CN106952311A - Auxiliary parking system and method based on panoramic mosaic data mapping tables - Google Patents

Auxiliary parking system and method based on panoramic mosaic data mapping tables Download PDF

Info

Publication number
CN106952311A
CN106952311A CN201710120841.XA CN201710120841A CN106952311A CN 106952311 A CN106952311 A CN 106952311A CN 201710120841 A CN201710120841 A CN 201710120841A CN 106952311 A CN106952311 A CN 106952311A
Authority
CN
China
Prior art keywords
image
bird
eye view
uncalibrated
region
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.)
Granted
Application number
CN201710120841.XA
Other languages
Chinese (zh)
Other versions
CN106952311B (en
Inventor
闫旭琴
李研强
王磊
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.)
Institute of Automation Shandong Academy of Sciences
Original Assignee
Institute of Automation Shandong Academy of Sciences
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 Institute of Automation Shandong Academy of Sciences filed Critical Institute of Automation Shandong Academy of Sciences
Priority to CN201710120841.XA priority Critical patent/CN106952311B/en
Publication of CN106952311A publication Critical patent/CN106952311A/en
Application granted granted Critical
Publication of CN106952311B publication Critical patent/CN106952311B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
    • B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
    • B60R2300/303—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing using joined images, e.g. multiple camera images
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
    • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
    • B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Mechanical Engineering (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

Parked method and system the invention discloses the auxiliary based on panoramic mosaic data mapping tables, demarcation cloth is set on the ground of vehicle body surrounding, using the layout and dimension information for demarcating gridiron pattern region and common footprint domain on cloth, the image in the overlay area of the adjacent camera on automobile body is subjected to rough registration；Then the image in the overlay area of adjacent camera is finely adjusted using the object features in the domain of common footprint, utilize the non-similarity of characteristics of image, it is all belonging to the non-similarity of different cameras acquired image feature and when reaching minimum, find optimal image registration position；Panoramic mosaic data mapping tables are generated using panoramic mosaic template image, full-view video image can be generated in real time according to the file comprising data mapping table.The registration accuracy of panorama uncalibrated image can be effectively improved using the present invention, the splicing syncretizing effect of full-view video image is improved, effectively meets the requirement of real-time of hardware.

Description

Auxiliary parking system and method based on panoramic mosaic data mapping tables
Technical field
The present invention relates to technical field of image processing, the auxiliary more particularly to based on panoramic mosaic data mapping tables is parked System and method.
Background technology
Panorama auxiliary parking system is by the way that installed in vehicle body, all around 4 road fish-eye cameras are gathered around vehicle body in real time Image, the road fish eye images of graphics processing unit Jiang Zhe tetra- carry out distortion correction, and then the road fish eye images of Jiang Zhe tetra- become by perspective Change under a space coordinates, then generate panoramic picture, and be sent to console display device, user can be directly perceived in the car The environment seen around vehicle body, the security of driving can be effectively improved.
Panorama auxiliary parking system is got due to the original image of input by multiple ultra-wide angle vehicle-mounted cameras, and Need to carry out system calibrating by distortion correction, homography conversion, this will cause object deformation and color distortion larger no matter Using which kind of registration Algorithm, preferable registration effect can not be all obtained, an optimal image registration position is found, is that panorama is auxiliary That helps parking system realizes difficult point.Panorama auxiliary parking system is because the special applications demand of system is, it is necessary to the hardware dress of system Put the requirement of real-time that disclosure satisfy that in practical application.
The content of the invention
In order to solve the deficiencies in the prior art, the invention provides the auxiliary side of parking based on panoramic mosaic data mapping tables Method, it is therefore intended that utilize panoramic mosaic template image generation panoramic mosaic data mapping tables.
It is a further object of the present invention to provide the auxiliary parking system based on panoramic mosaic data mapping tables, the system according to File comprising data mapping table can generate full-view video image in real time.
Auxiliary based on panoramic mosaic data mapping tables is parked method, including：
Demarcation cloth is set on the ground of vehicle body surrounding, the cloth for demarcating gridiron pattern region and common footprint domain on cloth is utilized Office and dimension information, rough registration is carried out by the image in the overlay area of the adjacent camera on automobile body；
Then the image in the overlay area of adjacent camera is carried out using the object features in the domain of common footprint micro- Adjust, it is all belonging to the non-similarity of different cameras acquired image feature and reach using the non-similarity of characteristics of image During to minimum, optimal image registration position is found；
Panoramic mosaic data mapping tables are generated using panoramic mosaic template image, according to the text for including data mapping table Part can generate full-view video image in real time.
Further, 4 road flake ultra wide-angle imaging heads are installed in vehicle vehicle front to be demarcated, left, rear and right.
Further, vehicle front, left, rear and four width flake uncalibrated image A of right are obtained using camera0 (x00,y00)、A1(x10,y10)、A2(x20,y20)、A3(x30,y30), distortion correction is carried out to this fourth officer flake uncalibrated image, obtained Flake uncalibrated image B after four width distortion corrections0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31)。
Further, B is recognized respectively0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31) chessboard in image Angle point in lattice, obtains the world coordinates and image coordinate of angle point in the gridiron pattern in image, according to the world of angle point in gridiron pattern Coordinate and image coordinate can calculate B0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31) image homography Transformation matrix H0、H1、H2、H3, according to the homography conversion matrix, to image B0(x01,y01)、B1(x11,y11)、B2(x21,y21)、 B3(x31,y31) carry out getting a bird's eye view conversion respectively, obtain four width and get a bird's eye view uncalibrated image C0(x02,y02)、C1(x12,y12)、C2(x22,y22)、 C3(x32,y32)。
Further, homography conversion needs to ensure the image that four width get a bird's eye view the single checker being related in uncalibrated image Size is identical, and it is consistent with the direction of panoramic mosaic to get a bird's eye view tessellated direction in uncalibrated image.
Further, the generating mode of the panoramic mosaic template image is：According to the reality in demarcation cloth gridiron pattern region Actual vertical interval, the image dimension information in gridiron pattern region and panorama between size, gridiron pattern region get a bird's eye view calibration maps The display distance of picture, generates panoramic mosaic template image.
Further, the panoramic mosaic template image is by central area Rcent, front region RA, left area RB, rear Region RC, right region RDFive pieces of compositions, central area RcentFor car model image, front region RA, left area RB, rear Region RC, right region RDRespectively uncalibrated image C is got a bird's eye view with respective direction0(x02,y02)、C1(x12,y12)、C2(x22,y22)、C3 (x32,y32) corresponding, determined to get a bird's eye view the splicing gap of uncalibrated image two-by-two according to the size in gridiron pattern region, splice gap pair The rectangular area answered is exactly the overlapping region for getting a bird's eye view uncalibrated image two-by-two.
Further, according to tessellated picture position in the position of splicing line, birds-eye view picture, four width are got a bird's eye view into calibration maps Uncalibrated image D (x are got a bird's eye view as being spliced into the complete panorama of a width3,y3)。
Further, it is described to find optimal image registration position and specifically include：Determine the adjacent weight for getting a bird's eye view uncalibrated image Folded region, carries out feature extraction, according to the two overlapping regions respectively to the adjacent overlapping region image for getting a bird's eye view uncalibrated image Characteristics of image, gets a bird's eye view uncalibrated image position by this two width and is finely adjusted, and searches the optimal registration position of adjacent birds-eye view picture two-by-two Put, it is final to cause in 4 overlapping regions, it is all belonging to the non-similarity of different cameras acquired image feature and reach To minimum.
Further, panoramic mosaic map file is generated, panoramic mosaic mapping table consists of the following components：
F0：Get a bird's eye view uncalibrated image C0(x02,y02) and front flake uncalibrated image A0(x00,y00) between pixel point coordinates reflect Firing table M0；
F1：Get a bird's eye view uncalibrated image C1(x12,y12) and left flake uncalibrated image A1(x10,y10) between pixel point coordinates reflect Firing table M1；
F2：Get a bird's eye view uncalibrated image C2(x22,y22) and rear flake uncalibrated image A2(x20,y20) between pixel point coordinates reflect Firing table M2；
F3：Get a bird's eye view uncalibrated image C3(x32,y32) and right flake uncalibrated image A3(x30,y30) between pixel point coordinates reflect Firing table M3；
F4：Panorama gets a bird's eye view uncalibrated image D (x3,y3) and 4 directions get a bird's eye view pixel affiliated area between uncalibrated image and map Table M4, mapping table M4It is represented by formula (1), wherein R0、R1、R2、R3It is to get a bird's eye view uncalibrated image C respectively0(x02,y02)、C1(x12, y12)、C2(x22,y22)、C3(x32,y32) subgraph, and be not belonging to the adjacent fusion for getting a bird's eye view uncalibrated image in full-view video image Region, the adjacent integration region for getting a bird's eye view uncalibrated image is the adjacent subgraph for getting a bird's eye view uncalibrated image overlapping region, R4、R5、R6、R7 Belong to the adjacent integration region for getting a bird's eye view uncalibrated image, fusion treatment is carried out to affiliated overlapping region image in integration region, its Middle R4It is to get a bird's eye view uncalibrated image C0(x02,y02)、C1(x12,y12) overlapping region subgraph, R5It is to get a bird's eye view uncalibrated image C1(x12, y12)、C2(x22,y22) overlapping region subgraph, R6It is to get a bird's eye view uncalibrated image C2(x22,y22)、C3(x32,y32) overlapping region Subgraph, R7It is to get a bird's eye view uncalibrated image C0(x02,y02)、C3(x32,y32) overlapping region subgraph；
F5：Panorama gets a bird's eye view uncalibrated image D (x3,y3) get a bird's eye view uncalibrated image C with 4 directions0(x02,y02)、C1(x12,y12)、 C2(x22,y22)、C3(x32,y32) between pixel coordinate map M5, and got a bird's eye view for adjacent in uncalibrated image integration region Any pixel (x '3,y′3), it is necessary to illustrate (x '3,y′3) with affiliated two birds-eye views as the coordinate mapping relations of pixel；
F6：For the adjacent integration region R for getting a bird's eye view uncalibrated image4、R5、R6、R7The interior fusion factor h for determining pixel1、 h2, wherein h1、h2Be respectively affiliated birds-eye view as the weights of pixel under lap respective coordinates, by integration region R4、R5、R6、 R7In the coordinate (x ' of any pixel that is related to3,y′3) with the fusion factor of pixel deposit mapping table M6。
Further, the demarcation cloth is made up of gridiron pattern region and common footprint domain, and common footprint domain is mainly As the label of panoramic mosaic, on the ground all around of automobile before vehicle body setpoint distance is placed or drawn respectively Demarcate cloth, afterwards demarcation cloth, left demarcation cloth and right demarcation cloth, it is ensured that adjacent demarcation cloth gridiron pattern rectangular area is mutually perpendicular to, and is protected Card demarcation cloth is located in the visual range of flake shooting all around, according to placing or be drawn on automobile four direction all around Demarcation cloth, utilize camera obtain automobile surrounding uncalibrated image information.
Further, the panoramic mosaic template image front region RABy region R0、R7Composition, left area RBBy area Domain R1、R4Composition, rear area RCBy region R2、R5Composition, right region RDBy region R3、R6Composition.
Further, generation full-view video image realizes step in real time：The 4 road flakes obtained in real time around vehicle body are real-time After image, to R0、R1、R2、R3Pixel in region, the data mapping tables file generated according to calibration system, is mapped to affiliated original The coordinate of beginning fish eye images, determines output pixel value, for R4、R5、R6、R7Pixel in region, according to data mapping tables text Part, is mapped to the coordinate for the original fish eye images to be participated in calculating, the fusion factor determined according to mapping table, by the pixel Merged, determine output pixel value.
Based on the auxiliary parking system of panoramic mosaic data mapping tables, including：
Image capture module, is taken the photograph using the 4 road flake ultra-wide angle installed in automobile body front, left, rear and right As head obtains image, and synchronize to image processing；
Judge module, for carrying out judging whether to need demarcation to the image after synchronization process, if desired then by synchronous place Otherwise image transmitting after reason, is transferred to panorama generation module to system calibrating module；
Preceding video image, rear video image, left video image and right video image after system calibrating module, synchronization process Distortion correction is carried out respectively, carries out getting a bird's eye view conversion afterwards respectively again, will be got a bird's eye view the image after conversion and is carried out panoramic mosaic and generate Panoramic mosaic data mapping tables；
Panorama generation module, for remapping conversion to video image, is passed after handling afterwards the image after conversion Display module progress image is transported to show.
Compared with prior art, the beneficial effects of the invention are as follows：
The panorama auxiliary parking system of the present invention will get a bird's eye view uncalibrated image progress rough registration using cloth information is demarcated, and utilize public affairs Image is finely adjusted by the object features in overlay area altogether, realizes the optimization registration for getting a bird's eye view uncalibrated image, using automatic The splice template of generation, utilizes panoramic mosaic data mapping generation panoramic mosaic data mapping tables.
The registration accuracy of panorama uncalibrated image can be effectively improved using the present invention, improve the spelling of full-view video image Connect syncretizing effect, effectively meet the requirement of real-time of hardware.
Actual demand in product development of the invention of being parked with reference to panorama, solves the key issue in panoramic parking system.
Brief description of the drawings
The Figure of description for constituting the part of the application is used for providing further understanding of the present application, and the application's shows Meaning property embodiment and its illustrate be used for explain the application, do not constitute the improper restriction to the application.
Fig. 1 is panorama auxiliary parking system module frame chart；
Fig. 2 is demarcation cloth position view；
Fig. 3 is panoramic mosaic Prototype drawing；
Fig. 4 is that panoramic mosaic gets a bird's eye view image display range figure.
Embodiment
It is noted that described further below is all exemplary, it is intended to provide further instruction to the application.Unless another Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
As background technology is introduced, the deficiencies in the prior art, in order to solve technical problem as above, this Shen The auxiliary based on panoramic mosaic data mapping tables please be propose to park method and system.
The course of work of panorama auxiliary parking system can be divided into two subsystems, and one of working subsystem is for demarcation System, is to install demarcated after system first, carries out image procossing to 4 road fish eye images, generates panoramic mosaic image, finally Purpose be data mapping tables between the original fish eye images of generation and panoramic mosaic image, another working subsystem is in mark Determine after system, after 4 road flake realtime graphics are got, it is real-time that the data mapping tables generated using calibration system generate panorama Image.
In a kind of typical embodiment of the application, the embodiment of the present invention uses following system design scheme：Utilize PC demarcates panorama auxiliary parking system, determines uncalibrated image and panoramic mosaic image that flake ultra wide-angle imaging head is got Data mapping tables, and the data mapping tables are write in text, then copy this document to storage using USB interface In equipment, the hardware device of panorama auxiliary parking system is completed by the file comprising data mapping tables read in USB port Panorama aids in the initialization of parking equipment.When starting panorama auxiliary parking equipment in next time, system, which is read, includes data in flash memory The information unit of mapping table, is handled real-time four roads flake video image using the data mapping tables, and generation is real-time Full-view video image, and it is shown on a display screen.A kind of panorama that is used for aids in picture system of parking in the embodiment of the present invention Block diagram work as shown in Figure 1.
In vehicle body 4 flake ultra-wide angle vehicle-mounted cameras are all around fixed, for the front and back of automobile Camera, may be mounted above car plate nearby, setting angle be diagonally downward, for the camera of automobile left and right, It may be mounted near rearview mirror, setting angle is vertically downward.According to the Aspect Ratio of vehicle, it is determined that the size of demarcation cloth and Being drawn on layout, demarcation cloth has gridiron pattern and splice marks thing, demarcation cloth is placed on to the surrounding of automobile so that before vehicle Side, rear and both sides are placed with the gridiron pattern label for demarcation respectively, while in the common footprint domain of camera two-by-two Splice marks thing is inside placed with, cloth position view such as accompanying drawing 2 is demarcated.
The fisheye camera to be used in system is demarcated from fisheye camera calibration tool, can from opencv or Person's matlab calibration tool casees are demarcated to fisheye camera, here from matlab calibration tool casees.
In another typical embodiment of the application, demarcating steps：4 road flake uncalibrated images are carried out at image Reason, generates panoramic mosaic image, and final purpose is that the data between the original fish eye images of generation and panoramic mosaic image map Table, realizes that step is described as follows：
Step (1)：4 road fish-eye cameras are fixed in vehicle vehicle front to be demarcated, left, rear and right, on ground According to (drafting) demarcation cloth is placed accompanying drawing 2 Suo Shi on face, the layout and size in the four gridiron pattern regions demarcated here on cloth are all It is identical.
Step (2)：Obtain vehicle front, left, rear and four width flake uncalibrated image A of right0(x00,y00)、A1 (x10,y10)、A2(x20,y20)、A3(x30,y30)；According to distortion correction model to front, left, rear and right flake calibration maps As carrying out distortion correction, the flake uncalibrated image B after four width distortion corrections is obtained0(x01,y01)、B1(x11,y11)、B2(x21, y21)、B3(x31,y31)。
Step (3)：Angle point in the gridiron pattern in the flake uncalibrated image after identification distortion correction, is obtained in gridiron pattern respectively The rectangular area upper left top that angle point is constituted in the image coordinate on four summits in rectangular area that angle point is constituted, all checkers The corresponding image coordinate of point, right vertices, bottom left vertex, bottom right vertex is respectively P0、P1、P2、P3.If horizontal direction in image Having has b checker in a checker, vertical direction.If P4(x0,y0) it is the rectangle region that angle point is constituted in checker Domain left upper apex corresponding coordinate in birds-eye view picture, then in checker angle point constitute rectangular area right vertices, lower-left Summit, the bottom right vertex corresponding coordinate in birds-eye view picture are respectively P5((a-2)×u+x0,y0)、P6(x0,(b-2)×u+y0)、 P7((a-2)×u+x0,(b-2)×u+y0), wherein u is the picture size for getting a bird's eye view single checker after conversion, C '0、C′1、C ′2、C′3Respectively by image B0、B1、B2、B3Centered on left upper apex after 0 degree of rotate counterclockwise, 90 degree, 180 degree and 270 degree Image, calculate P4、P5、P6、P7In image C '0、C′1、C′2、C′3In corresponding pixel P '0、P′1、P′2、P′3, according to chessboard The image coordinate P of angle point in lattice0、P1、P2、P3With the world coordinates P ' of angle point in gridiron pattern0、P′1、P′2、P′3Figure can be calculated The homography conversion matrix of picture；According to homography conversion matrix, bird is carried out respectively to flake uncalibrated image after every width distortion correction Look down from a height conversion, obtain four width birds-eye views as C0(x02,y02)、C1(x12,y12)、C2(x22,y22)、C3(x32,y32), fourth officer is determined respectively The integration region of birds-eye view picture.
Step (4)：Generated as shown in Figure 3 according to formula (2), (3), (4), (5), (6), (7), (8), (9), (10) Splice template image, wherein wlr、wrr、hfr、hrrIt is related to the display distance of panorama birds-eye view picture, as shown in Figure 4.
wv=a × u (10)
Four width birds-eye view pictures are spliced into the complete panorama birds-eye view of a width as D (x3,y3), it is determined that getting a bird's eye view calibration maps two-by-two The overlapping region of picture.
Step (5)：Binary conversion treatment is carried out respectively to the adjacent overlapping region for getting a bird's eye view uncalibrated image, wherein a feature A To Template image A is chosen on imagemh, size is Mmh×Nmh, there is template A on another characteristic imagemhUnder covering Search sub-prime image Bmh, size is Lmh×Wmh, remember MmhAnd LmhIn maximum be r, remember NmhAnd WmhIn maximum be c, for Non-existent pixel on image, its another pixel value is 0, that is, it is not the characteristic point on the image to represent this pixel.Utilize Formula (11) calculates To Template AmhWith search subgraph BmhNon- similarity Pmh, according to template AmhSon under being covered with template Scheme BmhP during matchingmhMinimum value is obtained, the registration between two images is completed, is set up by the matching relationship of feature between image Registering mapping transformation.Final to cause in 4 overlapping regions of panoramic mosaic image, all adhere to separately is adopted with different cameras The non-similarity of characteristics of image of collection and reach minimum.
Step (6)：The homography conversion matrix and used fish eye images distortion correction mould calculated according to step (3) Type, can generate panoramic mosaic mapping table M0、M1、M2And M3, mapping table M can be generated according to panoramic mosaic template image4、M5。 The method that the use of integration region image co-registration is sprouted wings, specific fusion method such as formula (12), formula (13), formula (14), wherein d1、d2Respectively splicing integration region pixel is calculating integration region R to overlapping border AC, AB distance4、R5、R6、R7Picture During vegetarian refreshments pixel value, the overlay chart calculated is participated in as IsRespectively A0、A1、A2And A3, the overlay chart calculated is participated in as ItRespectively A1、A2、A3And A0.By integration region R4、R5、R6、R7In the coordinate of pixel that is related to deposited with the fade factor that merges of the pixel Enter mapping table M6.Panoramic mosaic mapping table M will be included0、M1、M2、M3、M4、M5And M6Information write-in panoramic mosaic mapping table File.
h1+h2=1 (13)
E (x, y)=h1Is(x,y)+h2It(x,y) (14)
If (x '3,y′3) be full-view video image in pixel, after having demarcated, getting 4 road flake realtime graphics Afterwards, the data mapping tables generated using calibration system generate panorama realtime graphic, realize that step is described as follows：
Step (1)：Panoramic mosaic map file is read, will be initialized with panoramic mosaic mapping table correlated variables；
Step (2)：According to mapping table M4, it may be determined that pixel (x '3,y′3) belonging to region；
Step (3)：If pixel (x '3,y′3) belong to R0、R1、R2、R3In a region, determine pixel (x '3,y′3) With the coordinate map M of fish eye imagesk.According to coordinate map M5, it may be determined that with pixel (x '3,y′3) corresponding get a bird's eye view Image pixel point coordinates Ck(x′k2,y′k2), according to coordinate map MkBirds-eye view can be determined as pixel Ck(x′k2,y′k2) phase Corresponding fish eye images pixel point coordinates Ak(x′k0,y′k0), so that it is determined that the pixel value of final pixel point；
Step (4) is if pixel (x '3,y′3) belong to R4、R5、R6、R7In a region, determine overlapping region pixel (x′3,y′3) with the coordinate map M of fish eye imagess、Mt.According to coordinate map M5, it may be determined that participate in calculating pixel (x′3,y′3) the corresponding birds-eye view of pixel value is as pixel point coordinates Cs(x′s2,y′s2)、Ct(x′t2,y′t2), mapped according to coordinate Table Ms、MtBirds-eye view can be determined as pixel Cs(x′s2,y′s2)、Ct(x′t2,y′t2) corresponding fish eye images pixel sits Mark As(x′s0,y′s0)、At(x′t0,y′t0).According to mapping table M6It is determined that (x '3,y′3) fusion factor, the pixel is carried out Fusion treatment, obtains the pixel value of final output.
The preferred embodiment of the application is the foregoing is only, the application is not limited to, for the skill of this area For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair Change, equivalent, improvement etc., should be included within the protection domain of the application.

Claims (10)

  1. The method 1. auxiliary based on panoramic mosaic data mapping tables is parked, it is characterized in that, including：
    Demarcation cloth is set on the ground of vehicle body surrounding, using demarcate on cloth the layout in gridiron pattern region and common footprint domain and Dimension information, rough registration is carried out by the image in the overlay area of the adjacent camera on automobile body；
    Then the image in the overlay area of adjacent camera is finely adjusted using the object features in the domain of common footprint, profit It is all belonging to the non-similarity of different cameras acquired image feature and reach minimum with the non-similarity of characteristics of image When, find optimal image registration position；
    Panoramic mosaic data mapping tables are generated using panoramic mosaic template image, can according to the file comprising data mapping table To generate full-view video image in real time.
  2. The method 2. auxiliary as claimed in claim 1 based on panoramic mosaic data mapping tables is parked, it is characterized in that, utilize shooting Head obtains vehicle front, left, rear and four width flake uncalibrated image A of right0(x00,y00)、A1(x10,y10)、A2(x20, y20)、A3(x30,y30), distortion correction is carried out to this fourth officer flake uncalibrated image, the demarcation of the flake after four width distortion corrections is obtained Image B0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31)。
  3. The method 3. auxiliary as claimed in claim 2 based on panoramic mosaic data mapping tables is parked, it is characterized in that, recognize respectively B0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31) angle point in gridiron pattern in image, obtain the chessboard in image The world coordinates and image coordinate of angle point in lattice, B can be calculated according to the world coordinates and image coordinate of angle point in gridiron pattern0 (x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31) image homography conversion matrix H0、H1、H2、H3, according to the list Answering property transformation matrix, to image B0(x01,y01)、B1(x11,y11)、B2(x21,y21)、B3(x31,y31) carry out getting a bird's eye view conversion respectively, Obtain four width and get a bird's eye view uncalibrated image C0(x02,y02)、C1(x12,y12)、C2(x22,y22)、C3(x32,y32)。
  4. The method 4. auxiliary as claimed in claim 3 based on panoramic mosaic data mapping tables is parked, it is characterized in that, homography becomes Change the picture size for needing four width of guarantee to get a bird's eye view the single checker being related in uncalibrated image identical, and get a bird's eye view uncalibrated image In tessellated direction it is consistent with the direction of panoramic mosaic.
  5. The method 5. auxiliary as claimed in claim 1 based on panoramic mosaic data mapping tables is parked, it is characterized in that, the panorama The generating mode of splice template image is：According to the reality between the actual size in demarcation cloth gridiron pattern region, gridiron pattern region Vertical interval, the image dimension information in gridiron pattern region and panorama get a bird's eye view the display distance of uncalibrated image, generate panoramic mosaic Template image.
  6. The method 6. auxiliary as claimed in claim 5 based on panoramic mosaic data mapping tables is parked, it is characterized in that, the panorama Splice template image is by central area Rcent, front region RA, left area RB, rear area RC, right region RDFive pieces of compositions, Central area RcentFor car model image, front region RA, left area RB, rear area RC, right region RDRespectively with phase That answers direction gets a bird's eye view uncalibrated image C0(x02,y02)、C1(x12,y12)、C2(x22,y22)、C3(x32,y32) corresponding, according to gridiron pattern The size in region determines the adjacent splicing gap for getting a bird's eye view uncalibrated image, and the corresponding rectangular area in splicing gap is exactly adjacent to get a bird's eye view mark Determine the overlapping region of image；
    According to tessellated picture position in the position of splicing line, birds-eye view picture, four width are got a bird's eye view into uncalibrated image and are spliced into a width Complete panorama gets a bird's eye view uncalibrated image D (x3,y3)。
  7. The method 7. auxiliary as claimed in claim 1 based on panoramic mosaic data mapping tables is parked, it is characterized in that, it is described to find Optimal image registration position is specifically included：The adjacent overlapping region for getting a bird's eye view uncalibrated image is determined, uncalibrated image is got a bird's eye view to adjacent Overlapping region image carry out feature extraction respectively, according to the characteristics of image of the two overlapping regions, this two width is got a bird's eye view into demarcation Picture position is finely adjusted, and searches the optimal registration position of adjacent birds-eye view picture two-by-two, final to cause 4 overlapping regions It is interior, it is all belonging to the non-similarity of different cameras acquired image feature and reach minimum.
  8. The method 8. auxiliary as claimed in claim 1 based on panoramic mosaic data mapping tables is parked, it is characterized in that, generate panorama Splice map file, panoramic mosaic mapping table consists of the following components：
    F0：Get a bird's eye view uncalibrated image C0(x02,y02) and front flake uncalibrated image A0(x00,y00) between pixel coordinate map M0；
    F1：Get a bird's eye view uncalibrated image C1(x12,y12) and left flake uncalibrated image A1(x10,y10) between pixel coordinate map M1；
    F2：Get a bird's eye view uncalibrated image C2(x22,y22) and rear flake uncalibrated image A2(x20,y20) between pixel coordinate map M2；
    F3：Get a bird's eye view uncalibrated image C3(x32,y32) and right flake uncalibrated image A3(x30,y30) between pixel coordinate map M3；
    F4：Panorama gets a bird's eye view uncalibrated image D (x3,y3) and 4 directions get a bird's eye view pixel affiliated area mapping table between uncalibrated image M4, mapping table M4It is represented by formula (1), wherein R0、R1、R2、R3It is to get a bird's eye view uncalibrated image C respectively0、C1、C2、C3Subgraph, And be not belonging to the adjacent integration region for getting a bird's eye view uncalibrated image in full-view video image, it is adjacent get a bird's eye view uncalibrated image integration region be The adjacent subgraph for getting a bird's eye view uncalibrated image overlapping region, R4、R5、R6、R7Belong to the adjacent integration region for getting a bird's eye view uncalibrated image, Fusion treatment, wherein R are carried out to affiliated overlapping region image in integration region4It is to get a bird's eye view uncalibrated image C0、C1Overlapping region son Image, R5It is to get a bird's eye view uncalibrated image C1、C2Overlapping region subgraph, R6It is to get a bird's eye view uncalibrated image C2、C3Overlapping region subgraph Picture, R7It is to get a bird's eye view uncalibrated image C0、C3Overlapping region subgraph；
    FM 4 ( x 4 , y 4 ) = 0 , ( x 4 , y 4 ) ∈ R 0 1 , ( x 4 , y 4 ) ∈ R 1 2 , ( x 4 , y 4 ) ∈ R 2 3 , ( x 4 , y 4 ) ∈ R 3 4 , ( x 4 , y 4 ) ∈ R 4 5 , ( x 4 , y 4 ) ∈ R 5 6 , ( x 4 , y 4 ) ∈ R 6 7 , ( x 4 , y 4 ) ∈ R 7 - - - ( 1 )
    F5：Panorama gets a bird's eye view uncalibrated image D (x3,y3) get a bird's eye view uncalibrated image C with 4 directions0(x02,y02)、C1(x12,y12)、C2 (x22,y22)、C3(x32,y32) between pixel coordinate map M5, and for adjacent times got a bird's eye view in uncalibrated image integration region Anticipate pixel (x '3,y′3), it is necessary to illustrate (x '3,y′3) with affiliated two birds-eye views as the coordinate mapping relations of pixel；
    F6：For the adjacent integration region R for getting a bird's eye view uncalibrated image4、R5、R6、R7The interior fusion factor h for determining pixel1、h2, its Middle h1、h2Be respectively affiliated birds-eye view as the weights of pixel under lap respective coordinates, by integration region R4、R5、R6、R7In relate to And any pixel coordinate (x '3,y′3) with the fusion factor of pixel deposit mapping table M6。
  9. The method 9. auxiliary as claimed in claim 1 based on panoramic mosaic data mapping tables is parked, it is characterized in that, give birth in real time Step is realized into full-view video image：Obtain in real time after 4 road flake realtime graphics around vehicle body, to R0、R1、R2、R3In region Pixel, the data mapping tables file generated according to calibration system, be mapped to belonging to original fish eye images coordinate, it is determined that output Pixel value, for R4、R5、R6、R7Pixel in region, according to data mapping tables file, is mapped to be participated in the original of calculating The pixel is merged, determines output pixel value by the coordinate of fish eye images, the fusion factor determined according to mapping table.
  10. 10. based on the auxiliary parking system of panoramic mosaic data mapping tables, it is characterized in that, including：
    Image capture module, utilizes the 4 road flake ultra wide-angle imaging heads installed in automobile body front, left, rear and right Image is obtained, and synchronizes to image processing；
    Judge module, for carrying out judging whether to need demarcation to the image after synchronization process, if desired then by after synchronization process Image transmitting to system calibrating module, otherwise, be transferred to panorama generation module；
    Preceding video image, rear video image, left video image and right video image difference after system calibrating module, synchronization process Distortion correction is carried out, carries out getting a bird's eye view conversion afterwards respectively again, the image after conversion will be got a bird's eye view and carry out panoramic mosaic and generate panorama Splice data mapping tables；
    Panorama generation module, for remapping conversion to video image, transmitted after handling afterwards the image after conversion to Display module carries out image and shown.
CN201710120841.XA 2017-03-02 2017-03-02 Auxiliary parking system and method based on panoramic stitching data mapping table Active CN106952311B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710120841.XA CN106952311B (en) 2017-03-02 2017-03-02 Auxiliary parking system and method based on panoramic stitching data mapping table

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710120841.XA CN106952311B (en) 2017-03-02 2017-03-02 Auxiliary parking system and method based on panoramic stitching data mapping table

Publications (2)

Publication Number Publication Date
CN106952311A true CN106952311A (en) 2017-07-14
CN106952311B CN106952311B (en) 2020-04-07

Family

ID=59468022

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710120841.XA Active CN106952311B (en) 2017-03-02 2017-03-02 Auxiliary parking system and method based on panoramic stitching data mapping table

Country Status (1)

Country Link
CN (1) CN106952311B (en)

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107492125A (en) * 2017-07-28 2017-12-19 哈尔滨工业大学深圳研究生院 The processing method of automobile fish eye lens panoramic view picture
CN107590773A (en) * 2017-08-25 2018-01-16 包谦 A kind of preparation method of panoramic picture
CN107633545A (en) * 2017-08-25 2018-01-26 包谦 A kind of processing method of panoramic picture
CN107958440A (en) * 2017-12-08 2018-04-24 合肥工业大学 Double fish eye images real time panoramic image split-joint methods and system are realized on GPU
CN108712604A (en) * 2018-05-07 2018-10-26 维沃移动通信有限公司 A kind of panorama shooting method and mobile terminal
CN109068207A (en) * 2018-07-04 2018-12-21 广州希脉创新科技有限公司 A kind of earphone and earphone system
CN109204141A (en) * 2018-09-19 2019-01-15 深圳市众鸿科技股份有限公司 Method for early warning and device in vehicle travel process
CN109429013A (en) * 2017-08-28 2019-03-05 华利纳企业股份有限公司 Image correcting system and image correcting method
CN109544647A (en) * 2018-11-30 2019-03-29 郑州天迈科技股份有限公司 Calibration cloth, place and method for 360 ° of panoramic parking assist systems
CN109600565A (en) * 2018-12-13 2019-04-09 广州路派电子科技有限公司 A kind of kinescope method based on parking system
CN109613920A (en) * 2018-12-27 2019-04-12 睿驰达新能源汽车科技（北京）有限公司 A kind of method and device of determining vehicle location
CN109767473A (en) * 2018-12-30 2019-05-17 惠州华阳通用电子有限公司 A kind of panorama parking apparatus scaling method and device
CN109948398A (en) * 2017-12-20 2019-06-28 深圳开阳电子股份有限公司 The image processing method and panorama parking apparatus that panorama is parked
CN110022459A (en) * 2018-01-08 2019-07-16 联发科技股份有限公司 Overall view monitoring system and overall view monitoring calibration method for vehicle
CN110264395A (en) * 2019-05-20 2019-09-20 深圳市森国科科技股份有限公司 A kind of the camera lens scaling method and relevant apparatus of vehicle-mounted monocular panorama system
CN110288527A (en) * 2019-06-24 2019-09-27 北京智行者科技有限公司 The vehicle-mounted camera panorama of looking around of one kind gets a bird's eye view drawing generating method
CN110838086A (en) * 2019-11-07 2020-02-25 上海大学 Outdoor image splicing method based on correlation template matching
CN111086455A (en) * 2020-03-19 2020-05-01 吉利汽车研究院（宁波）有限公司 Data processing method and device, electronic equipment and storage medium
CN111559314A (en) * 2020-04-27 2020-08-21 长沙立中汽车设计开发股份有限公司 Depth and image information fused 3D enhanced panoramic looking-around system and implementation method
CN112435161A (en) * 2020-11-12 2021-03-02 蘑菇车联信息科技有限公司 Panoramic all-around image splicing method and system, electronic equipment and storage medium
CN112606829A (en) * 2020-12-16 2021-04-06 广州市车智连电子有限公司 Auxiliary parking system based on panoramic stitching data mapping
CN113674363A (en) * 2021-08-26 2021-11-19 龙岩学院 Panoramic parking image splicing calibration method and calibration object thereof
CN114881863A (en) * 2022-06-30 2022-08-09 湖北芯擎科技有限公司 Image splicing method, electronic equipment and computer readable storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102298779A (en) * 2011-08-16 2011-12-28 淮安盈科伟力科技有限公司 Image registering method for panoramic assisted parking system
CN103177439B (en) * 2012-11-26 2015-10-28 惠州华阳通用电子有限公司 A kind of automatic calibration method based on black and white lattice corners Matching
CN105894549A (en) * 2015-10-21 2016-08-24 乐卡汽车智能科技（北京）有限公司 Panorama assisted parking system and device and panorama image display method
CN106373091A (en) * 2016-09-05 2017-02-01 山东省科学院自动化研究所 Automatic panorama parking aerial view image splicing method, system and vehicle

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102298779A (en) * 2011-08-16 2011-12-28 淮安盈科伟力科技有限公司 Image registering method for panoramic assisted parking system
CN103177439B (en) * 2012-11-26 2015-10-28 惠州华阳通用电子有限公司 A kind of automatic calibration method based on black and white lattice corners Matching
CN105894549A (en) * 2015-10-21 2016-08-24 乐卡汽车智能科技（北京）有限公司 Panorama assisted parking system and device and panorama image display method
CN106373091A (en) * 2016-09-05 2017-02-01 山东省科学院自动化研究所 Automatic panorama parking aerial view image splicing method, system and vehicle

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CHUNBAO HUO 等: "Research on the auxiliary panoramic parking technology based on fast image mosaic", 《2016 3RD INTERNATIONAL CONFERENCE ON INFORMATIVE AND CYBERNETICS FOR COMPUTATIONAL SOCIAL SYSTEMS (ICCSS)》 *
眭昊天: "多视点全景图像辅助泊车系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107492125A (en) * 2017-07-28 2017-12-19 哈尔滨工业大学深圳研究生院 The processing method of automobile fish eye lens panoramic view picture
CN107590773A (en) * 2017-08-25 2018-01-16 包谦 A kind of preparation method of panoramic picture
CN107633545A (en) * 2017-08-25 2018-01-26 包谦 A kind of processing method of panoramic picture
CN109429013A (en) * 2017-08-28 2019-03-05 华利纳企业股份有限公司 Image correcting system and image correcting method
CN107958440A (en) * 2017-12-08 2018-04-24 合肥工业大学 Double fish eye images real time panoramic image split-joint methods and system are realized on GPU
CN109948398A (en) * 2017-12-20 2019-06-28 深圳开阳电子股份有限公司 The image processing method and panorama parking apparatus that panorama is parked
CN109948398B (en) * 2017-12-20 2024-02-13 深圳开阳电子股份有限公司 Image processing method for panoramic parking and panoramic parking device
CN110022459A (en) * 2018-01-08 2019-07-16 联发科技股份有限公司 Overall view monitoring system and overall view monitoring calibration method for vehicle
CN108712604A (en) * 2018-05-07 2018-10-26 维沃移动通信有限公司 A kind of panorama shooting method and mobile terminal
CN108712604B (en) * 2018-05-07 2022-02-01 维沃移动通信有限公司 Panoramic shooting method and mobile terminal
CN109068207A (en) * 2018-07-04 2018-12-21 广州希脉创新科技有限公司 A kind of earphone and earphone system
CN109068207B (en) * 2018-07-04 2023-05-09 广州希脉创新科技有限公司 Earphone and earphone system
CN109204141A (en) * 2018-09-19 2019-01-15 深圳市众鸿科技股份有限公司 Method for early warning and device in vehicle travel process
CN109544647A (en) * 2018-11-30 2019-03-29 郑州天迈科技股份有限公司 Calibration cloth, place and method for 360 ° of panoramic parking assist systems
CN109600565A (en) * 2018-12-13 2019-04-09 广州路派电子科技有限公司 A kind of kinescope method based on parking system
CN109613920B (en) * 2018-12-27 2022-02-11 睿驰达新能源汽车科技（北京）有限公司 Method and device for determining vehicle position
CN109613920A (en) * 2018-12-27 2019-04-12 睿驰达新能源汽车科技（北京）有限公司 A kind of method and device of determining vehicle location
CN109767473B (en) * 2018-12-30 2022-10-28 惠州华阳通用电子有限公司 Panoramic parking device calibration method and device
CN109767473A (en) * 2018-12-30 2019-05-17 惠州华阳通用电子有限公司 A kind of panorama parking apparatus scaling method and device
CN110264395A (en) * 2019-05-20 2019-09-20 深圳市森国科科技股份有限公司 A kind of the camera lens scaling method and relevant apparatus of vehicle-mounted monocular panorama system
CN110264395B (en) * 2019-05-20 2023-11-28 深圳市森国科科技股份有限公司 Lens calibration method and related device of vehicle-mounted monocular panoramic system
CN110288527A (en) * 2019-06-24 2019-09-27 北京智行者科技有限公司 The vehicle-mounted camera panorama of looking around of one kind gets a bird's eye view drawing generating method
CN110288527B (en) * 2019-06-24 2023-10-24 北京智行者科技股份有限公司 Panoramic aerial view generation method of vehicle-mounted panoramic camera
CN110838086A (en) * 2019-11-07 2020-02-25 上海大学 Outdoor image splicing method based on correlation template matching
CN111086455A (en) * 2020-03-19 2020-05-01 吉利汽车研究院（宁波）有限公司 Data processing method and device, electronic equipment and storage medium
CN111559314B (en) * 2020-04-27 2021-08-24 长沙立中汽车设计开发股份有限公司 Depth and image information fused 3D enhanced panoramic looking-around system and implementation method
CN111559314A (en) * 2020-04-27 2020-08-21 长沙立中汽车设计开发股份有限公司 Depth and image information fused 3D enhanced panoramic looking-around system and implementation method
CN112435161A (en) * 2020-11-12 2021-03-02 蘑菇车联信息科技有限公司 Panoramic all-around image splicing method and system, electronic equipment and storage medium
CN112606829A (en) * 2020-12-16 2021-04-06 广州市车智连电子有限公司 Auxiliary parking system based on panoramic stitching data mapping
CN113674363B (en) * 2021-08-26 2023-05-30 龙岩学院 Panoramic parking image stitching calibration method and calibration object thereof
CN113674363A (en) * 2021-08-26 2021-11-19 龙岩学院 Panoramic parking image splicing calibration method and calibration object thereof
CN114881863B (en) * 2022-06-30 2022-09-30 湖北芯擎科技有限公司 Image splicing method, electronic equipment and computer readable storage medium
CN114881863A (en) * 2022-06-30 2022-08-09 湖北芯擎科技有限公司 Image splicing method, electronic equipment and computer readable storage medium

Also Published As

Publication number Publication date
CN106952311B (en) 2020-04-07

Similar Documents

Publication Publication Date Title
CN106952311A (en) Auxiliary parking system and method based on panoramic mosaic data mapping tables
CN111062873B (en) Parallax image splicing and visualization method based on multiple pairs of binocular cameras
US9451236B2 (en) Apparatus for synthesizing three-dimensional images to visualize surroundings of vehicle and method thereof
JP3871614B2 (en) Driving assistance device
CN106408511B (en) The vertical view transformation of fish eye images, overhead view image obtains and mapping table construction method
CN106373091A (en) Automatic panorama parking aerial view image splicing method, system and vehicle
US20030117488A1 (en) Stereoscopic panoramic image capture device
CN101000461A (en) Method for generating stereoscopic panorama by fish eye image
CN101487895B (en) Reverse radar system capable of displaying aerial vehicle image
CN104966318A (en) A reality augmenting method having image superposition and image special effect functions
CN110264395A (en) A kind of the camera lens scaling method and relevant apparatus of vehicle-mounted monocular panorama system
CN107292954B (en) Three-dimensional model and photo fusion method
CN106994936A (en) A kind of 3D panoramic parking assist systems
CN110008779A (en) A kind of stereoscopic two-dimensional code processing method and processing device
CN111815752B (en) Image processing method and device and electronic equipment
CN117611438B (en) Monocular image-based reconstruction method from 2D lane line to 3D lane line
RU2735066C1 (en) Method for displaying augmented reality wide-format object
CN103546680B (en) A kind of deformation-free omni-directional fisheye photographic device and a method for implementing the same
JP2003346189A (en) Image display device for vehicle
JP2003115057A (en) Texture editing device, texture editing system and method
CN116862997A (en) Method, device, equipment and storage medium for calculating and verifying camera calibration
CN110035275A (en) City panorama dynamic display system and method based on large screen fusion projection
CN113468991B (en) Parking space detection method based on panoramic video
CN103903274A (en) Small-radius large-curvature distortion surface projection correction and fusion method
CN112866507A (en) Intelligent panoramic video synthesis method and system, electronic device and medium

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
GR01 Patent grant
GR01 Patent grant