar scanning data by arranging from small to large, adjacent two data point p is calculatedi-1
(xi-1,yi-1) and pi(xi,yi) the distance between di, calculation formula is as follows:
Resulting distance between two points d will be calculatediWith the threshold value d of settingtCompare, if di≤dt, then can determine this two o'clock
Belong to same target;If di> dt, then two o'clock is not belonging to same target, the data is updated and reject, until by a frame data
Processing is completed.Finally determine the point data for belonging to same target.
dtThe distance dependent of selection and target away from radar, dt=R*sin λ.λ is the angular resolution of radar, according to frequency
Rate is different, and for resolution ratio between 1 ° -3 °, R can be directly detected the radial distance with target by radar.
After all the points mark for counting the target, the minimum range of the target and maximum distance are calculated into the mesh by formula
Target full-size dmax, dmaxIt will be with the judgement of obstacle identity later
The point mark number m of the target counted on resets threshold value N, the points that the selection of threshold value N and radar receive
According to related, N is the 1/20 of all the points data amount check, and the number that number of targets strong point collects, which is greater than threshold value, can just be determined as target, no
Then, it will be filtered out;
Step 3: target component is extracted, the small barrier having has no effect on this vehicle traveling, for the size of barrier
Preresearch estimates is carried out, according to the RCS sequential value of detections of radar to target, extracts statistical nature, data change is carried out to RCS sequence
It changes.
Detections of radar is to target RCS discrete data { σ1, σ 2 ... σN, enable Δk=σk-σk+1。
The data transformation for mula of RCS is
S=-j ω is taken, is had
It can obtain
If target has a m marks, ω=0,1 ..., m,
By the RCS of the extractable target out of above formula transformation.
Step 4: fuzziness identification realizes the estimation to target by triangle fuzziness recognizer.
A, b, c are coordinate of the vertex in x-axis in above formula, are arranged from small to large for all point data distance parameters of the target
Minimum value, average value, maximum value in column.It is determined as barrier if blur estimation is greater than 0.5;If blur estimation is less than 0.5
Then it is determined as false target, filters out the false target.
Step 5: barrier determines, is foundation d after barrier by the target discriminationmaxWith RCS value to obstacle identity
Estimated, so that result is transferred to automotive control system, in obstacle probe module, by following table to the target
Maximum width and RCS value carry out Model Matching.
Pedestrian | Car | Motor bus | |
dmax | 0.1~0.8 | 1.7~5.0 | 2.5~12.0 |
RCS | - 10~15 | 5~30 | 10~40 |
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, may be used
It a variety of to the progress of these embodiments can be changed without departing from the principles and spirit of the present invention with understanding, modified, replaced
It changes and modification, the scope of the present invention is defined by the appended.
Claims (5)
1. the differentiating obstacle based on millimeter wave, the system is by Subscriber Interface Module SIM, data reception module, data prediction
Module, obstacle probe module composition, it is characterised in that:
Subscriber Interface Module SIM: connection automobile general control system;
Data reception module: the data information that front-end collection arrives is received;
Data preprocessing module: adjusting the distance, the front-end informations such as position are filtered out and converted, and validity feature is extracted, to processing
Corresponding model is matched after data fuzziness identification afterwards;
Obstacle probe module: judging barrier, and the obstacle identity of judgement is finally sent to automotive control system, to the mesh
Mark makes early warning.
2. the detection method of the differentiating obstacle according to claim 1 based on millimeter wave, it is characterised in that: include
Following steps:
Step 1: detection zone is arranged in information collection in front of system, will test scope limitation in specific region, is detecting
Target except region without computational discrimination,;
Step 2: filtering processing, for millimetre-wave radar in effective detection zone, wave beam carries out periodic scan, the data of return
For distance, speed, the angle of corresponding each target cycle point, realized using cluster algorithm by the point mark of same object
It is attributed to one kind, and then the target detection that will likely become barrier identifies;
Step 3: extracting target component, carries out preresearch estimates for the size of barrier.
Step 4: fuzziness identification realizes the estimation to target by triangle fuzziness recognizer.
Step 5: barrier determines, which after barrier, estimates obstacle identity, thus by result
It is transferred to automotive control system.
3. the detection method of the differentiating obstacle according to claim 2 based on millimeter wave, it is characterised in that: described
In step 1, it includes speed, distance, angle, RCS value that data reception module, which receives echo data,.
4. the detection method of the differentiating obstacle according to claim 2 based on millimeter wave, it is characterised in that: described
In step 1, the scan period frequency of radar is 50Hz.
5. the detection method of the differentiating obstacle according to claim 2 based on millimeter wave, it is characterised in that: described
In step 2, calculation formula are as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811372342.0A CN109541601A (en) | 2018-11-16 | 2018-11-16 | Differentiating obstacle and its detection method based on millimeter wave |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811372342.0A CN109541601A (en) | 2018-11-16 | 2018-11-16 | Differentiating obstacle and its detection method based on millimeter wave |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109541601A true CN109541601A (en) | 2019-03-29 |
Family
ID=65848061
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811372342.0A Pending CN109541601A (en) | 2018-11-16 | 2018-11-16 | Differentiating obstacle and its detection method based on millimeter wave |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109541601A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110118966A (en) * | 2019-05-28 | 2019-08-13 | 长沙莫之比智能科技有限公司 | Personnel's detection and number system based on millimetre-wave radar |
CN111273268A (en) * | 2020-01-19 | 2020-06-12 | 北京百度网讯科技有限公司 | Obstacle type identification method and device and electronic equipment |
CN112455503A (en) * | 2019-09-09 | 2021-03-09 | 中车株洲电力机车研究所有限公司 | Train positioning method and device based on radar |
CN113435230A (en) * | 2020-03-23 | 2021-09-24 | 中国电信股份有限公司 | Abnormal area detection method, device, system and computer readable storage medium |
CN113778084A (en) * | 2021-08-30 | 2021-12-10 | 普达迪泰(天津)智能装备科技有限公司 | Complex grassland environment intelligent obstacle avoidance system based on multispectral detection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077601A (en) * | 2014-07-08 | 2014-10-01 | 中国航空无线电电子研究所 | Method for carrying out synthetic target recognition through information of different types |
CN106291503A (en) * | 2016-08-31 | 2017-01-04 | 西南交通大学 | A kind of radar-probing system Density Clustering method for early warning |
CN107015228A (en) * | 2016-11-15 | 2017-08-04 | 财团法人车辆研究测试中心 | The Environment identification system of automobile-used millimetre-wave radar |
CN107966700A (en) * | 2017-11-20 | 2018-04-27 | 天津大学 | A kind of front obstacle detecting system and method for pilotless automobile |
-
2018
- 2018-11-16 CN CN201811372342.0A patent/CN109541601A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077601A (en) * | 2014-07-08 | 2014-10-01 | 中国航空无线电电子研究所 | Method for carrying out synthetic target recognition through information of different types |
CN106291503A (en) * | 2016-08-31 | 2017-01-04 | 西南交通大学 | A kind of radar-probing system Density Clustering method for early warning |
CN107015228A (en) * | 2016-11-15 | 2017-08-04 | 财团法人车辆研究测试中心 | The Environment identification system of automobile-used millimetre-wave radar |
CN107966700A (en) * | 2017-11-20 | 2018-04-27 | 天津大学 | A kind of front obstacle detecting system and method for pilotless automobile |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110118966A (en) * | 2019-05-28 | 2019-08-13 | 长沙莫之比智能科技有限公司 | Personnel's detection and number system based on millimetre-wave radar |
CN112455503A (en) * | 2019-09-09 | 2021-03-09 | 中车株洲电力机车研究所有限公司 | Train positioning method and device based on radar |
CN111273268A (en) * | 2020-01-19 | 2020-06-12 | 北京百度网讯科技有限公司 | Obstacle type identification method and device and electronic equipment |
CN111273268B (en) * | 2020-01-19 | 2022-07-19 | 北京百度网讯科技有限公司 | Automatic driving obstacle type identification method and device and electronic equipment |
CN113435230A (en) * | 2020-03-23 | 2021-09-24 | 中国电信股份有限公司 | Abnormal area detection method, device, system and computer readable storage medium |
CN113435230B (en) * | 2020-03-23 | 2024-03-15 | 中国电信股份有限公司 | Abnormal region detection method, device, system and computer readable storage medium |
CN113778084A (en) * | 2021-08-30 | 2021-12-10 | 普达迪泰(天津)智能装备科技有限公司 | Complex grassland environment intelligent obstacle avoidance system based on multispectral detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109541601A (en) | Differentiating obstacle and its detection method based on millimeter wave | |
Lim et al. | Radar and camera early fusion for vehicle detection in advanced driver assistance systems | |
CN107609522B (en) | Information fusion vehicle detection system based on laser radar and machine vision | |
CN111369541B (en) | Vehicle detection method for intelligent automobile under severe weather condition | |
CN110979321B (en) | Obstacle avoidance method for unmanned vehicle | |
US9429650B2 (en) | Fusion of obstacle detection using radar and camera | |
CN102765365B (en) | Pedestrian detection method based on machine vision and pedestrian anti-collision warning system based on machine vision | |
EP1796043B1 (en) | Object detection | |
CN113156421A (en) | Obstacle detection method based on information fusion of millimeter wave radar and camera | |
CN104237881B (en) | FMCW anti-collision radar multi-target detecting and tracking system and method | |
CN107991671A (en) | A kind of method based on radar data and vision signal fusion recognition risk object | |
CN110609274B (en) | Distance measurement method, device and system | |
CN113850102B (en) | Vehicle-mounted vision detection method and system based on millimeter wave radar assistance | |
CN109541583A (en) | A kind of leading vehicle distance detection method and system | |
CN107942329B (en) | Method for detecting sea surface ship target by maneuvering platform single-channel SAR | |
CN106683530A (en) | Computerized judging system and method based on three-dimensional laser vision and high-precision lane model | |
CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
CN110379178A (en) | Pilotless automobile intelligent parking method based on millimetre-wave radar imaging | |
CN110659552B (en) | Tramcar obstacle detection and alarm method | |
CN113848545B (en) | Fusion target detection and tracking method based on vision and millimeter wave radar | |
CN109696676B (en) | Effective obstacle target determination method and device and vehicle | |
CN111123262B (en) | Automatic driving 3D modeling method, device and system | |
CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
CN106803262A (en) | The method that car speed is independently resolved using binocular vision | |
CN116699602A (en) | Target detection system and method based on millimeter wave radar and camera fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190329 |