CN101498889B - Multi-eye stereo camera shooting method and device - Google Patents

Multi-eye stereo camera shooting method and device Download PDF

Info

Publication number
CN101498889B
CN101498889B CN2009100791613A CN200910079161A CN101498889B CN 101498889 B CN101498889 B CN 101498889B CN 2009100791613 A CN2009100791613 A CN 2009100791613A CN 200910079161 A CN200910079161 A CN 200910079161A CN 101498889 B CN101498889 B CN 101498889B
Authority
CN
China
Prior art keywords
parallax
image
image acquisition
corresponding point
pixel
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.)
Active
Application number
CN2009100791613A
Other languages
Chinese (zh)
Other versions
CN101498889A (en
Inventor
欧阳骏
胡振程
叶建军
汪林
田臣礼
沈华东
张旭
高晓平
陆春
梁丽娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang SunYu Zhiling Technology Co.,Ltd.
Original Assignee
Wuxi Intelligent Vehicle Systems Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuxi Intelligent Vehicle Systems Co Ltd filed Critical Wuxi Intelligent Vehicle Systems Co Ltd
Priority to CN2009100791613A priority Critical patent/CN101498889B/en
Publication of CN101498889A publication Critical patent/CN101498889A/en
Application granted granted Critical
Publication of CN101498889B publication Critical patent/CN101498889B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The embodiment of the invention discloses a multicast and stereoscopic camera shooting method and a device thereof, belonging to the field of image processing. The method comprises: finding a corresponding point of each pixel point in the image picked up by a first image pickup device in the same image acquired by a second image pickup device which is of the shortest baseline distance to the first image pickup device; according to the corresponding point, predicting the position of the pixel point in the same images acquired by other image pickup devices; according to the predicted position, detecting the corresponding point of the pixel point in the same images acquired by other image pickup devices; calculating the parallax difference between the pixel point and the corresponding points in the same image acquired by each image pickup device; and producing a stereoscopic image according to the parallax.

Description

A kind of multi-eye stereo camera shooting method and device
Technical field
The present invention relates to image processing field, particularly a kind of multi-eye stereo camera shooting method and device.
Background technology
Current society, automobile has become a kind of requisite vehicles.People are enjoying convenience that automobile brings and while efficiently, and motor traffic accidents has also become increasingly serious global social concern.The vehicle environment sensory perceptual system utilizes various sensors that information such as vehicle self, surrounding environment and driver status are surveyed, by comparing with predefined standard, differentiate whether in the hole and hazard level of vehicle, can carry out early warning to the driver by modes such as sound, light in case of necessity.
The camera chain of vehicle-mounted three-dimensional environment sensing is mainly measured three dimensional space coordinate, information such as barrier position with the binocular solid camera in the prior art.Binocular solid camera system structural drawing the simplest and the most commonly used is parallel to each other by two optical axises as shown in Figure 1, and shooting face constitutes at conplane camera.(X, Y Z), are x1 and xr in the projection plane position of left and right sides camera to any 1 P of three dimensions.According to principle of triangulation, the difference of left and right sides projection coordinate, promptly parallax becomes following relation with three-dimensional apart from Z.
Δ = x l - x r = f b Z
Wherein f is the focal length of camera, and b is the spacing of the optical centre of two cameras, also claims base length.
Because f and b are known quantities or can obtain by correction,, just can obtain three-dimensional by calculating parallax apart from Z therefore as long as from the image of the left and right sides, find the position of corresponding point.
The technology that also has three three-dimensional cameras of a kind of L type to carry out the vehicle to run environmental monitoring in the prior art.This technology is according to needing this principle of enough characteristic informations (such as level or vertical edge) in the matching process of exploring corresponding point, by about two cameras obtain the steric information of the unique point of vertical direction, obtain the steric information of horizontal directions by two cameras up and down, comprehensive then two groups of steric informations obtain end product.This technology can be avoided the insensitivity of horizontal stereo camera shooting head system to horizontal properties information (such as the top or the bottom of vehicle).
After above-mentioned prior art was analyzed, the inventor found:
In the prior art one because the needs of installing, the camera focal length and the base length of vehicle-mounted binocular solid camera are fixed, just parallax and three-dimensional relation apart from Z are fixed, and therefore can't satisfy the needs that carry out distant place range finding (as 100 to the 200 meters vehicle detection in middle the place ahead of running at high speed) and up-close inspection (such as the detection of obstacles in 2 meters in the place ahead) simultaneously simultaneously;
Though can avoid the insensitivity of horizontal stereo camera shooting head system in the prior art two to horizontal properties information (such as the top or the bottom of vehicle), but the allocation plan of L type can't be assembled to the preceding top of vehicle usually, and prior art two can't solve the problem of carrying out the measurement of long distance and low coverage simultaneously.
Summary of the invention
In order to carry out the measurement of long distance and low coverage simultaneously, the embodiment of the invention provides a kind of multi-eye stereo camera shooting method and device.Described technical scheme is as follows:
A kind of multi-eye stereo camera shooting method, described method comprises:
Each pixel in the image that first image acquisition equipment is obtained in the identical image of obtaining with the shortest second image acquisition equipment of the first image acquisition equipment parallax range, is sought corresponding point;
According to described corresponding point, predict the position of described pixel in the identical image that other image acquisition equipments obtain;
According to the position of described prediction, in the identical image that other image acquisition equipments obtain, explore the corresponding point of described pixel;
Calculate described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, obtain three-dimensional distance according to described parallax, the optical axis of described each image acquisition equipment is parallel, imaging direction is identical, and the plane of delineation of described each image acquisition equipment in one plane.
Wherein, before described searching corresponding point, described method also comprises:
The image of gathering is proofreaied and correct.
Calculate described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, obtain three-dimensional distance, specifically comprise according to described parallax:
Parallax between the corresponding point of the pixel of the identical image that two the longest image acquisition equipments of calculating parallax range obtain obtains three-dimensional distance according to described parallax.
Calculate described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, obtain three-dimensional distance, specifically comprise according to described parallax:
Carry out linear on average according to the gray scale matching value of the corresponding point of described pixel, obtain mean parallax, obtain three-dimensional distance according to described mean parallax.
A kind of multi-eye stereo camera shooting device, described device comprises:
Search module, be used for each pixel of image that first image acquisition equipment is obtained, in the identical image of obtaining with the shortest second image acquisition equipment of the first image acquisition equipment parallax range, seek corresponding point;
Prediction module is used for searching the corresponding point that module obtains according to described, predicts the position of described pixel in the identical image that other image acquisition equipments obtain;
Explore module, be used for position, in the identical image that other image acquisition equipments obtain, explore the corresponding point of described pixel according to described prediction module prediction;
Computing module, be used for calculating the parallax of described pixel between the identical image corresponding point that each image acquisition equipment obtains, obtain three-dimensional distance according to described parallax, the optical axis of described each image acquisition equipment is parallel, imaging direction is identical, and the plane of delineation of described each image acquisition equipment in one plane.
Described device also comprises:
Correction module is used for the image of gathering is proofreaied and correct.
Wherein, described computing module specifically is used to calculate the parallax between the corresponding point of pixel of the identical image that two the longest image acquisition equipments of parallax range obtain, and obtains three-dimensional distance according to described parallax.
Wherein, described computing module specifically is used for gray scale matching value according to the corresponding point of described pixel and carries out linear on average, obtains mean parallax, obtains three-dimensional distance according to described mean parallax.
The beneficial effect of the technical scheme that the embodiment of the invention provides is: by at least three above image acquisition equipment measurement space distances, can carry out the measurement of long distance and low coverage simultaneously.
Description of drawings
Fig. 1 is a binocular solid camera system structural representation in the prior art;
Fig. 2 is the multi-eye stereo camera shooting method schematic flow sheet that the embodiment of the invention 1 provides;
Fig. 3 is the searching synoptic diagram of the corresponding point that provide of the embodiment of the invention 1;
Fig. 4 is that prior art and the present invention that the embodiment of the invention 1 provides measures field range contrast synoptic diagram;
Fig. 5 is the multi-eye stereo camera shooting apparatus structure synoptic diagram that the embodiment of the invention 2 provides.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, embodiment of the present invention is described further in detail below in conjunction with accompanying drawing.
Embodiment 1
Referring to Fig. 2, the embodiment of the invention provides a kind of multi-eye stereo camera shooting method, and the embodiment of the invention is that example describes with three image acquisition equipments, does not get rid of three above image acquisition equipments, and this method comprises:
101: each pixel in the image that first image acquisition equipment is obtained, in the identical image that second image acquisition equipment with the first image acquisition equipment parallax range minimum obtains, seek corresponding point;
Concrete, if three image acquisition equipments are divided into 1,2 and 3, the identical image that these three image acquisition equipments are obtained is also referred to as the three-dimensional image that absorbs of three orders, referring to Fig. 3, establishes the pixel of three dimensions point P in the image I 1 that image acquisition equipment 1 obtains for (x 1, y1), parallax range between image acquisition equipment 1 and the image acquisition equipment 2 is the shortest, then in the pixel column of the same ordinate y1 in the image I 2 that image acquisition equipment 2 obtains, begins to seek corresponding point left from x1.Be generally the purpose that reaches real-time processing, the corresponding point search can be limited in (such as N pixel) within certain pixel coverage, promptly at the (x1-N of I2, y1) to (x1, y1) seek only corresponding point by methods such as gray scale couplings within the pixel coverage, here suppose pixel among the I2 (x1-d, y1) be with I1 in pixel (x1, y1) Dui Ying corresponding point.
102:, predict the position of this pixel in the identical image that other image acquisition equipments obtain according to these corresponding point that obtain;
For example, the pixel of the image I 1 that default image acquisition equipment 1 obtains (x1, the position in the image I of y1) in image acquisition equipment 3, obtaining 3 for (xr, y1), according to principle of triangulation, xr should meet the following conditions:
Z = f b 12 x l - ( x l - d ) = f b 12 d = f b 13 x l - x r
Promptly can calculate the parallax of corresponding point between I1 and the I3 according to the parallax of corresponding point between I1 and the I2.Be simple declaration, suppose that three spacings between the image acquisition equipment equate that b12=b23 that is to say b13=b12*2.Following formula just can be converted to so:
x l-x r=2*d
The parallax that is corresponding point between I1 and the I3 is 2 times of parallax of corresponding point between I1 and the I2.Therefore can predict pixel point (x1, y1) position of corresponding point should be at (x1-2*d in image I 3, y1) near, by in the 3rd identical image that image acquisition equipment obtains, pixel (x1 in prediction and the I1 image, y1) calculated amount that corresponding point are explored can greatly be lowered in corresponding point position.
103: the corresponding point of in the identical image that other image acquisition equipments obtain, exploring this pixel according to the position of prediction;
The predict pixel point (x1, y1) in image I 3 position of corresponding point (x1-2*d, y1) near, therefore, (x1 is during y1) corresponding point to explore pixel in I3, just can be in that (x1-2*d explores near y1), has greatly reduced the calculated amount that corresponding point are explored.Wherein, explore near future position, seeking corresponding point is prior aries, is not giving unnecessary details herein.
104: calculate the parallax between the corresponding point of this pixel in the identical image that each image acquisition equipment obtains, obtain three-dimensional distance according to parallax.
For example, according to principle of triangulation, the parallax of left and right sides projection coordinate is as follows with three-dimensional relation apart from Z:
Δ = x l - x r = f b Z - - - ( 1 )
Wherein, Δ is represented parallax, and f is the focal length of camera, and b is a baseline, has therefore obtained parallax, just can obtain three-dimensional apart from Z by through type (1).
Wherein, the base length between each image acquisition equipment also can be inequality, and the camera lens of each image acquisition equipment adopts the camera lens of same focal length.
Equally, if whole base length is constant, three eye stereo camera shootings can be when keeping the distance measuring distance, in the effective range of 1 times of low coverage increase so.Referring to Fig. 4, A is the measured scope of binocular solid shooting among Fig. 4 (a), A+B+C is the measured scope of three eye stereo camera shootings that the embodiment of the invention provides among Fig. 4 (b), can find out obviously that from Fig. 4 A+B+C is far longer than A, promptly the measured scope of three eye stereo camera shootings is far longer than the measured scope of binocular solid shooting.
Wherein, before the corresponding point of calculating between two short image acquisition equipments of baseline, this method also comprises:
The image of gathering is proofreaied and correct.
Wherein, the parallax according between the corresponding point of this pixel in the identical image that each image acquisition equipment obtains obtains three-dimensional distance, specifically comprises:
Parallax between the corresponding point of the pixel of the identical image that two the longest image acquisition equipments of calculating parallax range obtain obtains three-dimensional distance according to this parallax.
Continue above-mentioned example, the parallax range of image acquisition equipment 1 and image acquisition equipment 3 is the longest, and then computed image is obtained the parallax between the corresponding point of pixel of the identical image that equipment 1 and 3 obtains, and obtains three-dimensional distance according to this parallax.
Perhaps, the parallax according between the corresponding point of this pixel in the identical image that each image acquisition equipment obtains obtains three-dimensional distance, specifically comprises:
Carry out linear on average according to the gray scale matching value of the corresponding point of this pixel, obtain mean parallax, this mean parallax accuracy of detection will be far longer than the precision of traditional double eye stereo camera shooting, obtain three-dimensional distance according to this mean parallax.
The beneficial effect of the embodiment of the invention is: by at least three above image acquisition equipment measurement space distances, increased effective measuring distance, solved long distance and the simultaneously-measured problem of low coverage; Also increased the field range of stereo camera shooting; By the gray scale matching value with corresponding point is the linear average of yardstick, has improved the parallax accuracy of detection of stereo camera shooting; By corresponding point are predicted, the corresponding point of raising are explored speed; And the zone that can't detect owing to block in the binocular solid image capture method, the embodiment of the invention is carried out cross-reference by the image acquisition equipment group of the different baselines of length, thereby has greatly lowered because of the error of blocking or noise brings.
Embodiment 2
Referring to Fig. 5, the embodiment of the invention provides a kind of multi-eye stereo camera shooting device, and the embodiment of the invention is that example describes with three image acquisition equipments, does not get rid of three above image acquisition equipments, and this device comprises:
Search module 501, be used for each pixel of image that first image acquisition equipment is obtained, in the identical image of obtaining with the shortest second image acquisition equipment of the first image acquisition equipment parallax range, seek corresponding point;
Concrete, if three image acquisition equipments are divided into 1,2 and 3, the identical image that these three image acquisition equipments are obtained is also referred to as the three-dimensional image that absorbs of three orders, and referring to Fig. 3, establishing the pixel of three dimensions point P in the image I 1 that image acquisition equipment 1 obtains is (xl, y1), parallax range between image acquisition equipment 1 and the image acquisition equipment 2 is the shortest, then in the pixel column of the same ordinate yl in the image I 2 that image acquisition equipment 2 obtains, begins to seek corresponding point left from xl.Be generally the purpose that reaches real-time processing, the corresponding point search can be limited in (such as N pixel) within certain pixel coverage, promptly at the (xl-N of I2, y1) to (xl, y1) seek only corresponding point by methods such as gray scale couplings within the pixel coverage, here suppose pixel among the I2 (xl-d, y1) be with I1 in pixel (xl, y1) Dui Ying corresponding point.
Prediction module 502 is used for predicting the position of this pixel in the identical image that other image acquisition equipments obtain according to searching the corresponding point that module 501 obtains;
For example, the pixel of the image I 1 that default image acquisition equipment 1 obtains (xl, the position in the image I of y1) in image acquisition equipment 3, obtaining 3 for (xr, y1), according to principle of triangulation, xr should meet the following conditions:
Z = f b 12 x l - ( x l - d ) = f b 12 d = f b 13 x l - x r
Promptly can calculate the parallax of corresponding point between I1 and the I3 according to the parallax of corresponding point between I1 and the I2.Be simple declaration, suppose that three spacings between the image acquisition equipment equate that b12=b23 that is to say b13=b12*2.Following formula just can be converted to so:
x l-x r=2*d
The parallax that is corresponding point between I1 and the I3 is 2 times of parallax of corresponding point between I1 and the I2.Therefore can predict pixel point (xl, y1) position of corresponding point should be at (xl-2*d in image I 3, y1) near, by in the 3rd identical image that image acquisition equipment obtains, pixel (x1 in prediction and the I1 image, y1) calculated amount that corresponding point are explored can greatly be lowered in corresponding point position.
Explore module 503, the identical image that the position that is used for predicting according to prediction module 502 obtains at other image acquisition equipments is explored the corresponding point of this pixel;
The predict pixel point (xl, y1) in image I 3 position of corresponding point (xl-2*d, y1) near, therefore, (xl is during y1) corresponding point to explore pixel in I3, just can be in that (xl-2*d explores near y1), has greatly reduced the calculated amount that corresponding point are explored.Wherein, explore near future position, seeking corresponding point is prior aries, is not giving unnecessary details herein.
Computing module 504 is used for calculating the parallax of this pixel between the corresponding point of the identical image that each image acquisition equipment obtains, and obtains the three dimensions distance according to parallax.
For example, according to principle of triangulation, the parallax of left and right sides projection coordinate is as follows with three-dimensional relation apart from Z:
Δ = x l - x r = f b Z - - - ( 2 )
Wherein, Δ is represented parallax, and f is the focal length of camera, and b is a baseline, has therefore obtained parallax, just can obtain three-dimensional apart from Z by through type (2).
Wherein, the base length between each image acquisition equipment also can be inequality, and the camera lens of each image acquisition equipment adopts the camera lens of same focal length.
Equally, if whole base length is constant, three eye stereo camera shooting head systems can be when keeping the distance measuring distance, in the effective range of 1 times of low coverage increase so.Referring to Fig. 4, A is the measured scope of binocular solid shooting among Fig. 4 (a), A+B+C is the measured scope of three eye stereo camera shootings that the embodiment of the invention provides among Fig. 4 (b), can find out obviously that from Fig. 4 A+B+C is far longer than A, promptly the measured scope of three eye stereo camera shootings is far longer than the measured scope of binocular solid shooting.
Wherein, this device also comprises:
Correction module is used for the image of gathering is proofreaied and correct.
Wherein, computing module specifically is used to calculate the parallax between the corresponding point of pixel of the identical image that two the longest image acquisition equipments of parallax range obtain, and obtains the three dimensions distance according to this parallax.
Continue above-mentioned example, the parallax range of image acquisition equipment 1 and image acquisition equipment 3 is the longest, and then computed image is obtained the parallax between the corresponding point of pixel of the identical image that equipment 1 and 3 obtains, and obtains three-dimensional distance according to this parallax.
Perhaps, computing module specifically is used for gray scale matching value according to the corresponding point of this pixel and carries out linear on average, obtains mean parallax, this mean parallax accuracy of detection will be far longer than the precision of traditional double eye stereo camera shooting, obtain the three dimensions distance according to this mean parallax.
The beneficial effect of the embodiment of the invention is: by at least three above image acquisition equipment measurement space distances, increased effective measuring distance, solved long distance and the simultaneously-measured problem of low coverage; Also increased the field range of stereo camera shooting; By the gray scale matching value with corresponding point is the linear average of yardstick, has improved the parallax accuracy of detection of stereo camera shooting; By corresponding point are predicted, the corresponding point of raising are explored speed; And the zone that can't detect owing to block in the binocular solid camera system, the device that the embodiment of the invention provides carries out cross-reference by the image acquisition equipment group of the different baselines of length, thereby has greatly lowered because of the error of blocking or noise brings.
The embodiment of the invention can utilize software to realize that corresponding software programs can be stored in the storage medium that can read, for example, and in the hard disk of computing machine, buffer memory or the CD.
The above only is preferred embodiment of the present invention, and is in order to restriction the present invention, within the spirit and principles in the present invention not all, any modification of being done, is equal to replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (8)

1. a multi-eye stereo camera shooting method is characterized in that, described method comprises:
Each pixel in the image that first image acquisition equipment is obtained in the identical image of obtaining with the shortest second image acquisition equipment of the first image acquisition equipment parallax range, is sought corresponding point;
According to described corresponding point, predict the position of described pixel in the identical image that other image acquisition equipments obtain;
According to the position of described prediction, in the identical image that other image acquisition equipments obtain, explore the corresponding point of described pixel;
Calculate described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, obtain three-dimensional distance according to described parallax, the optical axis of described each image acquisition equipment is parallel, imaging direction is identical, and the plane of delineation of described each image acquisition equipment in one plane.
2. method according to claim 1 is characterized in that, before described searching corresponding point, described method also comprises:
The image of gathering is proofreaied and correct.
3. method according to claim 1 is characterized in that, calculates described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, and obtains three-dimensional distance according to described parallax, specifically comprises:
Calculate the parallax between the corresponding point of pixel of the identical image that parallax range obtains greater than two image acquisition equipments of predetermined threshold value, obtain three-dimensional distance according to described parallax.
4. method according to claim 1 is characterized in that, calculates described pixel parallax between the corresponding point in the identical image that each image acquisition equipment obtains, and obtains three-dimensional distance according to described parallax, specifically comprises:
Carry out linear on average according to the gray scale matching value of the corresponding point of described pixel, obtain mean parallax, obtain three-dimensional distance according to described mean parallax.
5. a multi-eye stereo camera shooting device is characterized in that, described device comprises:
Search module, be used for each pixel of image that first image acquisition equipment is obtained, in the identical image of obtaining with the shortest second image acquisition equipment of the first image acquisition equipment parallax range, seek corresponding point;
Prediction module is used for searching the corresponding point that module obtains according to described, predicts the position of described pixel in the identical image that other image acquisition equipments obtain;
Explore module, be used for position, in the identical image that other image acquisition equipments obtain, explore the corresponding point of described pixel according to described prediction module prediction;
Computing module, be used for calculating the parallax of described pixel between the identical image corresponding point that each image acquisition equipment obtains, obtain three-dimensional distance according to described parallax, the optical axis of described each image acquisition equipment is parallel, imaging direction is identical, and the plane of delineation of described each image acquisition equipment in one plane.
6. device according to claim 5 is characterized in that, described device also comprises:
Correction module is used for the image of gathering is proofreaied and correct.
7. device according to claim 5, it is characterized in that, described computing module specifically is used to calculate the parallax between the corresponding point of pixel of the identical image that two the longest image acquisition equipments of parallax range obtain, and obtains three-dimensional distance according to described parallax.
8. device according to claim 5 is characterized in that, described computing module specifically is used for gray scale matching value according to the corresponding point of described pixel and carries out linear on average, obtains mean parallax, obtains three-dimensional distance according to described mean parallax.
CN2009100791613A 2009-03-03 2009-03-03 Multi-eye stereo camera shooting method and device Active CN101498889B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2009100791613A CN101498889B (en) 2009-03-03 2009-03-03 Multi-eye stereo camera shooting method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2009100791613A CN101498889B (en) 2009-03-03 2009-03-03 Multi-eye stereo camera shooting method and device

Publications (2)

Publication Number Publication Date
CN101498889A CN101498889A (en) 2009-08-05
CN101498889B true CN101498889B (en) 2011-09-21

Family

ID=40946007

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2009100791613A Active CN101498889B (en) 2009-03-03 2009-03-03 Multi-eye stereo camera shooting method and device

Country Status (1)

Country Link
CN (1) CN101498889B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5068782B2 (en) * 2009-03-25 2012-11-07 富士フイルム株式会社 Distance measuring method and apparatus
KR100971730B1 (en) * 2010-04-15 2010-07-21 (주)에이직뱅크 Parallel axis stereoscopic camera
WO2012002018A1 (en) * 2010-06-30 2012-01-05 富士フイルム株式会社 Stereoscopic image playback device, parallax adjustment method of same, parallax adjustment program, and image capture device
CN101976460B (en) * 2010-10-18 2012-02-22 无锡维森智能传感技术有限公司 Generating method of virtual view image of surveying system of vehicular multi-lens camera
JP5634643B2 (en) 2012-05-22 2014-12-03 三菱電機株式会社 Image processing device
CN104539934A (en) * 2015-01-05 2015-04-22 京东方科技集团股份有限公司 Image collecting device and image processing method and system
WO2017107192A1 (en) * 2015-12-25 2017-06-29 Boe Technology Group Co., Ltd. Depth map generation apparatus, method and non-transitory computer-readable medium therefor
CN105700551A (en) * 2016-01-27 2016-06-22 浙江大华技术股份有限公司 An unmanned aerial vehicle landing area determination method, an unmanned aerial vehicle landing method and related apparatuses
CN106052637B (en) * 2016-06-03 2018-12-18 用友网络科技股份有限公司 Based on dual camera apart from inducing method
WO2018006296A1 (en) 2016-07-06 2018-01-11 SZ DJI Technology Co., Ltd. Systems and methods for stereoscopic imaging
CN107801017A (en) * 2017-10-30 2018-03-13 北京都是科技有限公司 A kind of more mesh 3D video cameras and its 3D rendering modeling method
TWI662694B (en) * 2017-12-20 2019-06-11 緯創資通股份有限公司 3d image capture method and system
CN108958243A (en) * 2018-06-27 2018-12-07 芜湖市越泽机器人科技有限公司 A kind of robot avoiding barrier control method
CN112129262B (en) * 2020-09-01 2023-01-06 珠海一微半导体股份有限公司 Visual ranging method and visual navigation chip of multi-camera group

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1177749A (en) * 1996-09-23 1998-04-01 稻叶稔 Stereo camera
CN1188252A (en) * 1996-12-11 1998-07-22 稻叶稔 Lens adjustment device of stereo camera
US5892994A (en) * 1997-05-14 1999-04-06 Inaba; Minoru Stereo camera with prism finder
US6430373B1 (en) * 2000-05-24 2002-08-06 Minoru Inaba Stereo camera
CN101294801A (en) * 2007-07-13 2008-10-29 东南大学 Vehicle distance measuring method based on binocular vision

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1177749A (en) * 1996-09-23 1998-04-01 稻叶稔 Stereo camera
CN1188252A (en) * 1996-12-11 1998-07-22 稻叶稔 Lens adjustment device of stereo camera
US5892994A (en) * 1997-05-14 1999-04-06 Inaba; Minoru Stereo camera with prism finder
US6430373B1 (en) * 2000-05-24 2002-08-06 Minoru Inaba Stereo camera
CN101294801A (en) * 2007-07-13 2008-10-29 东南大学 Vehicle distance measuring method based on binocular vision

Also Published As

Publication number Publication date
CN101498889A (en) 2009-08-05

Similar Documents

Publication Publication Date Title
CN101498889B (en) Multi-eye stereo camera shooting method and device
CN107272021B (en) Object detection using radar and visually defined image detection areas
US20200273336A1 (en) Vehicular information systems and methods
CN101487970B (en) Mirror-image stereo camera apparatus and method
KR100854766B1 (en) Method for detecting of parking area by using range sensor
CN102806913B (en) Novel lane line deviation detection method and device
GB2555214A (en) Depth map estimation with stereo images
CN113487759B (en) Parking patrol method and device, mobile patrol equipment and patrol system
JP4979306B2 (en) Vehicle automatic measurement device, vehicle automatic measurement system, and vehicle automatic measurement method
US20220270358A1 (en) Vehicular sensor system calibration
JP5982298B2 (en) Obstacle detection device and obstacle detection method
JP2018180772A (en) Object detection device
US20190152487A1 (en) Road surface estimation device, vehicle control device, and road surface estimation method
KR101735557B1 (en) System and Method for Collecting Traffic Information Using Real time Object Detection
CN103177582A (en) All-in-one machine with video velocity measurement and vehicle license plate recognition
CN113743171A (en) Target detection method and device
CN114724110A (en) Target detection method and device
KR101030317B1 (en) Apparatus for tracking obstacle using stereo vision and method thereof
CN102927964B (en) Distance-measuring device, method and vehicle
JP5957359B2 (en) Stereo image processing apparatus and stereo image processing method
CN104005324A (en) Pavement texture information detection system
CN103630110A (en) Vehicle range finding system and vehicle range finding method
CN104091450A (en) Video tachymeter and video speed measurement method
CN110411499B (en) Evaluation method and evaluation system for detection and identification capability of sensor
KR102385907B1 (en) Method And Apparatus for Autonomous Vehicle Navigation System

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
ASS Succession or assignment of patent right

Owner name: WUXI ESCO ELECTRONICS TECHNOLOGY CO., LTD.

Free format text: FORMER OWNER: BEIJING MICROVIEW NEW ERA SCIENCE AND TECHNOLOGY CO.LTD.

Effective date: 20091211

C41 Transfer of patent application or patent right or utility model
TA01 Transfer of patent application right

Effective date of registration: 20091211

Address after: Postal code 617, zone 1, science and Technology Pioneer Park, 7 Changjiang Road, New District, Jiangsu, Wuxi: Si-Park 214028

Applicant after: Wuxi Intelligent Vehicle Systems Co., Ltd.

Address before: Beijing City, Haidian District Zhongguancun Road No. 18 smartfortune International Building A block 10 layer encoding post: 100083

Applicant before: Beijing micro vision new era technology Co., Ltd.

Co-applicant before: Hu Zhencheng

Co-applicant before: Ou Yangjun

C14 Grant of patent or utility model
GR01 Patent grant
C41 Transfer of patent application or patent right or utility model
TR01 Transfer of patent right

Effective date of registration: 20170224

Address after: 214000 Jiangsu, Wuxi New District Longshan Road, No. 4 (Wang Zhuang science and Technology Venture Center) C building 203-204

Patentee after: Wuxi Wissen Intelligent Sensing Technology Co., Ltd.

Address before: 214028 Wuxi science and Technology Innovation Park (Si-Park) No. 617, Changjiang Road, New District, Jiangsu, China

Patentee before: Wuxi Intelligent Vehicle Systems Co., Ltd.

CP01 Change in the name or title of a patent holder

Address after: 214000 C 203-204, Longshan Road, Wuxi New District, Wuxi, Jiangsu, China (203-204)

Patentee after: Wuxi wisdom Sensor Technology Co., Ltd.

Address before: 214000 C 203-204, Longshan Road, Wuxi New District, Wuxi, Jiangsu, China (203-204)

Patentee before: Wuxi Wissen Intelligent Sensing Technology Co., Ltd.

CP01 Change in the name or title of a patent holder
TR01 Transfer of patent right

Effective date of registration: 20181126

Address after: 315400 No. 67-69 Fengle Road, Yangming Street, Yuyao City, Ningbo City, Zhejiang Province

Patentee after: Ningbo wisdom Sensor Technology Co., Ltd.

Address before: 214000 C 203-204, Longshan Road, Wuxi New District, Wuxi, Jiangsu, China (203-204)

Patentee before: Wuxi wisdom Sensor Technology Co., Ltd.

TR01 Transfer of patent right
CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: 315400 No. 67-69 Fengle Road, Yangming Street, Yuyao City, Ningbo City, Zhejiang Province

Patentee after: Zhejiang SunYu Zhiling Technology Co.,Ltd.

Address before: 315400 No. 67-69 Fengle Road, Yangming Street, Yuyao City, Ningbo City, Zhejiang Province

Patentee before: NINGBO WISSEN INTELLIGENT SENSING TECHNOLOGY Co.,Ltd.