CN105206109B - A kind of vehicle greasy weather identification early warning system and method based on infrared CCD - Google Patents
A kind of vehicle greasy weather identification early warning system and method based on infrared CCD Download PDFInfo
- Publication number
- CN105206109B CN105206109B CN201510496878.3A CN201510496878A CN105206109B CN 105206109 B CN105206109 B CN 105206109B CN 201510496878 A CN201510496878 A CN 201510496878A CN 105206109 B CN105206109 B CN 105206109B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- module
- infrared ccd
- front vehicles
- 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
Abstract
The invention discloses a kind of vehicle greasy weather identification early warning system and method based on infrared CCD, it is therefore intended that:Applied to greasy weather complexity environment, safety guarantee can be provided for driver, passenger and third party, used technical scheme is:Including:Infrared CCD photographing module, gather the infrared image sequence of front vehicles;Image processing module and distance-measurement module, image processing module can carry out sharpening processing to the image sequence that infrared CCD photographing module inputs, by identifying the edge feature of vehicle, identify front vehicles;The image sequence that distance-measurement module can input to infrared CCD photographing module establishes image coordinate system, imaging plane coordinate system, camera coordinate system and world coordinate system, calculates the distance with front vehicles;Warning module, it is connected with the output end of image procossing and distance-measurement module, warning information can be sent to driver;And power module.
Description
Technical field
The present invention relates to mobile unit technical field, and in particular to a kind of vehicle greasy weather identification early warning based on infrared CCD
System and method.
Background technology
With the development of national economy, people are more and more important to the demand of vehicle, but the thing followed is on continuous
The road accident rate risen, the traffic accident of wherein travelling in fog day take place frequently, and it is exactly because people are safe in the present context to trace it to its cause
The condition of driving is limited.Situation Just because of this, vehicle-mounted identifying system are just able to fast development.At present, prior art also only
Fixed external environment can be corresponded to and carry out safe early warning, the environment for that can not provide identification condition just can not identify early warning, institute
It need further to study to treat the identification early warning of complex environment.
The content of the invention
In order to solve the problems of the prior art, the present invention proposes that one kind is applied to greasy weather complexity environment, Neng Gouwei
Driver, passenger and third party provide the identification early warning system of the vehicle greasy weather based on infrared CCD and method of safety guarantee.
In order to realize the above object the technical solution adopted in the present invention is:
A kind of vehicle greasy weather identification early warning system based on infrared CCD, including:
Infrared CCD photographing module, including infrared CCD video camera and image pick-up card, can gather the infrared of front vehicles
Image sequence simultaneously sends image processing module and distance-measurement module to;
Image processing module and distance-measurement module, it is connected with the output end of infrared CCD photographing module, image processing module
Sharpening processing can be carried out to the image sequence that infrared CCD photographing module inputs, by identifying the edge feature of vehicle, identification
Front vehicles;The image sequence that distance-measurement module can input to infrared CCD photographing module establishes image coordinate system, imaging is put down
Areal coordinate system, camera coordinate system and world coordinate system, calculate the distance with front vehicles;
Warning module, it is connected with the output end of image procossing and distance-measurement module, early warning letter can be sent to driver
Breath;
Power module, connect respectively with infrared CCD photographing module, image processing module, distance-measurement module and warning module
Connect.
The warning module includes optical signal alarm unit, and concealed light represents that front does not have vehicle, and green light represents to be in safety
Spacing, amber light expression will be less than safe distance between vehicles, and red light represents dangerous.
A kind of vehicle greasy weather identification method for early warning based on infrared CCD, comprises the following steps:
1) utilize infrared CCD camera acquisition front vehicles infrared image sequence, and send to image processing module and
Distance-measurement module;
2) image processing module is handled infrared image sequence:Including converting analog signals into data signal, pressure
Contracting processing, pretreatment, segmentation analyzing and processing and classification processing, by identifying the edge feature of vehicle, identify front vehicles;
3) vehicle is identified according to the vertically profiling of vehicle for distance-measurement module, and uses Zhang Zhengyou plane references
Method and the measurement of pinhole imaging system principle and the distance of front vehicles;
4) according to the identification and range measurement of image processing module and distance-measurement module to front vehicles, to warning module
Pre-warning signal is exported, prompts driver to realize people's car information exchange.
Basic precognition feature of the described image processing module based on automobile tail:The symmetry and vehicle tail of vehicle are vertical
The characteristics of profile is obvious, then vehicle is identified for gradation of image zone boundary jumpy based on vehicle's contour, utilize
OTSU methods determine the partition threshold of display foreground and background, and front automobile is entered under the discernmible situation of front vehicles profile
Row positioning.
The pretreatment to infrared image sequence includes:Denoising and image sharpening processing.
The denoising reduces the noise of infrared image using medium filtering.
The distance-measurement module establishes image coordinate system, imaging plane coordinate system, camera coordinate system and world coordinates
System, f is taken the photograph for focal length of camera CCD using Zhang Zhengyou plane references method with the corresponding relation of 3-D view by the two dimension of foundation
Camera calibration, the intrinsic parameter of infrared CCD video camera is determined, using the bottom point of the vehicle wheel profile of left and right identification as characteristic point (u1,
v1) and (u2, v2), it is stored in first using the vehicle identification result of each frame as a vehicle list in caching, is next step
Spline interpolation calculates and provides data basis, when a certain vehicle is tracked is less than three frames, uses characteristic point (u1, v1) and (u2,
v2) original value calculated, after three frames, using identical method amendment vehicle coordinate position, utilize this three two field pictures meter
Internal reference matrix is calculated, is the angle point image that distinguished point based is established herein;Pinhole imaging system principle is recycled to derive front vehicles
Actual range.
The longitudinally opposed spacing calculation formula of the front vehicles is:
Wherein, W1For the real width of vehicle, it is assumed that all vehicle widths are identical, W2The width for being vehicle on ccd video camera
Degree, by camera calibration and the pixel wide W of vehiclecIt is calculated, f is focal length of camera.
The pixel wide W of the vehiclecNeeded when calculating by the width calibration of vehicle's contour, it is first determined front vehicles
Region, it is assumed that Ben Che and front vehicles are all the time in same lanes, i.e., by target search area reduction to by two tracks
The Delta Region of the intersecting composition of line is region of interest;
Then binary conversion treatment is carried out to image, image passes through after binary conversion treatment, by vehicle in area-of-interest
Vertical edge separate, first the marginal point of the vertical edge image in area-of-interest is added up in the height direction, i.e.,
Obtain the vertical direction projection value at edge, then the symmetry of vehicle analyzed, using each row horizontal pixel in image as
Basic calculation symmetry, Symmetry measurement is defined with energy function, judge front by judging whether to meet symmetry requirement
Whether it is vehicle;
The reference axis u of symmetry axis is found finally by Symmetry measurements, make us=u0, then thrown at the edge of region of interest
Shadow finds the upright projection value max of maximum, using the 1/3 of the maximal projection value max judgment condition as searching right boundary, from right
Claim axle on the left of start to scan, when more than max 1/3 when, that is, it is u to regard as left side profile line coordinatesmin;Swept on the right of symmetry axis
During face, when undergoing mutation, more than max 1/3 when, that is, it is u to regard as right edge outline line coordinatesmax, then the vehicle pixel surveyed
Width Wc=umax-umin。
The binary conversion treatment uses OTSU algorithms, and gradation of image figure is divided into two parts with optimal threshold values, a part
Variance within clusters it is minimum, the inter-class variance of another part is maximum.
Compared with prior art, present system gathers the infrared image sequence of front vehicles by infrared CCD photographing module
Row, and send image processing module and distance-measurement module to, the image that image processing module inputs to infrared CCD photographing module
Sequence carries out sharpening processing, by identifying the edge feature of vehicle, identifies front vehicles;Distance-measurement module is to infrared CCD
The image sequence of photographing module input establishes image coordinate system, imaging plane coordinate system, camera coordinate system and world coordinate system,
Calculate the distance with front vehicles;Image processing module and distance-measurement module export pre-warning signal, early warning mould to warning module
Block sends warning information prompting driver's front vehicles information to driver, and the system using the present invention makes in the case of the greasy weather
With also being used under some special cases, for example the condition such as preceding tail-light breakage, do not open fog lamp under dense fog environment
Situation, can interpolate that whether front has the distance of vehicle and front vehicles, and early warning letter is sent to driver using warning module
Number, prompt driver's regulation speed and make corresponding driver behavior, safe guarantor is provided for driver, passenger and third party
Barrier.
The inventive method gathers the infrared image sequence of front vehicles using infrared CCD photographing module, and sends image to
Processing module and distance-measurement module, image processing module are handled infrared image sequence:Including analog signal is changed
Into data signal, compression processing, pretreatment, segmentation analyzing and processing and classification processing, by identifying the edge feature of vehicle, know
Vehicle is identified according to the vertically profiling of vehicle for other front vehicles, distance-measurement module, and uses Zhang Zhengyou plane marks
Method and the measurement of pinhole imaging system principle and the distance of front vehicles, and the identification according to front vehicles and distance are determined, to early warning mould
Block exports pre-warning signal, prompts driver to realize people's car information exchange, and the identification of front vehicles is accurately clear, and range measurement is accurate
Really, safe and reliable warning information can be provided for driver.
Brief description of the drawings
Fig. 1 is the structural representation of present system;
Fig. 2 a are the example artwork before Edge contrast, and Fig. 2 b are the example image after Edge contrast;
Fig. 3 is foggy weather vehicle traveling figure;
Fig. 4 is the graph of a relation of image coordinate system and imaging plane coordinate system;
Fig. 5 is the graph of a relation of camera coordinate system and world coordinate system;
Fig. 6 is road image imaging schematic diagram;
Fig. 7 is area-of-interest vertical edge Symmetry measurement figure.
Embodiment
The present invention is further explained with reference to specific embodiment and Figure of description.
Referring to Fig. 1, system of the invention includes:Infrared CCD photographing module, including infrared CCD video camera and IMAQ
Card, can gather the infrared image sequence of front vehicles and send image processing module and distance-measurement module to;
Image processing module and distance-measurement module, it is connected with the output end of infrared CCD photographing module, image processing module
Sharpening processing can be carried out to the image sequence that infrared CCD photographing module inputs, by identifying the edge feature of vehicle, identification
Front vehicles;The image sequence that distance-measurement module can input to infrared CCD photographing module establishes image coordinate system, imaging is put down
Areal coordinate system, camera coordinate system and world coordinate system, calculate the distance with front vehicles;
Warning module, it is connected with the output end of image procossing and distance-measurement module, early warning letter can be sent to driver
Breath, warning module include optical signal alarm unit, and concealed light represents that front does not have vehicle, and green light represents to be in safe distance between vehicles, amber light
Expression will be less than safe distance between vehicles, and red light represents dangerous;
Power module, connect respectively with infrared CCD photographing module, image processing module, distance-measurement module and warning module
Connect.
Infrared CCD photographing module in the inventive method provides single camera vision system, and video camera hands over the image of collection
Handled to computer, picture signal is converted into the half-tone information of data signal, i.e. image;
Image processing module is pre-processed infrared image, and mainly noise remove and image sharpening are handled,
The noise of infrared image is reduced using medium filtering, medium filtering typically uses a sliding window, by each gray value in window
Intermediate value be for n element, intermediate value to substitute the central point of window:
N is odd number
N is even number
The pixel coordinate of image defines for f (u, v), defines gradient vectors of the f (u, v) at point (u, v) place
For:
The amplitude of gradient is with G [f (u, v)], its value:
It can thus be concluded that go out such conclusion, the numerical value of gradient be exactly units of the f (u, v) on its maximum rate of change direction away from
From increased amount, can be write as discrete digital picture above formula:
Certain threshold values Δ is reset, if G [f (u, v)]<Δ then keeps former ash angle value, if G [f (u, v)]>Δ, then assignment
G [f (u, v)] is i.e.:
Threshold values is chosen for image after 10 after image procossing as shown in Fig. 2 automobile the greasy weather traveling image such as
Shown in Fig. 3;
Distance-measurement module first establishes reference axis:Image coordinate system and imaging plane reference axis;Image coordinate system utilizes number
The size of element numerical value carrys out the gray value of respective pixel in group.Pixel is represented with columns of the pixel in image array and line number
Abscissa value and ordinate value, are expressed as (u, v), and imaging plane reference axis method for building up is as follows:By the plane of delineation and video camera
The intersection point of optical axis is origin O1, its coordinate is (u0, v0) define dxFor the physical size of pixel in the direction of the x axis, dyIt is pixel in y
Physical size on axle, the relation of image coordinate system and imaging plane coordinate system are as follows as shown in Figure 4:
Camera coordinate system (Xc,Yc,Zc) and world coordinate system (Xw,Yw,Zw) relation as shown in figure 5, OcO1For video camera
Focal length f;
Imaging plane coordinate system has with camera coordinate system relation:
World coordinate system has to camera coordinate system relation:
Wherein R, T represent to describe the translation vector and spin matrix of world coordinate system and camera coordinate system, R generations respectively
One 3*3 of table orthogonal matrices, T=(t1,t2,t3)TRepresent D translation vector;
Conversion of the P points from world coordinates to image coordinate can be drawn by above formula, formula is:
Wherein, A be video camera Intrinsic Matrix, [R T] is the outer parameter matrix of video camera, if video camera put for
It is rigidly connected, that is, sets outer parameter constant.
cxWith cyFor (u0,v0) coordinate in imager coordinate axle, just obtain in two-dimensional digital image
The position coordinates of front vehicles, by the two dimension of foundation and the corresponding relation of 3-D view using Zhang Zhengyou standardizations to video camera
Demarcation, determine the intrinsic parameter of video camera.Using the bottom point of the contour line of left and right identification as characteristic point (u1, v1) and (u2, v2), it is first
First be stored in using the vehicle identification result of each frame as a vehicle list in caching (nearest one second of storage, i.e., preceding 30 frame
Data), so the spline interpolation for next step, which calculates, provides data basis, when a certain vehicle is tracked is less than three frames, makes
With characteristic point (u1, v1)、(u2, v2) original value calculated.After three frames, identical method amendment vehicle coordinate position is used
Put.Internal reference matrix is calculated using this three two field picture, is the angle point image that distinguished point based is established herein, recycles pinhole imaging system former
Reason derives the actual range of vehicle, as shown in Figure 6:
Longitudinally opposed spacing calculation formula is:
Wherein W1For the real width of vehicle, the width of in general vehicle is roughly the same, assumes all vehicle widths accordingly
It is identical, W2, can be by camera calibration and the pixel wide W of vehicle for the width of vehicle on a sensorcIt is calculated.
Calculating the pixel wide W of vehiclecWhen need first by the width calibration of vehicle's contour, first determine front vehicles first
Region, because it was assumed that Ben Che and front vehicles are all the time in same lanes, you can with by target search area reduction to by
The Delta Region of the intersecting composition of two lane lines, referred to as region of interest (Region of Interest, ROI), it is specific using public
Formula from bottom to top be scanned calculating:
In formula:
The left end pixel coordinate of v rows in lb (v)-AOI;
The right-hand member pixel coordinate of v rows in rb (v)-AOI;
The gray value of g (u, v)-pixel;
The average gray of v rows in G (v)-AOI;
Using the row k (k values are obtained by Experimental Calibration) of gray scale value mutation as AOI base, base and two lane lines are asked
Intersection point, then two sides of the vertical curve as rectangle AOI are drawn by left and right intersection point upwards respectively, make a rectangle frame, height
Vehicle is integrally incorporated in rectangle frame by selection as far as possible according to the priori of vehicle shape;
And then need to carry out binary conversion treatment to image, gradation of image figure is divided into two by OTSU algorithms with optimal threshold values
Point, make the variance within clusters of a part minimum, the inter-class variance of another part is maximum, and image passes through after binary conversion treatment, is feeling
The vertical edge of vehicle can be separated in interest region, first in the height direction by the vertical edge in area-of-interest
The marginal point of image is cumulative to obtain the vertical direction projection value at edge;And then the symmetry of vehicle is analyzed, symmetry
Estimate and be based on any function and can be write as the form of an even function and odd function sum, the importance of the two it is relative
Big I reflects symmetrical degree, and even function is more more symmetrical than great explanation, using each row horizontal pixel in image as
Basic calculation symmetry, it is as follows that the definition of its energy function symmetrically estimates s:
S=1 represents full symmetric, and s=-1 represents completely asymmetric.Judged by judging whether to meet symmetry requirement
Whether front is vehicle, and symmetry experiment is as shown in Figure 7;
Wherein usFor the symmetrical axial coordinate of pixel, w is symmetric domains width, and Ee is even energy function, and Eo is strange energy function.
E (f (x))=∫ f2(x)dx。
For certain usAnd w, function g (x)=g (us+ u) even function and odd function be respectively:
The reference axis u of symmetry axis can be found by Symmetry measurements, make us=u0Then looked in edge projection interested
To the upright projection value max of maximum, using the 1/3 of maximal projection value max as the judgment condition for finding right boundary, from symmetry axis
Left side starts to scan, when more than max 1/3 when, that is, regard as left side contour line, coordinate umin.The surface sweeping on the right of symmetry axis
When, when undergoing mutation, more than max 1/3 when, that is, regard as right edge outline line, coordinate umax, then the pixel wide surveyed
Wc=umax-umin。
In present system, infrared CCD photographing module is connected with image processing module and distance-measurement module, early warning mould
Block is connected with the output end of image processing module and distance-measurement module, power module respectively with infrared CCD photographing module, figure
As processing module, distance-measurement module are connected with warning module.
Infrared CCD module transfer pictorial information, image procossing and distance-measurement module are entered according to output information to picture
Row processing and progress range measurement, people's car information exchange, warning module and cab signal are realized eventually through warning module
Lamp is connected, and by reminding driver to reach the purpose of control speed, power module is directly connected with automobile storage battery, when automobile does not open
When dynamic, system does not work.After automobile starting, system switching, system starts are pressed.
The present invention uses in the case of the greasy weather, is also used under some special cases, for example the condition such as preceding tail-light breakage,
Do not open the situation of fog lamp under dense fog environment, can interpolate that whether front has the distance of vehicle and front vehicles, profit
Pre-warning signal is sent to driver with warning module, driver's regulation speed is prompted and makes corresponding driver behavior, to drive
Member, passenger and third party provide safety guarantee.
Claims (7)
1. a kind of vehicle greasy weather identification method for early warning based on infrared CCD, it is characterised in that comprise the following steps:
1) infrared image sequence of infrared CCD camera acquisition front vehicles is utilized, and sends image processing module and distance to
Measurement module;
2) image processing module is handled infrared image sequence:Including converting analog signals into data signal, at compression
Reason, pretreatment, segmentation analyzing and processing and classification processing, by identifying the edge feature of vehicle, identify front vehicles;
3) vehicle is identified according to the vertically profiling of vehicle for distance-measurement module, and use Zhang Zhengyou plane references method with
And the measurement of pinhole imaging system principle and the distance of front vehicles, specifically include:The distance-measurement module establish image coordinate system, into
Photo coordinate system, camera coordinate system and world coordinate system, utilized by the two dimension of foundation and the corresponding relation of 3-D view
Zhang Zhengyou plane references method determines the intrinsic parameter of infrared CCD video camera to infrared CCD camera calibration, the car that left and right is identified
The bottom point of contour line is as characteristic point (u1, v1) and (u2, v2), first using the vehicle identification result of each frame as a car
List is stored in caching, is calculated for the spline interpolation of next step and is provided data basis, is less than when a certain vehicle is tracked
During three frames, characteristic point (u is used1, v1) and (u2, v2) original value calculated, after three frames, use identical method amendment
Vehicle coordinate position, internal reference matrix is calculated using this three two field picture, be the angle point image that distinguished point based is established herein;Recycle
Pinhole imaging system principle derives the actual range of front vehicles;
4) according to the identification and range measurement of image processing module and distance-measurement module to front vehicles, exported to warning module
Pre-warning signal, driver is prompted to realize people's car information exchange.
A kind of 2. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 1, it is characterised in that institute
State basic precognition feature of the image processing module based on automobile tail:The symmetry and vehicle tail vertically profiling of vehicle are obvious
Feature, then vehicle is identified for gradation of image zone boundary jumpy based on vehicle's contour, utilize OTSU methods to determine
The partition threshold of display foreground and background, front automobile is positioned under the discernmible situation of front vehicles profile.
A kind of 3. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 2, it is characterised in that institute
Stating the pretreatment to infrared image sequence includes:Denoising and image sharpening processing.
A kind of 4. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 3, it is characterised in that institute
Stating denoising reduces the noise of infrared image using medium filtering.
A kind of 5. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 1, it is characterised in that institute
The longitudinally opposed spacing calculation formula for stating front vehicles is:
<mrow>
<mi>Z</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>f</mi>
<mo>*</mo>
<msub>
<mi>W</mi>
<mn>1</mn>
</msub>
</mrow>
<msub>
<mi>W</mi>
<mn>2</mn>
</msub>
</mfrac>
</mrow>
Wherein, W1For the real width of vehicle, it is assumed that all vehicle widths are identical, W2The width for being vehicle on ccd video camera,
By camera calibration and the pixel wide W of vehiclecIt is calculated, f is focal length of camera.
A kind of 6. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 5, it is characterised in that institute
State the pixel wide W of vehiclecNeeded when calculating by the width calibration of vehicle's contour, it is first determined the region of front vehicles, it is false
If this car all the time in same lanes, i.e., forms target search area reduction to by two lane lines are intersecting with front vehicles
Delta Region be region of interest;
Then binary conversion treatment is carried out to image, image passes through after binary conversion treatment, the hanging down vehicle in area-of-interest
Straight edge separates, and first the marginal point of the vertical edge image in area-of-interest adds up in the height direction, that is, obtained
The vertical direction projection value at edge, then the symmetry of vehicle is analyzed, based on each row horizontal pixel in image
Symmetry is calculated, Symmetry measurement is defined with energy function, whether judges front by judging whether to meet symmetry requirement
For vehicle;
The reference axis u of symmetry axis is found finally by Symmetry measurements, make us=u0, then looked in the edge projection of region of interest
To the upright projection value max of maximum, using the 1/3 of maximal projection value max as the judgment condition for finding right boundary, from symmetry axis
Left side starts to scan, when more than max 1/3 when, that is, it is u to regard as left side profile line coordinatesmin;On the right of symmetry axis during surface sweeping,
When undergoing mutation, more than max 1/3 when, that is, it is u to regard as right edge outline line coordinatesmax, then the vehicle pixel wide surveyed
Wc=umax-umin。
A kind of 7. vehicle greasy weather identification method for early warning based on infrared CCD according to claim 6, it is characterised in that institute
State binary conversion treatment and use OTSU algorithms, gradation of image figure is divided into by two parts, a part of variance within clusters with optimal threshold values
Minimum, the inter-class variance of another part are maximum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510496878.3A CN105206109B (en) | 2015-08-13 | 2015-08-13 | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510496878.3A CN105206109B (en) | 2015-08-13 | 2015-08-13 | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105206109A CN105206109A (en) | 2015-12-30 |
CN105206109B true CN105206109B (en) | 2017-12-15 |
Family
ID=54953748
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510496878.3A Expired - Fee Related CN105206109B (en) | 2015-08-13 | 2015-08-13 | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105206109B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107618437A (en) * | 2016-07-14 | 2018-01-23 | 芜湖优必慧新能源科技有限公司 | A kind of vehicle safety travel active infrared camera system |
CN106529530A (en) * | 2016-10-28 | 2017-03-22 | 上海大学 | Monocular vision-based ahead vehicle detection method |
CN106650708B (en) * | 2017-01-19 | 2023-08-11 | 南京航空航天大学 | Automatic driving obstacle vision detection method and system |
CN106828308A (en) * | 2017-01-24 | 2017-06-13 | 桂林师范高等专科学校 | Lane departure warning device |
CN107290738A (en) * | 2017-06-27 | 2017-10-24 | 清华大学苏州汽车研究院(吴江) | A kind of method and apparatus for measuring front vehicles distance |
DE102018218997A1 (en) * | 2017-11-10 | 2019-05-16 | Denso Corporation | camera module |
CN108230295B (en) * | 2017-11-21 | 2021-07-02 | 北京工业大学 | Identification method of concerned target in infrared panoramic monitoring annular display area |
CN108319910B (en) * | 2018-01-30 | 2021-11-16 | 海信集团有限公司 | Vehicle identification method and device and terminal |
CN108645408B (en) * | 2018-05-07 | 2020-07-17 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle autonomous recovery target prediction method based on navigation information |
CN108731683B (en) * | 2018-05-07 | 2020-09-18 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle autonomous recovery target prediction method based on navigation information |
CN110299026A (en) * | 2019-06-19 | 2019-10-01 | 淮安信息职业技术学院 | Section safety monitoring method and system under the conditions of a kind of mist |
CN110341554B (en) * | 2019-06-24 | 2021-05-25 | 福建中科星泰数据科技有限公司 | Controllable environment adjusting system |
CN110599431B (en) * | 2019-08-27 | 2022-03-08 | 武汉华中数控股份有限公司 | Time domain filtering method applied to infrared camera |
CN112200144A (en) * | 2020-11-02 | 2021-01-08 | 广州杰赛科技股份有限公司 | Method and device for identifying faces of prisoners based on facial features |
CN113191303B (en) * | 2021-05-14 | 2023-04-18 | 山东新一代信息产业技术研究院有限公司 | Method for calculating distance and steering of front vehicle based on single camera |
CN114228614A (en) * | 2021-12-29 | 2022-03-25 | 阿波罗智联(北京)科技有限公司 | Vehicle alarm method and device, electronic equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1078549C (en) * | 1997-04-08 | 2002-01-30 | 张国栋 | Automatic collisionproof method for motor vehicles and its embodiment |
EP2187236A1 (en) * | 2008-11-06 | 2010-05-19 | Ford Global Technologies, LLC | A collision warning apparatus |
US20120287276A1 (en) * | 2011-05-12 | 2012-11-15 | Delphi Technologies, Inc. | Vision based night-time rear collision warning system, controller, and method of operating the same |
CN104392629B (en) * | 2014-11-07 | 2015-12-09 | 深圳市中天安驰有限责任公司 | The method and apparatus of inspection vehicle distance |
-
2015
- 2015-08-13 CN CN201510496878.3A patent/CN105206109B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN105206109A (en) | 2015-12-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
CN109389064B (en) | Vehicle feature acquisition method and device | |
CN109190523B (en) | Vehicle detection tracking early warning method based on vision | |
CN105550665B (en) | A kind of pilotless automobile based on binocular vision can lead to method for detecting area | |
JP6519262B2 (en) | Three-dimensional object detection device, three-dimensional object detection method, three-dimensional object detection program, and mobile device control system | |
CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
CN107891808B (en) | Driving reminding method and device and vehicle | |
CN104700072B (en) | Recognition methods based on lane line historical frames | |
US7561721B2 (en) | System and method for range measurement of a preceding vehicle | |
CN105574552A (en) | Vehicle ranging and collision early warning method based on monocular vision | |
CN105740782A (en) | Monocular vision based driver lane-changing process quantization method | |
CN106503636A (en) | A kind of road sighting distance detection method of view-based access control model image and device | |
CN107886034B (en) | Driving reminding method and device and vehicle | |
US20200074212A1 (en) | Information processing device, imaging device, equipment control system, mobile object, information processing method, and computer-readable recording medium | |
WO2022151664A1 (en) | 3d object detection method based on monocular camera | |
CN103020948A (en) | Night image characteristic extraction method in intelligent vehicle-mounted anti-collision pre-warning system | |
WO2017145605A1 (en) | Image processing device, image pickup device, moving body apparatus control system, image processing method, and program | |
CN102303563B (en) | System and method for prewarning front vehicle collision | |
CN103810720A (en) | Target point arrival detector and vehicle-mounted device control system | |
JP6753134B2 (en) | Image processing device, imaging device, mobile device control system, image processing method, and image processing program | |
CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
CN105512641B (en) | A method of dynamic pedestrian and vehicle under calibration sleet state in video | |
WO2017145634A1 (en) | Image processing device, imaging device, system for controlling mobile body, image processing method, and program | |
CN103679121B (en) | Method and system for detecting roadside using visual difference image | |
CN110991264A (en) | Front vehicle detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
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: 20171215 Termination date: 20180813 |