CN107826115A - A kind of automobile recognition methods - Google Patents
A kind of automobile recognition methods Download PDFInfo
- Publication number
- CN107826115A CN107826115A CN201711017924.2A CN201711017924A CN107826115A CN 107826115 A CN107826115 A CN 107826115A CN 201711017924 A CN201711017924 A CN 201711017924A CN 107826115 A CN107826115 A CN 107826115A
- Authority
- CN
- China
- Prior art keywords
- barrier
- automobile
- dynamic
- motion state
- environmental information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a kind of automobile recognition methods, including:Laser radar obtains the environmental information on periphery, and the environmental information is modeled, the barrier feature of analysis modeling, monitoring is tracked to barrier, according to the feature of barrier, changes the motion state of automobile.The embodiment of the present invention can carry out tracking and monitoring in real time to barrier, so as to change vehicle condition accordingly.
Description
Technical field
The present embodiments relate to non-destructive testing technology, more particularly to a kind of unpiloted automobile recognition methods.
Background technology
With the development and expanding economy of reform and opening-up, the auto industry in China is just increased with high speed,
The advance of highway communication cause is greatly facilitated.To come, China will turn highway, railway, aviation cubic network traffic lattice into
Office, highway has accounted for chief component among these.The features such as safety coefficient of highway communication is high, stationarity is strong, adaptability is high.
The development of Domestic Automotive Industry, increasing Automobile Design start to inject new element, by traditional work(of automobile
It can combine with the information technology in modern times, more convenient, safe experience is brought for user.Pilotless automobile is as new
Emerging industry, the brand-new experience of people just is brought with the development of high speed, wherein the identification on pilotless automobile barrier is outstanding
It is the key for concerning pilotless automobile success to be important.The intelligent transportation decision system of complete set needs to perceive nothing
Traffic environment residing for people's car is so as to making correct decisions.Dynamic barrier detecting and tracking of the prior art frequently with geometric properties
Mode, for judging barrier.
However, the recognition methods based on dynamic barrier geometric properties and motion state is influenceed to compare by distance and scanning angle
It is larger, it is impossible to meet the needs of realistic situation, it is necessary to further improve very well, improve object identification rate.For different obstacles
Thing, the reaction that can quickly make.
The content of the invention
The embodiment of the present invention provides a kind of automobile recognition methods, and barrier can be carried out to track and monitor in real time, from
And change vehicle condition accordingly.
The embodiments of the invention provide a kind of automobile recognition methods, including:
Laser radar obtains the environmental information on periphery;
The environmental information is modeled;
The barrier feature of analysis modeling;
Monitoring is tracked to barrier;
According to the feature of barrier, change the motion state of automobile;
Preferably, the laser radar is arranged on the front portion of the headstock of automobile;
Preferably, described laser radar is four line laser radars.
Preferably, the barrier feature of the analysis analysis modeling, the dynamic barrier in barrier and list is carried out
Matching, updates the motion state of dynamic barrier or obtains new barrier;
Preferably, it is described to be matched barrier with the dynamic barrier in list, if be repeatedly not detected by
The dynamic barrier, the dynamic barrier is rejected from list;
Preferably, the motion state of the renewal dynamic barrier, using Kalman filter to barrier motion state
Estimated;
Preferably, the laser radar obtains the environmental information on periphery, and the environmental information is included according to arranged clockwise
Laser point data, each point includes angle, distance and reflected impulse width information;
Preferably, described to be modeled the environmental information, the modeling type includes frame model or point model.This hair
Bright embodiment can carry out tracking and monitoring in real time to barrier, so as to change vehicle condition accordingly.
Brief description of the drawings
Fig. 1 is the flow chart of automobile identification provided in an embodiment of the present invention;
Embodiment
For make present invention solves the technical problem that, the technical scheme that uses and the technique effect that reaches it is clearer, below
The technical scheme of the embodiment of the present invention will be described in further detail with reference to accompanying drawing, it is clear that described embodiment is only
It is part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those skilled in the art exist
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is the flow chart of automobile identification provided in an embodiment of the present invention
For unmanned, the dynamic barrier monitoring and tracking method false drop rate based on geometric properties is higher, dynamic
The recognition methods of barrier geometric properties and motion state is influenceed bigger by distance and scanning angle, can not meet actual traffic
The requirement of scene application.For these deficiency, the present invention propose a kind of dynamic disorder analyte detection based on multi-feature fusion with
Tracking and the military recognition methods of dynamic Zhao love based on space-time characteristic vector.
As shown in figure 1, step S101 sends laser detection signal using laser radar, the environmental information on periphery is obtained.Make
The information of environment is obtained with the line laser radars of IBEO LUX2010 tetra- installed in automobile forefront, compared to 3-dimensional laser radar,
Its scan period is shorter, and detecting distance is farther, more to obtain the geometric profile information of barrier, due to small volume, may be used also
To be embeddedly arranged among car body.Four line laser radars have 4 scanning slices, and the angle between every layer is 0.8 °, in frequency
When being arranged to 12.5Hz, its sensor angular resolution is 0.25 °, can effectively scan vehicle front angle in the direction of the clock
The sector region for being 200m for 100 °, distance, position of the wealthy barrier of data class in polar coordinate system of laser radar output with
And echo impulse width value.Step S102, after the laser intelligence of transmitting detects barrier, return to detecting system, extraction barrier
Hinder thing information.
Step S103, the information of barrier is modeled processing.Dynamic disorder analyte detection is divided into barrier with tracking and built
Mould and the step of detecting and tracking two.From laser data extract barrier feature, then merge obtained by feature establish frame model or
Point model.Barrier is represented using frame model, the real-time of dynamic disorder analyte detection identification can be increased.Laser radar data bag
Include the laser point data according to arranged clockwise, laser spots be subjected to cluster segmentation, wherein each point include angle, distance and
Reflected impulse width information.Wherein reflected impulse width is relevant with surface extra coarse degree with color, the material of barrier, difference barrier
Hinder pulse width values corresponding to thing to have very big difference, can be used for the matching association of barrier.
Next, carry out step S104, the information of analysis modeling.By barrier and the dynamic barrier in storage list
Prediction result is matched, and is updated the motion state of dynamic barrier or is obtained new dynamic barrier, then passes through filter
System excludes the dynamic barrier for the condition that is unsatisfactory for, and finally predicts that the state of dynamic barrier carries out the matching of next round, uses
Kalman filter estimates that barrier motion state barrier state includes position, the direction of motion and movement velocity.
Finally perform step S105, according to detect barrier information, in time change automobile motion state.
The embodiment of the present invention can carry out tracking and monitoring in real time to barrier, so as to change vehicle condition accordingly.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (8)
- A kind of 1. automobile recognition methods, it is characterised in that including:Laser radar launches laser signal;Obtain the environmental information on periphery;The environmental information is modeled;The barrier feature of analysis modeling;Monitoring is tracked to barrier;According to the feature of barrier, change the motion state of automobile.
- 2. the method as described in claim 1, it is characterised in that the laser radar is arranged on the front portion of the headstock of automobile.
- 3. the method as described in claim 1, it is characterised in that described laser radar is four line laser radars.
- 4. the method as described in claim 1, it is characterised in that the barrier feature of the analysis analysis modeling, by barrier Matched with the dynamic barrier in list, update the motion state of dynamic barrier or obtain new barrier.
- 5. method as claimed in claim 4, it is characterised in that the dynamic barrier progress by barrier and list Match somebody with somebody, if being repeatedly not detected by the dynamic barrier, the dynamic barrier is rejected from list.
- 6. method as claimed in claim 4, it is characterised in that the motion state of the renewal dynamic barrier, use karr Graceful wave filter is estimated barrier motion state.
- 7. the method as described in claim 1, it is characterised in that the laser radar obtains the environmental information on periphery, the ring Environment information includes the laser point data according to arranged clockwise, and each point includes angle, distance and reflected impulse width information.
- 8. the method as described in claim 1, it is characterised in that described to be modeled the environmental information, the modeling class Type includes frame model or point model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711017924.2A CN107826115A (en) | 2017-10-26 | 2017-10-26 | A kind of automobile recognition methods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711017924.2A CN107826115A (en) | 2017-10-26 | 2017-10-26 | A kind of automobile recognition methods |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107826115A true CN107826115A (en) | 2018-03-23 |
Family
ID=61649710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711017924.2A Pending CN107826115A (en) | 2017-10-26 | 2017-10-26 | A kind of automobile recognition methods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107826115A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558838A (en) * | 2018-11-29 | 2019-04-02 | 北京经纬恒润科技有限公司 | A kind of object identification method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103879404A (en) * | 2012-12-19 | 2014-06-25 | 财团法人车辆研究测试中心 | Moving-object-traceable anti-collision warning method and device thereof |
CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
CN107161141A (en) * | 2017-03-08 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Pilotless automobile system and automobile |
CN107161143A (en) * | 2017-05-18 | 2017-09-15 | 江苏大学 | A kind of vehicle active collision avoidance method of use Artificial Potential Field Method |
-
2017
- 2017-10-26 CN CN201711017924.2A patent/CN107826115A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103879404A (en) * | 2012-12-19 | 2014-06-25 | 财团法人车辆研究测试中心 | Moving-object-traceable anti-collision warning method and device thereof |
CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
CN107161141A (en) * | 2017-03-08 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Pilotless automobile system and automobile |
CN107161143A (en) * | 2017-05-18 | 2017-09-15 | 江苏大学 | A kind of vehicle active collision avoidance method of use Artificial Potential Field Method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558838A (en) * | 2018-11-29 | 2019-04-02 | 北京经纬恒润科技有限公司 | A kind of object identification method and system |
CN109558838B (en) * | 2018-11-29 | 2021-02-02 | 北京经纬恒润科技股份有限公司 | Object identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107609522B (en) | Information fusion vehicle detection system based on laser radar and machine vision | |
CN110850403B (en) | Multi-sensor decision-level fused intelligent ship water surface target feeling knowledge identification method | |
EP3283843B1 (en) | Generating 3-dimensional maps of a scene using passive and active measurements | |
CN112101128B (en) | Unmanned formula racing car perception planning method based on multi-sensor information fusion | |
Kim et al. | Sensor fusion algorithm design in detecting vehicles using laser scanner and stereo vision | |
CN111899568B (en) | Bridge anti-collision early warning system, method and device and storage medium | |
CN107341454A (en) | The detection method and device of barrier, electronic equipment in a kind of scene | |
EP3631363A1 (en) | Device and method for detection and localization of vehicles | |
CN110018496A (en) | Obstacle recognition method and device, electronic equipment, storage medium | |
CN103454639A (en) | Apparatus and method for detecting moving-object around vehicle | |
CN109782267B (en) | Track correlation method and vehicle-mounted radar | |
CN111094095B (en) | Method and device for automatically sensing driving signal and vehicle | |
CN101634705B (en) | Method for detecting target changes of SAR images based on direction information measure | |
Hafeez et al. | Insights and strategies for an autonomous vehicle with a sensor fusion innovation: A fictional outlook | |
KR20080075730A (en) | Method for esrimating location using objectionrecognition of a robot | |
CN110007279A (en) | A kind of target visibility judging method based on millimetre-wave radar model | |
CN109633686B (en) | Method and system for detecting ground obstacle based on laser radar | |
CN108027423A (en) | Mine Work machine | |
Yu et al. | An evidential sensor model for velodyne scan grids | |
CN115485698A (en) | Space-time interaction network | |
CN110703272B (en) | Surrounding target vehicle state estimation method based on vehicle-to-vehicle communication and GMPHD filtering | |
CN114547866A (en) | Intelligent detection method for prefabricated part based on BIM-unmanned aerial vehicle-mechanical dog | |
CN107826115A (en) | A kind of automobile recognition methods | |
Gate et al. | Using targets appearance to improve pedestrian classification with a laser scanner | |
Zhao et al. | Moving object classification using horizontal laser scan data |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180323 |
|
RJ01 | Rejection of invention patent application after publication |