CN108805790A - A kind of Information acquisition system of the drive way and the lane information processing method using the system - Google Patents
A kind of Information acquisition system of the drive way and the lane information processing method using the system Download PDFInfo
- Publication number
- CN108805790A CN108805790A CN201810592903.1A CN201810592903A CN108805790A CN 108805790 A CN108805790 A CN 108805790A CN 201810592903 A CN201810592903 A CN 201810592903A CN 108805790 A CN108805790 A CN 108805790A
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- image processing
- processing method
- light source
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 230000010365 information processing Effects 0.000 title description 5
- 230000033001 locomotion Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000000034 method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009977 dual effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
This application involves the processing methods of a kind of lane information harvester and the image obtained based on the lane information harvester, wherein, lane information harvester includes light source, image acquisition units and image processing unit, it is characterized in that, the quantity of the light source, described image collecting unit and described image processing unit is two, and the light that is sent out of the light source is line-structured light, the relative movement direction of the line-structured light and collected object is at an angle.The device of the application can carry out Image Acquisition to broader road surface simultaneously, and can handle the image collected, obtain more true information of road surface.
Description
Technical field
The application belongs to vehicular field, and in particular to a kind of Information acquisition system of the drive way and the information processing using the system
Method.
Background technology
Currently, for the detection of carriageway surfacing, it is using line to have had the detection mode of automation, one of which
Structure light image acquisition system carries out information of road surface acquisition to track, is then based on collected information and judges pavement behavior.Tool
For body, line-structured light image capturing system is to be based on laser triangulation principle, utilizes area array CCD camera and cable architecture light source pair
Road surface measures.The measurement method emits light beam in testee surface by cable architecture light source, forms a laser
Line, CCD camera deform due to being influenced by body surface height fluctuating, lead to from another angular observation, the laser rays
Elevation information on the profiling object surface line can be obtained by crossing the correlation computations of the pixel coordinate of the laser rays in image plane.Together
When only need to can be realized to obtain the three-D profile distribution of object plus one-dimensional scanning on the basis of the detection method.
However, for this system, single this system can only acquire the track of 2m wide.In order to cover state, save
The full track of main line must consider to use dual system, so as to realize the acquisition to the tracks 4m.When using two systems,
As a result of two cameras, must consider to being spliced by two obtained images of camera.Using two lasers
When, if the laser rays of two lasers all perpendicular to vehicle direction of advance, for vehicle forward direction, controls two
A camera photographed two laser rays, can cause crosstalk in this way.
Invention content
To solve the above-mentioned problems, present applicant proposes a kind of new Information acquisition system of the drive way, and are based on the system
Collected information and the lane information processing method that carries out.
Specifically, the Information acquisition system of the drive way of the application uses laser deflecting certain angle, two laser
Line is parallel, avoids occurring two laser rays in a camera.
1, a kind of image collecting device, including light source, image acquisition units and image processing unit, which is characterized in that
The quantity of the light source, described image collecting unit and described image processing unit is two, and the light source is sent out
Light be line-structured light, the relative movement direction of the line-structured light and collected object is at an angle.
2, image collecting device as described in technical solution 1, which is characterized in that the light source is laser.
3, image collecting device as described in technical solution 1, which is characterized in that described image collecting unit is CCD camera.
4, such as technical solution 1-3 any one of them image collecting device, which is characterized in that described image harvester is pacified
Loaded on vehicle.
5, the image processing method based on such as technical solution 1-4 any one of them image collecting device, which is characterized in that
Include the following steps：
Step 1：Collected two images, referred to as left figure and right figure are read, left figure is formed into matrix aL, right figure formed
Matrix aR；
Step 2：Left figure is first handled, the P points that j rows i is arranged in matrix is taken, the point positions P is moved up according to certain linear scale；
Step 3：It carries out being recycled to image most terminal column according to row；
Step 4：Step 2,3 operations are carried out to right figure；
Step 5：Left and right figure is spliced.
6, such as 5 described image processing method of technical solution, which is characterized in that the matrix a described in the step 1LAnd aR
It is as follows：
In position it is linearly to move up to the gray value of all pixels point in image, movement rule is such as in the step 2
Under：
Appoint any point P taken in matrix, it is i rows j row to remember it in a matrix, and laser rays is being installed with horizontal direction angle
Shi Jiwei angle, tan (angle) value is denoted as t.P is that the coordinate of (n-j) * t, P are (i, j) at a distance from P ', then the seat of P '
It is designated as (i, (n-j) * t+j), the abscissa of note P ' is j_new, and value range, between n, stops calculating 1 as beyond if.It will
Grey value interpolation neighbouring j_new is assigned to new matrix b (i, j).
7, such as 6 described image processing method of technical solution, which is characterized in that in the step 3, row is recycled into every trade
End, then into row_column cycle, arrive next column, traverse each pixel.
8, such as 7 described image processing method of technical solution, which is characterized in that in the step 5, will be corrected in step 4
Left and right figure afterwards is spliced, and spliced image is obtained.
, can be to avoid crosstalk caused by dual system according to above system, also, use the above-mentioned image mosaic side of the application
Method can effectively restore image, so as to effectively carry out Image Acquisition to broader road surface.
Description of the drawings
Fig. 1 is the schematic diagram of single system in the prior art.
Fig. 2 is the installation diagram of the dual system of the application onboard.
Fig. 3 is the laser rays and vehicle traveling direction schematic diagram of the application.
Fig. 4 is the collected original image of dual system of the application.
Fig. 5 is using direct rotation mode treated image.
Fig. 6 is the schematic diagram of the image procossing of the application.
Fig. 7 is the figure with deceleration strip obtained using the image processing method of the application.
Fig. 8 is the figure with pavement strip obtained using the image processing method of the application.
Specific implementation mode
Below in conjunction with attached drawing come to the present invention Information acquisition system of the drive way and the information processing that is carried out based on the system
Method.
As shown in Fig. 2, laser, CCD camera in the image capturing system in the present invention, including traditional system and
Image processing unit, whole system are installed onboard, with the traveling of vehicle, are acquired to the information of road surface in track.Wherein,
The number of laser is two, also, the direction of advance of the laser of laser sent out and vehicle is at an angle, and two
The direction of the laser of laser is parallel to each other, as shown in Figure 3.
Although above-described embodiment is by taking the acquisition of the road pavement information of vehicle as an example, it will be evident that the application
In image capturing system can be equally used for the acquisition of other information, such as information collection or the big template on railway road surface
Surface information acquisition of material etc., as long as there are relative motions between laser and collected object.
Further, the system based on the present invention, since the image collected information needs to splice, and due to directly to two
A camera the image collected, which carries out rotary splicing, can lead to the dislocation of image, and therefore, correspondingly, the application is also to this system
The collected information of institute provides a kind of image split-joint method.
As shown in figure 4, it is the collected original image information of information acquisition system, wherein Fig. 4 (a) is left side
The image information that system acquisition arrives, Fig. 4 (b) are the image information that the system acquisition on right side arrives.The laser sent out due to laser
There are certain angles with road direction, therefore, collected information there is also the inclination of certain angle, this just need be by two
The image of system is spliced.If artwork directly rotated according to certain angle, as shown in Figure 5, it can be seen that deceleration strip becomes
For level, but deceleration strip still misplaces.If further carrying out translation splicing up and down to image, deceleration strip can be spelled
It connects, but road surface still misplaces, and also this spliced based on artificial observation, changing a width figure can misplace again, Bu Nengshi
Existing automatic Mosaic.In order to ensure the correctness of image mosaic, present applicant proposes joining method below, principle such as Fig. 6 institutes
Show.
Image is denoted as matrix A firstm×n, it is shown below.
As shown in fig. 6, appointing any point P taken in matrix, it is i rows j row to remember it in a matrix.Laser rays and horizontal direction
Angle can determine when mounted is denoted as α.P is that the coordinate of (n-j) tan α, P are (i, j) at a distance from P ', then the coordinate of P ' is
The abscissa of (i, (n-j) tan α+j), note P ' are j ', and value range should stop calculating 1 between n as beyond if.By j '
Neighbouring grey value interpolation is assigned to new matrix b (i, j), and this completes the linear movements of gray value.
P ' the coordinates after moving up are calculated first, determine it without departing from range, then to it into row interpolation.Then it is recycled to
Next line, until last column, then arrive next column.
J'=(n-j) tan α+j (1)
In formula, j is the ordinate of P points, and j ' is the ordinate of P ' points, and n is picturewide, and α is laser rays and horizontal direction
Angle.J ' is not exactly integer, rounds up to it and downward rounding, such as formula (2)：
A=ceil (j'), b=floor (j') (2)
In formula, a j's ' rounds up, and b is downward rounding.Acquire P ' point coordinate after, by P ' point near point (i,
A), (i, b) point carries out grey value interpolation, and is assigned to (i, j) point of new images, as shown in formula (3)：
G=A (i, a) (a-j') (3) (j'-b)+A (i, b)
G is the gray value after interpolation in formula, since G may be non-integer, need to carry out rounding to it.
G'=floor (G) (4)
The upper each point of whole figure is carried out formula (1) to (4) such as to handle, picture is corrected, a left side for acquisition is applied to
Right figure, then spliced just to have can be obtained and meet actual picture.
Using the above method, to actual acquisition to figure splice, good reduction effect can be obtained.Using this
Method in application handles the image with deceleration strip, and treated, and figure such as Fig. 7 (a) and Fig. 7 (b) in left and right is shown.It can
To find out deceleration strip leveling, and left and right figure other positions are also relatively reasonable.Left and right figure is spliced, such as Fig. 7 (c) institutes
Show, it can be seen that splicing effect is preferable.
Fig. 8 (a) and Fig. 8 (b) is the image of left and right system while the right and left of acquisition, this image is vehicle in turn
The cross-hair lines of the picture of acquisition, left and right is a graticule being unified into, and is obviously had dislocation in the figure of left and right.It will according to the algorithm of research
Left and right figure is corrected and is spliced, shown in stitching image such as Fig. 8 (c).
Claims (8)
1. a kind of image collecting device, including light source, image acquisition units and image processing unit, which is characterized in that described
The quantity of light source, described image collecting unit and described image processing unit is two, and the light that the light source is sent out
For line-structured light, the relative movement direction of the line-structured light and collected object is at an angle.
2. image collecting device as described in claim 1, which is characterized in that the light source is laser.
3. image collecting device as described in claim 1, which is characterized in that described image collecting unit is CCD camera.
4. image collecting device as described in any one of claims 1-3, which is characterized in that described image harvester is installed on
On vehicle.
5. the image processing method based on image collecting device according to any one of claims 1-4, which is characterized in that including
Following steps：
Step 1：Collected two images, referred to as left figure and right figure are read, left figure is formed into matrix aL, right figure formation matrix
aR；
Step 2：Left figure is first handled, the P points that j rows i is arranged in matrix is taken, the point positions P is moved up according to certain linear scale；
Step 3：It carries out being recycled to image most terminal column according to row；
Step 4：Step 2,3 operations are carried out to right figure；
Step 5：Left and right figure is spliced.
6. image processing method as claimed in claim 5, which is characterized in that the matrix a described in the step 1LAnd aRSuch as
Under：
In position it is linearly to move up to the gray value of all pixels point in image, movement rule is as follows in the step 2：
Appoint any point P taken in matrix, it is i rows j row to remember it in a matrix, and laser rays is remembered when mounted with horizontal direction angle
For angle, tan (angle) value is denoted as t, P and P ' at a distance from be the coordinate of (n-j) * t, P be (i, j), then the coordinate of P ' is
The abscissa of (i, (n-j) * t+j), note P ' are j_new, and value range, between n, stops calculating 1 as beyond if.By j_new
Neighbouring grey value interpolation is assigned to new matrix b (i, j).
7. image processing method as claimed in claim 6, which is characterized in that in the step 3, row end is recycled into every trade
Tail, then into row_column cycle, arrive next column, traverse each pixel.
8. image processing method as claimed in claim 7, which is characterized in that in the step 5, after being corrected in step 4
Left and right figure is spliced, and spliced image is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810592903.1A CN108805790A (en) | 2018-06-11 | 2018-06-11 | A kind of Information acquisition system of the drive way and the lane information processing method using the system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810592903.1A CN108805790A (en) | 2018-06-11 | 2018-06-11 | A kind of Information acquisition system of the drive way and the lane information processing method using the system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108805790A true CN108805790A (en) | 2018-11-13 |
Family
ID=64088247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810592903.1A Pending CN108805790A (en) | 2018-06-11 | 2018-06-11 | A kind of Information acquisition system of the drive way and the lane information processing method using the system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805790A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114111651A (en) * | 2021-11-25 | 2022-03-01 | 江苏科技大学 | Vehicle-mounted pavement depression detection method based on multi-line structured light |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098047A (en) * | 2010-10-29 | 2012-05-24 | Toshiba Transport Eng Inc | Apparatus, method and program for measuring wheel shape |
| EP2517799A1 (en) * | 2011-04-26 | 2012-10-31 | Centre de Recherches Métallurgiques asbl - Centrum voor Research in de Metallurgie vzw | Apparatus and method for industrial online micro-topography and waviness measurements on moving products |
| CN103485266A (en) * | 2013-10-09 | 2014-01-01 | 武汉武大卓越科技有限责任公司 | High-definition pavement image acquisition method and apparatus |
| CN103993547A (en) * | 2014-05-07 | 2014-08-20 | 长安大学 | Relative datum point equipped line laser pavement rutting detection system and method |
| CN105067633A (en) * | 2015-08-11 | 2015-11-18 | 江西省公路工程检测中心 | Vehicle-mounted type automatic pavement damage recognition device based on image processing and application method |
| CN105421201A (en) * | 2015-11-24 | 2016-03-23 | 中公高科养护科技股份有限公司 | Road surface image acquisition device and road surface image acquisition vehicle |
| CN105571512A (en) * | 2015-12-15 | 2016-05-11 | 北京康拓红外技术股份有限公司 | Vehicle information acquisition method based on integration of depth information and visual image information and device thereof |
| CN105651207A (en) * | 2016-02-23 | 2016-06-08 | 中山大学 | Laser and image processing based vehicular side skewing angle dynamic measurement method and device |
| EP3115742A1 (en) * | 2015-07-10 | 2017-01-11 | Hexagon Technology Center GmbH | 3d measuring machine |
| CN107830813A (en) * | 2017-09-15 | 2018-03-23 | 浙江理工大学 | The longaxones parts image mosaic and flexural deformation detection method of laser wire tag |
-
2018
- 2018-06-11 CN CN201810592903.1A patent/CN108805790A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098047A (en) * | 2010-10-29 | 2012-05-24 | Toshiba Transport Eng Inc | Apparatus, method and program for measuring wheel shape |
| EP2517799A1 (en) * | 2011-04-26 | 2012-10-31 | Centre de Recherches Métallurgiques asbl - Centrum voor Research in de Metallurgie vzw | Apparatus and method for industrial online micro-topography and waviness measurements on moving products |
| CN103485266A (en) * | 2013-10-09 | 2014-01-01 | 武汉武大卓越科技有限责任公司 | High-definition pavement image acquisition method and apparatus |
| CN103993547A (en) * | 2014-05-07 | 2014-08-20 | 长安大学 | Relative datum point equipped line laser pavement rutting detection system and method |
| EP3115742A1 (en) * | 2015-07-10 | 2017-01-11 | Hexagon Technology Center GmbH | 3d measuring machine |
| CN105067633A (en) * | 2015-08-11 | 2015-11-18 | 江西省公路工程检测中心 | Vehicle-mounted type automatic pavement damage recognition device based on image processing and application method |
| CN105421201A (en) * | 2015-11-24 | 2016-03-23 | 中公高科养护科技股份有限公司 | Road surface image acquisition device and road surface image acquisition vehicle |
| CN105571512A (en) * | 2015-12-15 | 2016-05-11 | 北京康拓红外技术股份有限公司 | Vehicle information acquisition method based on integration of depth information and visual image information and device thereof |
| CN105651207A (en) * | 2016-02-23 | 2016-06-08 | 中山大学 | Laser and image processing based vehicular side skewing angle dynamic measurement method and device |
| CN107830813A (en) * | 2017-09-15 | 2018-03-23 | 浙江理工大学 | The longaxones parts image mosaic and flexural deformation detection method of laser wire tag |
Non-Patent Citations (2)
| Title |
|---|
| 李清泉等: "车载道路快速检测与测量技术研究", 《交通信息与安全》 * |
| 郑建用等: "一种基于双线激光的三维测量方法", 《计算机与现代化》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114111651A (en) * | 2021-11-25 | 2022-03-01 | 江苏科技大学 | Vehicle-mounted pavement depression detection method based on multi-line structured light |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11062155B2 (en) | Monocular cued detection of three-dimensional structures from depth images | |
| CN106871805B (en) | vehicle-mounted rail gauge measuring system and measuring method | |
| WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
| JP3895238B2 (en) | Obstacle detection apparatus and method | |
| CN102506830B (en) | Vision-based positioning method and device | |
| CN104567684A (en) | Contact network geometrical parameter detection method and device | |
| JP6551623B1 (en) | Information processing apparatus, moving body, image processing system, and information processing method | |
| US11671574B2 (en) | Information processing apparatus, image capture apparatus, image processing system, and method of processing a plurality of captured images of a traveling surface where a moveable apparatus travels | |
| CN112880599B (en) | Roadbed flatness detection system based on four-foot robot and working method | |
| DE102009012435A1 (en) | Apparatus and method for monocular motion stereo-based detection of free parking spaces | |
| CN112204614B (en) | Motion segmentation in video from non-stationary cameras | |
| CN111091076B (en) | Tunnel limit data measuring method based on stereoscopic vision | |
| JP2002156229A (en) | Mobile displacement measuring method and device for structure | |
| CN106403828A (en) | Monorail contact line remain height measurement method based on checkerboard calibration and monorail contact line remain height measurement system thereof | |
| CN110023988B (en) | Method and system for generating a combined overhead image of a roadway | |
| CN112833784B (en) | Steel rail positioning method combining monocular camera with laser scanning | |
| CN109544607B (en) | Point cloud data registration method based on road sign line | |
| CN117848238B (en) | Rail transit station actual limit measurement method based on laser point cloud | |
| CN113847884B (en) | Line scanning-based refined three-dimensional measurement and modeling method | |
| CN118348015A (en) | Self-moving subway tunnel structure apparent defect detection equipment and method | |
| CN111390913B (en) | Automatic detection method for bridge bottom structure | |
| CN108805790A (en) | A kind of Information acquisition system of the drive way and the lane information processing method using the system | |
| JP3629935B2 (en) | Speed measurement method for moving body and speed measurement device using the method | |
| JP5952759B2 (en) | Overhead wire position measuring apparatus and method | |
| WO2021044564A1 (en) | Forward monitoring device and method for calibrating forward monitoring 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181113 |