CN112308986A - Vehicle-mounted image splicing method, system and device - Google Patents
Vehicle-mounted image splicing method, system and device Download PDFInfo
- Publication number
- CN112308986A CN112308986A CN202011212532.3A CN202011212532A CN112308986A CN 112308986 A CN112308986 A CN 112308986A CN 202011212532 A CN202011212532 A CN 202011212532A CN 112308986 A CN112308986 A CN 112308986A
- Authority
- CN
- China
- Prior art keywords
- image
- sub
- images
- conversion
- adjacent
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000006243 chemical reaction Methods 0.000 claims abstract description 145
- 238000013178 mathematical model Methods 0.000 claims abstract description 65
- 238000013507 mapping Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 96
- 238000005070 sampling Methods 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 9
- 238000002156 mixing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 9
- 238000013519 translation Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 241000283070 Equus zebra Species 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention provides an image splicing method, an image splicing system and an image splicing device, wherein the image splicing method, the image splicing system and the image splicing device applying the image splicing method are used for forming at least two conversion images by constructing a three-dimensional mathematical model, mapping at least two obtained initial images into the three-dimensional mathematical model, dividing the at least two conversion images into two sub conversion images along the radial direction of the three-dimensional mathematical model respectively, and stretching one of the two adjacent sub conversion images towards the other one. Therefore, the sub-conversion images which are respectively positioned in the adjacent conversion images and adjacent to the sub-conversion images are gapless, and the spliced image generated by fusing the overlapped areas of the stretched sub-conversion images and the adjacent sub-conversion images is not in poor splicing after being connected end to end.
Description
Technical Field
The invention relates to the field of image stitching, in particular to a vehicle-mounted image stitching method, a vehicle-mounted image stitching system and a vehicle-mounted image stitching device.
Background
Along with the popularization of automobiles, more and more automobiles enter thousands of households, the living consumption level of people is continuously improved, the number of automobiles is also continuously increased, the intelligent requirements of people on electric appliances in the automobiles are higher and higher, and ADAS and vehicle-mounted 360-degree panoramic images in the intelligent automobiles are important configurations of high-vehicle-distribution types. The vehicle-mounted 3D panoramic system utilizes wide-angle cameras installed around the vehicle to reconstruct the vehicle and surrounding scenes, and generates a vehicle-mounted panoramic image. The driver can safely park the vehicle, avoid obstacles and eliminate visual blind areas by observing the panoramic image, thereby achieving the purpose of safe driving.
The concept of an on-board look-around system was first proposed by k.kato et al in 2006. Then, various active safety technologies such as lane detection, parking space detection and tracking, parking assistance, and moving object detection are applied to the vehicle-mounted all-round system. Byeongchaen Jeon et al proposed a solution to a high resolution panoramic surround view system in 2015. These schemes all feature the use of multiple cameras to complete the modeling of the actual scene, producing visual effects including 2D and pseudo-3D. The number of the cameras is determined according to the actual car model, the general household car is modeled by adopting 4-way fisheye cameras, and the final purpose is to unify images of multiple cameras in the same visual coordinate system to form a complete visual field for a driver to observe the conditions around the car.
The method for image stitching in the existing vehicle-mounted panoramic system generally selects an initial image to be stitched as a reference image, and then adjusts the other images in the direction of the reference image in sequence, but the current adjusting method can cause the problem that the last adjusted image and the reference image cannot be connected end to end.
Disclosure of Invention
The invention aims to provide a vehicle-mounted image splicing method, a system and a device, which aim to solve the problem of poor splicing caused by the fact that images spliced by the conventional vehicle-mounted all-around system are not connected end to end.
In order to solve the above problems, the present invention provides a vehicle-mounted image stitching method, including:
acquiring at least two initial images;
constructing a three-dimensional mathematical model with a world coordinate system, and sequentially mapping at least two initial images into the three-dimensional mathematical model to form at least two conversion images which are distributed in a surrounding way, wherein the overlapping areas of the adjacent conversion images are overlapped and the image contents are the same;
dividing at least two of the converted images into two sub-converted images along the radial direction of the three-dimensional mathematical model respectively;
stretching two adjacent sub-conversion images which are respectively positioned in two adjacent conversion images and one of the two adjacent sub-conversion images towards the other of the two adjacent conversion images until the image contents of the overlapping areas of the two sub-conversion images are overlapped;
and fusing the overlapped areas of the two sub-conversion images to generate a spliced image.
Optionally, before stretching two adjacent sub-transformation images which are respectively located in two adjacent transformation images and one of the two adjacent sub-transformation images towards the other of the two adjacent transformation images, the method further includes:
will be located in two adjacent said converted images, respectively, and the other of the two adjacent said sub-converted images will be stretched towards one of them.
Optionally, the method for stretching the sub-converted image includes:
and acquiring a homography matrix, and updating the sub-conversion image before stretching according to the homography matrix so as to stretch the sub-conversion image.
Optionally, obtaining coordinates of a plurality of first sampling points on the stretched sub-transformed image according to the homography matrix and coordinates of a plurality of initial first sampling points on the sub-transformed image before stretching;
acquiring a plurality of first texture coordinates according to the coordinates of the first sampling points;
acquiring a plurality of first target images according to the first texture coordinates;
updating the sub-converted image before stretching according to the plurality of first target images to stretch the sub-converted image.
Optionally, the method for obtaining coordinates of a plurality of first sample points on the stretched sub-converted image includes:
the method comprises the following steps: obtaining an inverse matrix corresponding to the corresponding initial first overlook point after the initial first sampling point mapping is obtained according to the homography matrix;
step two: obtaining the coordinates of a corresponding first depression viewpoint after the stretched sub-conversion image is mapped according to the inverse matrix;
step three: obtaining the coordinates of the first sampling point on the stretched sub-conversion image according to a bus equation of the three-dimensional mathematical model and the coordinates of the first depression viewpoint; and the number of the first and second groups,
and repeating the first step to the third step until the coordinates of all the first sampling points on the stretched sub-conversion image are obtained.
Optionally, the method for obtaining the inverse matrix includes:
obtaining the coordinates of the initial first depression viewpoint corresponding to the initial first sampling point after mapping according to the coordinates of the initial first sampling point;
obtaining an included angle between a connecting line between the initial first depression viewpoint and the origin of the three-dimensional mathematical model and an X axis or a Y axis according to the coordinates of the initial first depression viewpoint;
obtaining a weight value according to the included angle;
blending an identity matrix into the homography matrix according to the weight value, updating the homography matrix according to the identity matrix, and obtaining an inverse matrix corresponding to the initial first overlooking point according to the updated homography matrix.
Optionally, the three-dimensional mathematical model is a bowl-shaped three-dimensional mathematical model, and the bowl-shaped three-dimensional mathematical model includes a bowl edge and a bowl bottom;
the homography matrix includes: a first sub homography matrix corresponding to the bowl rim and a second sub homography matrix corresponding to the bowl bottom;
and merging an identity matrix into the first sub-homography matrix.
Optionally, the method for obtaining the homography matrix includes:
obtaining a first homography matrix which is positioned in two adjacent conversion images and corresponds to one of the two adjacent sub conversion images, and obtaining a second homography matrix which corresponds to the other of the two sub conversion images; and the number of the first and second groups,
the method for obtaining the second homography matrix comprises the following steps:
obtaining a first homography matrix which is positioned in two adjacent conversion images and corresponds to one of two adjacent sub-conversion images;
carrying out image registration on the overlapped area of the two sub-conversion images to obtain a matching characteristic point pair, and obtaining an initial second homography matrix according to the matching characteristic point pair;
and multiplying the initial second homography matrix and the first homography matrix to obtain the second homography matrix.
In order to solve the above problem, the present invention further provides a vehicle-mounted image stitching system, including:
the image acquisition module is used for acquiring at least two initial images;
the three-dimensional mathematical model building module is used for building a three-dimensional mathematical model with a world coordinate system, and mapping at least two initial images into the three-dimensional mathematical model in sequence to form at least two conversion images which are distributed in a surrounding way, wherein the overlapping areas of the adjacent conversion images are overlapped and the image contents are the same;
the data processing module is used for dividing at least two conversion images into two sub conversion images along the radial direction of the three-dimensional mathematical model respectively; stretching one of the two adjacent sub-conversion images towards the other one of the two adjacent sub-conversion images until the image contents of the overlapping areas of the two sub-conversion images are overlapped;
and the image splicing module is used for fusing the overlapping areas of the two sub-conversion images to generate a spliced image.
In order to solve the above problems, the present invention further provides a vehicle-mounted image stitching device, which includes a central control host and the vehicle-mounted image stitching system;
the image acquisition module comprises image acquisition equipment, the image acquisition equipment is connected with the central control host, and the acquired initial image is transmitted to the central control host for image processing so as to complete image splicing;
the three-dimensional mathematical model building module, the data processing module and the image splicing module are positioned in the central control host.
The invention provides an image splicing method, which comprises the steps of constructing a three-dimensional mathematical model, mapping at least two acquired initial images into the three-dimensional mathematical model to form at least two converted images, dividing the at least two converted images into two sub-converted images along the radial direction of the three-dimensional mathematical model respectively, and stretching one of the two sub-converted images which are adjacent to each other towards the other sub-converted image. Therefore, the sub-conversion images which are respectively positioned in the adjacent conversion images and adjacent to the sub-conversion images are gapless, and the spliced image generated by fusing the overlapped areas of the stretched sub-conversion images and the adjacent sub-conversion images is not in poor splicing after being connected end to end.
Drawings
FIG. 1 is a flow chart of a vehicle-mounted image stitching method in an embodiment of the invention;
FIG. 2 is a schematic diagram of a construction equation of a three-dimensional mathematical model established in the vehicle-mounted image stitching method in an embodiment of the present invention;
FIG. 3 is a schematic model diagram of a three-dimensional mathematical model established in the vehicle-mounted image stitching method according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the stretching of the converted image in the vehicle-mounted image stitching method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a vehicle-mounted image stitching system in an embodiment of the present invention;
FIG. 6 is a schematic diagram of an on-board image stitching device according to an embodiment of the present invention;
reference numerals
11-forward looking transformation of images; 110-transforming the image from the front viewer;
111-forward looking transformation image sloping edge part; 112-front view inverted image bowl bottom portion;
12-right view conversion image; 120-right view sub-conversion image;
121-a right-view transformation image grace portion; 122-right view translation image bowl bottom part;
13-converting the image for rear view; 130-rear view sub-conversion image;
131-a rear view transformation image grace portion; 132-rear view translation image bowl bottom portion;
14-left view transformation image; 140-left view transformed image;
141-left view transformation image grace portion; 142-left view translation image bowl bottom portion;
a1-graceful edge; a2-bowl bottom;
a-a first overlap region; b-a second overlap region;
c-a third overlap region; d-a fourth overlap region;
1-an image acquisition module; 2-a three-dimensional mathematical model construction module;
3-an image stitching module;
100-central control host.
Detailed Description
The following describes the vehicle-mounted image stitching method, system and apparatus in detail with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention. Further, the structures illustrated in the drawings are often part of actual structures. In particular, the drawings may have different emphasis points and may sometimes be scaled differently.
Fig. 1 is a flowchart of a vehicle-mounted image stitching method in an embodiment of the present invention. The vehicle-mounted image stitching method of the present embodiment as shown in fig. 1 includes the following steps S10 to S50.
In step S10, at least two initial images are acquired. In this step, at least two initial images located around the vehicle are acquired by at least two image acquisition devices.
The at least two image capturing devices may be fisheye cameras, and in a specific embodiment, for example, four fisheye cameras may be provided, and the four fisheye cameras are respectively disposed at front, rear, left, and right positions of a vehicle body, for example, at a front mirror, a rear mirror, a left rear mirror, and a right rear mirror of the vehicle body to capture images of a surrounding area of the vehicle in real time. The image content of the at least two initial images of the surroundings of the vehicle acquired by the at least two image acquisition devices may include a ground portion and an aerial portion, the image of the ground portion may include a sidewalk zebra crossing, a road edge and the like on the ground, and the image of the aerial portion may include pedestrians, surrounding vehicles, traffic lights and the like.
In step S20, a three-dimensional mathematical model with a world coordinate system is constructed, at least two of the initial images are sequentially mapped into the three-dimensional mathematical model to form at least two circularly distributed transformed images, and overlapping regions of adjacent transformed images overlap and image contents are the same.
Fig. 2 is a schematic view of a construction equation of a three-dimensional mathematical model established in the vehicle-mounted image stitching method in an embodiment of the present invention. Fig. 3 is a schematic model diagram of a three-dimensional mathematical model established in the vehicle-mounted image stitching method in an embodiment of the present invention. As shown in fig. 2 and 3, in the present embodiment, the three-dimensional mathematical model is a three-dimensional bowl-shaped mathematical model, the construction equation for constructing the three-dimensional bowl-shaped mathematical model is shown in fig. 2, and X, Y, Z is a world coordinate system, where X0Y represents the ground, 0 represents the geometric center of the projection of the vehicle on the ground, 0Y represents the advancing direction of the vehicle, 0Z represents the rotation axis, and 0R represents the rotation axis0P represents a bus, the bowl-shaped curved surface is formed by rotating the bus around a rotating shaft, and the formula of a bus equation for constructing the three-dimensional bowl-shaped model is shown as formula (1).
Wherein R is0Represents the radius of the bowl bottom A2, the radius R of the bowl bottom A20Radius R of said bowl bottom A2 in relation to vehicle size0Is typically about 100cm larger than one-half the size of the vehicle, in this embodiment, the radius R of the bowl bottom a20Is 250 cm-350 cm, preferably, the radius R of the bowl bottom A20The size of (2) is 300 cm; the units of the camera coordinate system and the world coordinate system are cm.
And K is an adjusting coefficient of the bowl edge a1, in this embodiment, the relative size between the bowl edge a1 and the bowl bottom a2 is adjusted by the adjusting coefficient K of the bowl edge a1, that is, the larger the K value, the larger the area corresponding to the bowl edge a 1. Regardless of whether the bowl edge a1 area is too large, the bowl bottom a2 area is too small, or the bowl bottom a2 area is too small, the bowl edge a1 area is too large, which results in poor splicing effect, so that the adjustment coefficient k of the bowl edge a1 needs to be given a value in a proper range. In this embodiment, the k value ranges from 0.1 to 0.2. Preferably, in this embodiment, the K value ranges from 0.15.
In this embodiment, the number of the acquired initial images may be two, and two of the converted images formed by mapping are arranged around the initial images, or the number of the acquired initial images may be three, and three of the converted images formed by mapping are arranged around the initial images. And the number of the obtained initial images can be four or more, and four or more converted images formed by mapping are arranged in a surrounding manner.
Fig. 4 is a schematic diagram of the stretching of the converted image in the vehicle-mounted image stitching method according to the embodiment of the invention. Specifically, fig. 4 is shown to illustrate a specific case of acquiring four initial images and mapping the converted images to form four surround settings in the present embodiment. In this embodiment, the number of the acquired initial images may be four, and the four initial images are respectively acquired by sequentially setting four positions of a vehicle head, a right rear-view mirror, a vehicle tail and a left rear-view mirror. And mapping the four sequentially acquired initial images to form four conversion images which are distributed in a surrounding manner, wherein the four conversion images which are arranged in a surrounding manner can be correspondingly defined as a front-view conversion image 11, a right-view conversion image 12, a rear-view conversion image 13 and a left-view conversion image 14 according to the positions of the image acquisition equipment which is arranged on the periphery of the vehicle. Wherein each of the converted images includes a creeping portion and a bowl bottom portion. Specifically, with continued reference to fig. 4, the forward looking translation image 11 includes a forward looking translation image bowl bottom portion 112 and a forward looking translation image sloping portion 111; the right-view transformation image 12 comprises a right-view transformation image bowl bottom part 122 and a right-view transformation image grace edge part 121; the rear-view transformation image 13 includes a rear-view transformation image bowl bottom portion 132 and a rear-view transformation image warping portion 131; the left-view transformed image 14 includes a left-view transformed image bowl bottom portion 142 and a left-view transformed image warping portion 141.
In step S30, at least two of the converted images are divided into two sub-converted images along the radial direction of the three-dimensional mathematical model, respectively.
In this embodiment, 4 initial images are obtained, and 4 conversion images are formed by mapping. With continued reference to fig. 4a of fig. 4, in the present embodiment, the radial direction of the three-dimensional mathematical model refers to the direction in which the origin of the three-dimensional bowl model extends towards the curve. As such, with continued reference to fig. 4a, in this embodiment, the forward view transformed image 11 is divided into two forward view sub-transformed images 110 along the radial direction of the three-dimensional mathematical model, the right view transformed image 12 is divided into two rear view sub-transformed images 120 along the radial direction of the three-dimensional mathematical model, the rear view transformed image 13 is divided into two rear view sub-transformed images 130 along the radial direction of the three-dimensional mathematical model, and the left view sub-transformed image 14 is divided into two left view sub-transformed images 140 along the radial direction of the three-dimensional mathematical model.
In step S40, the two sub-transformation images which are respectively located in two adjacent transformation images and adjacent to each other are stretched towards each other until the image contents of the overlapping areas of the two sub-transformation images are overlapped.
As shown in fig. 4a, in the present embodiment, when performing image stretching on sub-converted images, a right-view sub-converted image 120 close to a front-view converted image 11 may be stretched towards the front-view sub-converted image 110 adjacent thereto until the image contents of the first overlapping area a of the adjacent front-view sub-converted image 110 and the right-view sub-converted image 120 coincide. The right sub-conversion image 120 close to the rear conversion image 13 is stretched towards the rear sub-conversion image 130 adjacent to the right sub-conversion image until the image contents of the second overlapping area B of the adjacent right sub-conversion image 120 and rear sub-conversion image 130 coincide. Stretching the left sub-conversion image 140 close to the rear-view conversion image 13 towards the adjacent rear-view sub-conversion image 130 until the image contents of the third overlapping area C of the adjacent rear-view sub-conversion image 140 and the left sub-conversion image 140 coincide. The left sub-conversion image 140 adjacent to the front sub-conversion image 11 is stretched towards the front sub-conversion image 110 adjacent to the front sub-conversion image until the image contents of the fourth overlapping area D of the adjacent front sub-conversion image 110 and the left sub-conversion image 140 are overlapped.
Optionally, when the sub-converted images are subjected to image stretching, the right-view sub-converted image 120 close to the front-view converted image 11 may be stretched towards the front-view sub-converted image 110 adjacent to the front-view sub-converted image until the image contents of the first overlapping area a of the adjacent front-view sub-converted image 110 and the right-view sub-converted image 120 coincide. The rear sub-conversion image 130 close to the right sub-conversion image 12 is stretched towards the right sub-conversion image 120 adjacent to the rear sub-conversion image until the image contents of the second overlapping area B of the adjacent right sub-conversion image 120 and the rear sub-conversion image 130 coincide. Stretching the left sub-conversion image 140 close to the rear-view conversion image 13 towards the adjacent rear-view sub-conversion image 130 until the image contents of the third overlapping area C of the adjacent rear-view sub-conversion image 140 and the left sub-conversion image 140 coincide. The front sub-conversion image 110 close to the rear sub-conversion image 13 is stretched towards the left sub-conversion image 140 adjacent to the front sub-conversion image until the image contents of the fourth overlapping area D of the front sub-conversion image 110 and the left sub-conversion image 140 adjacent to each other are overlapped. The method and the sequence of the sub-conversion image stretching are not specifically limited herein, and the actual conditions are used as the standard.
In this embodiment, only the transformation image located at the rim portion of the three-dimensional bowl-shaped model can be stretched, and with reference to fig. 4a, in this embodiment, when the sub-transformation image is stretched, the narrow rim portion of the right sub-transformation image 120 close to the forward-looking transformation image 11 can be stretched towards the narrow rim portion of the forward-looking sub-transformation image 110 adjacent thereto until the image contents of the first overlapping area a of the forward-looking sub-transformation image 110 and the right sub-transformation image 120 adjacent thereto are overlapped. The curved portion of the right sub-conversion image 120 close to the rear conversion image 13 is stretched toward the curved portion of the rear sub-conversion image 130 adjacent thereto until the image contents of the first overlapping area B of the adjacent right sub-conversion image 120 and rear sub-conversion image 130 are overlapped. The curved portion of the left sub-converted image 140 close to the rear-view converted image 13 is stretched towards the curved portion of the rear-view sub-converted image 130 adjacent to the curved portion until the image contents of the third overlapping area C of the adjacent rear-view sub-converted image 140 and the left sub-converted image 140 are overlapped. The curved portion of the left sub-converted image 140 close to the front converted image 11 is stretched toward the curved portion of the front sub-converted image 110 adjacent thereto until the image contents of the fourth overlapping area D of the front sub-converted image 110 and the left sub-converted image 140 adjacent thereto are overlapped.
In the embodiment, by constructing the three-dimensional mathematical model, the obtained at least two initial images are mapped into the three-dimensional mathematical model to form at least two converted images, the at least two converted images are respectively divided into two sub-converted images along the radial direction of the three-dimensional mathematical model, and the two sub-converted images are respectively positioned in adjacent converted images, and one of the two adjacent sub-converted images is stretched towards the other. Therefore, the sub-conversion images which are respectively positioned in the adjacent conversion images and adjacent to the sub-conversion images are gapless, and the spliced image generated by fusing the overlapped areas of the stretched sub-conversion images and the adjacent sub-conversion images is not in poor splicing after being connected end to end.
Further, referring to fig. 4b in fig. 4, before stretching the two sub-transformation images which are respectively located in two adjacent transformation images and adjacent to each other, toward each other, the method further comprises: will be located in two adjacent said converted images, respectively, and the other of the two adjacent said sub-converted images will be stretched towards one of them.
Specifically, as shown in fig. 4b, in the present embodiment, before stretching a right-view sub-converted image 120 close to a front-view converted image 11 toward the front-view sub-converted image 110 adjacent thereto, the front-view sub-converted image 110 adjacent to the right-view sub-converted image 120 to be stretched is stretched toward the right-view sub-converted image 120 to be stretched. Before stretching a right sub conversion image 120 adjacent to a rear sub conversion image 130 toward the rear sub conversion image 130 adjacent thereto, stretching the rear sub conversion image 130 adjacent to the right sub conversion image 120 to be stretched toward the right sub conversion image 120 to be stretched. Before stretching the left view sub-converted image 140 adjacent to the rear view converted image 13 toward the rear view sub-converted image 130 adjacent thereto, the rear view sub-converted image 130 adjacent to the right view sub-converted image 140 to be stretched is stretched toward the right view sub-converted image 140 to be stretched. And, before stretching a left view sub-conversion image 140 adjacent to a front view conversion image 11 toward the front view sub-conversion image 110 adjacent thereto, stretching the left view sub-conversion image 130 to be stretched toward the front view sub-conversion image 110 adjacent thereto toward the left view sub-conversion image 140 to be stretched.
Thus, as shown in fig. 4b, the problem of misalignment between the bowl bottom portion and the lip portion of the converted image can be alleviated.
Further, in this embodiment, the method of stretching the converted image includes:
and acquiring a homography matrix H, and updating the sub-conversion image before stretching according to the homography matrix to stretch the sub-conversion image.
In this embodiment, the method for obtaining the homography matrix H includes: obtaining a first homography matrix H1 corresponding to one of two adjacent sub-transformation images located in two adjacent transformation images, and obtaining a second homography matrix H2 corresponding to the other of the two adjacent sub-transformation images located in two adjacent transformation images.
And the method for obtaining the second homography matrix H2 comprises the following steps.
First, a first homography matrix H1 is obtained, which is located in two adjacent transformation images and corresponds to one of the two adjacent sub-transformation images.
Specifically referring to fig. 4b, in this embodiment, the front sub transformation image 110 and the right sub transformation image 120 are adjacent to each other, and the stretching sequence of the adjacent front sub transformation images 110 and the adjacent right sub transformation images 120 is as follows: the front sub-convertible image 110 is stretched toward the right sub-convertible image 120, and then the right sub-convertible image 120 is stretched toward the front sub-convertible image 110. In the present embodiment, the first homography matrix H1 corresponding to the front view sub-converted image 110 adjacent to the right view sub-converted image 120 is first obtained.
In this embodiment, the initial first homography matrix H1 can be calculated by the following formula (2).
Where Cx is half the width of the top projection image. Cy is the angle of the rotation angle which is half the height of the overlooked projection image theta. In the present embodiment, θ is between 1 ° and 4 °. Optionally, in this embodiment, θ is 2.5 °.
Then, image registration is performed on the overlapping region of the two sub-converted images to obtain matching feature point pairs, and an initial second homography matrix H2' is obtained according to the matching feature point pairs.
Specifically, in this embodiment, after the first homography matrix H1 is obtained, the right sub-conversion image 120 is stretched toward the front sub-conversion image 110 until the image contents of the overlapping area of the right sub-conversion image 120 and the front sub-conversion image 110 are overlapped. Thereafter, the overlapping regions of the adjacent front-view sub-converted image 110 and the right-view sub-converted image 120 are image-registered to obtain a plurality of matching feature point pairs (P1, P2). And computing an initial second homography matrix H2' from the plurality of matching pairs of feature points (P1, P2). The formula for calculating the initial second homography matrix H2' is shown in the following formula (3).
Applying the above equation (3) to establish a linear system of equations for a plurality of matching pairs of feature points (P1, P2), and solving the initial second homography matrix H2' using a least squares method.
Then, the initial second homography matrix H2 'and the first homography matrix H1 are multiplied, that is, calculated according to the formula H1 × H2', to obtain a second homography matrix H2 corresponding to the right-view sub-converted image 120.
Further, the method for updating the sub-converted image before stretching according to the homography matrix comprises the following steps:
obtaining the coordinates of a plurality of first sampling points P1 'on the stretched sub-transformed image according to the homography matrix H and the coordinates of a plurality of initial first sampling points P1 on the sub-transformed image before stretching, obtaining a plurality of first texture coordinates Te according to the coordinates of a plurality of first sampling points P1' on the sub-transformed image before stretching, obtaining a plurality of first target images according to the plurality of first texture coordinates Te, and updating the sub-transformed image before stretching according to the plurality of first target images. Wherein the first texture coordinate Te is the coordinate at which the plurality of first sampling points P1' correspond to on the acquisition device.
In the present embodiment, the method of obtaining the coordinates of the plurality of first sampling points P1' on the stretched sub-converted image includes the following steps one to three.
In the first step: according to the homography matrix H, obtaining an inverse matrix corresponding to the initial first depression point Pt1 after the initial first sampling point P1 on the sub-conversion image before stretching is mapped
Acquiring an inverse matrix corresponding to the initial first depression point Pt1
The method comprises the following steps:
firstly, the coordinates of the initial first depression point Pt1 corresponding to the initial first sample point P1 after mapping are obtained according to the coordinates of the initial first sample point P1 on the sub-converted image before stretching.
Then, an angle θ between a line connecting the initial first depression point Pt1 and the origin of the three-dimensional mathematical model and the X axis or the Y axis is obtained according to the coordinates of the initial first depression point Pt 1. Wherein the included angle θ can be obtained according to formula (5).
Then, a weight value is obtained according to the included angle theta. Wherein the weight value w may be calculated according to equation (4) and equation (5).
w＝(-b-1)×θ2+ b × θ + 1-formula (4)
Wherein, the thetasIs an included angle between a splicing seam and an X axis or a Y axis in the three-dimensional mathematical model, the theta is 30-50 degrees, and the theta is bettersMay be 45. In the present embodiment, when the converted image to be stretched is located on the X-axis, then the θ issFor the splice seam and the X-axis in said three-dimensional mathematical modelAnd θ is an angle of an angle between a line connecting the initial first depression viewpoint Pt1 and the origin of the three-dimensional mathematical model and the X-axis. When the converted image to be stretched is located on the X-axis, then the theta issAnd theta is an included angle between a splicing seam and the Y axis in the three-dimensional mathematical model, and theta is an angle of an included angle between a connecting line between the initial first depression viewpoint Pt1 and the origin of the three-dimensional mathematical model and the Y axis.
Finally, blending an identity matrix I into the homography matrix H according to the weight value w, updating the homography matrix H according to the identity matrix I, and obtaining an inverse matrix corresponding to the initial first depression viewpoint Pt1 according to the updated homography matrix H
In this embodiment, the homography matrix H may be the first homography matrix H1 or the second homography matrix H2, and the inverse matrix corresponding to the first depression point Pt1
Obtainable according to formula (6).
In this embodiment, since one unit matrix I is merged into the homography matrix H, the problem of tearing in the middle of the stretched sub-converted image can be avoided.
Specifically, as shown in fig. 3, the three-dimensional mathematical model is a bowl-shaped three-dimensional mathematical model, the bowl-shaped three-dimensional mathematical model includes a graceful edge and a bowl bottom, and the homography matrix H includes a first sub-homography matrix H11 corresponding to the bowl edge portion a1 and a second sub-homography matrix H12 corresponding to the bowl bottom portion a2, wherein a unit matrix I is merged into the first sub-homography matrix H11. This avoids the problem of tearing of the stretched sub-converted image at the curved edge portion a 1.
Step two: according to the inverse matrix
Obtaining coordinates Pt1(x1, y1) of a first depression point Pt1 corresponding to the stretched sub-converted image after mapping;
step three: obtaining coordinates P1(x1, y1, z1) of the first sampling point P1 on the stretched sub-converted image according to a generatrix equation of the three-dimensional mathematical model and coordinates Pt1(x1, y1) of the first depression point Pt 1. And repeating the first step to the third step until coordinates P1(x1, y1, z1) of all the first sampling points P1 on the stretched sub-converted image are obtained.
After acquiring the plurality of first sampling points P1 on the stretched sub-converted image, the method of acquiring a plurality of first target images according to the first sampling points P1 on the stretched sub-converted image includes:
according to the coordinates P1(x1, y1, z1) of the plurality of first sampling points P1, the first texture coordinates Te (u, v) corresponding to the first sampling points P1 are calculated, and finally, a first lookup table (LUT1) is generated. In the present embodiment, the first texture coordinates Te (u, V) indicate coordinates corresponding to a point in the image acquisition apparatus coordinate system when one of the first sampling points V1 is converted into the image acquisition apparatus coordinate system in the world coordinate system.
The method of calculating the first texture coordinate Te (u, v) corresponding to the first sampling point P1 on the stretched sub-converted image includes the following first to second steps.
In the first step, internal and external reference information of the first image acquisition device can be obtained through calibration. For the first sampling point P1(x1, y1, z1) in the world coordinate system, the coordinates of its corresponding first initial sampling point Vc in the coordinate system of the image acquisition device can be calculated by equation (7).
Vc RP1+ T-equation (7)
Wherein, R and T are respectively a rotation matrix and a translation matrix in the external parameter information of the image acquisition equipment.
In step two, the first texture coordinates Te (u, v) are calculated from the imaging model of the image acquisition device.
In this embodiment, if the image capturing device is a fisheye camera, the first texture coordinate Te (u, v) is calculated according to an imaging model of the fisheye camera. Wherein the imaging model calculation formula is shown in the following formula (8).
Wherein k is1,k2,k3,k4For distortion coefficients, f, in reference information of fisheye camerax,fyIs the focal length of the fisheye camera, cx,cyIs the optical center position of the fisheye camera.
Finally, searching is performed according to the first lookup table (LUT1) to obtain image content corresponding to each first depression point Pt1 after the projection of the stretched sub-converted image, where the image content corresponding to the first depression point Pt1 is the first target image corresponding to the first sampling point P1.
In step S50, the overlapping regions of the two sub-converted images are fused to generate a stitched image. The fusion method is not described herein in detail, and the fusion can be performed by using the existing fusion method.
FIG. 5 is a diagram of a vehicle-mounted image stitching system according to an embodiment of the present invention. As shown in fig. 5, this embodiment further discloses a vehicle-mounted image stitching system, where the vehicle-mounted image stitching system includes:
the image acquisition module 1 is used for acquiring at least two initial images.
And the three-dimensional mathematical model building module 2 is used for building a three-dimensional mathematical model with a world coordinate system, and sequentially mapping at least two initial images into the three-dimensional mathematical model to form at least two conversion images which are distributed in a surrounding way, wherein the overlapping areas of the adjacent conversion images are overlapped, and the image contents are the same.
And the data processing module 3 is used for dividing each of the at least two converted images into two sub-converted images along the radial direction of the three-dimensional mathematical model, and stretching one of the two sub-converted images which are respectively positioned at two adjacent converted images and adjacent to each other towards the other of the two sub-converted images until the image contents of the overlapped areas of the two sub-converted images are overlapped.
And the image splicing module 4 is used for fusing the overlapping areas of the two sub-conversion images to generate a spliced image.
Fig. 6 is a schematic diagram of a vehicle-mounted image stitching device in an embodiment of the present invention. Further, as shown in fig. 6, in this embodiment, a vehicle-mounted image stitching device is further provided, where the vehicle-mounted image stitching device includes a central control host 100 and the vehicle-mounted image stitching system; the image acquisition device is connected to the central control host 100, and transmits the acquired initial image to the central control host 100 for image processing, thereby completing image stitching. And the three-dimensional mathematical model building module 2, the data processing module 3 and the image stitching module 4 are located in the central control host 100.
In this embodiment, the image capturing devices 1 are installed around the vehicle, and the image capturing devices 1 may be fish-eye cameras, where the number of the fish-eye cameras is 4, and the 4 image capturing devices 1 are respectively installed at the front, the rear, the left, and the right positions of the vehicle body.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (10)
1. A vehicle-mounted image stitching method is characterized by comprising the following steps:
acquiring at least two initial images;
constructing a three-dimensional mathematical model with a world coordinate system, and sequentially mapping at least two initial images into the three-dimensional mathematical model to form at least two conversion images which are distributed in a surrounding way, wherein the overlapping areas of the adjacent conversion images are overlapped and the image contents are the same;
dividing at least two of the converted images into two sub-converted images along the radial direction of the three-dimensional mathematical model respectively;
stretching two adjacent sub-conversion images which are respectively positioned in two adjacent conversion images and one of the two adjacent sub-conversion images towards the other of the two adjacent conversion images until the image contents of the overlapping areas of the two sub-conversion images are overlapped;
and fusing the overlapped areas of the two sub-conversion images to generate a spliced image.
2. The on-vehicle image stitching method according to claim 1, wherein before stretching one of the adjacent two sub-converted images located respectively in the adjacent two converted images toward the other one thereof, the method further comprises:
will be located in two adjacent said converted images, respectively, and the other of the two adjacent said sub-converted images will be stretched towards one of them.
3. The on-vehicle image stitching method according to claim 1 or 2, wherein the method of stretching the sub-converted images includes:
and acquiring a homography matrix, and updating the sub-conversion image before stretching according to the homography matrix so as to stretch the sub-conversion image.
4. The vehicle-mounted image stitching method according to claim 3,
obtaining the coordinates of a plurality of initial first sampling points on the stretched sub-transformation image according to the homography matrix and the coordinates of the plurality of initial first sampling points on the sub-transformation image before stretching;
acquiring a plurality of first texture coordinates according to the coordinates of the first sampling points;
acquiring a plurality of first target images according to the first texture coordinates;
updating the sub-converted image before stretching according to the plurality of first target images to stretch the sub-converted image.
5. The vehicle-mounted image stitching method according to claim 4, wherein the method for obtaining the coordinates of the plurality of first sample points on the stretched sub-converted image comprises:
the method comprises the following steps: obtaining an inverse matrix corresponding to the corresponding initial first overlook point after the initial first sampling point mapping is obtained according to the homography matrix;
step two: obtaining the corresponding coordinates of a first depression viewpoint after the stretched sub-conversion image is mapped according to the inverse matrix;
step three: obtaining the coordinates of the first sampling point on the stretched sub-conversion image according to a bus equation of the three-dimensional mathematical model and the coordinates of the first depression viewpoint; and the number of the first and second groups,
and repeating the first step to the third step until the coordinates of all the first sampling points on the stretched sub-conversion image are obtained.
6. The vehicle-mounted image stitching method according to claim 5, wherein the method of obtaining the inverse matrix comprises:
obtaining the coordinates of the initial first depression viewpoint corresponding to the initial first sampling point after mapping according to the coordinates of the initial first sampling point;
obtaining an included angle between a connecting line between the initial first depression viewpoint and the origin of the three-dimensional mathematical model and an X axis or a Y axis according to the coordinates of the initial first depression viewpoint;
obtaining a weight value according to the included angle;
blending an identity matrix into the homography matrix according to the weight value, updating the homography matrix according to the identity matrix, and obtaining an inverse matrix corresponding to the initial first overlooking point according to the updated homography matrix.
7. The vehicle-mounted image stitching method according to claim 6,
the three-dimensional mathematical model is a bowl-shaped three-dimensional mathematical model, and the bowl-shaped three-dimensional mathematical model comprises a bowl edge and a bowl bottom;
the homography matrix includes: a first sub homography matrix corresponding to the bowl rim and a second sub homography matrix corresponding to the bowl bottom;
and merging an identity matrix into the first sub-homography matrix.
8. The vehicle-mounted image stitching method according to claim 3, wherein the method of obtaining the homography matrix comprises:
obtaining a first homography matrix which is positioned in two adjacent conversion images and corresponds to one of the two adjacent sub conversion images, and obtaining a second homography matrix which corresponds to the other of the two sub conversion images; and the number of the first and second groups,
the method for obtaining the second homography matrix comprises the following steps:
obtaining a first homography matrix which is positioned in two adjacent conversion images and corresponds to one of two adjacent sub-conversion images;
carrying out image registration on the overlapped area of the two sub-conversion images to obtain a matching characteristic point pair, and obtaining an initial second homography matrix according to the matching characteristic point pair;
and multiplying the initial second homography matrix and the first homography matrix to obtain the second homography matrix.
9. An on-vehicle image stitching system, comprising:
the image acquisition module is used for acquiring at least two initial images;
the three-dimensional mathematical model building module is used for building a three-dimensional mathematical model with a world coordinate system, and mapping at least two initial images into the three-dimensional mathematical model in sequence to form at least two conversion images which are distributed in a surrounding way, wherein the overlapping areas of the adjacent conversion images are overlapped and the image contents are the same;
the data processing module is used for dividing at least two conversion images into two sub conversion images along the radial direction of the three-dimensional mathematical model respectively; stretching one of the two adjacent sub-conversion images towards the other one of the two adjacent sub-conversion images until the image contents of the overlapping areas of the two sub-conversion images are overlapped;
and the image splicing module is used for fusing the overlapping areas of the two sub-conversion images to generate a spliced image.
10. An on-vehicle image stitching device, which is characterized by comprising a central control host and the on-vehicle image stitching system according to claim 9;
the image acquisition module comprises image acquisition equipment, the image acquisition equipment is connected with the central control host, and the acquired initial image is transmitted to the central control host for image processing so as to complete image splicing;
the three-dimensional mathematical model building module, the data processing module and the image splicing module are positioned in the central control host.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212532.3A CN112308986B (en) | 2020-11-03 | 2020-11-03 | Vehicle-mounted image stitching method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212532.3A CN112308986B (en) | 2020-11-03 | 2020-11-03 | Vehicle-mounted image stitching method, system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112308986A true CN112308986A (en) | 2021-02-02 |
| CN112308986B CN112308986B (en) | 2024-04-12 |
Family
ID=74333883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011212532.3A Active CN112308986B (en) | 2020-11-03 | 2020-11-03 | Vehicle-mounted image stitching method, system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308986B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801874A (en) * | 2021-02-03 | 2021-05-14 | 广州六环信息科技有限公司 | Vehicle image splicing method and device and vehicle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274739A1 (en) * | 2009-12-21 | 2012-11-01 | Huawei Device Co.,Ud. | Image splicing method and apparatus |
| CN106127683A (en) * | 2016-06-08 | 2016-11-16 | 中国电子科技集团公司第三十八研究所 | A kind of real-time joining method of unmanned aerial vehicle SAR image |
| CN106886979A (en) * | 2017-03-30 | 2017-06-23 | 深圳市未来媒体技术研究院 | A kind of image splicing device and image split-joint method |
| CN109087244A (en) * | 2018-07-26 | 2018-12-25 | 贵州火星探索科技有限公司 | A kind of Panorama Mosaic method, intelligent terminal and storage medium |
| US20190311459A1 (en) * | 2016-09-29 | 2019-10-10 | Beijing Qiyi Century Science & Technology Co., Ltd . | Method and device for performing mapping on spherical panoramic image |
| CN110782394A (en) * | 2019-10-21 | 2020-02-11 | 中国人民解放军63861部队 | Panoramic video rapid splicing method and system |
| CN111223038A (en) * | 2019-12-02 | 2020-06-02 | 上海赫千电子科技有限公司 | Automatic splicing method and display device for vehicle-mounted all-around images |
| CN111275621A (en) * | 2020-01-17 | 2020-06-12 | 中南大学 | Panoramic image generation method and system in driving all-round system and storage medium |
| CN111461963A (en) * | 2020-03-30 | 2020-07-28 | 南京泓众电子科技有限公司 | Fisheye image splicing method and device |
| 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 |
-
2020
- 2020-11-03 CN CN202011212532.3A patent/CN112308986B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274739A1 (en) * | 2009-12-21 | 2012-11-01 | Huawei Device Co.,Ud. | Image splicing method and apparatus |
| CN106127683A (en) * | 2016-06-08 | 2016-11-16 | 中国电子科技集团公司第三十八研究所 | A kind of real-time joining method of unmanned aerial vehicle SAR image |
| US20190311459A1 (en) * | 2016-09-29 | 2019-10-10 | Beijing Qiyi Century Science & Technology Co., Ltd . | Method and device for performing mapping on spherical panoramic image |
| CN106886979A (en) * | 2017-03-30 | 2017-06-23 | 深圳市未来媒体技术研究院 | A kind of image splicing device and image split-joint method |
| CN109087244A (en) * | 2018-07-26 | 2018-12-25 | 贵州火星探索科技有限公司 | A kind of Panorama Mosaic method, intelligent terminal and storage medium |
| 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 |
| CN110782394A (en) * | 2019-10-21 | 2020-02-11 | 中国人民解放军63861部队 | Panoramic video rapid splicing method and system |
| CN111223038A (en) * | 2019-12-02 | 2020-06-02 | 上海赫千电子科技有限公司 | Automatic splicing method and display device for vehicle-mounted all-around images |
| CN111275621A (en) * | 2020-01-17 | 2020-06-12 | 中南大学 | Panoramic image generation method and system in driving all-round system and storage medium |
| CN111461963A (en) * | 2020-03-30 | 2020-07-28 | 南京泓众电子科技有限公司 | Fisheye image splicing method and device |
Non-Patent Citations (4)
| Title |
|---|
| （美）罗伊·希尔克罗特（ROYSHILKROT）, （西班牙）大卫·米兰: "深入理解OpenCV:实用计算机视觉项目解析", 31 January 2020, 机械工业出版社, pages: 203 - 204 * |
| 何志东;张建伟;梁斌斌;: "一种基于拼接算法的鱼眼图像畸变校正方法", 现代计算机, no. 03, pages 58 - 63 * |
| 卢官明;陈浩;肖鲁宁;苏昊;钟锐;: "全景视图泊车辅助***中的多视点视频拼接", 南京邮电大学学报(自然科学版), no. 03, pages 165 - 170 * |
| 石雪冬;陈天恩;陆宇红;刘凤英;黄杨;崔继祥;: "车载全景影像的严密拼接方法研究与实验", 测绘与空间地理信息, no. 09, pages 174 - 177 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801874A (en) * | 2021-02-03 | 2021-05-14 | 广州六环信息科技有限公司 | Vehicle image splicing method and device and vehicle |
| CN112801874B (en) * | 2021-02-03 | 2024-04-05 | 广州六环信息科技有限公司 | Vehicle image stitching method and device and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112308986B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7245295B2 (en) | METHOD AND DEVICE FOR DISPLAYING SURROUNDING SCENE OF VEHICLE-TOUCHED VEHICLE COMBINATION | |
| CN111223038B (en) | Automatic splicing method of vehicle-mounted looking-around images and display device | |
| JP3286306B2 (en) | Image generation device and image generation method | |
| JP5455124B2 (en) | Camera posture parameter estimation device | |
| JP5739584B2 (en) | 3D image synthesizing apparatus and method for visualizing vehicle periphery | |
| CN106799993B (en) | Streetscape acquisition method and system and vehicle | |
| CN107792179B (en) | A kind of parking guidance method based on vehicle-mounted viewing system | |
| CN109948398B (en) | Image processing method for panoramic parking and panoramic parking device | |
| CN108765496A (en) | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method | |
| CN110381255A (en) | Using the Vehicular video monitoring system and method for 360 panoramic looking-around technologies | |
| CN108263283A (en) | More marshalling varied angle vehicle panoramic viewing system calibration and joining method | |
| CN104851076A (en) | Panoramic 360-degree-view parking auxiliary system for commercial vehicle and pick-up head installation method | |
| JP2002135765A (en) | Camera calibration instruction device and camera calibration device | |
| CN106994936A (en) | A kind of 3D panoramic parking assist systems | |
| CN102045546A (en) | Panoramic parking assist system | |
| CN105321160B (en) | The multi-camera calibration that 3 D stereo panorama is parked | |
| CN110719411B (en) | Panoramic all-around view image generation method of vehicle and related equipment | |
| CN108174089B (en) | Backing image splicing method and device based on binocular camera | |
| CN110400255B (en) | Vehicle panoramic image generation method and system and vehicle | |
| CN105818763A (en) | Method, device and system for confirming distance of object around vehicle | |
| DE102014223237A1 (en) | Inductive charging system for charging an electric vehicle | |
| CN112825546A (en) | Generating a composite image using an intermediate image surface | |
| US20190100141A1 (en) | Ascertainment of Vehicle Environment Data | |
| CN104691415A (en) | Panoramic auxiliary parking device | |
| CN113658262A (en) | Camera external parameter calibration method, device, system and storage 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 |