CN107424116A - Position detecting method of parking based on side ring depending on camera - Google Patents
Position detecting method of parking based on side ring depending on camera Download PDFInfo
- Publication number
- CN107424116A CN107424116A CN201710534936.6A CN201710534936A CN107424116A CN 107424116 A CN107424116 A CN 107424116A CN 201710534936 A CN201710534936 A CN 201710534936A CN 107424116 A CN107424116 A CN 107424116A
- Authority
- CN
- China
- Prior art keywords
- parking
- parking position
- camera
- side ring
- areas
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007935 neutral effect Effects 0.000 claims description 4
- 241000251468 Actinopterygii Species 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009189 diving Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001757 vomitory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T3/04—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Abstract
The invention discloses a kind of position detecting method of parking based on side ring depending on camera, the present invention by look around in camera scene can traffic areas segmentation, under earth axes, the actual size of the plane domain is calculated by inverse perspective mapping, and the region is confirmed using multiframe time series image data combination state of motion of vehicle, optimize actual parking position zone position information, finally realize effective parking position detection.The present invention has and can improve parking position detection and reliability and can improve the characteristics of parking accuracy.
Description
Technical field
The present invention relates to vehicle electronics technical field, can improve parking position detection reliability more particularly, to one kind and can carry
Height is parked the position detecting method of parking based on side ring depending on camera of accuracy.
Background technology
With the lifting of automotive automation degree, automated parking system becomes the high-end car system standard configuration in part, in real time
It is the important prerequisite that such system is realized accurately to detect effective parking place.Existing automated parking system is mostly based on ultrasonic wave
Radar sensor carries out parking position detection.Ultrasonic radar sensor has measurement distance short, is also easy to produce between adjacent sensors
The features such as signal interference, and cannot be distinguished from barrier size and classification.Therefore, it can not accurately be had in some scenarios
Parking position information is imitated, application scenarios have certain limitation, it is necessary to which driver artificially confirms the correctness of parking areas.
Vision system is more and more wider in the field application of vehicle active safety.360 degree of viewing systems are that existing battle wagon is auxiliary
One of security system is helped, such system can provide vehicle periphery situation under speed operation for driver, be driver's low speed
Operation provides vision auxiliary, has become the standard configuration of numerous volume production vehicles.But existing such volume production system is only
Driver provides the vision auxiliary of vehicle periphery relevant range, and the trafficability in the region can not be detected.
For some above-mentioned problems, Chinese patent notification number is CN104916163U, in September in 2015 16 days, is disclosed
One kind is parked position detecting method, including:Gather the binocular image of driving vehicle side, optical axis direction and the traveling side of IMAQ
To vertical and parallel with vehicle bottom surface;Detect the feature pixel included in binocular image and its distribution, the feature picture
Vegetarian refreshments is used for the feature for characterizing parking position setting-out or vehicle shape;Judge in any image whether to contain in binocular image and correspond to
In all feature pixels of a parking position setting-out, if then prompting detects parking position;Feature picture in binocular image
Vegetarian refreshments and its distribution, the spacing between the two obstacle cars that are berthed on parking position is determined, if the spacing is not less than pre-set threshold value,
It is parking position to prompt between the two obstacles car.The advantages of invention is:Can parking position get on the bus it is less in the case of
Parking position is able to detect that, and the scope detected is bigger.But its weak point is:The invention is the side using image recognition
Formula detects parking position, although detection range is bigger, can not accurately obtain effective parking position information, as parking position region has
Dark hole or parking position region are Vomitory etc..
The content of the invention
The present invention is to overcome in the prior art, and ultrasonic radar sensor measurement distance is short, between adjacent sensors
Signal interference is also easy to produce, and cannot be distinguished from barrier size and classification, can not accurately obtain effectively park in some scenarios
Position information is, it is necessary to the problem of driver artificially confirms parking areas correctness, there is provided it is reliable that one kind can improve parking position detection
Property and can improve the position detecting method of parking based on side ring depending on camera of accuracy of parking.
To achieve the above object, the present invention uses following technical scheme:
A kind of position detecting method of parking based on side ring depending on camera, comprise the following steps:
(1-1) fisheye camera distortion correction
(1-1-1) removes the radial direction in fish eye images using demarcation gained camera internal parameter by following distortion model
Distortion:θ '=θ (1+ θ2+θ4), wherein, θ is imaging perspective angle corresponding to image midpoint;
(1-2) side ring depending on can parking areas segmentation
(1-2-1) regards visual angle, image-region using the method training deep neural network of supervised learning for splitting side ring
It is interior can parking areas and can not parking areas;
(1-3) image can parking areas inverse perspective mapping
(1-3-1) regards camera calibration parameter using side ring, pair can parking areas carry out inverse perspective mapping, calculate road plane
Can parking areas area under coordinate system;
(1-4) top view parking position is searched for
Horizontal stroke, the longitudinal parking position physical dimension threshold information of (1-4-1) using setting, according to gained in step (1-3-1)
Region confirms potential parking position;
(1-5) road surface can parking areas sequential confirmation
(1-5-1) is according to yaw plane vehicle kinematics model, utilization orientation disk corner and GES estimation vehicle
Movable information, using multiframe sequential picture confirm can parking areas, according to parking position physical dimension threshold value screen calculate parking position
Final position.
The present invention by look around in camera scene can traffic areas segmentation, under earth axes, pass through inverse perspective
Transformation calculations go out the actual size of the plane domain, and using multiframe time series image data combination state of motion of vehicle to the region
Confirmed, optimize actual parking position zone position information, finally realize effective parking position detection.The present invention have can improve pool
Parking stall measure reliability and the characteristics of parking accuracy can be improved.
Preferably, in side ring depending on can also comprise the following steps in the segmentation step of parking areas:
(1-2) also comprises the following steps:
(1-2-2) collection side ring regards video sample, and distortion correction is carried out to video data and carries out pixel level demarcation, will be schemed
As be divided into can parking areas with can not parking areas, using network increase income algorithm slightly demarcate indirect labor calibration method lifted
Demarcate efficiency;
(1-2-3) projected depth neutral net framework, using full convolutional network structure;
(1-2-4) utilizes the sample and demarcation label gathered in step (1-2-2), to designed in step (1-2-3)
Deep neural network framework exercise supervision training, training process uses the gradient descent method based on mini batch mode:I.e.
In each circulation, optimal solution is asked to optimize network weight parameter to softmax losses based on the method for reverse recursion, until setting
Loop iteration number complete, softmax costing bio disturbance formula are:
Wherein, zjFor each element of output vector;
(1-2-5) is looked around camera and gathered in real time using training gained deep neural network parameter, offside in step (1-2-4)
Correction after video data, carry out image can parking areas prediction, obtain the moment side ring depending on parking in camera perspective
Image-region.
Preferably, regard camera calibration parameter using side ring, pair can parking areas carry out inverse perspective mapping, calculate road and put down
Under areal coordinate system can parking areas area the step of, in addition to:
By projective transformation matrix H by the point [u, v, 1] in the image coordinate system after distortion correctionTCoordinate as follows
The point [X, Y, 1] being converted into earth axesT:
[X, Y, 1]T=H* [u, v, 1]T;
Projective transformation matrix H scaling method is:The chessboard of a known dimensions is placed in camera perspective specific region
Lattice, Corner Detection is carried out to the gridiron pattern and obtains angle point set I1, geographical coordinates point set I2, can lead to corresponding to the angle point set
Cross tessellated physical dimension and relative position to obtain, gathered by matching I1 and I2, using least-squares calculation meeting point away from
H is obtained from matching error.
Preferably, using the horizontal stroke of setting, longitudinal parking position physical dimension threshold information, according to institute in step (1-3-1)
The step of region confirms potential parking position is obtained, in addition to:
Definition starts the parking position search moment, and vehicle right lateral side angle point is earth axes origin, is moored using horizontal, longitudinal direction
Parking stall minimum dimension template, all of all threshold values for meeting the size can be searched in parking areas in top view and potential are parked
Position, parking position mean place are defined as the arithmetic mean of instantaneous value of potential parking position vertex position, and parking position maximum magnitude is defined as diving
Maximum rectangular extent in parking position region, position and the parking position of current time vehicle are recorded in parking position register
Mean place and maximum magnitude.
Preferably, according to yaw plane vehicle kinematics model, utilization orientation disk corner and GES estimation car
Movable information, using multiframe sequential picture confirm can parking areas, parked according to the screening calculating of parking position physical dimension threshold value
The step of position final position, in addition to:
According to yaw plane auto model, using speed v and steering wheel angle signal δ, vehicle is calculated as follows
The movable information under earth axes:
X=x0+∫vcos(δ)dt
Y=y0+∫vsin(δ)dt
According to vehicle movement information, in earth axes compensation can parking position region relative motion, if parking position is posted
The parking position mean place continuous n moment is confirmed to be effective parking position in storage, then confirms and prompt effective parking space information.
If the parking position mean place continuous n moment is not confirmed to be effective parking position in bit register of parking, posted according to parking position
Parking position maximum magnitude and current time potential parking position information in storage, update the information in bit register of parking again.
Therefore, the present invention has the advantages that:(1) can be carried out with the position detecting method of parking based on ultrasonic radar
Fusion, the robustness of lifting system;(2) parking position detection and automatic parking independently can be carried out using viewing system, saves system
System cost;(3) parking position detection reliability can be improved;(4) accuracy of parking can be improved.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the present invention.
Embodiment
The present invention will be further described with embodiment below in conjunction with the accompanying drawings:
A kind of position detecting method of parking based on side ring depending on camera as shown in Figure 1, comprises the following steps:
Step 100, fisheye camera distortion correction
Step 110, using demarcation gained camera internal parameter, the radial direction in fish eye images is removed by following distortion model
Distortion:θ '=θ (1+ θ2+θ4), wherein, θ is imaging perspective angle corresponding to image midpoint;
Step 200, side ring depending on can parking areas segmentation
Step 210, deep neural network is trained using the method for supervised learning, visual angle, image district is regarded for splitting side ring
In domain can parking areas and can not parking areas;
Step 220, collection side ring regards video sample, and distortion correction is carried out to video data and carries out pixel level demarcation, will
Image be divided into can parking areas with can not parking areas, can use network increase income algorithm slightly demarcate indirect labor calibration method
Lifting demarcation efficiency;
Step 230, projected depth neutral net framework, using full convolutional network structure;
Step 240, using the sample gathered in step 220 and demarcation label, to depth god designed in step 230
Exercised supervision training through the network architecture.Training process uses the gradient descent method based on mini batch mode:I.e. each circulation
It is interior, optimal solution is asked to optimize network weight parameter to softmax losses based on the method for reverse recursion, until the circulation of setting changes
Generation counts up into, and softmax costing bio disturbance formula are:
Wherein, zj is each element of output vector;
Step 250, look around what camera gathered in real time using training gained deep neural network parameter, offside in step 240
Video data after correction, carry out image can parking areas prediction, obtain the moment side ring depending on the figure of parking in camera perspective
As region.
Step 300, image can parking areas inverse perspective mapping
Step 310, regard camera calibration parameter using side ring, pair can parking areas carry out inverse perspective mapping, calculate road put down
Can parking areas area under areal coordinate system:
By projective transformation matrix H by the point [u, v, 1] in the image coordinate system after distortion correctionTCoordinate as follows
The point [X, Y, 1] being converted into earth axesT:
[X, Y, 1]T=H* [u, v, 1]T;
Projective transformation matrix H scaling method is:The chessboard of a known dimensions is placed in camera perspective specific region
Lattice, Corner Detection is carried out to the gridiron pattern and obtains angle point set I1, geographical coordinates point set I2, can lead to corresponding to the angle point set
Cross tessellated physical dimension and relative position to obtain, gathered by matching I1 and I2, using least-squares calculation meeting point away from
H is obtained from matching error.
Step 400, top view parking position is searched for
Step 410, definition starts the parking position search moment, and vehicle right lateral side angle point is earth axes origin, utilizes horizontal stroke
To, longitudinal parking position minimum dimension template, all of all threshold values for meeting the size can be searched in parking areas in top view
Potential parking position, parking position mean place are defined as the arithmetic mean of instantaneous value of potential parking position vertex position, parking position maximum magnitude
The maximum rectangular extent being defined as in potential parking position region, in parking position register record current time vehicle position with
And parking position mean place and maximum magnitude.
Step 500, road surface can parking areas sequential confirmation
Step 510, according to yaw plane auto model, using speed v and steering wheel angle signal δ, as follows
Calculate vehicle movable information under earth axes:
X=x0+∫vcos(δ)dt
Y=y0+∫vsin(δ)dt
According to vehicle movement information, in earth axes compensation can parking position region relative motion, if parking position is posted
Parking position mean place in storage, each moment in 2 minutes are confirmed to be effective parking position, then confirm and prompt
Effective parking space information, if parking position mean place in bit register of parking, each moment in 2 minutes is not true
Think effective parking position, then according to parking position maximum magnitude in bit register of parking and current time potential parking position information, weight
The new information updated in bit register of parking.
It should be understood that the present embodiment is only illustrative of the invention and is not intended to limit the scope of the invention.In addition, it is to be understood that
After having read the content of the invention lectured, those skilled in the art can make various changes or modifications to the present invention, these etc.
Valency form equally falls within the application appended claims limited range.
Claims (5)
1. a kind of position detecting method of parking based on side ring depending on camera, it is characterized in that, comprise the following steps:
(1-1) fisheye camera distortion correction
(1-1-1) removes the radial distortion in fish eye images using demarcation gained camera internal parameter by following distortion model:
θ '=θ (1+ θ2+θ4), wherein, θ is imaging perspective angle corresponding to image midpoint;
(1-2) side ring depending on can parking areas segmentation
(1-2-1) regards visual angle, in image-region using the method training deep neural network of supervised learning for splitting side ring
Can parking areas and can not parking areas;
(1-3) image can parking areas inverse perspective mapping
(1-3-1) regards camera calibration parameter using side ring, pair can parking areas carry out inverse perspective mapping, calculate road plane coordinate
Can parking areas area under system;
(1-4) top view parking position is searched for
Horizontal stroke, the longitudinal parking position physical dimension threshold information of (1-4-1) using setting, according to gained region in step (1-3-1)
Confirm potential parking position;
(1-5) road surface can parking areas sequential confirmation
(1-5-1) is according to yaw plane vehicle kinematics model, utilization orientation disk corner and GES estimation vehicle movement
Information, using multiframe sequential picture confirm can parking areas, according to parking position physical dimension threshold value screen calculate parking position it is final
Position.
2. the position detecting method of parking according to claim 1 based on side ring depending on camera, it is characterized in that, step (1-2) is also
Comprise the following steps:
(1-2-2) collection side ring regards video sample, carries out distortion correction to video data and carries out pixel level demarcation, by image point
Be segmented into can parking areas with can not parking areas, using network increase income algorithm slightly demarcate indirect labor calibration method lifted demarcation
Efficiency;
(1-2-3) projected depth neutral net framework, using full convolutional network structure;
(1-2-4) utilizes the sample and demarcation label gathered in step (1-2-2), to depth designed in step (1-2-3)
Degree neutral net framework exercises supervision training, and training process uses the gradient descent method based on mini batch mode:It is i.e. each
In circulation, optimal solution is asked to optimize network weight parameter to softmax losses based on the method for reverse recursion, until setting follows
Ring iterative number is completed, and softmax costing bio disturbance formula are:
<mrow>
<mi>&sigma;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>z</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<msup>
<mi>e</mi>
<msub>
<mi>z</mi>
<mi>j</mi>
</msub>
</msup>
<mrow>
<msup>
<mi>&Sigma;e</mi>
<msub>
<mi>z</mi>
<mi>j</mi>
</msub>
</msup>
</mrow>
</mfrac>
</mrow>
Wherein, zjFor each element of output vector;
(1-2-5) using training gained deep neural network parameter in step (1-2-4), what offside looked around that camera gathers in real time rectifys
Video data after just, carry out image can parking areas prediction, obtain the moment side ring depending on the image of parking in camera perspective
Region.
3. the position detecting method of parking according to claim 1 based on side ring depending on camera, it is characterized in that, step (1-3-1)
Also comprise the following steps:
By projective transformation matrix H by the point [u, v, 1] in the image coordinate system after distortion correctionTCoordinate transform as follows
Point [X, Y, 1] into earth axesT:
[X, Y, 1]T=H* [u, v, 1]T;
Projective transformation matrix H scaling method is:The gridiron pattern of a known dimensions is placed in camera perspective specific region, it is right
The gridiron pattern carries out Corner Detection and obtains angle point set I1, and geographical coordinates point set I2, can pass through chess corresponding to the angle point set
The physical dimension of disk lattice obtains with relative position, is gathered by matching I1 and I2, utilizes least-squares calculation meeting point distance
H is obtained with error.
4. the position detecting method of parking according to claim 1 based on side ring depending on camera, it is characterized in that, step (1-4-1)
Also comprise the following steps:
Definition starts the parking position search moment, and vehicle right lateral side angle point is earth axes origin, utilizes horizontal, longitudinal parking position
Minimum dimension template, all potential parking positions of all threshold values for meeting the size, pool can be searched in parking areas in top view
Parking stall mean place is defined as the arithmetic mean of instantaneous value of potential parking position vertex position, and parking position maximum magnitude is defined as potential park
Maximum rectangular extent in the region of position, position and the parking position average bit of current time vehicle are recorded in parking position register
Put and maximum magnitude.
5. the position detecting method of parking according to claim 1 based on side ring depending on camera, it is characterized in that, step (1-5-1)
Also comprise the following steps:
According to yaw plane auto model, using speed v and steering wheel angle signal δ, vehicle is calculated as follows on ground
Movable information under areal coordinate system:
X=x0+∫vcos(δ)dt
Y=y0+∫vsin(δ)dt
According to vehicle movement information, in earth axes compensation can parking position region relative motion, if parking bit register
The middle parking position mean place continuous n moment is confirmed to be effective parking position, then confirms and prompt effective parking space information, if pool
The parking position mean place continuous n moment is not confirmed to be effective parking position in the register of parking stall, then according to bit register of parking
Middle parking position maximum magnitude and current time potential parking position information, the information in bit register of parking is updated again.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710534936.6A CN107424116B (en) | 2017-07-03 | 2017-07-03 | Parking space detection method based on side surround view camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710534936.6A CN107424116B (en) | 2017-07-03 | 2017-07-03 | Parking space detection method based on side surround view camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107424116A true CN107424116A (en) | 2017-12-01 |
CN107424116B CN107424116B (en) | 2020-06-19 |
Family
ID=60426806
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710534936.6A Active CN107424116B (en) | 2017-07-03 | 2017-07-03 | Parking space detection method based on side surround view camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107424116B (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680113A (en) * | 2017-10-27 | 2018-02-09 | 武汉大学 | The image partition method of multi-layer segmentation network based on Bayesian frame edge prior |
CN107993488A (en) * | 2017-12-13 | 2018-05-04 | 深圳市航盛电子股份有限公司 | A kind of parking stall recognition methods, system and medium based on fisheye camera |
CN108090455A (en) * | 2017-12-27 | 2018-05-29 | 北京纵目安驰智能科技有限公司 | Parking stall line vertex localization method, system, terminal and medium based on cascade mechanism |
CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
CN108357269A (en) * | 2018-04-12 | 2018-08-03 | 电子科技大学中山学院 | Intelligent pen rack |
CN108860139A (en) * | 2018-04-11 | 2018-11-23 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN109063632A (en) * | 2018-07-27 | 2018-12-21 | 重庆大学 | A kind of parking position Feature Selection method based on binocular vision |
CN109086708A (en) * | 2018-07-25 | 2018-12-25 | 深圳大学 | A kind of parking space detection method and system based on deep learning |
CN109146978A (en) * | 2018-07-25 | 2019-01-04 | 南京富锐光电科技有限公司 | A kind of high speed camera image deformation calibrating installation and method |
CN109147321A (en) * | 2018-08-23 | 2019-01-04 | 重庆文理学院 | ITS new model and its construction method and intelligent transportation system under Internet of Things |
CN109446909A (en) * | 2018-09-27 | 2019-03-08 | 山东省科学院自动化研究所 | A kind of monocular ranging auxiliary parking system and method |
CN109584304A (en) * | 2018-12-07 | 2019-04-05 | 中国科学技术大学 | A kind of steering wheel angle measurement method and device, system |
CN109649384A (en) * | 2019-02-15 | 2019-04-19 | 华域汽车系统股份有限公司 | A kind of parking assistance method |
CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研(天津)汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
CN109801234A (en) * | 2018-12-28 | 2019-05-24 | 南京美乐威电子科技有限公司 | Geometric image correction method and device |
CN110654373A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Automatic parking method and device and vehicle |
CN110942434A (en) * | 2019-11-22 | 2020-03-31 | 华兴源创(成都)科技有限公司 | Display compensation system and method of display panel |
CN111028534A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
CN111098850A (en) * | 2018-10-25 | 2020-05-05 | 北京初速度科技有限公司 | Automatic parking auxiliary system and automatic parking method |
CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
CN111746525A (en) * | 2020-07-07 | 2020-10-09 | 东风柳州汽车有限公司 | Parking path planning method, device, equipment and storage medium |
CN112016349A (en) * | 2019-05-29 | 2020-12-01 | 北京市商汤科技开发有限公司 | Parking space detection method and device and electronic equipment |
CN112668588A (en) * | 2020-12-29 | 2021-04-16 | 禾多科技(北京)有限公司 | Parking space information generation method, device, equipment and computer readable medium |
CN112983085A (en) * | 2021-04-30 | 2021-06-18 | 的卢技术有限公司 | Parking space line identification method based on vision |
CN113705474A (en) * | 2021-08-30 | 2021-11-26 | 北京易航远智科技有限公司 | Parking space detection method and device |
CN114347982A (en) * | 2021-12-24 | 2022-04-15 | 北京经纬恒润科技股份有限公司 | Path planning method and system for automatic parking |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103763517A (en) * | 2014-03-03 | 2014-04-30 | 惠州华阳通用电子有限公司 | Vehicle-mounted around view display method and system |
CN104512328A (en) * | 2013-09-27 | 2015-04-15 | 比亚迪股份有限公司 | Automobile all-round looking image generation method and automobile all-round looking system |
US20160090044A1 (en) * | 2014-09-26 | 2016-03-31 | Aisin Seiki Kabushiki Kaisha | Periphery monitoring apparatus and periphery monitoring system |
-
2017
- 2017-07-03 CN CN201710534936.6A patent/CN107424116B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104512328A (en) * | 2013-09-27 | 2015-04-15 | 比亚迪股份有限公司 | Automobile all-round looking image generation method and automobile all-round looking system |
CN103763517A (en) * | 2014-03-03 | 2014-04-30 | 惠州华阳通用电子有限公司 | Vehicle-mounted around view display method and system |
US20160090044A1 (en) * | 2014-09-26 | 2016-03-31 | Aisin Seiki Kabushiki Kaisha | Periphery monitoring apparatus and periphery monitoring system |
Non-Patent Citations (2)
Title |
---|
RAFAEL GROMPONE VON GIOI等: "a Line Segment Detector", 《IMAGE PROCESSING ON LINE》 * |
王旭东 等: "一种基于环视相机的自动泊车方法", 《上海交通大学学报》 * |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107680113A (en) * | 2017-10-27 | 2018-02-09 | 武汉大学 | The image partition method of multi-layer segmentation network based on Bayesian frame edge prior |
CN107993488A (en) * | 2017-12-13 | 2018-05-04 | 深圳市航盛电子股份有限公司 | A kind of parking stall recognition methods, system and medium based on fisheye camera |
CN107993488B (en) * | 2017-12-13 | 2021-07-06 | 深圳市航盛电子股份有限公司 | Parking space identification method, system and medium based on fisheye camera |
CN108090455A (en) * | 2017-12-27 | 2018-05-29 | 北京纵目安驰智能科技有限公司 | Parking stall line vertex localization method, system, terminal and medium based on cascade mechanism |
CN108090455B (en) * | 2017-12-27 | 2023-08-22 | 北京纵目安驰智能科技有限公司 | Cascade mechanism-based parking space line vertex positioning method, system, terminal and medium |
CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
CN108860139A (en) * | 2018-04-11 | 2018-11-23 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN108860139B (en) * | 2018-04-11 | 2019-11-29 | 浙江零跑科技有限公司 | A kind of automatic parking method for planning track based on depth enhancing study |
CN108357269B (en) * | 2018-04-12 | 2023-05-02 | 电子科技大学中山学院 | Intelligent pen rack |
CN108357269A (en) * | 2018-04-12 | 2018-08-03 | 电子科技大学中山学院 | Intelligent pen rack |
CN110654373A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Automatic parking method and device and vehicle |
CN109146978A (en) * | 2018-07-25 | 2019-01-04 | 南京富锐光电科技有限公司 | A kind of high speed camera image deformation calibrating installation and method |
CN109146978B (en) * | 2018-07-25 | 2021-12-07 | 南京富锐光电科技有限公司 | High-speed camera imaging distortion calibration device and method |
CN109086708A (en) * | 2018-07-25 | 2018-12-25 | 深圳大学 | A kind of parking space detection method and system based on deep learning |
CN109063632B (en) * | 2018-07-27 | 2022-02-01 | 重庆大学 | Parking space characteristic screening method based on binocular vision |
CN109063632A (en) * | 2018-07-27 | 2018-12-21 | 重庆大学 | A kind of parking position Feature Selection method based on binocular vision |
CN109147321A (en) * | 2018-08-23 | 2019-01-04 | 重庆文理学院 | ITS new model and its construction method and intelligent transportation system under Internet of Things |
CN109446909A (en) * | 2018-09-27 | 2019-03-08 | 山东省科学院自动化研究所 | A kind of monocular ranging auxiliary parking system and method |
CN111028534A (en) * | 2018-10-09 | 2020-04-17 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
CN111028534B (en) * | 2018-10-09 | 2022-04-26 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
CN111098850A (en) * | 2018-10-25 | 2020-05-05 | 北京初速度科技有限公司 | Automatic parking auxiliary system and automatic parking method |
CN109584304A (en) * | 2018-12-07 | 2019-04-05 | 中国科学技术大学 | A kind of steering wheel angle measurement method and device, system |
CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研(天津)汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
CN109801234A (en) * | 2018-12-28 | 2019-05-24 | 南京美乐威电子科技有限公司 | Geometric image correction method and device |
CN109801234B (en) * | 2018-12-28 | 2023-09-22 | 南京美乐威电子科技有限公司 | Image geometry correction method and device |
CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
CN109649384B (en) * | 2019-02-15 | 2020-08-14 | 华域汽车系统股份有限公司 | Parking assisting method |
CN109649384A (en) * | 2019-02-15 | 2019-04-19 | 华域汽车系统股份有限公司 | A kind of parking assistance method |
CN112016349A (en) * | 2019-05-29 | 2020-12-01 | 北京市商汤科技开发有限公司 | Parking space detection method and device and electronic equipment |
WO2020238284A1 (en) * | 2019-05-29 | 2020-12-03 | 北京市商汤科技开发有限公司 | Parking space detection method and apparatus, and electronic device |
CN110942434A (en) * | 2019-11-22 | 2020-03-31 | 华兴源创(成都)科技有限公司 | Display compensation system and method of display panel |
CN110942434B (en) * | 2019-11-22 | 2023-05-05 | 华兴源创(成都)科技有限公司 | Display compensation system and method of display panel |
CN111746525A (en) * | 2020-07-07 | 2020-10-09 | 东风柳州汽车有限公司 | Parking path planning method, device, equipment and storage medium |
CN112668588B (en) * | 2020-12-29 | 2023-09-12 | 禾多科技(北京)有限公司 | Parking space information generation method, device, equipment and computer readable medium |
CN112668588A (en) * | 2020-12-29 | 2021-04-16 | 禾多科技(北京)有限公司 | Parking space information generation method, device, equipment and computer readable medium |
CN112983085A (en) * | 2021-04-30 | 2021-06-18 | 的卢技术有限公司 | Parking space line identification method based on vision |
CN113705474A (en) * | 2021-08-30 | 2021-11-26 | 北京易航远智科技有限公司 | Parking space detection method and device |
CN114347982A (en) * | 2021-12-24 | 2022-04-15 | 北京经纬恒润科技股份有限公司 | Path planning method and system for automatic parking |
Also Published As
Publication number | Publication date |
---|---|
CN107424116B (en) | 2020-06-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107424116A (en) | Position detecting method of parking based on side ring depending on camera | |
CN111448478B (en) | System and method for correcting high-definition maps based on obstacle detection | |
Li et al. | Springrobot: A prototype autonomous vehicle and its algorithms for lane detection | |
CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
CN102867416B (en) | Vehicle part feature-based vehicle detection and tracking method | |
CN101629820B (en) | Road-edge detection | |
JP3521860B2 (en) | Vehicle travel path recognition device | |
CN102682292B (en) | Method based on monocular vision for detecting and roughly positioning edge of road | |
Kühnl et al. | Spatial ray features for real-time ego-lane extraction | |
CN104204726B (en) | Moving object position attitude estimating device and moving object position Attitude estimation method | |
US10922817B2 (en) | Perception device for obstacle detection and tracking and a perception method for obstacle detection and tracking | |
CN104700414A (en) | Rapid distance-measuring method for pedestrian on road ahead on the basis of on-board binocular camera | |
CN107284455B (en) | A kind of ADAS system based on image procossing | |
CN103204104B (en) | Monitored control system and method are driven in a kind of full visual angle of vehicle | |
CN111461048B (en) | Vision-based parking lot drivable area detection and local map construction method | |
CN109919074A (en) | A kind of the vehicle cognitive method and device of view-based access control model cognition technology | |
CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
Zhang et al. | Robust inverse perspective mapping based on vanishing point | |
CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
CN114325634A (en) | Method for extracting passable area in high-robustness field environment based on laser radar | |
Kellner et al. | Multi-cue, model-based detection and mapping of road curb features using stereo vision | |
CN107220632B (en) | Road surface image segmentation method based on normal characteristic | |
CN104267209B (en) | Method and system for expressway video speed measurement based on virtual coils | |
CN202454078U (en) | Road vehicle detecting device | |
Chun-Zhao et al. | Drivable road boundary detection for intelligent vehicles based on stereovision with plane-induced homography |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder |
Address after: 6 / F, Xintu building, 451 Internet of things street, Binjiang District, Hangzhou City, Zhejiang Province, 310051 Patentee after: Zhejiang Zero run Technology Co.,Ltd. Address before: 6 / F, Xintu building, 451 Internet of things street, Binjiang District, Hangzhou City, Zhejiang Province, 310051 Patentee before: ZHEJIANG LEAPMOTOR TECHNOLOGY Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |