CN108256470A - A kind of lane shift judgment method and automobile - Google Patents
A kind of lane shift judgment method and automobile Download PDFInfo
- Publication number
- CN108256470A CN108256470A CN201810040516.7A CN201810040516A CN108256470A CN 108256470 A CN108256470 A CN 108256470A CN 201810040516 A CN201810040516 A CN 201810040516A CN 108256470 A CN108256470 A CN 108256470A
- Authority
- CN
- China
- Prior art keywords
- automobile
- panoramic picture
- edge point
- key
- key edge
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 56
- 230000009466 transformation Effects 0.000 claims abstract description 30
- 230000002708 enhancing effect Effects 0.000 claims abstract description 12
- 239000000284 extract Substances 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000004091 panning Methods 0.000 abstract description 4
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 abstract 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 abstract 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T5/80—
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Abstract
The invention belongs to automotive fields, provide a kind of lane shift judgment method and automobile.In embodiments of the present invention, firstly generate the panoramic picture of automobile, then greyscale transformation is carried out to the panoramic picture according to predetermined manner, and edge enhancing processing is carried out to the panoramic picture after the progress greyscale transformation, and extract the key edge point for carrying out the enhanced panoramic picture in edge, and clustering processing is carried out to the key edge point, then determine whether the traveling lane of automobile shifts according to the key edge point after clustering processing.The embodiment of the present invention carries out lane shift detection based on panorama system under panning mode, realizes and improves lane shift Detection accuracy, and increases the target of the integrated level of ADAS technologies.
Description
Technical field
The invention belongs to automotive field more particularly to a kind of lane shift judgment method and automobiles.
Background technology
With the fast development of intelligent driving technology, ADAS (Advanced Driving Assisting System, height
Grade driving assistance system) technology has been more and more widely used.One of major technique as ADAS technologies, lane shift inspection
It surveys and early warning system drives in accident rate in correction driving habit and reduction and plays an important roll.At present, lane shift detection and
Early warning mainly acquires the picture of track by being mounted on single camera after windshield, is examined by the methods of edge detection
Lane position is surveyed, and then judges whether driving vehicle deviates current lane, and early warning is carried out according to the situation of deviation.And it is used as another
One of kind main ADAS technologies, panorama system the auxiliary and eliminating of parking had been obtained on eliminating driving blind area it is relatively broad should
With.
But lane shift system and panorama system are still two completely self-contained systems at present, and current track
There are the shortcomings of Detection accuracy is low, algorithm complexity is high for bias detecting method.
Invention content
The embodiment of the present invention is designed to provide a kind of lane shift judgment method, it is intended to solve current lane shift system
System and panorama system are two completely self-contained systems, and there are Detection accuracy is low, algorithm is complicated for lane shift detection method
Spend the problem of high.
In order to solve the above-mentioned technical problem, the invention is realized in this way：A kind of lane shift judgment method, applied to vapour
Vehicle the described method comprises the following steps：
Generate the panoramic picture of automobile；
Greyscale transformation carries out the panoramic picture, and to the panorama sketch after the progress greyscale transformation according to predetermined manner
As carrying out edge enhancing processing；
The key edge point of the progress enhanced panoramic picture in edge is extracted, and the key edge point is gathered
Class processing；
Determine whether the traveling lane of automobile shifts according to the key edge point after clustering processing.
Further, the step of panoramic picture of the generation automobile, including：
The multiple cameras for being mounted on the automobile predeterminated position are demarcated；
Establish the mapping between each camera image coordinate system and earth axes in calibrated the multiple camera
Relationship；
Default distortion correction processing is carried out to the multi-path video data of the multiple camera acquisition；
According to the mapping relations to by default distortion correction, treated that video data splices, obtain described complete
Scape image.
Further, it is described that greyscale transformation is carried out, and to the carry out gray scale to the panoramic picture according to predetermined manner
Panoramic picture after transformation carries out the step of edge enhances processing and includes：
Extract pixel value of the V channel values in hsv color space as gray level image；
Greyscale transformation is carried out to the panoramic picture according to the pixel value, obtains panorama gray level image；
Convolutional calculation is carried out to the panorama gray level image using Sobel operators, obtains the side of the panorama gray level image
Edge enhances image.
Further, the key edge point for carrying out the enhanced panoramic picture in edge is extracted, and to the key side
Edge point carries out the step of clustering processing, including：
The edge enhanced images are scanned according to presetted pixel interval；
The pixel that gray value in the edge enhanced images is more than to default gray threshold is labeled as key edge point；
The key edge point is traversed, and clustering processing is carried out to the key edge point, obtains the key of multiple classifications
Marginal point.
Further, the key edge point according to after clustering processing determines whether the traveling lane of automobile shifts
The step of, including：
Two most classifications of key edge point quantity are chosen, and calculate each key edge point in described two classifications respectively
The mean value of x coordinateWith
It willWithIt is respectively labeled as the x coordinate of two lane lines of the automobile current lane；
IfWithThe x coordinate x of continuous default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then
Judge that the running car track shifts, and carries out early warning.
The embodiment of the present invention additionally provides a kind of automobile, and the automobile includes：
Generation unit, for generating the panoramic picture of automobile；
Processing unit, for carrying out greyscale transformation to the panoramic picture according to predetermined manner, and to the carry out gray scale
Panoramic picture after transformation carries out edge enhancing processing and the extraction key side for carrying out the enhanced panoramic picture in edge
Edge point, and clustering processing is carried out to the key edge point；
Judging unit, for determining whether the traveling lane of automobile occurs partially according to the key edge point after clustering processing
It moves.
Further, the generation unit is specifically used for：
The multiple cameras for being mounted on the automobile predeterminated position are demarcated；
Establish the mapping between each camera image coordinate system and earth axes in calibrated the multiple camera
Relationship；
Default distortion correction processing is carried out to the multi-path video data of the multiple camera acquisition；
According to the mapping relations to by default distortion correction, treated that video data splices, obtain described complete
Scape image.
Further, the processing unit is specifically used for：
Extract pixel value of the V channel values in hsv color space as gray level image；
Greyscale transformation is carried out to the panoramic picture according to the pixel value, obtains panorama gray level image；
Convolutional calculation is carried out to the panorama gray level image using Sobel operators, obtains the side of the panorama gray level image
Edge enhances image.
Further, the processing unit also particularly useful for：
The edge enhanced images are scanned according to presetted pixel interval；
The pixel that gray value in the edge enhanced images is more than to default gray threshold is labeled as key edge point；
The key edge point is traversed, and clustering processing is carried out to the key edge point, obtains the key of multiple classifications
Marginal point.
Further, the judging unit is specifically used for：
Two most classifications of key edge point quantity are chosen, and calculate each key edge point in described two classifications respectively
The mean value of x coordinateWith
It willWithIt is respectively labeled as the x coordinate of two lane lines of the automobile current lane；
IfWithThe x coordinate x of continuous default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then
Judge that the running car track shifts, and carries out early warning.
In embodiments of the present invention, the panoramic picture of automobile is firstly generated, then according to predetermined manner to the panorama sketch
Carry out edge enhancing processing as carrying out greyscale transformation, and to the panoramic picture after the progress greyscale transformation, and extract it is described into
The key edge point of the enhanced panoramic picture in row edge, and clustering processing is carried out to the key edge point, then according to poly-
Treated that key edge point determines whether the traveling lane of automobile shifts for class.The embodiment of the present invention is using panorama system as base
Plinth carries out lane shift detection under panning mode, realizes and improves lane shift Detection accuracy, and increases ADAS technologies
The target of integrated level.
Description of the drawings
Fig. 1 is the flow chart of the lane shift judgment method provided in an embodiment of the present invention applied to automobile；
Fig. 2 is panoramic picture provided in an embodiment of the present invention；
Fig. 3 a are panorama gray level images provided in an embodiment of the present invention；
Fig. 3 b are the edge enhanced images of panorama gray level image provided in an embodiment of the present invention；
Fig. 4 is the key edge point image of extraction provided in an embodiment of the present invention；
Fig. 5 is the key edge point image of multiple classifications provided in an embodiment of the present invention；
Fig. 6 is lane shift detection image provided in an embodiment of the present invention；
Fig. 7 is the circuit theory schematic diagram of automobile provided in an embodiment of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The specific implementation of the present invention is described in detail below in conjunction with specific embodiment：
Fig. 1 shows the flow chart of the lane shift judgment method provided in an embodiment of the present invention applied to automobile, in order to
Convenient for explanation, only list with the relevant part of the embodiment of the present invention, details are as follows：
Lane shift judgment method provided in an embodiment of the present invention applied to automobile includes the following steps：
Step S10 generates the panoramic picture of automobile.In embodiments of the present invention, the peace of predeterminated position all around of automobile
Multiple cameras have been filled, the multiple cameras for being mounted on the automobile predeterminated position have been demarcated first, and after establishing calibration
The multiple camera in mapping relations between each camera image coordinate system and earth axes, then to the multiple
The multi-path video data of camera acquisition carries out default distortion correction processing, finally according to the mapping relations to by default abnormal
The video data become after correction process is spliced, and obtains the panoramic picture got a bird's eye view under visual angle as shown in Figure 2.
Step S20, according to predetermined manner to the panoramic picture carry out greyscale transformation, and to it is described progress greyscale transformation after
Panoramic picture carry out edge enhancing processing.
In embodiments of the present invention, it is contemplated that standard vehicle diatom has white and two kinds of colors of yellow, in order to enhance yellow vehicle
The brightness of diatom extracts the V channel values (i.e. the channel of numerical value maximum in R, G, B triple channel) in hsv color space as ash first
The pixel value of image is spent, greyscale transformation is then carried out to the panoramic picture according to the pixel value, is obtained as shown in Figure 3a
Panorama gray level image, and convolutional calculation is carried out to the panorama gray level image using Sobel operators, obtain institute as shown in Figure 3b
State the edge enhanced images of panorama gray level image.
In embodiments of the present invention, the coordinate system of panoramic picture is using the direction of running car as y-axis direction, track arrangement
Direction is x-axis direction, and edge enhancing processing is carried out using the Sobel operators of x-axis direction.Wherein, the Sobel operators of x-axis direction
Formula is as follows：
Step S30 extracts the key edge point for carrying out the enhanced panoramic picture in edge, and to the key edge
Point carries out clustering processing.
In embodiments of the present invention, according to presetted pixel interval (systemic presupposition or User Defined are set) to the side
Edge enhancing image is scanned；Gray value in the edge enhanced images is more than the pixel of default gray threshold labeled as pass
Key marginal point extracts key edge point image as shown in Figure 4, then traverses the key edge point, and to the key
Marginal point carries out clustering processing, obtains the key edge point of multiple classifications as shown in Figure 5.
In embodiments of the present invention, it is to the concrete mode of key edge point progress clustering processing：1. shown in choosing
Central point of first key edge o'clock as the 1st classification in key edge point；2. remaining key edge point is traversed successively, when
The absolute value of the difference of the x coordinate of the x coordinate of the key edge point traversed and the central point of current class is less than r, and (r values can basis
Actual conditions are chosen) when, which is denoted as current class；3. when there is first pass for being not belonging to current class
During key marginal point, which is denoted as to the central point of new classification, successively the remaining key edge not being classified of traversal
When the absolute value of the difference of point, the x coordinate of the key edge point traversed and the x coordinate of Current central point is less than r, the key edge
Point is denoted as current class；4. above-mentioned operation 3. is repeated, until all key edge points have been classified.
Step S40 determines whether the traveling lane of automobile shifts according to the key edge point after clustering processing.
In the panoramic picture view of the embodiment of the present invention, the position of automobile in the picture is fixed, therefore only need
It determines and automobile just can determine that whether vehicle occurs lane shift at a distance of two nearest lane lines.First, key edge is chosen
Two most classifications of point quantity, and the mean value of each key edge point x coordinate in described two classifications is calculated respectivelyWith
It is located in panoramic picture view coordinate, the minimum and maximum width in track is respectively WminAnd WmaxIf meet the following conditions：
ThenWithIt is respectively the x coordinate of two lane lines of current lane, it willWithIt is respectively labeled as described
The x coordinate of two lane lines of automobile current lane if being unsatisfactory for above-mentioned condition, skips this frame image.IfWithContinuously
The x coordinate x of default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then judge the running car track hair
Raw offset, and carry out early warning.Wherein, lane detection result is as shown in Figure 6.
In embodiments of the present invention, the panoramic picture of automobile is firstly generated, then according to predetermined manner to the panorama sketch
Carry out edge enhancing processing as carrying out greyscale transformation, and to the panoramic picture after the progress greyscale transformation, and extract it is described into
The key edge point of the enhanced panoramic picture in row edge, and clustering processing is carried out to the key edge point, then according to poly-
Treated that key edge point determines whether the traveling lane of automobile shifts for class.The embodiment of the present invention is using panorama system as base
Plinth carries out lane shift detection under panning mode, realizes and improves lane shift Detection accuracy, and increases ADAS technologies
The target of integrated level.
Fig. 7 shows the circuit theory schematic diagram of automobile provided in an embodiment of the present invention, for convenience of description, only list with
The relevant part of the embodiment of the present invention, details are as follows：
Automobile provided in an embodiment of the present invention, including generation unit 100, processing unit 200 and judging unit 300；
Generation unit 100, for generating the panoramic picture of automobile；
Processing unit 200 for carrying out greyscale transformation to the panoramic picture according to predetermined manner, and carries out ash to described
Panoramic picture after degree transformation carries out edge enhancing processing and the extraction key for carrying out the enhanced panoramic picture in edge
Marginal point, and clustering processing is carried out to the key edge point；
Judging unit 300, for determining whether the traveling lane of automobile occurs according to the key edge point after clustering processing
Offset.
As a preferred embodiment of the present invention, generation unit 100 is specifically used for：
The multiple cameras for being mounted on the automobile predeterminated position are demarcated；
Establish the mapping between each camera image coordinate system and earth axes in calibrated the multiple camera
Relationship；
Default distortion correction processing is carried out to the multi-path video data of the multiple camera acquisition；
According to the mapping relations to by default distortion correction, treated that video data splices, obtain described complete
Scape image.
As a preferred embodiment of the present invention, processing unit 200 is specifically used for：
Extract pixel value of the V channel values in hsv color space as gray level image；
Greyscale transformation is carried out to the panoramic picture according to the pixel value, obtains panorama gray level image；
Convolutional calculation is carried out to the panorama gray level image using Sobel operators, obtains the side of the panorama gray level image
Edge enhances image.
As a preferred embodiment of the present invention, processing unit 200 also particularly useful for：
The edge enhanced images are scanned according to presetted pixel interval；
The pixel that gray value in the edge enhanced images is more than to default gray threshold is labeled as key edge point；
The key edge point is traversed, and clustering processing is carried out to the key edge point, obtains the key of multiple classifications
Marginal point.
As a preferred embodiment of the present invention, judging unit 300 is specifically used for：
Two most classifications of key edge point quantity are chosen, and calculate each key edge point in described two classifications respectively
The mean value of x coordinateWith
It willWithIt is respectively labeled as the x coordinate of two lane lines of the automobile current lane；
IfWithThe x coordinate x of continuous default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then
Judge that the running car track shifts, and carries out early warning.
It should be noted that automobile provided in an embodiment of the present invention and above application are in the lane shift judgment method of automobile
Embodiment correspond to, operation principle and mode are corresponding to be applicable in, and is just repeated no more here.
In embodiments of the present invention, the panoramic picture of automobile is firstly generated, then according to predetermined manner to the panorama sketch
Carry out edge enhancing processing as carrying out greyscale transformation, and to the panoramic picture after the progress greyscale transformation, and extract it is described into
The key edge point of the enhanced panoramic picture in row edge, and clustering processing is carried out to the key edge point, then according to poly-
Treated that key edge point determines whether the traveling lane of automobile shifts for class.The embodiment of the present invention is using panorama system as base
Plinth carries out lane shift detection under panning mode, realizes and improves lane shift Detection accuracy, and increases ADAS technologies
The target of integrated level.
It will be appreciated by those skilled in the art that it is only carried out for each unit that above-described embodiment includes according to function logic
It divides, but is not limited to above-mentioned division, as long as corresponding function can be realized；In addition, the tool of each functional unit
Body title is also only to facilitate mutually distinguish, the protection domain being not intended to restrict the invention.
Those of ordinary skill in the art are further appreciated that all or part of the steps of the method in the foregoing embodiments are can
It is completed with instructing relevant hardware by program, the program can be stored in a computer read/write memory medium
In, the storage medium, including ROM/RAM, disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of lane shift judgment method, applied to automobile, which is characterized in that the described method comprises the following steps：
Generate the panoramic picture of automobile；
According to predetermined manner to the panoramic picture carry out greyscale transformation, and to it is described progress greyscale transformation after panoramic picture into
The enhancing processing of row edge；
The key edge point of the progress enhanced panoramic picture in edge is extracted, and the key edge point is carried out at cluster
Reason；
Determine whether the traveling lane of automobile shifts according to the key edge point after clustering processing.
2. according to the method described in claim 1, it is characterized in that, it is described generation automobile panoramic picture the step of, including：
The multiple cameras for being mounted on the automobile predeterminated position are demarcated；
Establish the mapping relations between each camera image coordinate system and earth axes in calibrated the multiple camera；
Default distortion correction processing is carried out to the multi-path video data of the multiple camera acquisition；
According to the mapping relations to treated that video data splices by default distortion correction, the panorama sketch is obtained
Picture.
3. according to the method described in claim 1, it is characterized in that, described carry out ash according to predetermined manner to the panoramic picture
Degree transformation, and the step of edge enhances processing is carried out to the panoramic picture after the progress greyscale transformation and is included：
Extract pixel value of the V channel values in hsv color space as gray level image；
Greyscale transformation is carried out to the panoramic picture according to the pixel value, obtains panorama gray level image；
Convolutional calculation is carried out to the panorama gray level image using Sobel operators, the edge for obtaining the panorama gray level image increases
Strong image.
4. the according to the method described in claim 3, it is characterized in that, extraction progress enhanced panoramic picture in edge
Key edge point, and to the key edge point carry out clustering processing the step of, including：
The edge enhanced images are scanned according to presetted pixel interval；
The pixel that gray value in the edge enhanced images is more than to default gray threshold is labeled as key edge point；
The key edge point is traversed, and clustering processing is carried out to the key edge point, obtains the key edge of multiple classifications
Point.
5. according to the method described in claim 4, it is characterized in that, the key edge point according to after clustering processing determines vapour
The step of whether traveling lane of vehicle shifts, including：
Two most classifications of key edge point quantity are chosen, and calculates each key edge point x in described two classifications respectively and sits
Target mean valueWith
It willWithIt is respectively labeled as the x coordinate of two lane lines of the automobile current lane；
IfWithThe x coordinate x of continuous default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then judge
The running car track shifts, and carries out early warning.
6. a kind of automobile, which is characterized in that the automobile includes：
Generation unit, for generating the panoramic picture of automobile；
Processing unit, for carrying out greyscale transformation to the panoramic picture according to predetermined manner, and to the carry out greyscale transformation
Panoramic picture afterwards carries out edge enhancing processing and the extraction key edge for carrying out the enhanced panoramic picture in edge
Point, and clustering processing is carried out to the key edge point；
Judging unit, for determining whether the traveling lane of automobile shifts according to the key edge point after clustering processing.
7. automobile according to claim 6, which is characterized in that the generation unit is specifically used for：
The multiple cameras for being mounted on the automobile predeterminated position are demarcated；
Establish the mapping relations between each camera image coordinate system and earth axes in calibrated the multiple camera；
Default distortion correction processing is carried out to the multi-path video data of the multiple camera acquisition；
According to the mapping relations to treated that video data splices by default distortion correction, the panorama sketch is obtained
Picture.
8. automobile according to claim 6, which is characterized in that the processing unit is specifically used for：
Extract pixel value of the V channel values in hsv color space as gray level image；
Greyscale transformation is carried out to the panoramic picture according to the pixel value, obtains panorama gray level image；
Convolutional calculation is carried out to the panorama gray level image using Sobel operators, the edge for obtaining the panorama gray level image increases
Strong image.
9. automobile according to claim 8, which is characterized in that the processing unit also particularly useful for：
The edge enhanced images are scanned according to presetted pixel interval；
The pixel that gray value in the edge enhanced images is more than to default gray threshold is labeled as key edge point；
The key edge point is traversed, and clustering processing is carried out to the key edge point, obtains the key edge of multiple classifications
Point.
10. automobile according to claim 9, which is characterized in that the judging unit is specifically used for：
Two most classifications of key edge point quantity are chosen, and calculates each key edge point x in described two classifications respectively and sits
Target mean valueWith
It willWithIt is respectively labeled as the x coordinate of two lane lines of the automobile current lane；
IfWithThe x coordinate x of continuous default frame left and right edges of automobile in the panoramic picturelAnd xrBetween, then judge institute
It states running car track to shift, and carries out early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810040516.7A CN108256470A (en) | 2018-01-16 | 2018-01-16 | A kind of lane shift judgment method and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810040516.7A CN108256470A (en) | 2018-01-16 | 2018-01-16 | A kind of lane shift judgment method and automobile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108256470A true CN108256470A (en) | 2018-07-06 |
Family
ID=62741260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810040516.7A Pending CN108256470A (en) | 2018-01-16 | 2018-01-16 | A kind of lane shift judgment method and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256470A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027423A (en) * | 2019-11-28 | 2020-04-17 | 北京百度网讯科技有限公司 | Lane line detection method and device and electronic equipment |
| CN111243034A (en) * | 2020-01-17 | 2020-06-05 | 广州市晶华精密光学股份有限公司 | Panoramic auxiliary parking calibration method, device, equipment and storage medium |
| CN114821531A (en) * | 2022-04-25 | 2022-07-29 | 广州优创电子有限公司 | Lane line recognition image display system based on electronic outside rear-view mirror ADAS |
| CN114801993A (en) * | 2022-06-28 | 2022-07-29 | 鹰驾科技（深圳）有限公司 | Automobile blind area monitoring system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470807A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Accurate detection method for highroad lane marker line |
| US20090174577A1 (en) * | 2007-11-29 | 2009-07-09 | Aisin Aw Co., Ltd. | Image recognition apparatuses, methods and programs |
| US20100188507A1 (en) * | 2009-01-23 | 2010-07-29 | Toyota Jidosha Kabushiki Kaisha | Road lane marker detection apparatus and road lane marker detection method |
| CN103192829A (en) * | 2013-03-22 | 2013-07-10 | 上海交通大学 | Lane departure warning method and lane departure warning device based on around view |
| CN104309606A (en) * | 2014-11-06 | 2015-01-28 | 中科院微电子研究所昆山分所 | 360-degree panorama based lane departure warning method |
-
2018
- 2018-01-16 CN CN201810040516.7A patent/CN108256470A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090174577A1 (en) * | 2007-11-29 | 2009-07-09 | Aisin Aw Co., Ltd. | Image recognition apparatuses, methods and programs |
| CN101470807A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Accurate detection method for highroad lane marker line |
| US20100188507A1 (en) * | 2009-01-23 | 2010-07-29 | Toyota Jidosha Kabushiki Kaisha | Road lane marker detection apparatus and road lane marker detection method |
| CN103192829A (en) * | 2013-03-22 | 2013-07-10 | 上海交通大学 | Lane departure warning method and lane departure warning device based on around view |
| CN104309606A (en) * | 2014-11-06 | 2015-01-28 | 中科院微电子研究所昆山分所 | 360-degree panorama based lane departure warning method |
Non-Patent Citations (1)
| Title |
|---|
| 蔡英凤等: "基于聚类算法的车道线检测方法", 《江苏大学学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027423A (en) * | 2019-11-28 | 2020-04-17 | 北京百度网讯科技有限公司 | Lane line detection method and device and electronic equipment |
| CN111027423B (en) * | 2019-11-28 | 2023-10-17 | 北京百度网讯科技有限公司 | Automatic driving lane line detection method and device and electronic equipment |
| CN111243034A (en) * | 2020-01-17 | 2020-06-05 | 广州市晶华精密光学股份有限公司 | Panoramic auxiliary parking calibration method, device, equipment and storage medium |
| CN114821531A (en) * | 2022-04-25 | 2022-07-29 | 广州优创电子有限公司 | Lane line recognition image display system based on electronic outside rear-view mirror ADAS |
| CN114801993A (en) * | 2022-06-28 | 2022-07-29 | 鹰驾科技（深圳）有限公司 | Automobile blind area monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970566B2 (en) | Lane line detection method and apparatus | |
| CN107862290B (en) | Lane line detection method and system | |
| US8244027B2 (en) | Vehicle environment recognition system | |
| US8332134B2 (en) | Three-dimensional LIDAR-based clear path detection | |
| US8428305B2 (en) | Method for detecting a clear path through topographical variation analysis | |
| JP4942509B2 (en) | Vehicle position detection method and apparatus | |
| US7106886B2 (en) | Road white line recognition apparatus and method | |
| US7936903B2 (en) | Method and a system for detecting a road at night | |
| JP3352655B2 (en) | Lane recognition device | |
| US8294794B2 (en) | Shadow removal in an image captured by a vehicle-based camera for clear path detection | |
| CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
| CN108256470A (en) | A kind of lane shift judgment method and automobile | |
| US7262710B2 (en) | Collision time estimation apparatus for vehicles, collision time estimation method for vehicles, collision alarm apparatus for vehicles, and collision alarm method for vehicles | |
| JP4856656B2 (en) | Vehicle detection device | |
| AU2133599A (en) | Process for determining vehicle dynamics | |
| CN107832674B (en) | Lane line detection method | |
| CN109829365B (en) | Multi-scene adaptive driving deviation and turning early warning method based on machine vision | |
| US20210042955A1 (en) | Distance estimation apparatus and operating method thereof | |
| JP2008262333A (en) | Road surface discrimination device and road surface discrimination method | |
| JP3800785B2 (en) | White line recognition device | |
| KR101699014B1 (en) | Method for detecting object using stereo camera and apparatus thereof | |
| CN107220632B (en) | Road surface image segmentation method based on normal characteristic | |
| JP5411671B2 (en) | Object detection device and driving support system | |
| JP2010224936A (en) | Object detection device | |
| JP6132807B2 (en) | Lane mark recognition device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |