CN206593670U - The device of lane detection is carried out using gyro sensor - Google Patents
The device of lane detection is carried out using gyro sensor Download PDFInfo
- Publication number
- CN206593670U CN206593670U CN201621194002.XU CN201621194002U CN206593670U CN 206593670 U CN206593670 U CN 206593670U CN 201621194002 U CN201621194002 U CN 201621194002U CN 206593670 U CN206593670 U CN 206593670U
- Authority
- CN
- China
- Prior art keywords
- gyro sensor
- module
- lane
- carried out
- lane detection
- 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.)
- Expired - Fee Related
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The utility model is related to a kind of device that lane detection is carried out using gyro sensor.It solves the existing low problem of lane detection precision.Including the image capture module being arranged on vehicle, described image capture module is connected by MCU module with image display, there is left demarcation straight line display unit and right demarcation straight line display unit in image display, and MCU module is connected with hand demarcation rectilinear movement operating-controlling mechanism, gyro sensor is additionally provided with vehicle, and gyro sensor is connected with MCU module, and MCU module is connected with the control unit that image capture module can be driven to move.Advantage is：Man-machine interaction is convenient and swift, requires relatively low to operating personnel, supports on-line proving, can remove a series of activities that off-line calibration needs to gather video image and handle from；Whole device is easily assembled, and can save a large amount of valuable times of developer, and the resource consumption in terms of human and material resources.
Description
Technical field
The utility model belongs to computer vision and intelligent transportation field, more particularly to a kind of to be entered using gyro sensor
The device of driveway line detection.
Background technology
In recent years, as the technology in terms of intelligent transportation field and computer vision is continued to develop, based on computer vision
Automobile active safety product also increasingly enrich.Such as adaptive cruise control system (ACC), lane departur warning (LDW), car
Road keeps auxiliary (LKA) and side object detection (SOD) etc., but these product correlation techniques are realized in the detection of lane line
Basis.
The common method for detecting lane lines based on camera is usually that first image is pre-processed, and then substantially determines car
Diatom location, recycles Hough transformation to carry out lane detection, but picture quality is bad, the lane line detected
Miscellaneous line is more, and especially slight crack of the rainy day wheel marking either on road can all be misidentified as lane line or run into barrier
Hinder thing closely to block, when the surface conditions such as blocking of trees or building effects, because camera can not be collected comprising foot
The image of more than enough lane information and the problems such as there is missing inspection, flase drop, the identification for the lane line for being thus is not accurate enough.Therefore,
The high robust algorithm that set of environmental strong adaptability, arithmetic speed are fast, transplantability is good how is designed, is the heat of association area research
One of point.Meanwhile, although the more existing product function admirable on lane detection, being due to that algorithm is relative complex makes
Early stage calibration process complexity is obtained, the professional knowledge to assembler requires of a relatively high, so research and development are a set of to be beneficial to industrial products
Accurately also it is necessary the algorithm and raising lane detection of assembling.
In order to solve the problem of prior art is present, people have carried out long-term exploration, it is proposed that miscellaneous solution
Scheme.For example, Chinese patent literature discloses a kind of method for detecting lane lines and device [application number：201310616153.4],
This method includes obtaining vehicle front image；Rim detection is carried out to vehicle front image, edge graph is obtained；Obtained according to former frame
The position of the lane line taken determines original lane line detection zone in edge graph；Original lane line detection zone is divided into N
Individual small detection zone, N is more than or equal to 2；According to the edge graph numerical value of each small detection zone and the pixel of each small detection zone
The sum of point, it is accurate lane detection region to determine some small detection zone；Obtain and work as from accurate lane detection region
The lane line of previous frame.Such scheme solves the problem of existing lane detection is not accurate enough to a certain extent, but the party
Case still can not fundamentally solve computationally intensive, the problem of subtracting influence of the miscellaneous line to testing result.
The content of the invention
The purpose of this utility model is in view of the above-mentioned problems, providing a kind of simple and reasonable, high-precision utilization gyro
Instrument sensor carries out the device of lane detection.
To reach above-mentioned purpose, the utility model employs following technical proposal：This enters driving using gyro sensor
The device of diatom detection, including the image capture module being arranged on vehicle, described image capture module by MCU module with
Image display is connected, it is characterised in that have left demarcation straight line display unit and right mark in described image display
Boning out display unit, and described MCU module is connected with hand demarcation rectilinear movement operating-controlling mechanism, is additionally provided with vehicle
Gyro sensor, and described gyro sensor is connected with MCU module, and described MCU module is with that can drive image to adopt
The control unit for collecting module movement is connected.
In the above-mentioned device that lane detection is carried out using gyro sensor, described gyro sensor has
Angle of pitch detection module, inclination angle detection module and yaw angle detection module.
In the above-mentioned device that lane detection is carried out using gyro sensor, described gyro sensor case peace
On meter panel of motor vehicle.
In the above-mentioned device that lane detection is carried out using gyro sensor, described hand demarcation straight line is moved
Dynamic operating-controlling mechanism includes button and/or knob, and described button and/or knob is connected with pattern process module, and described figure
Shape processing module is connected with MCU module.
In the above-mentioned device that lane detection is carried out using gyro sensor, described image display is to set
Put the display screen in vehicle body.
In the above-mentioned device that lane detection is carried out using gyro sensor, described hand demarcation straight line is moved
Dynamic operating-controlling mechanism is the touch sensible module being arranged in image display.
In the above-mentioned device that lane detection is carried out using gyro sensor, described image display is tactile
Touch screen.
In the above-mentioned device that lane detection is carried out using gyro sensor, described image capture module is to set
Put the video camera on vehicle body.
Compared with prior art, the advantage of this device that lane detection is carried out using gyro sensor is：Car
Diatom accuracy of detection is high, and man-machine interaction is convenient and swift, requires relatively low to operating personnel, supports on-line proving, can remove offline from
Demarcation needs a series of activities for gathering video image and handling；Whole device is easily assembled, and can save developer largely precious
Expensive time, and the resource consumption in terms of human and material resources.
Brief description of the drawings
Fig. 1 is structured flowchart of the present utility model.
Fig. 2 is the flow chart in embodiment of the present utility model.
Fig. 3 is lane detection flow chart in embodiment of the present utility model.
Fig. 4 is by the actual calibrated camera views figure of man-machine interaction.
Fig. 5 is image coordinate system schematic diagram.
Fig. 6 is the emerging administrative division map of sense that the maximum contiguous range fluctuated according to slope and intercept is chosen.
Fig. 7 is the emerging area segmentation figure of sense.
In figure, wherein Δ kLRepresent the difference of two straight slopes of red straight line and left-lane line；ΔbLRepresent blue straight line with
The difference of two Linear intercepts of left-lane line；ΔkRRepresent the difference of two straight slopes of red straight line and right-lane line；ΔbRRepresent blue
The difference of two Linear intercepts of color straight line and right-lane line；Region in picture between the blue line in two, left side is left-lane Gan Xing areas
Domain ROI；Region between the blue line in two, right side is the emerging region ROI of right lane sense；Δ h represents each section of height；1 represents left
Lane line；11 represent left demarcation straight line；2 represent right-lane line；21 represent that right demarcation straight line, image display 3, left demarcation are straight
Line display unit 31, touch sensible module 311, right demarcation straight line display unit 32, hand demarcation rectilinear movement operating-controlling mechanism
4th, pattern process module 41, image capture module 5, MCU module 6, gyro sensor 7, angle of pitch detection module 71, inclination angle
Detection module 72, yaw angle detection module 73, control unit 8.
Embodiment
The utility model is described in more detail with reference to the accompanying drawings and detailed description.
As described in Figure 1, this device that lane detection is carried out using gyro sensor, including the figure being arranged on vehicle
As acquisition module 5, image capture module 5 is connected by MCU module 6 with image display 3, it is characterised in that image is shown
There is left demarcation straight line display unit 31 and right demarcation straight line display unit 32 in module 3, and MCU module 6 is connected with hand
Demarcation rectilinear movement operating-controlling mechanism 4, is additionally provided with gyro sensor 7 on vehicle, and gyro sensor 7 is connected with MCU moulds
Block 6, and MCU module 6 is with that can drive the control unit 8 of the movement of image capture module 5 to be connected.
Specifically, gyro sensor 7 here have angle of pitch detection module 71, inclination angle detection module 72 and partially
Navigated angle detection module 73, it is preferable that gyro sensor 7 here is arranged on meter panel of motor vehicle.
Specifically, hand demarcation rectilinear movement operating-controlling mechanism 4 here includes button and/or knob, button and/or rotation
Button is connected with pattern process module 41, and pattern process module 41 is connected with MCU module 6.Here image display 3 is to set
Put the display screen in vehicle body.Hand demarcation rectilinear movement operating-controlling mechanism 4 can also be to be arranged on image display 3
On touch sensible module 311, that is to say, that image display 3 here be touch-screen.
As shown in figs. 1-7, the use for the device that lane detection is carried out using gyro sensor is used in the present embodiment
The method that lane detection effective range is determined using gyro sensor, is comprised the steps：S1, detection body gesture angle:
The posture of vehicle is monitored by the gyro sensor on vehicle and real-time attitude data are gathered；Gyro sensor case
On meter panel of motor vehicle and 3 current attitude angles of collection vehicle body, the respectively angle of pitch, inclination angle and yaw angle；It is S2, suitable
When adjust camera angle：Control unit gathers real-time attitude data according to gyro sensor, and camera is adjusted in real time, keeps
Camera is all the time parallel to immediately ahead of level, it is ensured that the lane line that camera is shot is all the time in FX；S3, lane line inspection
Survey：Lane detection is carried out using the device that lane detection is carried out using gyro sensor.
Specifically, the device for carrying out lane detection using gyro sensor in step S3 comprises the following steps：Step
Rapid A, selection demarcation scene:It is demarcation scene to choose and be decorated with the track of left-lane line 1 and right-lane line 2, and Current vehicle is stopped
Or travel between the left-lane line 1 and right-lane line 2 in place track, and ensure the left-lane line in Current vehicle place track
1 with right-lane line 2 in camera review it is visible；Here left-lane line 1 and right-lane line 2 is respectively solid line, dotted line, yellow line
With the combination of any one or more in white line；Current vehicle should stop or travel as far as possible the left-lane in place track
Centre between line 1 and right-lane line 2, has currently also been not excluded for a range of deviation.
Step B, man-machine interaction demarcation：The mobile default left demarcation straight line 11 being shown in camera review is so that left mark
Boning out 11 overlaps to realize that left-lane line 1 is demarcated with the tangent line of left-lane line 1 or left-lane line 1, and movement is shown in shooting
Default right demarcation straight line 21 in machine image is so that right demarcation straight line 21 is overlapped with the tangent line of right-lane line 2 or right-lane line 2
So as to realize that right-lane line 2 is demarcated, now left-lane line 1 and straight line of the right-lane line 2 in image coordinate system are calculated respectively
Equation；In above-mentioned steps B, using the intersection point of camera optical axis and camera image plane as origin, laterally prolonged to the right with origin
Direction is stretched as x-axis bearing of trend, using origin longitudinally downward direction as y-axis bearing of trend, image coordinate system is set up, after demarcation
Linear equation of the left-lane line 1 in image coordinate system is y=kL·x+bL, wherein kLIt is the slope of left-lane line, bLIt is left car
The intercept of diatom on the y axis, linear equation of the right-lane line 2 in image coordinate system is y=k after demarcationR·x+bR, wherein kR
It is the slope of right-lane line, bRIt is the intercept of right-lane line on the y axis；Pass through the left demarcation straight line 11 of manual manipulation mechanism controls
Translation and/or rotation pass through the right demarcation straight line of manual manipulation mechanism controls to adjust the intercept and/or slope of left demarcation straight line 11
21 translations and/or rotation are to adjust the intercept and/or slope of right demarcation straight line 21, and manual manipulation mechanism here includes button
And/or knob.
Step C, pretreatment image：By camera acquisition to present frame camera review be converted into gray-scale map, and will step
The neighborhood of left-lane line 1 demarcated in rapid B and the field of right-lane line 2 are respectively as region of interest ROI, then respectively to interested
Region ROI does fragmentation thresholdization processing；If the maximum magnitude of the slope fluctuation of left-lane line 1 is (- Δ kL,ΔkL), intercept fluctuation
Maximum magnitude be (- Δ bL,ΔbL), the maximum magnitude of the slope fluctuation of right-lane line 2 is (- Δ kR,ΔkR), intercept fluctuation
Maximum magnitude be (- Δ bR,ΔbR), choose the slope of left-lane line 1 contiguous range maximum with intercept fluctuation and be used as left-lane line
1 region of interest ROI, chooses the slope of right-lane line 2 contiguous range maximum with intercept fluctuation emerging as the sense of right-lane line 2
Interesting region ROI, being arranged on slope fluctuation range, camera has a little shake in the process of moving mainly due to vehicle, or
It is lane line width and track spacing difference under some other correlative factors, such as varying environment so that in camera views
Lane line can be fluctuated near the position of previous moment；Respectively by region of interest ROI homogenous segmentations or inequality from top to bottom
Even segmentation, every section of height is set to Δ hi, uneven can also be segmented with homogenous segmentations, for convenience, herein using uniform
Segmentation statement, is segmented more, testing result is more accurate in theory, it is contemplated that the problems such as real-time in practical application, institute
Segments should not be too many, should be appropriate according to actual conditions；The average of Δ hi in each section of region of interest ROI is calculated respectively
Δ h, and as the threshold value of this section, then by region of interest ROI binaryzation, the threshold of adjacent two sections of region of interest ROI
When being worth different, the slope in the line of demarcation of adjacent two sections of region of interest ROI is 0.
Step D, detection lane line and undated parameter：Lane line is detected respectively in step C region of interest ROI, if
Linear equation slope and/or intercept that new left-lane line 1 then updates left-lane line 1 are detected, otherwise retains its last moment
Value；The linear equation slope and/or intercept of right-lane line 2 are updated if new right-lane line 2 is detected, is otherwise retained thereon
The value at one moment；Lane line is detected respectively in the region of interest ROI in above-mentioned steps C using Hough transformation, if detecting
New left-lane line 1 then updates the linear equation slope and/or intercept of left-lane line 1, otherwise retains the value of its last moment；If
Linear equation slope and/or intercept that new right-lane line 2 then updates right-lane line 2 are detected, otherwise retains its last moment
Value；If the situation of change lane occurs in vehicle, when waiting the vehicle to enter the center traveling in next track, automatic detection is new
Lane line, if bend, then what the method was detected is the tangent line of bend.
Current vehicle traveling in the centre in place track, currently should be also not excluded for certain as far as possible in the utility model
The deviation of scope, demarcation scene is to be decorated with the highway of left and right lane line, without reconfiguring demarcation scene again, such as on the ground
Setting-out demarcation etc., it is so more simple and practical than traditional method, it is cost-effective；Fragmentation thresholdization can reduce because shade or
Barrier etc. blocks the problem of lane detection that lane line causes is inaccurate；Man-machine interaction is convenient and swift, will to operating personnel
Ask relatively low, therefore be adapted to changeable scene, it is workable；The scope fluctuated using lane line in front and rear two field pictures is set
Influence of the clutter to lane detection can be greatly reduced by putting the emerging region of sense, and improve the execution efficiency of algorithm；Support online mark
It is fixed, a series of activities that off-line calibration needs to gather video image and handle can be removed from, directly demarcate lane line slope and
Intercept, is one and simply and easily demarcates very much and computational methods, can save a large amount of valuable times of developer, Yi Jiren
Resource consumption in terms of power, material resources.
There is the possibility source of error in calibration process：
1st, scene error：Lane line for demarcation is not straight, ground unevenness etc.；
2nd, man-machine interaction error：Left and right lane line and calibration line in camera views is misaligned.By theory analysis with
It is substantial amounts of it was verified that the lane detection method of calibration-type not only principle is simple, simple operation, can be easily integrated in on-vehicle machines and regards
In feel system, on-line proving is also supported, or even can be carried out in vehicle traveling, so as to solve vehicle-mounted take the photograph to a certain extent
The drifting problem of camera relevant parameter, improves the accuracy of lane detection.
Specific embodiment described herein is only to the utility model spirit explanation for example.The utility model institute
Category those skilled in the art can make various modifications or supplement or using similar to described specific embodiment
Mode substitute, but without departing from spirit of the present utility model or surmount scope defined in appended claims.
Although more having used Δ k hereinLRepresent the difference of two straight slopes of red straight line and left-lane line；ΔbLTable
Show the difference of two Linear intercepts of blue straight line and left-lane line；ΔkRRepresent red straight line and two straight slopes of right-lane line it
Difference；ΔbRRepresent the difference of two Linear intercepts of blue straight line and right-lane line；Region in picture between the blue line in two, left side
It is the emerging region ROI of left-lane sense；Region between the blue line in two, right side is the emerging region ROI of right lane sense；Δ h represents each section
Height；1 represents left-lane line；11 represent left demarcation straight line；2 represent right-lane line；21 represent that right demarcation straight line, image are shown
Module 3, left demarcation straight line display unit 31, touch sensible module 311, right demarcation straight line display unit 32, hand demarcation are straight
Line movement operating-controlling mechanism 4, pattern process module 41, image capture module 5, MCU module 6, gyro sensor 7, angle of pitch inspection
The terms such as module 71, inclination angle detection module 72, yaw angle detection module 73, control unit 8 are surveyed, but are not precluded from using other
The possibility of term.It is used for the purpose of more easily describing and explaining essence of the present utility model using these terms；Them
Any additional limitation is construed to all to disagree with the utility model spirit.
Claims (8)
1. a kind of device that lane detection is carried out using gyro sensor, including the image capture module being arranged on vehicle
(5), described image capture module (5) is connected by MCU module (6) with image display (3), it is characterised in that described
Image display (3) on have left demarcation straight line display unit (31) and it is right demarcate straight line display unit (32), it is and described
MCU module (6) be connected with hand demarcation rectilinear movement operating-controlling mechanism (4), gyro sensor is additionally provided with vehicle
, and described gyro sensor (7) is connected with MCU module (6), and described MCU module (6) is with that can drive image to adopt (7)
Collect the mobile control unit (8) of module (5) to be connected.
2. the device according to claim 1 that lane detection is carried out using gyro sensor, it is characterised in that described
Gyro sensor (7) have angle of pitch detection module (71), inclination angle detection module (72) and yaw angle detection module
(73)。
3. the device according to claim 2 that lane detection is carried out using gyro sensor, it is characterised in that described
Gyro sensor (7) be arranged on meter panel of motor vehicle on.
4. the device that lane detection is carried out using gyro sensor according to claim 1 or 2 or 3, its feature is existed
In described hand demarcation rectilinear movement operating-controlling mechanism (4) includes button and/or knob, and described button and/or knob connect
Pattern process module (41) is connected to, and described pattern process module (41) is connected with MCU module (6).
5. the device that lane detection is carried out using gyro sensor according to claim 1 or 2 or 3, its feature is existed
In described image display (3) is the display screen being arranged in vehicle.
6. the device according to claim 5 that lane detection is carried out using gyro sensor, it is characterised in that described
Hand demarcation rectilinear movement operating-controlling mechanism (4) be to be arranged on touch sensible module (311) in image display (3).
7. the device according to claim 6 that lane detection is carried out using gyro sensor, it is characterised in that described
Image display (3) be touch-screen.
8. the device according to claim 1 that lane detection is carried out using gyro sensor, it is characterised in that described
Image capture module (5) be to be arranged on video camera on vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621194002.XU CN206593670U (en) | 2016-11-04 | 2016-11-04 | The device of lane detection is carried out using gyro sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621194002.XU CN206593670U (en) | 2016-11-04 | 2016-11-04 | The device of lane detection is carried out using gyro sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206593670U true CN206593670U (en) | 2017-10-27 |
Family
ID=60129926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621194002.XU Expired - Fee Related CN206593670U (en) | 2016-11-04 | 2016-11-04 | The device of lane detection is carried out using gyro sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206593670U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI693493B (en) * | 2019-03-11 | 2020-05-11 | 整技科技股份有限公司 | Guided vehicle control system and method |
-
2016
- 2016-11-04 CN CN201621194002.XU patent/CN206593670U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI693493B (en) * | 2019-03-11 | 2020-05-11 | 整技科技股份有限公司 | Guided vehicle control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948523B (en) | A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion | |
| CN106525056A (en) | Method for lane line detection by gyro sensor | |
| CN105260699B (en) | A kind of processing method and processing device of lane line data | |
| CN107235044B (en) | A kind of restoring method realized based on more sensing datas to road traffic scene and driver driving behavior | |
| CN107341453B (en) | Lane line extraction method and device | |
| CN105701449B (en) | The detection method and device of lane line on road surface | |
| CN102609934B (en) | Multi-target segmenting and tracking method based on depth image | |
| CN108519605A (en) | Curb detection method based on laser radar and video camera | |
| CN100544446C (en) | The real time movement detection method that is used for video monitoring | |
| CN104848851A (en) | Transformer substation patrol robot based on multi-sensor data fusion picture composition and method thereof | |
| CN110262517A (en) | The Trajectory Tracking Control method of AGV system | |
| EP2605185A2 (en) | Detection of obstacles at night by analysis of shadows | |
| CN106296814B (en) | Highway maintenance detection and virtual interactive interface method and system | |
| CN101776952B (en) | Novel interactive projection system | |
| CN111967360A (en) | Target vehicle attitude detection method based on wheels | |
| CN109325390B (en) | Positioning method and system based on combination of map and multi-sensor detection | |
| CN106584451A (en) | Visual navigation based transformer substation automatic composition robot and method | |
| CN101033978A (en) | Assistant navigation of intelligent vehicle and automatically concurrently assisted driving system | |
| CN113989379B (en) | Hub welding seam three-dimensional characteristic measuring device and method based on linear laser rotation scanning | |
| CN103605978A (en) | Urban illegal building identification system and method based on three-dimensional live-action data | |
| CN106951905A (en) | Apple identification and localization method on a kind of tree based on TOF camera | |
| CN101520892B (en) | Detection method of small objects in visible light image | |
| CN102122344A (en) | Road border detection method based on infrared image | |
| CN102073846A (en) | Method for acquiring traffic information based on aerial images | |
| CN110263607A (en) | A kind of for unpiloted road grade global context drawing generating method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171027 Termination date: 20201104 |