CN101425181B - Panoramic view vision auxiliary parking system demarcating method - Google Patents
Panoramic view vision auxiliary parking system demarcating method Download PDFInfo
- Publication number
- CN101425181B CN101425181B CN200810163310XA CN200810163310A CN101425181B CN 101425181 B CN101425181 B CN 101425181B CN 200810163310X A CN200810163310X A CN 200810163310XA CN 200810163310 A CN200810163310 A CN 200810163310A CN 101425181 B CN101425181 B CN 101425181B
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- distortion
- video camera
- eye
- 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
Images
Abstract
The invention discloses a parking method for a panoramic optical aid parking system, which uses images generated by at least two wide-angle fisheye cameras installed at the periphery of an automobile for generating a virtual aerial view image at a certain height at the top of the automobile. The method comprises the following steps: model parameters of the wide-angle fisheye cameras are calculated; a certain straight line in a public view field is identified as a splice seam; the position of a world coordinate system in a non-public view field is identified; the position of a visual aerial view camera is fixed; a single-mapping transformation matrix based on the ground level is calculated; the position of the splice position is totally optimized; position parameters among all images under the visual aerial view camera are calculated. The method has the advantages of low requirement to equipment, simple process, and no dependence on relative positions among cameras and accurate posture parameters, and reduces the complexity of system integration; calculated parameters during real-time work can be provided by one-time parking; and the method has favorable peripheral panoramic aerial view effect of automobiles.
Description
Technical field
The present invention relates to Digital Image Processing and computer vision technique, especially, relate to the scaling method of panoramic view vision auxiliary parking system.
Background technology
China is a country that traffic hazard is serious, and annual death toll and fatal rate all allow of no optimist.Reduce traffic hazard and not only will objectively more will improve the reliability of the safe driving of automobile own in subjective enhancing awareness of safety.Existing driver assistance instrument miscellaneous is exactly in order to address this problem.The automotive safety safeguards system can be divided into passive and active system substantially, and the former mainly comprises securing band, air bag etc., though can reduce the accident casualty degree, can not prevent the generation of accident.The latter then mainly utilize various kinds of sensors as, ultrasound wave, radar, infra-red heat sensor and video camera etc.They can provide traffic informations such as barrier for driver's decision-making.Simultaneously, the active safety safeguards system has also constituted the important component part of intelligent transportation system.In above-mentioned all methods, video camera has advantages such as low cost, easy care and high integration, has therefore obtained using widely.
Along with the fast development of Flame Image Process and computer vision, increasing advanced technology is applied to vehicle electric field.Traditional driver assistance based on image is only installed the reversing camera at automobile tail, can only cover the limited zone of motor vehicle environment, and the vision blind area in car both sides and the place ahead has increased the hidden danger of safe driving undoubtedly.In order to enlarge driver's field range, just necessary perception automobile is 360 ° of environment all around, and this just needs information fusion and registration between a plurality of vision sensors.Mutual alignment between a plurality of vision sensors and attitude Relation Parameters obtain from specific survey sensor, and this depends critically upon accurate position and attitude parameter with regard to making the result who merges registration.
Summary of the invention
The scaling method that the purpose of this invention is to provide a kind of panoramic view vision auxiliary parking system, it does not rely on mutual alignment and attitude relation between the video camera, can effectively obtain the splicing relation between the image.According to these relations, can produce virtual panorama general view picture, thereby enlarge driver's field range to greatest extent.
The scaling method of panoramic view vision auxiliary parking system of the present invention may further comprise the steps:
Step 1): adopt the calibration algorithm of flake wide-angle camera, calculate the inner parameter and the fish-eye percentage distortion of camera;
Step 2): the video camera with at least two step 1) are described is taken the image of motor vehicle environment zones of different, has certain public domain between the said video camera;
Public domain internal labeling 2 points of video camera step 3): in step 2) are confirmed the splicing slit between each image.
Along ground tiling calibrating template, specify the true origin and the x of each template world coordinate system simultaneously, the y direction in the non-public domain of video camera step 4): in step 2).
Step 5): the length of measured automobiles and wide, confirm the virtual position of getting a bird's eye view camera to the ground vertical projection, measure the relative position under each world coordinate system in step 4) of this position.
Step 6): the intrinsic parameters of the camera and the percentage distortion that obtain according to step 1), to step 2) image of gathering in carries out distortion to be removed and handles, and obtains image after the distortion correction.
Step 7): the undistorted figure according to step 6) obtains, calculate from the original camera position to virtual singly the reflecting property transformation matrix of getting a bird's eye view the position.Utilize this matrix, the undistorted image in the step 6) is transformed to the virtual camera visual angle image of getting a bird's eye view.
Step 8): obtain the virtual image of getting a bird's eye view the visual angle according to step 7), utilize nonlinear least square method to calculate splicing slit direction) alignment error between the calibrating template with compensation process 4.
Step 9): according to the splicing slit direction in the step 8), the virtual visual angle image of getting a bird's eye view in the step 7) is rotated and translation transformation, up to obtaining the panorama stitching image, record translation parameters at this moment.
Step 10): output calibrating parameters: the camera inner parameter, the fish eye lens percentage distortion, singly reflecting property matrix splices slit direction and translation parameters.
Among the present invention, the calibration algorithm of described employing flake wide-angle camera, the inner parameter and the fish-eye percentage distortion of calculating camera may further comprise the steps:
1) camera is represented with pin-hole model:
λu=K(XR+T)
Wherein
Be camera inner parameter, f
uAnd f
vBe the camera focus of representing with image row and column pixel, u
0, v
0Be projection centre, α is a degree of tilt; X is the three-dimensional point in the world coordinate system; R and T are rotation and the translation that world coordinates is tied to the camera coordinate system; U is the corresponding picture point coordinate of X.
2) with high-order radially model approximation fish-eye radially with the tangential distortion
u
dist=u+(u-u
0)[k
1r
2+k
2r
4+k
3r
6+k
4(r
2/u+2u)]
v
dist=v+(v-v
0)[k
1r
2+k
2r
4+k
3r
6+k
5(r
2/v+2v)]
K wherein
1, k
2, k
3Be radial distortion coefficient, k
4, k
5Be the tangential percentage distortion.
3) take a series of images of the different attitudes of calibrating template respectively, the corresponding point of marker template on each image, and the corresponding relation between the image.
4) initial calculation camera inner parameter K
iWith fish-eye percentage distortion k
i=[k
1, k
2, k
3, k
4, k
5], again according to the shortest principle of Euclidean distance between the corresponding observation station in the subpoint of calibrating template on image and the real image, with nonlinear least square method computation optimization K
iAnd k
i
The present invention is by simple calibrating template, carries out a series of conversion to being installed in the image that a plurality of video cameras produce around the automobile, thereby obtains being used for the various parameters of real time panoramic image mosaic.Its key step comprises: the model parameter of flake wide-angle camera is asked for; Certain bar straight line is as the splicing slit in the mark public view field; The position of world coordinate system in the non-public view field of mark; The fixing virtual position of getting a bird's eye view camera; Singly reflecting property transformation calculations based on ground level; The position global optimization in splicing slit; Virtually get a bird's eye view under the coordinate system that location parameter calculates between each image.This procedure is simple; Low for equipment requirements, do not rely on relative position and accurate attitude parameter between the video camera, thereby reduced the complicacy of the system integration; Only need to demarcate the calculating parameter that real-time working once can be provided; Panorama is got a bird's eye view effect around having good automobile.
Description of drawings
Fig. 1 is the demarcation process flow diagram of panoramic view vision auxiliary parking system
Fig. 2 is the calibrating template synoptic diagram
Fig. 3 is that the automobile that four flake video cameras are installed is got a bird's eye view synoptic diagram
Fig. 4 is that single flake camera (a) is the flake distorted image to the virtual view transformation process synoptic diagram of getting a bird's eye view among the present invention, (b) for the common fluoroscopy images after the distortion of removal flake, (c) is the general view picture.
Fig. 5 is the global optimization synoptic diagram of splicing slit direction
Embodiment
Fig. 1 has provided the demarcation process flow diagram of panoramic view vision auxiliary parking system, and it mainly may further comprise the steps:
Step 1: adopt the calibration algorithm of flake wide-angle camera, calculate the inner parameter and the fish-eye percentage distortion of camera;
1) camera is represented with pin-hole model:
λu=K(XR+T)
Wherein
Be camera inner parameter, f
uAnd f
vBe the camera focus of representing with image row and column pixel, u
0, v
0Be projection centre, α is a degree of tilt; X is the three-dimensional point in the world coordinate system; R and T are rotation and the translation that world coordinates is tied to camera coordinates system; U is the corresponding picture point coordinate of X.
2) with high-order radially model approximation fish-eye radially with the tangential distortion
u
dist=u+(u-u
0)[k
1r
2+k
2r
4+k
3r
6+k
4(r
2/u+2u)]
v
dist=v+(v-v
0)[k
1r
2+k
2r
4+k
3r
6+k
5(r
2/v+2v)]
K wherein
1, k
2, k
3Be radial distortion coefficient, k
4, k
5Be the tangential percentage distortion.
3) take a series of images of the different attitudes of calibrating template as shown in Figure 2 respectively, (gathered 10 two field pictures in the legend, got 5x5=25 point on every two field picture), three-dimensional point A on the template in the mark world coordinate system
j iAnd the corresponding point a on every two field picture
j i, the number index of here putting on i and j presentation video sequence number index and each calibrating template.
4) employing and Zhang; Z.Y:A flexible new technique for camera calibration.IEEETransactions on Pattern Analysis and Machine Intelligence 22 (11); 1330-1334 (2000). similar methods, initial calculation camera inner parameter K
iWith fish-eye percentage distortion k
i=[k
1, k
2, k
3, k
4, k
5].According to subpoint and the Euclidean distance the shortest principle corresponding point in real image between of calibrating template on image, optimize following formula with nonlinear least square method, calculating K again
iAnd k
i
Wherein Ψ is three-dimensional projection function to two dimension
Step 2: adopt four video camera C in this instance
i, i=1 ... 4 is as shown in Figure 3, and they have certain public domain 1 each other, and all video cameras can cover the zone of motor vehicle environment, and take the image I of these zoness of different
i
Step 3: according to step 1.4) gained parameter K
iAnd k
i, to the image I around the captured automobile
iRemove distortion and handle, obtain image I after the distortion correction
i UndistParticularly, suppose that Fig. 4 a is the image of calibrating template in the flake camera, through after the distortion correction, obtain the common skeleton view like Fig. 4 b, curve originally becomes straight line.
Public-land zone internal labeling two points of step 4. between per two video cameras are like the zone among Fig. 31.Use through 2 straight line and confirm the splicing slit (l between the image
Ij, i=1 ... 4 and j=1,2 are respectively the index in camera and splicing slit).
Step 5: in the non-public-land zone of video camera along ground tiling calibrating template, like the zone among Fig. 32.Make lattice square on the template to substantially parallel with the length and the cross direction of automobile.Specify the world coordinate system initial point O of every template
iAnd x, the y direction.
Step 6: the long L of measured automobiles and wide W, confirm the virtual position of getting a bird's eye view camera, as P among Fig. 3 (L/2, W/2, H) shown in, to the position P of ground vertical projection
vP is measured in (L/2, W/2,0)
vEach world coordinate system O in step 4)
iUnder relative position (X
i, Y
i).
Step 7: the undistorted figure I that obtains according to step 3
i Undist, calculate from original camera C
iThe position is to virtual singly the reflecting property transformation matrix H of getting a bird's eye view position P
iUtilize this matrix, with undistorted image I
i UndistTransform to the virtual camera visual angle image I of getting a bird's eye view
i GrdMainly may further comprise the steps:
1) calibrating template described in the markers step 3 is at undistorted image I
i UndistOn at least four some p of conllinear not
I, s(x
I, s, y
I, s, 1), s is the number of the point of institute's mark.
2) calculate p
I, s(x
I, s, y
I, s, 1) corresponding point at world coordinate system O separately
iIn three-dimensional position P
I, s(X
I, s, Y
I, s, 0).
3) calculate P
I, s(X
I, s, Y
I, s, 0) and projected position on virtual general view picture is following:
q
i,s=K
i{RP
i,s T+[X
i,Y
i,H]
T}
4) linear least square calculates singly reflecting property transformation matrix H
i:
5) undistorted image I
i UndistWarp is reflecting property matrix H singly
iTransform to the virtual visual angle image I of getting a bird's eye view
i GrdRepresented that to 4c singly reflecting property matrix is to the result of calibrating template conversion like Fig. 4 b.
Step 8: obtain the virtual image I of getting a bird's eye view the visual angle according to step 7)
i Grd, utilize nonlinear least square method to calculate splicing slit direction, with compensation process 5) in alignment error between the calibrating template.As having represented the rotation error between the splicing slit among Fig. 5, purpose makes adjacent slits parallel as far as possible exactly.Mainly may further comprise the steps:
1) splicing slit l in the markers step 4 said public domains
I, jIn image I
i GrdOn the position, calculate the slope m of line correspondence
I, j.
2) minimize like minor function compensating images I
i GrdCorresponding anglec of rotation Θ=[θ
1, θ
2... θ
M]:
Be without loss of generality, initial parameter Θ=0, M representes the number of used camera.
Step 9: according to the optimization stitching direction in the step 8, to the virtual visual angle image I of getting a bird's eye view of gained in the step 7)
i GrdCarry out translation transformation, up to obtaining satisfied panorama stitching image, record translation parameters T at this moment
i=[Δ x
i, Δ y
i].
Step 10 output calibrating parameters: each flake camera inner parameter matrix K
iWith the lens distortions coefficient k
i, singly the reflecting property matrix H at each visual angle
i, compensation calibrating template alignment rotation parameter θ
iWith translation parameters T
i
Arrive this, realized the demarcation of panoramic view vision auxiliary parking system.
Claims (2)
1. the scaling method of a panoramic view vision auxiliary parking system, it is characterized in that: this method comprises the steps:
Step 1): adopt the calibration algorithm of flake wide-angle imaging machine, calculate the inner parameter and the fish-eye percentage distortion of video camera;
Step 2): the video camera with four step 1) are described is taken the image of motor vehicle environment zones of different, and said shooting function covers the motor vehicle environment zone;
Step 3): in step 2) public-land zone internal labeling 2 points between per two video cameras are used through 2 straight line and are confirmed the splicing slit between the image;
Along ground tiling calibrating template, make lattice square on the template in the non-public domain of video camera step 4): in step 2), specify the true origin and the x of each template world coordinate system simultaneously, the y direction to substantially parallel with the length and the cross direction of automobile;
Step 5): the length of measured automobiles and wide, confirm the virtual position of getting a bird's eye view video camera to the ground vertical projection, measure the relative position under each world coordinate system in step 4) of this position;
Step 6): the intrinsic parameters of the camera and the percentage distortion that obtain according to step 1), to step 2) image of gathering in carries out distortion to be removed and handles, and obtains image after the distortion correction;
Step 7): image after the distortion correction that obtains based on step 6); Calculating from the original camera position to virtual singly the reflecting property transformation matrix of getting a bird's eye view camera position; Utilize this matrix, image after the distortion correction in the step 6) is transformed to the virtual video camera visual angle image of getting a bird's eye view;
Step 8): obtain the virtual video camera visual angle image of getting a bird's eye view according to step 7), utilize nonlinear least square method to calculate splicing slit direction) alignment error between the calibrating template with compensation process 4;
Step 9): according to the splicing slit direction in the step 8), the virtual video camera visual angle image of getting a bird's eye view in the step 7) is rotated and translation transformation, up to obtaining the panorama stitching image, record translation parameters at this moment;
Step 10): output calibrating parameters: intrinsic parameters of the camera, the fish eye lens percentage distortion, singly reflecting property transformation matrix splices slit direction and translation parameters.
2. the scaling method of panoramic view vision auxiliary parking system according to claim 1 is characterized in that: adopt the calibration algorithm of flake wide-angle imaging machine, calculate the inner parameter and the fish-eye percentage distortion of video camera, may further comprise the steps:
1) video camera is represented with pin-hole model:
λu=K(XR+T)
Wherein
Be intrinsic parameters of the camera, f
uAnd f
vBe the camera focus of representing with image row and column pixel, u
0, v
0Be projection centre, α is a degree of tilt; X is the three-dimensional point in the world coordinate system; R and T are rotation and the translation that world coordinates is tied to camera coordinate system; U is the corresponding picture point coordinate of X;
2) with high-order radially model approximation fish-eye radially with the tangential distortion
u
dist=u+(u-u
0)[k
1r
2+k
2r
4+k
3r
6+k
4(r
2/u+2u)]
v
dist=v+(v-v
0)[k
1r
2+k
2r
4+k
3r
6+k
5(r
2/v+2v)]
K wherein
1, k
2, k
3Be radial distortion coefficient, k
4, k
5Be the tangential percentage distortion;
3) take a series of images of the different attitudes of calibrating template respectively, the corresponding point of marker template on each image, and the corresponding relation between the image;
4) initial calculation intrinsic parameters of the camera K
iWith fish-eye percentage distortion k
i=[k
1, k
2, k
3, k
4, k
5], again according to the shortest principle of Euclidean distance between the corresponding observation station in the subpoint of calibrating template on image and the real image, with nonlinear least square method computation optimization K
iAnd k
i
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200810163310XA CN101425181B (en) | 2008-12-15 | 2008-12-15 | Panoramic view vision auxiliary parking system demarcating method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200810163310XA CN101425181B (en) | 2008-12-15 | 2008-12-15 | Panoramic view vision auxiliary parking system demarcating method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101425181A CN101425181A (en) | 2009-05-06 |
CN101425181B true CN101425181B (en) | 2012-05-09 |
Family
ID=40615775
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN200810163310XA Expired - Fee Related CN101425181B (en) | 2008-12-15 | 2008-12-15 | Panoramic view vision auxiliary parking system demarcating method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101425181B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105844624A (en) * | 2016-03-18 | 2016-08-10 | 上海欧菲智能车联科技有限公司 | Dynamic calibration system, and combined optimization method and combined optimization device in dynamic calibration system |
Families Citing this family (55)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8289189B2 (en) * | 2009-05-11 | 2012-10-16 | Robert Bosch Gmbh | Camera system for use in vehicle parking |
CN101577002B (en) * | 2009-06-16 | 2011-12-28 | 天津理工大学 | Calibration method of fish-eye lens imaging system applied to target detection |
CN102111610B (en) * | 2010-05-21 | 2012-08-29 | 深圳安科智能视频技术有限公司 | Panoramic image generating method for assisting driving |
CN101917577B (en) * | 2010-07-20 | 2012-07-25 | 惠州市华阳通用电子有限公司 | Embedded system and video correction method thereof |
CN102013099B (en) * | 2010-11-26 | 2012-07-04 | 中国人民解放军国防科学技术大学 | Interactive calibration method for external parameters of vehicle video camera |
CN102045546B (en) * | 2010-12-15 | 2013-07-31 | 广州致远电子股份有限公司 | Panoramic parking assist system |
CN102075785B (en) * | 2010-12-28 | 2012-05-23 | 武汉大学 | Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM) |
CN102298771A (en) * | 2011-08-16 | 2011-12-28 | 淮安盈科伟力科技有限公司 | Fish-eye image rapid correction method of panoramic parking auxiliary system |
CN102298779B (en) * | 2011-08-16 | 2013-08-21 | 淮安盈科伟力科技有限公司 | Image registering method for panoramic assisted parking system |
CN102291573A (en) * | 2011-08-30 | 2011-12-21 | 山推工程机械股份有限公司 | Panoramic operation monitoring method and system of engineering machinery |
EP2763404B1 (en) * | 2011-09-29 | 2019-11-13 | Toyota Jidosha Kabushiki Kaisha | Image display device, and image display method |
CN102510475A (en) * | 2011-10-21 | 2012-06-20 | 上海交通大学 | Automobile panoramic imaging device and method based on infrared calibration |
EP2620917B1 (en) * | 2012-01-30 | 2019-08-28 | Harman Becker Automotive Systems GmbH | Viewing system and method for displaying an environment of a vehicle |
CN102736634B (en) * | 2012-07-10 | 2014-09-03 | 浙江捷尚视觉科技股份有限公司 | Camera angle regulation method for vehicle panorama |
CN103593836A (en) * | 2012-08-14 | 2014-02-19 | 无锡维森智能传感技术有限公司 | A Camera parameter calculating method and a method for determining vehicle body posture with cameras |
TWI500318B (en) * | 2012-08-21 | 2015-09-11 | Tung Thin Electronic Co Ltd | Method for correcting automotive photography devices |
CN103685936A (en) * | 2012-09-25 | 2014-03-26 | 通用汽车环球科技运作有限责任公司 | WIDE field of view camera image calibration and de-warping |
KR101215563B1 (en) * | 2012-10-24 | 2013-01-21 | 주식회사 세코닉스 | Bird view imaging device using auto image calibration and method using the same |
CN103854272B (en) * | 2012-11-28 | 2018-10-16 | 比亚迪股份有限公司 | Panoramic parking system looks for a matching process automatically |
CN103065318B (en) * | 2012-12-30 | 2016-08-03 | 深圳普捷利科技有限公司 | The curved surface projection method and device of multiple-camera panorama system |
CN103106674B (en) * | 2013-01-18 | 2016-02-10 | 昆山市智汽电子科技有限公司 | A kind of method of panoramic picture synthesis and display and device |
CN103226827B (en) * | 2013-03-21 | 2016-04-27 | 深圳市汉华安道科技有限责任公司 | Camera external parameter correction method, device and auxiliary parking system |
CN103208120B (en) * | 2013-04-01 | 2016-01-20 | 南京理工大学 | The overall view ring belt image rectification method of deploying that the two approximate circle of tangential and radial direction is comprehensive |
CN103218820B (en) * | 2013-04-22 | 2016-02-10 | 苏州科技学院 | A kind of camera calibration error compensating method based on multidimensional characteristic |
CN104282010A (en) * | 2013-07-06 | 2015-01-14 | 南京车联网研究院有限公司 | Vehicle multi-fisheye-camera 360-degree overhead-view image splicing curve calibration method |
CN103546680B (en) * | 2013-07-08 | 2018-06-08 | 上海智汽电子科技有限公司 | A kind of deformation-free omni-directional fisheye photographic device and a method for implementing the same |
CN103617606B (en) * | 2013-11-26 | 2016-09-14 | 中科院微电子研究所昆山分所 | For assisting the vehicle multi-angle panorama generation method of driving |
CN103824296B (en) * | 2014-03-06 | 2017-02-08 | 武汉理工大学 | Fisheye image correction method of vehicle panoramic display system based on unit square |
CN103955916B (en) * | 2014-03-21 | 2017-02-15 | 深圳市达程科技开发有限公司 | Automobile panorama camera calibration method and apparatus |
CN103871070A (en) * | 2014-04-03 | 2014-06-18 | 深圳市德赛微电子技术有限公司 | Automatic calibration method of vehicle-mounted panoramic imaging system |
CN103871071B (en) * | 2014-04-08 | 2018-04-24 | 北京经纬恒润科技有限公司 | Join scaling method outside a kind of camera for panoramic parking system |
DE102014117888A1 (en) * | 2014-12-04 | 2016-10-13 | Connaught Electronics Ltd. | Online calibration of a motor vehicle camera system |
CN104809718B (en) * | 2015-03-17 | 2018-09-25 | 合肥晟泰克汽车电子股份有限公司 | A kind of vehicle-mounted camera Auto-matching scaling method |
CN105187753A (en) * | 2015-08-06 | 2015-12-23 | 佛山六滴电子科技有限公司 | System for recording panoramic video |
CN105894549A (en) * | 2015-10-21 | 2016-08-24 | 乐卡汽车智能科技(北京)有限公司 | Panorama assisted parking system and device and panorama image display method |
CN105894448B (en) * | 2015-11-06 | 2019-08-20 | 法法汽车(中国)有限公司 | The generation method of mask matrix, the synthetic method for image of parking and device |
CN105678787A (en) * | 2016-02-03 | 2016-06-15 | 西南交通大学 | Heavy-duty lorry driving barrier detection and tracking method based on binocular fisheye camera |
CN105894511B (en) * | 2016-03-31 | 2019-02-12 | 恒大法拉第未来智能汽车(广东)有限公司 | Demarcate target setting method, device and parking assistance system |
CN107784627A (en) * | 2016-08-31 | 2018-03-09 | 车王电子(宁波)有限公司 | The method for building up of vehicle panorama image |
CN106846410B (en) * | 2016-12-20 | 2020-06-19 | 北京鑫洋泉电子科技有限公司 | Driving environment imaging method and device based on three dimensions |
CN108269234B (en) * | 2016-12-30 | 2021-11-19 | 成都美若梦景科技有限公司 | Panoramic camera lens attitude estimation method and panoramic camera |
CN107146255A (en) * | 2017-04-05 | 2017-09-08 | 纵目科技(上海)股份有限公司 | Panoramic picture error calibration method and device |
CN107341766A (en) * | 2017-05-25 | 2017-11-10 | 深圳市汉华安道科技有限责任公司 | A kind of image automatic debugging system of panoramic parking assist system, method and apparatus |
CN107133988B (en) * | 2017-06-06 | 2020-06-02 | 科大讯飞股份有限公司 | Calibration method and calibration system for camera in vehicle-mounted panoramic looking-around system |
CN107392846B (en) * | 2017-07-31 | 2020-10-30 | 四川长虹电器股份有限公司 | Automobile data recorder image splicing method |
CN108280853A (en) * | 2018-01-11 | 2018-07-13 | 深圳市易成自动驾驶技术有限公司 | Vehicle-mounted vision positioning method, device and computer readable storage medium |
CN108313051B (en) * | 2018-01-15 | 2020-03-24 | 北京汽车集团有限公司 | Parking method, device, system and storage medium |
CN108269235A (en) * | 2018-02-26 | 2018-07-10 | 江苏裕兰信息科技有限公司 | A kind of vehicle-mounted based on OPENGL looks around various visual angles panorama generation method |
CN108596982A (en) * | 2018-04-24 | 2018-09-28 | 深圳市航盛电子股份有限公司 | A kind of easy vehicle-mounted multi-view camera viewing system scaling method and device |
CN109920005A (en) * | 2018-11-30 | 2019-06-21 | 广州汽车集团乘用车有限公司 | A kind of auto-panorama calibration system and method |
CN109741241B (en) * | 2018-12-26 | 2023-09-05 | 斑马网络技术有限公司 | Fisheye image processing method, device, equipment and storage medium |
CN109816732B (en) * | 2018-12-29 | 2020-12-11 | 百度在线网络技术(北京)有限公司 | Calibration method, calibration system, correction method, correction system and vehicle |
CN110555797B (en) * | 2019-08-01 | 2023-04-25 | 天津大学 | Panoramic aerial view image illumination homogenization processing method based on least square method |
CN112268506B (en) * | 2020-08-31 | 2022-06-07 | 中国航发南方工业有限公司 | Data splicing method based on non-contact optical scanning detection |
CN113283408A (en) * | 2021-07-22 | 2021-08-20 | 中国人民解放军国防科技大学 | Monitoring video-based social distance monitoring method, device, equipment and medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101059909A (en) * | 2006-04-21 | 2007-10-24 | 浙江工业大学 | All-round computer vision-based electronic parking guidance system |
CN101118648A (en) * | 2007-05-22 | 2008-02-06 | 南京大学 | Road conditions video camera marking method under traffic monitoring surroundings |
-
2008
- 2008-12-15 CN CN200810163310XA patent/CN101425181B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101059909A (en) * | 2006-04-21 | 2007-10-24 | 浙江工业大学 | All-round computer vision-based electronic parking guidance system |
CN101118648A (en) * | 2007-05-22 | 2008-02-06 | 南京大学 | Road conditions video camera marking method under traffic monitoring surroundings |
Non-Patent Citations (3)
Title |
---|
席志红等.基于鱼眼镜头的全视觉图像.《应用科技》.2007,第34卷(第12期),8-11,16. * |
李智等.动态场景下基于视差空间的立体视觉里程计.《浙江大学学报(工学版)》.2008,第42卷(第10期),1661-1665. * |
贾云得等.一种鱼眼镜头成像立体视觉系统的标定方法.《计算机学报》.2000,第23卷(第11期),1215-1219. * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105844624A (en) * | 2016-03-18 | 2016-08-10 | 上海欧菲智能车联科技有限公司 | Dynamic calibration system, and combined optimization method and combined optimization device in dynamic calibration system |
CN105844624B (en) * | 2016-03-18 | 2018-11-16 | 上海欧菲智能车联科技有限公司 | Combined optimization method and device in dynamic calibration system, dynamic calibration system |
Also Published As
Publication number | Publication date |
---|---|
CN101425181A (en) | 2009-05-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101425181B (en) | Panoramic view vision auxiliary parking system demarcating method | |
US9858639B2 (en) | Imaging surface modeling for camera modeling and virtual view synthesis | |
CN107133988B (en) | Calibration method and calibration system for camera in vehicle-mounted panoramic looking-around system | |
EP1253065B1 (en) | Parking assistance apparatus | |
CN105141945B (en) | Panorama camera chain (VPM) on-line calibration | |
CN103177439B (en) | A kind of automatic calibration method based on black and white lattice corners Matching | |
CN107228681A (en) | A kind of navigation system for strengthening navigation feature by camera | |
CN103617606B (en) | For assisting the vehicle multi-angle panorama generation method of driving | |
JP4555876B2 (en) | Car camera calibration method | |
CN102745138B (en) | Dual view-field dynamic-trajectory reverse image system | |
JP5124147B2 (en) | Camera calibration apparatus and method, and vehicle | |
US20080181488A1 (en) | Camera calibration device, camera calibration method, and vehicle having the calibration device | |
CN102915532B (en) | Determine the method and vehicle vision system of vehicle vision system external parameter | |
CN105825475B (en) | 360 degree of full-view image generation methods based on single camera | |
CN102629372A (en) | 360 degree panoramic aerial view generation method used for assisting vehicle driving | |
JP5077606B2 (en) | Method for calibrating a device comprising at least one omnidirectional camera and an optical display unit | |
CN103871071A (en) | Method for camera external reference calibration for panoramic parking system | |
US20090179916A1 (en) | Method and apparatus for calibrating a video display overlay | |
CN105445721A (en) | Combined calibrating method of laser radar and camera based on V-shaped calibrating object having characteristic protrusion | |
JP2008187566A (en) | Camera calibration apparatus and method and vehicle | |
WO2000007373A1 (en) | Method and apparatus for displaying image | |
US20110304726A1 (en) | All-around parking assisting system | |
JP6471522B2 (en) | Camera parameter adjustment device | |
CN103182984A (en) | Vehicle image display system and correction method thereof | |
CN107146255A (en) | Panoramic picture error calibration 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 | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120509 Termination date: 20141215 |
|
EXPY | Termination of patent right or utility model |