CN109359409A - A kind of vehicle passability detection system of view-based access control model and laser radar sensor - Google Patents
A kind of vehicle passability detection system of view-based access control model and laser radar sensor Download PDFInfo
- Publication number
- CN109359409A CN109359409A CN201811290887.7A CN201811290887A CN109359409A CN 109359409 A CN109359409 A CN 109359409A CN 201811290887 A CN201811290887 A CN 201811290887A CN 109359409 A CN109359409 A CN 109359409A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- laser radar
- data
- sensor
- 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 59
- 230000004888 barrier function Effects 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004088 simulation Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 230000001133 acceleration Effects 0.000 claims abstract description 4
- 230000004927 fusion Effects 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 230000036544 posture Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000012706 support-vector machine Methods 0.000 description 9
- 238000013459 approach Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 241000209094 Oryza Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000006748 scratching Methods 0.000 description 2
- 230000002393 scratching effect Effects 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000000280 densification Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The invention discloses the vehicle passability detection systems of a kind of view-based access control model and laser radar sensor, comprising: onboard sensor, data processing module;Wherein, the point cloud data that road is acquired by onboard sensor, carries out the three-dimensional reconstruction of road scene, wherein point cloud data includes the characteristic model data of road, tunnel, barrier;Data processing module establishes space tree for the scene to three-dimensional reconstruction, generates corresponding acceleration collision detection solution procedure;Vehicle is modeled according to trafficability geometric parameter, obtains vehicle rigid body geometric profile model;Vehicle dynamic date is acquired, vehicle movement model is established;According to vehicle movement model and road scene data, vehicle movement simulation track is generated;Along vehicle movement simulation track, real-time perfoming collision detection is calculated, and obtains passability testing result.
Description
Technical field
The present invention relates to vehicle terrain trafficability simulation analysis technical field, espespecially a kind of view-based access control model and laser radar are passed
The vehicle passability detection system of sensor.
Background technique
In vehicle travel process, usually because driver to the location estimation of both sides of the road limit for width barrier inaccuracy and
The accidents such as cause to scratch, can not only bring certain economic loss, it is also desirable to driver take some time place to go director therefore.
Thus, become a kind of today of habit in the use of vehicle, needing a kind of mode can replace driver accurately estimate road two
The position of the wide barrier of lateral confinement, and the generation that corresponding measure prevents from scratching accident is provided.
In the prior art there is only the technology of detection runway mark, camera is generallyd use to realize, specifically, is
Vehicle driving road is imaged using camera, image processing region is set separately in left and right in captured image,
The runway being then based in image processing region identifies to identify lane.Obviously, this to be only using the technology of camera
Detect runway mark, and other object be not processed, had a single function, can not identify both sides of the road limit for width barrier or
Other barriers not can avoid the generation for the accident of scratching certainly yet.
Summary of the invention
To overcome the shortcomings of the prior art, guarantee during fleet carries out, in real time for fleet road is provided can
Passability testing result guarantees the passability of fleet, and present applicant proposes a kind of view-based access control model and laser radar sensors
Vehicle passability detection system.
Specifically, the system includes: onboard sensor, data processing module;Wherein, road is acquired by onboard sensor
Point cloud data, carry out the three-dimensional reconstruction of road scene, wherein point cloud data includes the characteristic model of road, tunnel, barrier
Data;Data processing module establishes space tree for the scene to three-dimensional reconstruction, generates corresponding acceleration collision detection and solved
Journey;Vehicle is modeled according to trafficability geometric parameter, obtains vehicle rigid body geometric profile model;Acquire vehicle power
Data establish vehicle movement model;According to vehicle movement model and road scene data, generates vehicle movement and emulate rail
Mark;Along vehicle movement simulation track, real-time perfoming collision detection is calculated, and obtains passability testing result.
Further, onboard sensor includes: video camera, laser radar.
Further, video camera includes: monocular-camera, forward direction Narrow Field Of Vision, and 300 meters of detecting distance;Binocular vision camera shooting
Machine, forward direction main view is wild, binocular camera, and 200 meters of ranging distance.
Further, laser radar is solid-state laser radar, and forward detection, field angle is not less than 60 ° × 20 °, angular resolution
Rate is not less than 0.2 °.
Further, the point cloud data of road is acquired by onboard sensor, the three-dimensional reconstruction for carrying out road scene includes:
Establish the coordinate system between radar fix system, three-dimensional world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system
Sensing data is carried out Space integration by transformational relation;Measurement point under radar fix system is transformed into camera shooting by coordinate system
Under the corresponding pixel coordinate system of machine, the spatial synchronization of sensing data is carried out.
Further, further includes: the combined calibrating of sensor is carried out using plane target drone;Pass through video camera, laser radar
The data under the multiple postures of scaling board are acquired simultaneously, video camera is demarcated, and are obtained the inside and outside ginseng of video camera, are established video camera seat
Mark system;According to coordinate system, combined calibrating is carried out to laser radar and millimetre-wave radar.
Further, video camera carries out the synchronous of sampling time by time synchronization control circuit with laser radar, establishes
Time unification benchmark and corresponding trigger collection mechanism carry out Fusion in Time, make radar data and camera data in time
It is synchronous.
Further, the Road Detection of this system includes: that successive frame Road Detection limits data processing with method for distinguishing is known
The neighborhood in previous frame data processed result is made, on the basis of establishing road model, kinematics model and kinetic model, meter
It calculates road parameters and carries out passability relative to the location information and motion information of road according to vehicle and detect analog simulation.
The vehicle passability detection system of view-based access control model and laser radar sensor that the application proposes has following effect
Fruit: 1, using be based on combined of multi-sensor information Data Acquisition Design, so that each sensor is had complementary advantages, meet the time and space
Availability requirement, guarantee that system is stable, reliable road scene sensing capability, investigative range can up to 200m, measurement accuracy
Up to ± 10cm, and has night detectivity, measurement road space profiles provide night auxiliary for vehicle and drive function;2, make
It, can real-time detection identification structuring, unstructured (field, bushes, hole with accurate, efficient successive frame Approach for road detection
Depression band) road, extracts the space profiles in road (including tunnel), and provide the size of barrier (including low-lying obstacle);3,
Establish road model, kinematics model and kinetic model, according to vehicle relative to road location information and motion information into
Row passability detects real-time simulated animation, being given by property testing result;Key technology relative maturity involved in the program, can
Row is high, and technical risk is not present.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, not
Constitute limitation of the invention.In the accompanying drawings:
Fig. 1 is the configuration diagram of the combined calibrating that sensor is carried out using plane target drone of one embodiment of the invention.
Fig. 2 is the combined calibrating flow chart of one embodiment of the invention.
Fig. 3 is the sample frequency schematic diagram of one embodiment of the invention.
Fig. 4 is the clock synchronization system configuration diagram of one embodiment of the invention.
Fig. 5 is the Road Detection and identification configuration diagram of one embodiment of the invention.
Fig. 6 is the unstructured road detection algorithm schematic diagram of one embodiment of the invention.
Fig. 7 is the detection of obstacles flow diagram based on image procossing of one embodiment of the invention.
Fig. 8 is the vehicle geometric parameter schematic diagram of one embodiment of the invention.
Specific embodiment
Cooperate schema and presently preferred embodiments of the present invention below, the present invention is further explained to reach predetermined goal of the invention institute
The technological means taken.
The vehicle passability detection system of view-based access control model and laser radar sensor that the application proposes includes: vehicle-mounted biography
Sensor, data processing module, onboard sensor are set on vehicle;Wherein,
The point cloud data that road is acquired by onboard sensor, carries out the three-dimensional reconstruction of road scene, wherein point cloud data
Characteristic model data including road, tunnel, barrier;Data processing module establishes space for the scene to three-dimensional reconstruction
Tree generates corresponding acceleration collision detection solution procedure;Vehicle is modeled according to trafficability geometric parameter, obtains vehicle
Rigid body geometric profile model;Vehicle dynamic date is acquired, vehicle movement model is established;According to vehicle movement model and road
Scene data generates vehicle movement simulation track;Along vehicle movement simulation track, real-time perfoming collision detection is calculated,
Obtain passability testing result.
This system is with the following functions: this system has to the detection of the passabilities such as road ahead, tunnel and judgement,
Testing result is provided for the passability of fleet;The Special zones such as rural road, bushes, hollow area can be passed through by being also equipped with
Property detection and judgement, provide testing result for the passability of fleet;Guarantee that fleet is being not less than 50Km/h travel speed
Under (distance is less than 200 meters between guide car and fleet), have real-time detection ability, and can provide what whether fleet can pass through
Reliable conclusion;Can measurement road space profiles, for vehicle provide night auxiliary drive function;Have real-time detection tunnel face and
The ability of tunnel inner wall situation, and collision preanalysis can be carried out according to large special vehicle, avoid oversize vehicle from being strayed into tunnel
It is difficult to the case where retracting.
Specifically, onboard sensor includes: video camera, laser radar.
Video camera includes:
Monocular-camera, forward direction Narrow Field Of Vision, 300 meters of detecting distance;
Binocular vision video camera, forward direction main view is wild, binocular camera, and 200 meters of ranging distance.
Laser radar is solid-state laser radar, and forward detection, not less than 60 ° × 20 °, angular resolution is not less than field angle
0.2°(H/V)。
To sum up, the technical indicator of this system are as follows: automatic 200 meters of investigative range detects obstacle height automatically, automatic to detect
Barrier width detects in low-lying barrier (e.g., tunnel, low-lying land) automatically, and real-time collision early warning in tunnel, measurement accuracy can reach
To ± 10cm.
Data Fusion technology is utilized in this system, contains Space integration, Fusion in Time, carries out Three-dimensional Gravity with this
It builds.
Space integration: accurate radar fix system, three-dimensional world coordinate system, camera coordinate system, image coordinate system are established
Coordinate transformation relation between pixel coordinate system is the key that the Space integration for realizing multi-sensor data.Radar and vision
Sensor space fusion is exactly that the measured value of different sensors coordinate system is transformed into the same coordinate system.It is realized in this system
In the process, the measurement point under radar fix system is transformed under the corresponding pixel coordinate system of video camera by coordinate system can be realized
The spatial synchronization of multisensor.
As shown in connection with fig. 1, for utilize plane target drone carry out sensor combined calibrating configuration diagram.It is first when calibration
First camera, laser radar acquire the data under the multiple postures of scaling board simultaneously.Then camera is demarcated, is obtained inside and outside camera
Ginseng, establishes camera coordinates system;Combined calibrating finally is carried out to laser radar and millimetre-wave radar, detailed process can refer to Fig. 2
It is shown.
Fusion in Time: radar and visual information are except spatially being merged, it is also necessary to which sensor is in time
Synchronous acquisition realizes the fusion of time.As shown in connection with fig. 3, since the data of radar sensor and visual sensor acquire
Frequency is inconsistent, in order to guarantee the reliability of data, need to establish high-precision time unification benchmark and corresponding trigger collection machine
System guarantees radar data and camera data in time synchronous;The configuration diagram of clock synchronization system can refer to Fig. 4 institute
Show.
Three-dimensional reconstruction: relative to camera, the information of laser radar is relatively sparse, and the depth information that obtain each pixel is non-
It is often difficult.Usually assume that body surface is locally smooth, similar part can be approximately plane, and this compares kiss with actual conditions
It closes.Therefore according to the images like attribute such as color or gray scale, image is split, block of pixels is obtained.These block of pixels with
Body surface is corresponding.Then the block of pixels for possessing radar data to each piece carries out plane estimation, and according to the normal direction of plane
The distance for measuring origin, estimates the depth information of all pixels, to obtain the result of panorama densification three-dimensional reconstruction.
Road Detection and identification are one of core functions of this system.As shown in figure 5, mainly by Road Detection, continuous
Three frame Road Detection, Road recognition and tracking modules are realized.
Data processing can be limited in the neighborhood of previous frame data processed result by successive frame Road Detection, can be significantly improved
The speed of Road Detection reduces hardware and calculates cost, meets requirement of real-time;
Road recognition and tracking system establishes system on the basis of road model, kinematics model and kinetic model
Except road parameters are calculated, it is imitative also passability detection simulation can be carried out relative to the location information and motion information of road according to vehicle
Very;
The above process, which removes, is related to numerous image processing algorithms, it is also necessary to which a large amount of 3D operation supports, and is given full play to this
The effect of Multi-sensor Fusion data.
Test object generally comprises: structured road, unstructured road, tunnel, barrier.
Structured road detection: structured road generally refers to the preferable highway of the structurings such as highway, arterial street.
This kind of road has clearly road mark line, and the background environment of road is relatively simple, and the geometrical characteristic of road is also obvious.
Tie non-structure Road Detection: the Approach for road detection generallyd use based on feature and based on model can be to structuring
Road Detection problem solving.
Unstructured road generally refers to the lower road of the structurings degree such as the non-major trunk roads in city, rural streets, this kind of
Road does not have lane line and clearly road boundary, along with being influenced by shade and water mark etc., road area and non-rice habitats area
Domain is difficult to differentiate between.Weather of changeable road type, complex environment background and shade, water mark and variation etc. all right and wrong
Structured road detects faced difficulty.
For the method that these problems, system use machine learning, use support vector machines (SVM) as classifier to road
Image classification, to extract the road area in image.System chooses road area and non-rice habitats according to the various features of road
Area sample uses support vector machines (SVM) as classifier segmented image.In order to improve the adaptability to environment, examining
The result real-time update training sample and re -training SVM classified in survey according to previous frame.
Due to, to road image classification, needing artificially to select the sample of training SVM in initialization with SVM classifier,
Laser radar data and image co-registration are carried out innovatory algorithm by system, and process is as shown in Figure 6:
Firstly, replacing SVM with fuzzy support vector machine (FSVM), increasing the confidence level of sample in detection and reducing noise
Interference to classification;
Then, road surface is extracted with laser radar, and radar result is mapped on image, it is automatic further according to the result of mapping
Obtain road and non-rice habitats area sample in image.
It needs to carry out Sample Refreshment in the detection process, is according to the association current radar data of previous frame point
Analysis further improves the effect of classification as a result, to select correct sample.
Tunnel and inner wall detection: since the illumination condition in tunnel is poor, camera is difficult to obtain and clearly be imaged enough, and
The accuracy of data acquisition of laser radar is unaffected, and therefore, after vehicle enters tunnel, the data source of detection and identification is to swash
Subject to optical radar sensor.
The tunnel inner wall data of laser radar acquisition itself have more regular chamfered shape.At this point, combining denoising, mould
Type characteristic matching scheduling algorithm can get more accurately tunnel inner wall skeleton pattern, calculate for the detection of subsequent passability.
Detection of obstacles: to a width three-dimensional laser data image, the iteration self-organizing data in pattern recognition theory are utilized
Analytic approach (ISODATA) extracts ground (datum level), judged by seeking in image each point to the range difference of datum level it is recessed,
Convex obstacle object point, and these points are marked, to extract each obstacle target in image.Barrier can be calculated as a result,
Hinder the height and the width and the information such as low-lying barrier of object.
Relative to visual sensor, laser radar has that resolution ratio is lower, detection range is not remote enough.Remote
Workspace, acquisition precision are impacted larger, it may occur however that the mistake of small barrier missing inspection.For this purpose, can merge vision data into
The result that image and laser radar detect is mutually authenticated, reduces the omission factor of system by row detection of obstacles.
Barrier is detected using the method for binocular stereo vision, every a pair of of left images pixel that needs determine is carried out
The calculating of stereoscopic vision obtains its height and depth information.The be above the ground level point of certain threshold value of height value is considered as barrier point,
Height value is considered as low-lying barrier point lower than the point of the certain threshold value in ground.The detection of obstacles and the process of identification and three-dimensional swash
The treatment process of light point cloud data is similar.
Use monocular camera as the means of supplementing out economy, further during detection of obstacles to enhance the reliability of system
The omission factor of reduction system.Monocular camera detection of obstacles realizes that foundation is road ahead using the method based on image procossing
Barrier characteristic information, treatment process is as shown in Figure 7.
Wherein, 1, the conversion of color image to gray level image is image gray processing.
2, median filtering can retain image detail to a certain extent, utilize median filtering method smooth road image.
Sobel operator can enhance the pixel of both sides of edges, and suitable for the vision system by boundary information identification target, edge becomes thick
And it is obvious.
3, by obstacle target present in edge processing road image it sometimes appear that crack, should use at morphology
These cracks are bridged by reason method.
4, finally target obstacle is confined using a rectangle frame, completes the overall process of detection of obstacles.
The main target that this system is realized is to calculate the space profiles of road in real time and match the profile of itself and vehicle, from
And calculate passability testing result.
Wherein, most basic realization element passes through comparison path space profile and vehicle width, height, turning radius etc.
Basic index, judges whether it can pass through.
In addition to this, the trafficability that should also contain broad sense calculates, i.e., is calculated using the passability geometric parameter of vehicle
Automobile, with sufficiently high average speed, passes through the ability of different kinds of roads under certain loading condition.The passability geometric parameters of vehicle
Number can characterize its ability for passing through tunnel, bridge, ups and downs section and obstacle.
Due to the gap between vehicle and ground it is insufficient and held up by ground, can not by the case where, referred to as gap is failed.With
Fail related vehicle geometric parameter, referred to as the passability geometric parameter of vehicle in gap.These parameters mainly include minimum liftoff
Gap, approach angle, departure angle, ramp breakover angle, minimum turning diameter etc., as shown in Figure 8.
Wherein, 1, minimum ground clearance h:
When minimum ground clearance h is that automobile is fully loaded, static, between the intermediate region minimum point on supporting plane and automobile
Distance.It reflects the collisionless ability by ground protrusion of automobile.
2, approach angle γ1With departure angle γ2:
Approach angle γ1With departure angle γ2When referring to that automobile is fully loaded, static, forward and backward projecting point, forward, rear wheel draw tangent line
When, the angle between tangent line and road surface.When it characterizes vehicle and is toward or away from barrier, the ability that does not collide.It is close
Angle and departure angle are bigger, are more not susceptible to contact failure and support tail failure.
3) longitudinally through angle beta:
When automobile is fully loaded, static, made respectively by the forward and backward tire outer rim of wheel perpendicular to automobile longitudinal symmetrical plane
Tangent plane, the folded minimum acute angle when two tangent planes meet at vehicle bottom lower position.It, which characterizes vehicle, to lead to without collision
Cross the overall size of the barriers such as hillock, arch bridge.It is bigger longitudinally through angle beta, jack up failure a possibility that it is smaller, vehicle passes through
Property is better.
4) minimum turning diameter and turning clearance circles:
When deflecting roller goes to extreme position, vehicle with minimum stabilizing speed Turning travel, the center of outside deflecting roller is flat
The track circular diameter that face rolls across on supporting plane, characterization vehicle can be by narrow curved;Bent area or around can not cross
The ability of barrier.
Turning clearance circles refer to when deflecting roller goes to extreme position, automobile with minimum stabilizing speed Turning travel, car body
Projection of the upper all the points on supporting plane is respectively positioned on the maximum inscribed circle other than circumference, referred to as turning channel inner circle;Institute on car body
Projection a little on supporting plane is respectively positioned on the minimum outer circle within circumference, referred to as turning channel outer circle.Turning channel is inside and outside
The width that the difference of radius of circle takes up space when being turned by the automobile limit, this value determine that minimum required when automobile turning is empty
Between.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (8)
1. the vehicle passability detection system of a kind of view-based access control model and laser radar sensor characterized by comprising vehicle-mounted
Sensor, data processing module;Wherein,
The point cloud data that road is acquired by onboard sensor, carries out the three-dimensional reconstruction of road scene, wherein point cloud data includes
The characteristic model data of road, tunnel, barrier;
Data processing module establishes space tree for the scene to three-dimensional reconstruction, generates corresponding acceleration collision detection and solved
Journey;
Vehicle is modeled according to trafficability geometric parameter, obtains vehicle rigid body geometric profile model;
Vehicle dynamic date is acquired, vehicle movement model is established;
According to vehicle movement model and road scene data, vehicle movement simulation track is generated;
Along vehicle movement simulation track, real-time perfoming collision detection is calculated, and obtains passability testing result.
2. the vehicle passability detection system of view-based access control model according to claim 1 and laser radar sensor, special
Sign is that onboard sensor includes: video camera, laser radar.
3. the vehicle passability detection system of view-based access control model according to claim 2 and laser radar sensor, special
Sign is that video camera includes:
Monocular-camera, forward direction Narrow Field Of Vision, 300 meters of detecting distance;
Binocular vision video camera, forward direction main view is wild, binocular camera, and 200 meters of ranging distance.
4. the vehicle passability detection system of view-based access control model according to claim 2 and laser radar sensor, special
Sign is that laser radar is solid-state laser radar, and forward detection, not less than 60 ° × 20 °, angular resolution is not less than field angle
0.2°。
5. the vehicle passability detection system of view-based access control model according to claim 2 and laser radar sensor, special
Sign is, the point cloud data of road is acquired by onboard sensor, and the three-dimensional reconstruction for carrying out road scene includes:
Establish the seat between radar fix system, three-dimensional world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system
Sensing data is carried out Space integration by mark system transformational relation;
Measurement point under radar fix system is transformed under the corresponding pixel coordinate system of video camera by coordinate system, carries out sensor
The spatial synchronization of data.
6. the vehicle passability detection system of view-based access control model according to claim 5 and laser radar sensor, special
Sign is, further includes: the combined calibrating of sensor is carried out using plane target drone;
It acquires the data under the multiple postures of scaling board simultaneously by video camera, laser radar, video camera is demarcated, is taken the photograph
The inside and outside ginseng of camera, establishes camera coordinate system;According to coordinate system, combined calibrating is carried out to laser radar and millimetre-wave radar.
7. the vehicle passability detection system of view-based access control model according to claim 5 and laser radar sensor, special
Sign is that video camera carries out the synchronous of sampling time by time synchronization control circuit with laser radar, and settling time unifies base
Quasi- and corresponding trigger collection mechanism, carries out Fusion in Time, keeps radar data synchronous in time with camera data.
8. the vehicle passability detection system of view-based access control model according to claim 5 and laser radar sensor, special
Sign is, the Road Detection of the system and to know method for distinguishing include: that data processing is limited in previous frame by successive frame Road Detection
The neighborhood of data processed result calculates road parameters on the basis of establishing road model, kinematics model and kinetic model
And passability is carried out relative to the location information and motion information of road according to vehicle and detects analog simulation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811290887.7A CN109359409A (en) | 2018-10-31 | 2018-10-31 | A kind of vehicle passability detection system of view-based access control model and laser radar sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811290887.7A CN109359409A (en) | 2018-10-31 | 2018-10-31 | A kind of vehicle passability detection system of view-based access control model and laser radar sensor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109359409A true CN109359409A (en) | 2019-02-19 |
Family
ID=65343599
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811290887.7A Pending CN109359409A (en) | 2018-10-31 | 2018-10-31 | A kind of vehicle passability detection system of view-based access control model and laser radar sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109359409A (en) |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109870689A (en) * | 2019-01-08 | 2019-06-11 | 武汉中海庭数据技术有限公司 | Millimetre-wave radar and the matched lane grade localization method of high-precision map vector and system |
CN109946703A (en) * | 2019-04-10 | 2019-06-28 | 北京小马智行科技有限公司 | A kind of sensor attitude method of adjustment and device |
CN109947242A (en) * | 2019-02-26 | 2019-06-28 | 贵州翰凯斯智能技术有限公司 | A kind of factory's virtual application system and application method based on information fusion |
CN110228066A (en) * | 2019-05-29 | 2019-09-13 | 常州中铁科技有限公司 | Tunnel detector and its avoidance unit and barrier-avoiding method |
CN110264416A (en) * | 2019-05-28 | 2019-09-20 | 深圳大学 | Sparse point cloud segmentation method and device |
CN110371108A (en) * | 2019-06-14 | 2019-10-25 | 浙江零跑科技有限公司 | Cartborne ultrasound wave radar and vehicle-mounted viewing system fusion method |
CN110378196A (en) * | 2019-05-29 | 2019-10-25 | 电子科技大学 | A kind of road vision detection method of combination laser point cloud data |
CN110378077A (en) * | 2019-09-03 | 2019-10-25 | 重庆交通大学 | Tunnel luminous environment dynamic dark adaptation experimental method and device based on driver's seat |
CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and system |
CN110415232A (en) * | 2019-07-25 | 2019-11-05 | 嘉兴普勒斯交通技术有限公司 | A kind of 3-D image pavement detection method |
CN110471086A (en) * | 2019-09-06 | 2019-11-19 | 北京云迹科技有限公司 | A kind of radar survey barrier system and method |
CN110926417A (en) * | 2019-12-03 | 2020-03-27 | 西北工业大学 | Vehicle-mounted railway tunnel detection system based on machine vision |
CN111179329A (en) * | 2019-12-31 | 2020-05-19 | 智车优行科技(上海)有限公司 | Three-dimensional target detection method and device and electronic equipment |
CN111680611A (en) * | 2020-06-03 | 2020-09-18 | 江苏无线电厂有限公司 | Road trafficability detection method, system and equipment |
CN112085843A (en) * | 2020-08-24 | 2020-12-15 | 北京航天发射技术研究所 | Method and device for extracting and measuring tunnel type target features in real time |
CN112099040A (en) * | 2020-09-15 | 2020-12-18 | 浙江省机电设计研究院有限公司 | Whole-course continuous track vehicle tracking system and method based on laser radar network |
CN112132929A (en) * | 2020-09-01 | 2020-12-25 | 北京布科思科技有限公司 | Grid map marking method based on depth vision and single line laser radar |
CN112389440A (en) * | 2020-11-07 | 2021-02-23 | 吉林大学 | Vehicle driving risk prediction method in off-road environment based on vehicle-road action mechanism |
CN112698302A (en) * | 2020-12-16 | 2021-04-23 | 南京航空航天大学 | Sensor fusion target detection method under bumpy road condition |
CN113989775A (en) * | 2021-10-28 | 2022-01-28 | 江苏濠汉信息技术有限公司 | Vision-guided auxiliary driving system |
CN114357843A (en) * | 2022-01-11 | 2022-04-15 | 中国电建集团江西省水电工程局有限公司 | Method for carrying out numerical collision experiment simulation aiming at wind power equipment transportation |
CN114445307A (en) * | 2020-10-30 | 2022-05-06 | 高新兴科技集团股份有限公司 | Method, device, MEC and medium for acquiring target information based on radar and visible light image |
CN114719768A (en) * | 2022-03-31 | 2022-07-08 | 东风汽车集团股份有限公司 | Method for measuring minimum ground clearance of vehicle |
CN114802240A (en) * | 2022-06-24 | 2022-07-29 | 禾多科技(北京)有限公司 | Vehicle speed control method, device, equipment and computer readable medium |
CN115294527A (en) * | 2022-08-09 | 2022-11-04 | 中铁隧道局集团有限公司 | Subway tunnel damage detection method based on computer vision |
CN115562076A (en) * | 2022-11-29 | 2023-01-03 | 北京路凯智行科技有限公司 | Simulation system, method and storage medium for unmanned mine car |
CN116279457A (en) * | 2023-05-15 | 2023-06-23 | 北京斯年智驾科技有限公司 | Anti-collision method, device, equipment and storage medium based on Lei Dadian cloud |
TWI823613B (en) * | 2022-10-13 | 2023-11-21 | 鴻海精密工業股份有限公司 | Anti-collision warning method, vehicle-mounted device, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
CN106945668A (en) * | 2016-10-27 | 2017-07-14 | 蔚来汽车有限公司 | Vehicle travels arrow path accessory system |
CN107609522A (en) * | 2017-09-19 | 2018-01-19 | 东华大学 | A kind of information fusion vehicle detecting system based on laser radar and machine vision |
CN108058705A (en) * | 2016-11-09 | 2018-05-22 | 奥迪股份公司 | Vehicle drive assist system and method |
-
2018
- 2018-10-31 CN CN201811290887.7A patent/CN109359409A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
CN106945668A (en) * | 2016-10-27 | 2017-07-14 | 蔚来汽车有限公司 | Vehicle travels arrow path accessory system |
CN108058705A (en) * | 2016-11-09 | 2018-05-22 | 奥迪股份公司 | Vehicle drive assist system and method |
CN107609522A (en) * | 2017-09-19 | 2018-01-19 | 东华大学 | A kind of information fusion vehicle detecting system based on laser radar and machine vision |
Cited By (42)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109870689A (en) * | 2019-01-08 | 2019-06-11 | 武汉中海庭数据技术有限公司 | Millimetre-wave radar and the matched lane grade localization method of high-precision map vector and system |
CN109947242A (en) * | 2019-02-26 | 2019-06-28 | 贵州翰凯斯智能技术有限公司 | A kind of factory's virtual application system and application method based on information fusion |
CN109946703A (en) * | 2019-04-10 | 2019-06-28 | 北京小马智行科技有限公司 | A kind of sensor attitude method of adjustment and device |
CN109946703B (en) * | 2019-04-10 | 2021-09-28 | 北京小马智行科技有限公司 | Sensor attitude adjusting method and device |
CN110264416A (en) * | 2019-05-28 | 2019-09-20 | 深圳大学 | Sparse point cloud segmentation method and device |
CN110378196A (en) * | 2019-05-29 | 2019-10-25 | 电子科技大学 | A kind of road vision detection method of combination laser point cloud data |
CN110378196B (en) * | 2019-05-29 | 2022-08-02 | 电子科技大学 | Road visual detection method combining laser point cloud data |
CN110228066A (en) * | 2019-05-29 | 2019-09-13 | 常州中铁科技有限公司 | Tunnel detector and its avoidance unit and barrier-avoiding method |
CN110371108B (en) * | 2019-06-14 | 2020-12-15 | 浙江零跑科技有限公司 | Fusion method of vehicle-mounted ultrasonic radar and vehicle-mounted looking-around system |
CN110371108A (en) * | 2019-06-14 | 2019-10-25 | 浙江零跑科技有限公司 | Cartborne ultrasound wave radar and vehicle-mounted viewing system fusion method |
CN110415232A (en) * | 2019-07-25 | 2019-11-05 | 嘉兴普勒斯交通技术有限公司 | A kind of 3-D image pavement detection method |
CN110412986A (en) * | 2019-08-19 | 2019-11-05 | 中车株洲电力机车有限公司 | A kind of vehicle barrier detection method and system |
CN110378077A (en) * | 2019-09-03 | 2019-10-25 | 重庆交通大学 | Tunnel luminous environment dynamic dark adaptation experimental method and device based on driver's seat |
CN110378077B (en) * | 2019-09-03 | 2022-07-26 | 重庆交通大学 | Tunnel light environment dynamic dark adaptation experiment method and device based on driver vision |
CN110471086A (en) * | 2019-09-06 | 2019-11-19 | 北京云迹科技有限公司 | A kind of radar survey barrier system and method |
CN110926417B (en) * | 2019-12-03 | 2021-12-14 | 西北工业大学 | Vehicle-mounted railway tunnel detection system based on machine vision |
CN110926417A (en) * | 2019-12-03 | 2020-03-27 | 西北工业大学 | Vehicle-mounted railway tunnel detection system based on machine vision |
CN111179329A (en) * | 2019-12-31 | 2020-05-19 | 智车优行科技(上海)有限公司 | Three-dimensional target detection method and device and electronic equipment |
CN111179329B (en) * | 2019-12-31 | 2023-09-08 | 智车优行科技(上海)有限公司 | Three-dimensional target detection method and device and electronic equipment |
CN111680611A (en) * | 2020-06-03 | 2020-09-18 | 江苏无线电厂有限公司 | Road trafficability detection method, system and equipment |
CN111680611B (en) * | 2020-06-03 | 2023-06-16 | 江苏无线电厂有限公司 | Road trafficability detection method, system and equipment |
CN112085843A (en) * | 2020-08-24 | 2020-12-15 | 北京航天发射技术研究所 | Method and device for extracting and measuring tunnel type target features in real time |
CN112085843B (en) * | 2020-08-24 | 2023-11-28 | 北京航天发射技术研究所 | Tunnel class target feature real-time extraction and measurement method and device |
CN112132929A (en) * | 2020-09-01 | 2020-12-25 | 北京布科思科技有限公司 | Grid map marking method based on depth vision and single line laser radar |
CN112132929B (en) * | 2020-09-01 | 2024-01-26 | 北京布科思科技有限公司 | Grid map marking method based on depth vision and single-line laser radar |
CN112099040A (en) * | 2020-09-15 | 2020-12-18 | 浙江省机电设计研究院有限公司 | Whole-course continuous track vehicle tracking system and method based on laser radar network |
CN114445307A (en) * | 2020-10-30 | 2022-05-06 | 高新兴科技集团股份有限公司 | Method, device, MEC and medium for acquiring target information based on radar and visible light image |
CN112389440A (en) * | 2020-11-07 | 2021-02-23 | 吉林大学 | Vehicle driving risk prediction method in off-road environment based on vehicle-road action mechanism |
CN112698302A (en) * | 2020-12-16 | 2021-04-23 | 南京航空航天大学 | Sensor fusion target detection method under bumpy road condition |
CN112698302B (en) * | 2020-12-16 | 2023-11-07 | 南京航空航天大学 | Sensor fusion target detection method under bumpy road condition |
CN113989775A (en) * | 2021-10-28 | 2022-01-28 | 江苏濠汉信息技术有限公司 | Vision-guided auxiliary driving system |
CN114357843B (en) * | 2022-01-11 | 2023-05-12 | 中国电建集团江西省水电工程局有限公司 | Method for carrying out numerical collision experiment simulation on transportation of wind power equipment |
CN114357843A (en) * | 2022-01-11 | 2022-04-15 | 中国电建集团江西省水电工程局有限公司 | Method for carrying out numerical collision experiment simulation aiming at wind power equipment transportation |
CN114719768A (en) * | 2022-03-31 | 2022-07-08 | 东风汽车集团股份有限公司 | Method for measuring minimum ground clearance of vehicle |
CN114719768B (en) * | 2022-03-31 | 2023-12-29 | 东风汽车集团股份有限公司 | Method for measuring minimum ground clearance of vehicle |
CN114802240B (en) * | 2022-06-24 | 2022-09-27 | 禾多科技(北京)有限公司 | Vehicle speed control method, device, equipment and computer readable medium |
CN114802240A (en) * | 2022-06-24 | 2022-07-29 | 禾多科技(北京)有限公司 | Vehicle speed control method, device, equipment and computer readable medium |
CN115294527A (en) * | 2022-08-09 | 2022-11-04 | 中铁隧道局集团有限公司 | Subway tunnel damage detection method based on computer vision |
TWI823613B (en) * | 2022-10-13 | 2023-11-21 | 鴻海精密工業股份有限公司 | Anti-collision warning method, vehicle-mounted device, and storage medium |
CN115562076B (en) * | 2022-11-29 | 2023-03-14 | 北京路凯智行科技有限公司 | Simulation system, method and storage medium for unmanned mine car |
CN115562076A (en) * | 2022-11-29 | 2023-01-03 | 北京路凯智行科技有限公司 | Simulation system, method and storage medium for unmanned mine car |
CN116279457A (en) * | 2023-05-15 | 2023-06-23 | 北京斯年智驾科技有限公司 | Anti-collision method, device, equipment and storage medium based on Lei Dadian cloud |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109359409A (en) | A kind of vehicle passability detection system of view-based access control model and laser radar sensor | |
CN108960183B (en) | Curve target identification system and method based on multi-sensor fusion | |
CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
US11734848B2 (en) | Pseudo lidar | |
Huang et al. | Finding multiple lanes in urban road networks with vision and lidar | |
US20220290979A1 (en) | Vehicle localization using the ground surface with an event camera | |
EP2549457B1 (en) | Vehicle-mounting vehicle-surroundings recognition apparatus and vehicle-mounting vehicle-surroundings recognition system | |
Hautière et al. | Real-time disparity contrast combination for onboard estimation of the visibility distance | |
US8154594B2 (en) | Mobile peripheral monitor | |
CN104011737B (en) | Method for detecting mist | |
CN103487034B (en) | Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target | |
CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
US20030210807A1 (en) | Monitoring device, monitoring method and program for monitoring | |
US20090169052A1 (en) | Object Detector | |
CN106778593A (en) | A kind of track level localization method based on the fusion of many surface marks | |
CN110197173B (en) | Road edge detection method based on binocular vision | |
Shunsuke et al. | GNSS/INS/on-board camera integration for vehicle self-localization in urban canyon | |
EP3364336B1 (en) | A method and apparatus for estimating a range of a moving object | |
Ravi et al. | Lane width estimation in work zones using LiDAR-based mobile mapping systems | |
Welzel et al. | Accurate camera-based traffic sign localization | |
CN112464889A (en) | Road vehicle attitude and motion information detection method | |
US11677931B2 (en) | Automated real-time calibration | |
JP2004355139A (en) | Vehicle recognition system | |
Matowicki et al. | Analysis of possibility to utilize road marking for the needs of autonomous vehicles | |
CN115063771A (en) | Error correction method, system, storage medium and device for distance detection of obstacle |
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: 20190219 |
|
RJ01 | Rejection of invention patent application after publication |