CN108765496A - A kind of multiple views automobile looks around DAS (Driver Assistant System) and method - Google Patents
A kind of multiple views automobile looks around DAS (Driver Assistant System) and method Download PDFInfo
- Publication number
- CN108765496A CN108765496A CN201810507410.3A CN201810507410A CN108765496A CN 108765496 A CN108765496 A CN 108765496A CN 201810507410 A CN201810507410 A CN 201810507410A CN 108765496 A CN108765496 A CN 108765496A
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- automobile
- coordinate system
- around
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/2624—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects for obtaining an image which is composed of whole input images, e.g. splitscreen
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The invention discloses the present invention relates to a kind of multiple views automobiles to look around DAS (Driver Assistant System), which includes multiple cameras, message processing module, output module.Pass through a binocular camera mounted on vehicle body all around, the image of three fish-eye camera acquisition body of a motor car surroundings;Message processing module pre-processes the image collected, texture mapping, brightness correction, image co-registration, the processing such as viewpoint change, and by binocular camera the image collected by pre-processing, and the processing such as images match obtain the distance of front obstacle;By output module by 360 solid of automobile of formation look around image include in car-mounted display equipment, and realize risk distance alarm.
Description
Technical field
The present invention relates to automobiles, and technical field of parking, more particularly to a kind of multiple views automobile to be assisted to look around auxiliary and drive system
System.
Background technology
It is shown according to State Statistics Bureau's statistical data, the linear growth trend of China's motor vehicles for civilian use owning amount.Automobile quantity
To increase be a major reason that traffic accidents take place frequently, traditional panorama DAS (Driver Assistant System) utilizes visual sensor,
By above the front bumper of automobile, left and right rearview mirror and tailstock car plate install four video cameras by the scene of vehicle body surrounding with
The form of virtual vertical view is presented to driver, and driver can easily observe the pedestrian of vehicle periphery by panoramic picture
And vehicle distances information, the vision dead zone of vehicle is eliminated, helps driver safer, easily drives a vehicle and park.But
Typical panorama DAS (Driver Assistant System) is the plain splice image of single visual angle, weakens three-dimensional spatial information around vehicle body, makes
The field range for obtaining driver is limited, however it remains some potential safety problems.Most of anticollision early warning needs to use at present
Laser radar, laser radar precision is very high, and detection range is remote, but the operational difficulties under rain and fog weather, and expensive now.
Invention content
The object of the present invention is to provide a kind of multiple views automobiles to look around DAS (Driver Assistant System), can be by the vehicle body periphery of acquisition
Image is converted into the complete panoramic picture of a width by processing, is shown on Vehicular display device, keeps driver intuitive
Vehicle body surrounding situation is solved, avoids the security risk generated because of vision blind spot, and make in time according to front obstacle early warning
Corresponding operation avoids, because of traffic accident caused by vision dead zone or faulty operation, improving drive safety.
Technical scheme is as follows.
A kind of multiple views automobile looks around DAS (Driver Assistant System), including several cameras, message processing module and output mould
Block;
Camera obtains image around body of a motor car;Camera includes the first camera being mounted on car insurance bar,
Second camera on left-hand mirror is mounted on the third camera of right rear view mirror and on automobile trunk
The 4th camera;
Message processing module carries out image procossing:The threedimensional model needed for viewing system is established, the figure obtained to camera
Image is looked around as being handled to obtain solid around vehicle body;Become scaling method based on image viewpoint to check around vehicle body from several viewpoints
Ambient image and the image obtained based on the first camera calculate the distance of front obstacle;
The result that output module output information processing module handles image.
First camera is binocular camera, and second camera, third camera and the 4th camera are fish-eye camera;
Binocular camera includes two imaging sensors, and described two imaging sensors are on same baseline, two images
The image of sensor timing synchronization, shooting has overlapping region.
Threedimensional model is three dimensional network model, and bottom surface is three-dimensional planar, and joint face is cambered surface, and annular surface is cylinder, bottom surface,
Joint face is connected with annular surface.
The generation that solid looks around image includes camera calibration, establish threedimensional model vertex and the texture of image slices vegetarian refreshments reflects
Relationship is penetrated, the image that camera obtains is mapped on threedimensional model according to texture mapping relationship, the image after mapping is carried out
Brightness correction merges the image of splicing regions.
Camera calibration includes the internal reference for obtaining camera and outer ginseng;
The internal reference of camera includes focal length, picture centre and distortion factor;It includes that four cameras are opposite to join outside camera
Rotary flat between two sensors of the camera pose for establishing world coordinate system using vehicle center as origin and the first camera
Shifting relationship.
Output module includes image display and alarm.Result to information processing includes defeated by image display
The three-dimensional distance for looking around image and front obstacle around the vehicle body gone out, and the risk distance alarm by alarm output.
A kind of multiple views automobile looks around auxiliary driving method, includes the following steps:
Step S1, Image Acquisition:
The image of vehicle body surrounding is acquired by camera;Camera includes the first camera being mounted on car insurance bar
1, the second camera 2 being mounted on left-hand mirror is mounted on the third camera 3 of right rear view mirror and is mounted on automobile trunk
The 4th camera 4 on case, four cameras acquire the image in four orientation after automobile front left and right respectively;
Collected several images are carried out image procossing in message processing module, synthesize target image by step S2;
The three dimensional network model being made of three-dimensional planar, cambered surface joint face and annular cylinder is established, to camera into rower
Surely the internal reference of camera and outer ginseng are obtained, all around four orientation cameras are clapped by automobile using the internal reference of camera and outer ginseng
The image taken the photograph is mapped on three dimensional network model, and the solid that motor vehicle environment is obtained after texture mapping looks around image, according to original graph
The brightness of picture carries out brightness correction, carries out the fusion of image in image co-registration region, the splicing seams of image are looked around in reduction;By first
The image of camera shooting measures distance of the front obstacle apart from vehicle, different observation visual angles is arranged, by viewpoint change matrix
The image of display automobile different direction;
Step S3, the solid of synthesis is looked around image and is output in automobile mounted display equipment by output module, according to binocular
Camera range measurement principle obtains front obstacle distance, and risk distance alarm is sent out by alarm.
Step S2 specifically includes following steps:
(201) camera calibration:Based on gridiron pattern scaling board, camera to be calibrated shoots gridiron pattern calibration from different directions
Plate, according to the image coordinate of the angle point (characteristic point of gridiron pattern scaling board) on gridiron pattern scaling board and its in world coordinate system
Coordinate geometrical relationship, acquire the internal reference of camera, the internal reference of camera includes the focal length of camera, picture centre and distortion
Coefficient;
When joining outside solution camera, world coordinate system is established using underbody center as world origin, according to the camera shooting acquired
Head internal reference, carries out distortion correction, by the projection relation of characteristic point and the picture point in image imaging under world coordinate system, is taken the photograph
Rotation amount and translational movement as head coordinate system relative to world coordinate system;
(202), texture mapping is the process for the pixel being mapped to the texture pixel in texture space in screen space;Three
Dimension module is made of the point in real world coordinate, according to the imaging model of camera, is obtained in model vertices and camera
Pixel coordinate in image establishes one-to-one relationship, to map an image to three dimensional network model surface;
(203), brightness correction:According to the institute of the brightness calculation luminance balance of the image of the acquisition of four cameras all around
Gain is needed, and acts on the corresponding image of camera acquisition, eliminates the luminance difference between stitching image;
(204), image co-registration:According to Pixel-level Weighted Fusion algorithm, so that the image after synthesis is realized and seamlessly transits,
Obtain the blending image of high quality.
Step (201) calibrating template plane sets are former according to the imaging of video camera in the plane of world coordinate system Z=0
Reason, by shot by camera to image and three dimensions in object linear relationship obtain the internal reference of camera and outer
Ginseng;The imaging process of camera is related to the conversion between four coordinate systems.
Step (201) specifically include:
(201a) sets calibrating template plane in the plane of world coordinate system Z=0, and world coordinate system is transformed into camera shooting
On head coordinate plane, according to the imaging model of video camera, by shot by camera to image and three dimensions in object
Between linear relationship obtain the internal reference of camera and outer ginseng:
Wherein, (Xw, Yw, Zw) is the world coordinates of angle point in calibrating template, and (Xc, Yc, Zc) is angle point in calibrating template
Coordinate in the camera coordinate system, R and T are spin matrix and translation matrix in joining outside camera respectively, are closed according to formula (1)
System completes conversion of the world coordinate system to camera coordinate system;
(201b) completes camera coordinate system to imaging plane coordinate according to the similar triangles relationship of pinhole imaging system principle
The conversion of system:
Wherein, f is the focal length of camera, and (x, y) is the image plane coordinate of angle point, and (Xc, Yc, Zc) is angle in calibrating template
The coordinate of point in the camera coordinate system;
(201c) is sampled and is quantified to image plane, and the pixel value of angle point is obtained;
Wherein,It is the size of cmos pixel in the x and y direction respectively, (Cx, Cy) is in the optics of camera
The heart, (x, y) are the image plane coordinates of angle point, complete conversion of the imaging plane to pixel planes;(u, v) is that angle point is obtained in camera
Take the coordinate on image.
The distance that the image that first camera obtains calculates front obstacle specifically includes following steps:
(301), distortion is eliminated:The camera internal reference obtained according to camera calibration carries out the distortion correction of image, specifically
Ground, binocular camera, which is demarcated, obtains the inner parameter of each camera, while being measured between two cameras by demarcating
Relative position (translation vector and spin matrix of the i.e. right camera relative to left camera).
(302), binocular corrects:The parallax that target point is formed on two views in left and right is calculated, target point is existed first
Two corresponding Pixel matchings get up on the view of left and right;Matched search range is reduced using epipolar-line constraint, improves matching efficiency,
The two images after distortion correction into every trade be aligned, make two images to polar curve in the same horizontal line, alignment advance
Row linear search is matched to corresponding points.
(303), parallax is calculated, realizes ranging:Stereo matching is carried out using Block Matching algorithms, utilizes target point
The directly existing difference of the abscissa being imaged on two width views of left and right, i.e., deposit at a distance from parallax, with target point to imaging plane
In inversely prroportional relationship:
Wherein, (X, Y, Z) is target point using left camera optical center as the coordinate in the world coordinate system of origin, and Z is exactly
Target point is to the distance of imaging plane under left camera coordinate system, and Tx is left and right camera centre-to-centre spacing, and f is the coke of camera
Away from d is the directly existing difference of abscissa that target point is imaged on two width views of left and right, i.e. parallax.
Parallax d can be acquired by following formula,
D=xleft-xright
Wherein, xleftAnd xrightIt is abscissa of the target point on left and right cameras imaging plane respectively.F and Tx passes through mark
Surely initial value is obtained, and is optimized by stereo calibration so that two cameras are mathematically substantially parallel placement;According to inverse proportion
Relationship seeks parallax, obtains the distance between target point and camera.
Message processing module complete to the processing of image after, by output module by the automobile of generation look around image include
On vehicular platform, and the distance measured according to binocular camera monitors early warning in real time, when front obstacle distance danger away from
From it is interior when, send out alarm from alarm to driver.
Compared with prior art, the beneficial effects of the invention are as follows:
The present invention discloses a kind of multiple views automobile and looks around DAS (Driver Assistant System) camera, realizes the vertical of vehicle body surrounding environment
Body scene and front anti-collision alarm, driver can freely adjust the angle as needed, find the pedestrian closer from vehicle in time
Or object, and risk distance alarm is sent out to front obstacle, driving safety can be improved to reducing traffic accident
Property, and cost is relatively low;
A kind of multiple views automobile of the present invention looks around auxiliary driving method, and automobile is realized using the image that multiple cameras acquire
Around 360 degree scenes show that the three-dimension object scene of effective reduction motor vehicle environment, driver can be as needed, from different
Environment around viewing point vehicle body.While realizing look-around impression, provide front obstacle anticollision early warning, cost compared with
It is low, it is feature-rich.In running car and during park, abundant and clearly blind area scene is provided to driver, and in time
Risk distance alerts, and substantially increases the safety of car steering, can effectively reduce traffic accident.
Description of the drawings
Present invention will be further explained below with reference to the attached drawings and examples;
Fig. 1 is that a kind of multiple views automobile of the present invention looks around auxiliary driving method flow chart;
Fig. 2 is that a kind of multiple views automobile of the present invention looks around camera installation site side view in DAS (Driver Assistant System) example;
Fig. 3 is that a kind of multiple views automobile of the present invention looks around camera installation site vertical view in DAS (Driver Assistant System) example;
Fig. 4 is the specific steps schematic diagram that the present invention looks around image synthesis;
Fig. 5 is the specific steps schematic diagram of binocular camera ranging of the present invention;
Fig. 6 is the schematic diagram that present example middle ring visible image splices integration region.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings and by specific embodiment, and following embodiment is descriptive
, it is not restrictive, protection scope of the present invention cannot be limited with this.
In order to make technological means, creation characteristic, workflow, application method reached purpose and effect of the present invention, and it is
The evaluation method is set to be easy to understand with reference to specific embodiments the present invention is further explained.
As shown in Figure 1, a kind of multiple views automobile looks around DAS (Driver Assistant System), including several cameras, information processing mould
Block and output module;
Camera obtains image around body of a motor car;As shown in Figure 2 and Figure 3, camera includes being mounted on car insurance bar
The first camera, be mounted on left-hand mirror on second camera, be mounted on right rear view mirror third camera and installation
The 4th camera on automobile trunk;
Message processing module carries out image procossing:The threedimensional model needed for viewing system is established, the figure obtained to camera
Image is looked around as being handled to obtain solid around vehicle body;Become scaling method based on image viewpoint to check around vehicle body from several viewpoints
Ambient image and the image obtained based on the first camera calculate the distance of front obstacle;
The result that output module output information processing module handles image.
First camera is binocular camera, and second camera, third camera and the 4th camera are fish-eye camera;
Binocular camera includes two imaging sensors, and described two imaging sensors are on same baseline, two images
The image of sensor timing synchronization, shooting has overlapping region.
Threedimensional model is three dimensional network model, and bottom surface is three-dimensional planar, and joint face is cambered surface, and annular surface is cylinder, bottom surface,
Joint face is connected with annular surface.
The generation that solid looks around image includes camera calibration, establish threedimensional model vertex and the texture of image slices vegetarian refreshments reflects
Relationship is penetrated, the image that camera obtains is mapped on threedimensional model according to texture mapping relationship, the image after mapping is carried out
Brightness correction merges the image of splicing regions.
Camera calibration includes the internal reference (focal length, picture centre, distortion factor) for obtaining camera and outer ginseng (spin matrix
R and translation matrix T).Step (201) in following step S2 is the specific steps of camera calibration.
Ginseng includes four cameras relative to the camera position for establishing world coordinate system using vehicle center as origin outside camera
Rotation translation relation (spin matrix R and translation matrix T) between two sensors of appearance and the first camera.
Output module includes image display and alarm.Result to information processing includes defeated by image display
The three-dimensional distance for looking around image and front obstacle around the vehicle body gone out, and the risk distance alarm by alarm output.
Step S1, Image Acquisition:
The image of vehicle body surrounding is acquired by camera;Camera includes the first camera being mounted on car insurance bar
1, the second camera 2 being mounted on left-hand mirror is mounted on the third camera 3 of right rear view mirror and is mounted on automobile trunk
The 4th camera 4 on case, four cameras acquire the image in four orientation after automobile front left and right respectively;
Collected several images are carried out image procossing in message processing module, synthesize target image by step S2;
The three dimensional network model being made of three-dimensional planar, cambered surface joint face and annular cylinder is established, to camera into rower
Surely the internal reference of camera and outer ginseng are obtained, all around four orientation cameras are clapped by automobile using the internal reference of camera and outer ginseng
The image taken the photograph is mapped on three dimensional network model, and the solid that motor vehicle environment is obtained after texture mapping looks around image, according to original graph
The brightness of picture carries out brightness correction, carries out the fusion of image in image co-registration region, the splicing seams of image are looked around in reduction;By first
The image of camera shooting measures distance of the front obstacle apart from vehicle, different observation visual angles is arranged, by viewpoint change matrix
The image of display automobile different direction;
As shown in figure 5, the distance that the image that the first camera obtains calculates front obstacle specifically includes following steps:
(301), distortion is eliminated:The camera internal reference obtained according to camera calibration carries out the distortion correction of image, specifically
Ground, binocular camera, which is demarcated, obtains the inner parameter of each camera, while being measured between two cameras by demarcating
Relative position (translation vector and spin matrix of the i.e. right camera relative to left camera).
(302), binocular corrects:The parallax that target point is formed on two views in left and right is calculated, target point is existed first
Two corresponding Pixel matchings get up on the view of left and right;Matched search range is reduced using epipolar-line constraint, improves matching efficiency,
The two images after distortion correction into every trade be aligned, make two images to polar curve in the same horizontal line, alignment advance
Row linear search is matched to corresponding points.
(303), parallax is calculated, realizes ranging:Stereo matching is carried out using Block Matching algorithms, utilizes target point
The directly existing difference of the abscissa being imaged on two width views of left and right, i.e., deposit at a distance from parallax, with target point to imaging plane
In inversely prroportional relationship:
Wherein, (X, Y, Z) is target point using left camera optical center as the coordinate in the world coordinate system of origin, and Z is exactly
Target point is to the distance of imaging plane under left camera coordinate system, and Tx is left and right camera centre-to-centre spacing, and f is the coke of camera
Away from d is the directly existing difference of abscissa that target point is imaged on two width views of left and right, i.e. parallax.
Parallax d can be acquired by following formula,
D=xleft-xright
Wherein, xleftAnd xrightIt is abscissa of the target point on left and right cameras imaging plane respectively.F and Tx passes through mark
Surely initial value is obtained, and is optimized by stereo calibration so that two cameras are mathematically substantially parallel placement;According to inverse proportion
Relationship, it (in the prior art, is routinely the precision of pixel scale, which can be in the hope of sub-pix to seek sub-pixel precision rank
The precision of rank, the other precision higher of sub-pixel) parallax, obtain the distance between target point and camera.
Step S3, the solid of synthesis is looked around image and is output in automobile mounted display equipment by output module, according to binocular
Camera range measurement principle obtains front obstacle distance, and risk distance alarm is sent out by alarm.
Step S2 specifically includes following steps:
(201) camera calibration:Based on gridiron pattern scaling board, camera to be calibrated shoots gridiron pattern calibration from different directions
Plate, according to the image coordinate of the angle point (characteristic point of gridiron pattern scaling board) on gridiron pattern scaling board and its in world coordinate system
Coordinate geometrical relationship, acquire the internal reference of camera, the internal reference of camera includes the focal length of camera, picture centre and distortion
Coefficient;
When joining outside solution camera, world coordinate system is established using underbody center as world origin, according to the camera shooting acquired
Head internal reference, carries out distortion correction, and by the characteristic point under world coordinate system, (projection relation of the picture point in being imaged with image, obtains
Rotation amount and translational movement of the camera coordinate system relative to world coordinate system;
With reference to Fig. 4, synthesis target image first demarcates camera to obtain the inside and outside ginseng of camera, will be taken the photograph using outer ginseng
As head obtain image be mapped on threedimensional model, after texture mapping generate automobile solid look around image, according to original image
Brightness carry out brightness correction, carry out the fusion of image in image co-registration region, the splicing seams of image are looked around in reduction.Step
(201) calibrating template plane sets are in the plane of world coordinate system Z=0, according to the image-forming principle of video camera, by video camera institute
The linear relationship between object in the image and three dimensions that take obtains the internal reference of camera and outer ginseng;Camera at
As process is related to the conversion between four coordinate systems.
Step (201) specifically include:
(201a) sets calibrating template plane in the plane of world coordinate system Z=0, and world coordinate system is transformed into camera shooting
On head coordinate plane, according to the imaging model of video camera, by shot by camera to image and three dimensions in object
Between linear relationship obtain the internal reference of camera and outer ginseng:
Wherein, (Xw, Yw, Zw) is the world coordinates of angle point in calibrating template, and (Xc, Yc, Zc) is angle point in calibrating template
Coordinate in the camera coordinate system, R and T are spin matrix and translation matrix in joining outside camera respectively, are closed according to formula (1)
System completes conversion of the world coordinate system to camera coordinate system;
(201b) completes camera coordinate system to imaging plane coordinate according to the similar triangles relationship of pinhole imaging system principle
The conversion of system:
Wherein, f is the focal length of camera, and (x, y) is the image plane coordinate of angle point, and (Xc, Yc, Zc) is angle in calibrating template
The coordinate of point in the camera coordinate system;
(201c) is sampled and is quantified to image plane, and the pixel value of angle point is obtained;
Wherein,It is the size of cmos pixel in the x and y direction respectively, (Cx, Cy) is in the optics of camera
The heart, (x, y) are the image plane coordinates of angle point, complete conversion of the imaging plane to pixel planes;(u, v) is that angle point is obtained in camera
Take the coordinate on image.
(202), texture mapping is the process for the pixel being mapped to the texture pixel in texture space in screen space;Three
Dimension module is made of the point in real world coordinate, according to the imaging model of camera, is obtained in model vertices and camera
Pixel coordinate in image establishes one-to-one relationship, to map an image to three dimensional network model surface;
(203), brightness correction:According to the institute of the brightness calculation luminance balance of the image of the acquisition of four cameras all around
Gain is needed, and acts on the corresponding image of camera acquisition, eliminates the luminance difference between stitching image;
(204), image co-registration:According to Pixel-level Weighted Fusion algorithm, so that the image after synthesis is realized and seamlessly transits,
Obtain the blending image of high quality.
Specifically, Fig. 6 is the schematic diagram that an example middle ring visible image of the invention splices integration region, wherein integration region
For region 1,3,5,7,9, non-fused region is region 2,4,6,8,10, region 11 is automobile position.In integration region, calculate
Under world coordinates corresponding to threedimensional model is joined outside two different cameras respectively, the coordinate in corresponding original image,
By two decile of region, according to the variation of angle, the texture corresponding to different two original images of world coordinate point pair takes
Different weights realize merging for foreground and background in integration region.
Message processing module complete to the processing of image after, by output module by the automobile of generation look around image include
On vehicular platform, and the distance measured according to binocular camera monitors early warning in real time, when front obstacle distance danger away from
From it is interior when, send out alarm from alarm to driver.
Those skilled in the art can be modified to the present invention or the think of of modification designed but do not depart from the present invention
Think and range.Therefore, if these modifications and changes of the present invention belongs to the claims in the present invention and its equivalent technical scope
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of multiple views automobile looks around DAS (Driver Assistant System), which is characterized in that including several cameras, message processing module
And output module;
Camera obtains image around body of a motor car;Camera includes the first camera being mounted on car insurance bar, installation
Second camera on left-hand mirror, be mounted on the third camera of right rear view mirror and on automobile trunk the
Four cameras;
Message processing module carries out image procossing:Threedimensional model is established, the image obtained to camera is handled to obtain vehicle body
Surrounding solid looks around image;Based on image viewpoint become scaling method from several viewpoints check vehicle body ambient enviroment image and be based on first
The image that camera obtains calculates the distance of front obstacle;
The result that output module output information processing module handles image.
2. a kind of multiple views automobile according to claim 1 looks around DAS (Driver Assistant System), which is characterized in that
First camera is binocular camera, and second camera, third camera and the 4th camera are fish-eye camera;
The binocular camera includes two imaging sensors, and described two imaging sensors are on same baseline, two images
The image of sensor timing synchronization, shooting has overlapping region.
3. a kind of multiple views automobile according to claim 1 looks around DAS (Driver Assistant System), which is characterized in that threedimensional model is
Three dimensional network model, bottom surface are three-dimensional planar, and joint face is cambered surface, and annular surface is cylinder, and bottom surface, joint face and annular surface connect
It connects.
4. a kind of multiple views automobile according to claim 1 looks around DAS (Driver Assistant System), which is characterized in that three-dimensional panoramic view
The generation of picture includes camera calibration, establishes threedimensional model vertex and the texture mapping relationship of image slices vegetarian refreshments, is reflected according to texture
It penetrates relationship the image that camera obtains is mapped on threedimensional model, brightness correction is carried out to the image after mapping, to splice region
The image in domain is merged.
5. a kind of multiple views automobile according to claim 4 looks around DAS (Driver Assistant System), which is characterized in that the camera
Calibration includes the internal reference for obtaining camera and outer ginseng;
The internal reference of camera includes focal length, picture centre and distortion factor;
Join outside camera include four cameras relative to using vehicle center as origin establish the camera pose of world coordinate system with
Rotation translation relation between first sensor of camera two.
6. a kind of multiple views automobile according to claim 1 looks around DAS (Driver Assistant System), which is characterized in that the output mould
Block includes image display and alarm.
7. a kind of multiple views automobile looks around auxiliary driving method, which is characterized in that include the following steps:
Step S1, Image Acquisition:
The image of vehicle body surrounding is acquired by camera;Camera includes the first camera being mounted on car insurance bar, peace
Second camera on left-hand mirror is mounted on the third camera of right rear view mirror and on automobile trunk
4th camera, four cameras acquire the image in four orientation after automobile front left and right respectively;
Collected several images are carried out image procossing in message processing module, synthesize target image by step S2;
The three dimensional network model being made of three-dimensional planar, cambered surface joint face and annular cylinder is established, camera demarcate
Internal reference to camera and outer ginseng, using the internal reference and outer ginseng of camera by automobile four orientation cameras shootings all around
Image is mapped on three dimensional network model, and the solid that motor vehicle environment is obtained after texture mapping looks around image, according to original image
Brightness carries out brightness correction, carries out the fusion of image in image co-registration region, the splicing seams of image are looked around in reduction;By the first camera shooting
The image of head shooting measures distance of the front obstacle apart from vehicle, and different observation visual angles is arranged, is shown by viewpoint change matrix
The image of automobile different direction;
Step S3, the solid of synthesis is looked around image and is output in automobile mounted display equipment by output module, according to binocular camera shooting
Head range measurement principle obtains front obstacle distance, and risk distance alarm is sent out by alarm.
8. a kind of multiple views automobile according to claim 7 looks around auxiliary driving method, which is characterized in that including following step
Suddenly:
Step S2 specifically includes following steps:
(201) camera calibration:Based on gridiron pattern scaling board, camera to be calibrated shoots gridiron pattern scaling board from different directions,
According to the geometrical relationship of the image coordinate of the angle point on gridiron pattern scaling board and its coordinate in world coordinate system, camera shooting is acquired
The internal reference of head, the internal reference of camera includes the focal length of camera, picture centre and distortion factor;
When joining outside solution camera, world coordinate system is established using underbody center as world origin, according in the camera acquired
Ginseng carries out distortion correction, by the projection relation of characteristic point and the picture point in image imaging under world coordinate system, obtains camera
Rotation amount and translational movement of the coordinate system relative to world coordinate system;
(202), texture mapping is the process for the pixel being mapped to the texture pixel in texture space in screen space;Three-dimensional mould
Type is made of the point in real world coordinate, and according to the imaging model of camera, image is obtained in model vertices and camera
In pixel coordinate establish one-to-one relationship, to map an image to three dimensional network model surface;
(203), brightness correction:According to the required increasing of the brightness calculation luminance balance of the image of the acquisition of four cameras all around
Benefit, and the corresponding image of camera acquisition is acted on, eliminate the luminance difference between stitching image;
(204), image co-registration:According to Pixel-level Weighted Fusion algorithm, so that the image after synthesis is realized and seamlessly transit, obtain
The blending image of high quality.
9. a kind of multiple views automobile according to claim 8 looks around auxiliary driving method, which is characterized in that including following step
Suddenly:
Step (201) specifically include:
(201a) sets calibrating template plane in the plane of world coordinate system Z=0, and world coordinate system, which is transformed into camera, to be sat
In mark system plane, according to the imaging model of video camera, by shot by camera to image and three dimensions in object
Linear relationship obtain the internal reference of camera and outer ginseng:
Wherein, (Xw, Yw, Zw) is the world coordinates of angle point in calibrating template, and (Xc, Yc, Zc) is that angle point is being taken the photograph in calibrating template
As the coordinate in head coordinate system, R and T are spin matrix and translation matrix in joining outside camera respectively, according to formula (1) relationship,
Complete conversion of the world coordinate system to camera coordinate system;
(201b) completes camera coordinate system to imaging plane coordinate system according to the similar triangles relationship of pinhole imaging system principle
Conversion:
Wherein, f is the focal length of camera, and (x, y) is the image plane coordinate of angle point, and (Xc, Yc, Zc) is that angle point exists in calibrating template
Coordinate in camera coordinate system;
(201c) is sampled and is quantified to image plane, and the pixel value of angle point is obtained;
Wherein,It is the size of cmos pixel in the x and y direction respectively, (Cx, Cy) is the optical centre of camera, (x,
Y) be angle point image plane coordinate, complete conversion of the imaging plane to pixel planes;(u, v) is that angle point obtains image in camera
On coordinate.
10. a kind of multiple views automobile according to claim 6 looks around auxiliary driving method, which is characterized in that including following
Step:
The distance that the image that first camera obtains calculates front obstacle specifically includes following steps:
(301), distortion is eliminated:The camera internal reference obtained according to camera calibration carries out the distortion correction of image, specifically,
Binocular camera, which is demarcated, obtains the inner parameter of each camera, while being measured by demarcating opposite between two cameras
Position;
(302), binocular corrects:The parallax that target point is formed on two views in left and right is calculated, first target point in left and right
Two corresponding Pixel matchings get up on view;Matched search range is reduced using epipolar-line constraint, matching efficiency is improved, abnormal
Become correction after two images into every trade be aligned, make two images to polar curve in the same horizontal line, alignment row carry out one
Dimension search is matched to corresponding points;
(303), parallax is calculated, realizes ranging:Stereo matching is carried out using Block Matching algorithms, using target point on a left side
The directly existing parallax of the abscissa being imaged on right two width views, there are inverse proportion passes at a distance from target point to imaging plane
System:
Wherein, (X, Y, Z) is target point using left camera optical center as the coordinate in the world coordinate system of origin, and Z is exactly on a left side
Target point is to the distance of imaging plane under camera coordinate system, and Tx is left and right camera centre-to-centre spacing, and f is the focal length of camera, and d is
The directly existing difference of the abscissa that target point is imaged on two width views of left and right, i.e. parallax;
Parallax d is acquired by following formula,
D=xleft-xright
Wherein, xleftAnd xrightIt is abscissa of the target point on left and right cameras imaging plane respectively;F and Tx is obtained by calibration
Initial value is obtained, and is optimized by stereo calibration so that two cameras are mathematically substantially parallel placement;It is closed according to inverse proportion
System seeks parallax d and obtains the distance between target point and camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810507410.3A CN108765496A (en) | 2018-05-24 | 2018-05-24 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810507410.3A CN108765496A (en) | 2018-05-24 | 2018-05-24 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108765496A true CN108765496A (en) | 2018-11-06 |
Family
ID=64006480
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810507410.3A Pending CN108765496A (en) | 2018-05-24 | 2018-05-24 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108765496A (en) |
Cited By (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109624854A (en) * | 2018-12-03 | 2019-04-16 | 浙江明航智能科技有限公司 | A kind of 360 ° of panoramas auxiliary visible system suitable for special vehicle |
CN109712194A (en) * | 2018-12-10 | 2019-05-03 | 深圳开阳电子股份有限公司 | Vehicle-mounted viewing system and its stereo calibration method and computer readable storage medium |
CN109741456A (en) * | 2018-12-17 | 2019-05-10 | 深圳市航盛电子股份有限公司 | 3D based on GPU concurrent operation looks around vehicle assistant drive method and system |
CN109741455A (en) * | 2018-12-10 | 2019-05-10 | 深圳开阳电子股份有限公司 | A kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system |
CN109801357A (en) * | 2018-12-04 | 2019-05-24 | 先临三维科技股份有限公司 | Show method and device, the storage medium, processor of three-dimensional digital model |
CN109801339A (en) * | 2018-12-29 | 2019-05-24 | 百度在线网络技术(北京)有限公司 | Image processing method, device and storage medium |
CN109819169A (en) * | 2019-02-13 | 2019-05-28 | 上海闻泰信息技术有限公司 | Panorama shooting method, device, equipment and medium |
CN109887036A (en) * | 2019-01-21 | 2019-06-14 | 广州市安晓科技有限责任公司 | A kind of automobile looks around the semi-automatic calibration system and method for panorama |
CN109903556A (en) * | 2019-03-01 | 2019-06-18 | 成都众易通科技有限公司 | A kind of vehicle blind zone on-line monitoring early warning system |
CN109949205A (en) * | 2019-01-30 | 2019-06-28 | 广东工业大学 | A kind of automatic Pilot image perception System and method for for simulating human eye |
CN110276716A (en) * | 2019-06-19 | 2019-09-24 | 北京茵沃汽车科技有限公司 | The generation method of the 180 degree correction view of vehicle front-and rear-view fish eye images |
CN110336991A (en) * | 2019-06-28 | 2019-10-15 | 深圳数位传媒科技有限公司 | A kind of environmental cues method and device based on binocular camera |
CN110414487A (en) * | 2019-08-16 | 2019-11-05 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for identifying lane line |
CN110428361A (en) * | 2019-07-25 | 2019-11-08 | 北京麒麟智能科技有限公司 | A kind of multiplex image acquisition method based on artificial intelligence |
CN110443855A (en) * | 2019-08-08 | 2019-11-12 | Oppo广东移动通信有限公司 | Multi-camera calibration, device, storage medium and electronic equipment |
CN110517216A (en) * | 2019-08-30 | 2019-11-29 | 的卢技术有限公司 | A kind of SLAM fusion method and its system based on polymorphic type camera |
CN110796102A (en) * | 2019-10-31 | 2020-02-14 | 重庆长安汽车股份有限公司 | Vehicle target sensing system and method |
CN110827358A (en) * | 2019-10-15 | 2020-02-21 | 深圳数翔科技有限公司 | Camera calibration method applied to automatic driving automobile |
CN110827361A (en) * | 2019-11-01 | 2020-02-21 | 清华大学 | Camera group calibration method and device based on global calibration frame |
CN111256693A (en) * | 2018-12-03 | 2020-06-09 | 北京初速度科技有限公司 | Pose change calculation method and vehicle-mounted terminal |
CN111277796A (en) * | 2020-01-21 | 2020-06-12 | 深圳市德赛微电子技术有限公司 | Image processing method, vehicle-mounted vision auxiliary system and storage device |
CN111539973A (en) * | 2020-04-28 | 2020-08-14 | 北京百度网讯科技有限公司 | Method and device for detecting pose of vehicle |
TWI702577B (en) * | 2019-07-10 | 2020-08-21 | 中華汽車工業股份有限公司 | A method for generating a driving assistance image utilizing in a vehicle and a system thereof |
CN111698467A (en) * | 2020-05-08 | 2020-09-22 | 北京中广上洋科技股份有限公司 | Intelligent tracking method and system based on multiple cameras |
CN111768332A (en) * | 2019-03-26 | 2020-10-13 | 深圳市航盛电子股份有限公司 | Splicing method of vehicle-mounted all-around real-time 3D panoramic image and image acquisition device |
CN111861891A (en) * | 2020-07-13 | 2020-10-30 | 一汽奔腾轿车有限公司 | Method for realizing panoramic image system picture splicing display based on checkerboard calibration |
CN111986248A (en) * | 2020-08-18 | 2020-11-24 | 东软睿驰汽车技术(沈阳)有限公司 | Multi-view visual perception method and device and automatic driving automobile |
CN111986246A (en) * | 2019-05-24 | 2020-11-24 | 北京四维图新科技股份有限公司 | Three-dimensional model reconstruction method and device based on image processing and storage medium |
CN112208438A (en) * | 2019-07-10 | 2021-01-12 | 中华汽车工业股份有限公司 | Driving auxiliary image generation method and system |
CN112241930A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method, device and system and vehicle |
CN112347825A (en) * | 2019-08-09 | 2021-02-09 | 杭州海康威视数字技术股份有限公司 | Method and system for adjusting vehicle body all-round model |
CN113066158A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN113135181A (en) * | 2021-06-22 | 2021-07-20 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113212427A (en) * | 2020-02-03 | 2021-08-06 | 通用汽车环球科技运作有限责任公司 | Intelligent vehicle with advanced vehicle camera system for underbody hazard and foreign object detection |
CN113313813A (en) * | 2021-05-12 | 2021-08-27 | 武汉极目智能技术有限公司 | Vehicle-mounted 3D panoramic all-around viewing system capable of actively early warning |
WO2021226772A1 (en) * | 2020-05-11 | 2021-11-18 | 上海欧菲智能车联科技有限公司 | Surround view display method and apparatus, computer device, and storage medium |
CN113724133A (en) * | 2021-08-06 | 2021-11-30 | 武汉极目智能技术有限公司 | 360-degree all-round-view splicing method for trailer connected by non-rigid bodies |
CN113727064A (en) * | 2020-05-26 | 2021-11-30 | 北京罗克维尔斯科技有限公司 | Method and device for determining field angle of camera |
CN113763534A (en) * | 2021-08-24 | 2021-12-07 | 同致电子科技(厦门)有限公司 | Point cloud mapping method based on visual look-around system |
CN115661366A (en) * | 2022-12-05 | 2023-01-31 | 蔚来汽车科技(安徽)有限公司 | Method for constructing three-dimensional scene model and image processing device |
CN115830118A (en) * | 2022-12-08 | 2023-03-21 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
CN103810686A (en) * | 2014-02-27 | 2014-05-21 | 苏州大学 | Seamless splicing panorama assisting driving system and method |
CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
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 |
-
2018
- 2018-05-24 CN CN201810507410.3A patent/CN108765496A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
CN103810686A (en) * | 2014-02-27 | 2014-05-21 | 苏州大学 | Seamless splicing panorama assisting driving system and method |
CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
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 |
Non-Patent Citations (2)
Title |
---|
蔡泽平: "面向无人车的多目融合感知研究", 《万方学位论文》 * |
黄冬: "3D全景辅肋驾驶系统关键技术的硏究", 《中国优秀硕士学位论文全文数据库(科技信息II辑)》 * |
Cited By (59)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111256693A (en) * | 2018-12-03 | 2020-06-09 | 北京初速度科技有限公司 | Pose change calculation method and vehicle-mounted terminal |
CN111256693B (en) * | 2018-12-03 | 2022-05-13 | 北京魔门塔科技有限公司 | Pose change calculation method and vehicle-mounted terminal |
CN109624854A (en) * | 2018-12-03 | 2019-04-16 | 浙江明航智能科技有限公司 | A kind of 360 ° of panoramas auxiliary visible system suitable for special vehicle |
CN109801357B (en) * | 2018-12-04 | 2023-10-31 | 先临三维科技股份有限公司 | Method and device for displaying three-dimensional digital model, storage medium and processor |
CN109801357A (en) * | 2018-12-04 | 2019-05-24 | 先临三维科技股份有限公司 | Show method and device, the storage medium, processor of three-dimensional digital model |
CN109712194B (en) * | 2018-12-10 | 2021-09-24 | 深圳开阳电子股份有限公司 | Vehicle-mounted all-round looking system, three-dimensional calibration method thereof and computer readable storage medium |
CN109741455B (en) * | 2018-12-10 | 2022-11-29 | 深圳开阳电子股份有限公司 | Vehicle-mounted stereoscopic panoramic display method, computer readable storage medium and system |
CN109712194A (en) * | 2018-12-10 | 2019-05-03 | 深圳开阳电子股份有限公司 | Vehicle-mounted viewing system and its stereo calibration method and computer readable storage medium |
CN109741455A (en) * | 2018-12-10 | 2019-05-10 | 深圳开阳电子股份有限公司 | A kind of vehicle-mounted stereoscopic full views display methods, computer readable storage medium and system |
CN109741456A (en) * | 2018-12-17 | 2019-05-10 | 深圳市航盛电子股份有限公司 | 3D based on GPU concurrent operation looks around vehicle assistant drive method and system |
CN109801339A (en) * | 2018-12-29 | 2019-05-24 | 百度在线网络技术(北京)有限公司 | Image processing method, device and storage medium |
CN109887036A (en) * | 2019-01-21 | 2019-06-14 | 广州市安晓科技有限责任公司 | A kind of automobile looks around the semi-automatic calibration system and method for panorama |
CN109949205A (en) * | 2019-01-30 | 2019-06-28 | 广东工业大学 | A kind of automatic Pilot image perception System and method for for simulating human eye |
CN109819169A (en) * | 2019-02-13 | 2019-05-28 | 上海闻泰信息技术有限公司 | Panorama shooting method, device, equipment and medium |
CN109903556A (en) * | 2019-03-01 | 2019-06-18 | 成都众易通科技有限公司 | A kind of vehicle blind zone on-line monitoring early warning system |
CN111768332A (en) * | 2019-03-26 | 2020-10-13 | 深圳市航盛电子股份有限公司 | Splicing method of vehicle-mounted all-around real-time 3D panoramic image and image acquisition device |
CN111986246A (en) * | 2019-05-24 | 2020-11-24 | 北京四维图新科技股份有限公司 | Three-dimensional model reconstruction method and device based on image processing and storage medium |
CN110276716B (en) * | 2019-06-19 | 2023-06-20 | 北京茵沃汽车科技有限公司 | Method for generating 180-degree correction view of front and rear view fisheye images of vehicle |
CN110276716A (en) * | 2019-06-19 | 2019-09-24 | 北京茵沃汽车科技有限公司 | The generation method of the 180 degree correction view of vehicle front-and rear-view fish eye images |
CN110336991A (en) * | 2019-06-28 | 2019-10-15 | 深圳数位传媒科技有限公司 | A kind of environmental cues method and device based on binocular camera |
CN110336991B (en) * | 2019-06-28 | 2021-07-13 | 深圳数位传媒科技有限公司 | Binocular camera-based environment prompting method and device |
TWI702577B (en) * | 2019-07-10 | 2020-08-21 | 中華汽車工業股份有限公司 | A method for generating a driving assistance image utilizing in a vehicle and a system thereof |
CN112208438A (en) * | 2019-07-10 | 2021-01-12 | 中华汽车工业股份有限公司 | Driving auxiliary image generation method and system |
CN112241930A (en) * | 2019-07-18 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method, device and system and vehicle |
CN110428361A (en) * | 2019-07-25 | 2019-11-08 | 北京麒麟智能科技有限公司 | A kind of multiplex image acquisition method based on artificial intelligence |
CN110443855A (en) * | 2019-08-08 | 2019-11-12 | Oppo广东移动通信有限公司 | Multi-camera calibration, device, storage medium and electronic equipment |
CN112347825B (en) * | 2019-08-09 | 2023-08-22 | 杭州海康威视数字技术股份有限公司 | Adjusting method and system for vehicle body looking-around model |
CN112347825A (en) * | 2019-08-09 | 2021-02-09 | 杭州海康威视数字技术股份有限公司 | Method and system for adjusting vehicle body all-round model |
CN110414487B (en) * | 2019-08-16 | 2022-05-13 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for identifying lane line |
CN110414487A (en) * | 2019-08-16 | 2019-11-05 | 东软睿驰汽车技术(沈阳)有限公司 | Method and device for identifying lane line |
CN110517216B (en) * | 2019-08-30 | 2023-09-22 | 的卢技术有限公司 | SLAM fusion method and system based on multiple types of cameras |
CN110517216A (en) * | 2019-08-30 | 2019-11-29 | 的卢技术有限公司 | A kind of SLAM fusion method and its system based on polymorphic type camera |
CN110827358A (en) * | 2019-10-15 | 2020-02-21 | 深圳数翔科技有限公司 | Camera calibration method applied to automatic driving automobile |
CN110827358B (en) * | 2019-10-15 | 2023-10-31 | 深圳数翔科技有限公司 | Camera calibration method applied to automatic driving automobile |
CN110796102A (en) * | 2019-10-31 | 2020-02-14 | 重庆长安汽车股份有限公司 | Vehicle target sensing system and method |
CN110796102B (en) * | 2019-10-31 | 2023-04-14 | 重庆长安汽车股份有限公司 | Vehicle target sensing system and method |
CN110827361A (en) * | 2019-11-01 | 2020-02-21 | 清华大学 | Camera group calibration method and device based on global calibration frame |
CN113066158A (en) * | 2019-12-16 | 2021-07-02 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN113066158B (en) * | 2019-12-16 | 2023-03-10 | 杭州海康威视数字技术股份有限公司 | Vehicle-mounted all-round looking method and device |
CN111277796A (en) * | 2020-01-21 | 2020-06-12 | 深圳市德赛微电子技术有限公司 | Image processing method, vehicle-mounted vision auxiliary system and storage device |
CN113212427A (en) * | 2020-02-03 | 2021-08-06 | 通用汽车环球科技运作有限责任公司 | Intelligent vehicle with advanced vehicle camera system for underbody hazard and foreign object detection |
CN111539973A (en) * | 2020-04-28 | 2020-08-14 | 北京百度网讯科技有限公司 | Method and device for detecting pose of vehicle |
CN111698467A (en) * | 2020-05-08 | 2020-09-22 | 北京中广上洋科技股份有限公司 | Intelligent tracking method and system based on multiple cameras |
WO2021226772A1 (en) * | 2020-05-11 | 2021-11-18 | 上海欧菲智能车联科技有限公司 | Surround view display method and apparatus, computer device, and storage medium |
CN113727064B (en) * | 2020-05-26 | 2024-03-22 | 北京罗克维尔斯科技有限公司 | Method and device for determining camera field angle |
CN113727064A (en) * | 2020-05-26 | 2021-11-30 | 北京罗克维尔斯科技有限公司 | Method and device for determining field angle of camera |
CN111861891A (en) * | 2020-07-13 | 2020-10-30 | 一汽奔腾轿车有限公司 | Method for realizing panoramic image system picture splicing display based on checkerboard calibration |
CN111986248B (en) * | 2020-08-18 | 2024-02-09 | 东软睿驰汽车技术(沈阳)有限公司 | Multi-vision sensing method and device and automatic driving automobile |
CN111986248A (en) * | 2020-08-18 | 2020-11-24 | 东软睿驰汽车技术(沈阳)有限公司 | Multi-view visual perception method and device and automatic driving automobile |
CN113313813A (en) * | 2021-05-12 | 2021-08-27 | 武汉极目智能技术有限公司 | Vehicle-mounted 3D panoramic all-around viewing system capable of actively early warning |
CN113135181A (en) * | 2021-06-22 | 2021-07-20 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113135181B (en) * | 2021-06-22 | 2021-08-24 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113724133A (en) * | 2021-08-06 | 2021-11-30 | 武汉极目智能技术有限公司 | 360-degree all-round-view splicing method for trailer connected by non-rigid bodies |
CN113724133B (en) * | 2021-08-06 | 2024-03-05 | 武汉极目智能技术有限公司 | 360-degree circular splicing method for non-rigid body connected trailer |
CN113763534B (en) * | 2021-08-24 | 2023-12-15 | 同致电子科技(厦门)有限公司 | Point cloud mapping method based on visual looking-around system |
CN113763534A (en) * | 2021-08-24 | 2021-12-07 | 同致电子科技(厦门)有限公司 | Point cloud mapping method based on visual look-around system |
CN115661366A (en) * | 2022-12-05 | 2023-01-31 | 蔚来汽车科技(安徽)有限公司 | Method for constructing three-dimensional scene model and image processing device |
CN115830118A (en) * | 2022-12-08 | 2023-03-21 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
CN115830118B (en) * | 2022-12-08 | 2024-03-19 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108765496A (en) | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method | |
CN109360245B (en) | External parameter calibration method for multi-camera system of unmanned vehicle | |
US9858639B2 (en) | Imaging surface modeling for camera modeling and virtual view synthesis | |
US8199975B2 (en) | System and method for side vision detection of obstacles for vehicles | |
CN105763854B (en) | A kind of omnidirectional imaging system and its imaging method based on monocular cam | |
KR100414708B1 (en) | Picture composing apparatus and method | |
JP3652678B2 (en) | Vehicle surrounding monitoring apparatus and adjustment method thereof | |
JP5444338B2 (en) | Vehicle perimeter monitoring device | |
JP5455124B2 (en) | Camera posture parameter estimation device | |
JP4861574B2 (en) | Driving assistance device | |
CN107888894B (en) | A kind of solid is vehicle-mounted to look around method, system and vehicle-mounted control device | |
US20130250070A1 (en) | Image synthesis device | |
CN111559314B (en) | Depth and image information fused 3D enhanced panoramic looking-around system and implementation method | |
JP2014520337A (en) | 3D image synthesizing apparatus and method for visualizing vehicle periphery | |
CN112224132A (en) | Vehicle panoramic all-around obstacle early warning method | |
CN107972585A (en) | Scene rebuilding System and method for is looked around with reference to the adaptive 3 D of radar information | |
CN102291541A (en) | Virtual synthesis display system of vehicle | |
US20160037154A1 (en) | Image processing system and method | |
CN109285120A (en) | A kind of image mosaic, image calibration method, vehicle and calibration facility | |
JP2023505891A (en) | Methods for measuring environmental topography | |
JP3453960B2 (en) | Vehicle periphery monitoring device | |
JP2012019552A (en) | Driving support device | |
JP4545503B2 (en) | Image generating apparatus and method | |
KR20160034681A (en) | Environment monitoring apparatus and method for vehicle | |
JP2011028634A (en) | Image display device for vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |
|
RJ01 | Rejection of invention patent application after publication |