CN113936116B - Complex space curved surface mapping method for transparent A column - Google Patents

Complex space curved surface mapping method for transparent A column Download PDF

Info

Publication number
CN113936116B
CN113936116B CN202111342144.1A CN202111342144A CN113936116B CN 113936116 B CN113936116 B CN 113936116B CN 202111342144 A CN202111342144 A CN 202111342144A CN 113936116 B CN113936116 B CN 113936116B
Authority
CN
China
Prior art keywords
curved surface
model
space
transparent
following
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111342144.1A
Other languages
Chinese (zh)
Other versions
CN113936116A (en
Inventor
冉成荣
袁丹寿
张祺
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.)
Hozon New Energy Automobile Co Ltd
Original Assignee
Hozon New Energy Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hozon New Energy Automobile Co Ltd filed Critical Hozon New Energy Automobile Co Ltd
Priority to CN202111342144.1A priority Critical patent/CN113936116B/en
Publication of CN113936116A publication Critical patent/CN113936116A/en
Application granted granted Critical
Publication of CN113936116B publication Critical patent/CN113936116B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06T17/30—Polynomial surface description
    • 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
    • B60R2300/107—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using stereoscopic 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
    • B60R2300/20—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used
    • B60R2300/202—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used displaying a blind spot scene on the vehicle part responsible for the blind spot
    • 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
    • B60R2300/802—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 monitoring and displaying vehicle exterior blind spot views
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Algebra (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Mechanical Engineering (AREA)
  • Image Generation (AREA)

Abstract

The invention provides a complex space curved surface mapping method for a transparent A column, which comprises the following steps: s is S 1 Acquiring 3D coordinates of a series of discrete sampling points on the depth image; s is S 2 Establishing a curved surface model; s is S 3 Adding a regularization term; s is S 4 And obtaining model parameters by adopting an LM optimization algorithm. The complex space curved surface mapping method for the transparent A column has the following advantages: 1. a simple model is built, and a complex space is expressed; 2. the method of sampling in a large range is adopted, so that the fitting space range is increased; 3. adding a regularization method to prevent overfitting; 4. a filling method is adopted to prevent the influence of the cavity on the fitting result; 5. the model has wide application range, and is applicable to space planes, paraboloids, hyperboloids and the like; 6. the problem of holes can be solved, and the whole map can be increased in speed.

Description

Complex space curved surface mapping method for transparent A column
Technical Field
The invention relates to the field of 3D model fitting, in particular to a complex space curved surface mapping method for a transparent A column.
Background
In the prior art, 3D model fitting has wide application, such as obtaining object surface information with higher precision in a 3D reconstruction process, and obtaining a finer and smoother physical model in a 3D modeling process.
However, 3D model fitting also has some limitations, such as the need to know explicit models (e.g., planar, spherical, etc.), the greater the spatial extent of the fit in complex scenarios, and the lower the model accuracy.
Therefore, the approximate expression research of all the spaces in the imaging range of the camera is limited at present.
In view of this, those skilled in the art have devised a complex spatial surface mapping method for transparent a-pillars in an effort to overcome the above-mentioned technical problems.
Disclosure of Invention
The invention aims to overcome the defects that in the prior art, the larger the fitting space range of a 3D model fitting under a complex scene is, the lower the model accuracy is, and the like, and provides a complex space curved surface mapping method for a transparent A column.
The invention solves the technical problems by the following technical proposal:
the complex space curved surface mapping method for the transparent A column is characterized by comprising the following steps of:
S 1 acquiring 3D coordinates of a series of discrete sampling points on the depth image;
S 2 establishing a curved surface model;
S 3 adding a regularization term;
S 4 and obtaining model parameters by adopting an LM optimization algorithm.
According to one embodiment of the invention, the step S 1 And then further comprises:
S 11 and filling the depth map of the discrete sampling points.
According to one embodiment of the invention, the step S 11 Specifically comprises the following steps: calculating the depth of a cavity point by interpolating the existing depth information by adopting a nearest interpolation method;
according to one embodiment of the invention, the step S 2 Comprises the following steps: establishing a curved surface model, and establishing a curved surface equation z=ax after removing square terms of Z by combining the randomness of the space model 2 +by 2 +cxy+dxz+eyz+fx+gy+h。
According to one embodiment of the invention, the step S 3 Comprises the following steps: adding regularization term, adding regularization term alpha (a) into model equation to ensure model convergence 2 +b 2 +c 2 +d 2 +e 2 +f 2 +g 2 +h 2 )。
According to one embodiment of the invention, the step S 4 Comprises the following steps: model parameters are obtained by adopting an LM optimization algorithm, and a final iteration model is that
According to one embodiment of the invention, the step S 4 And then further comprises:
S 5 and calculating intersection points of the four corner points of the eyebrow coordinate and the A column display screen and the space curved surface equation under the space coordinate system to form a space intersection point.
According to one embodiment of the invention, the step S 5 And then further comprises:
S 6 and calculating the pixel point by the space intersection point through a projection equation.
According to one embodiment of the invention, the step S 6 And then further comprises:
S 7 and the imaging area on the image plane is deformed and then projected on the A-pillar display screen.
The invention has the positive progress effects that:
the complex space curved surface mapping method for the transparent A column has the following advantages:
1. a simple model is built, and a complex space is expressed;
2. the method of sampling in a large range is adopted, so that the fitting space range is increased;
3. adding a regularization method to prevent overfitting;
4. a filling method is adopted to prevent the influence of the cavity on the fitting result;
5. the model has wide application range, and is applicable to space planes, paraboloids, hyperboloids and the like;
6. the problem of holes can be solved, and the whole map can be increased in speed.
Drawings
The above and other features, properties and advantages of the present invention will become more apparent from the following description of embodiments taken in conjunction with the accompanying drawings in which like reference characters designate like features throughout the drawings, and in which:
fig. 1 is a schematic diagram of the arrangement of discrete points in the complex space surface mapping method for transparent a-pillars according to the present invention.
Fig. 2 is a schematic diagram of each coordinate point in the complex space curved surface mapping method for the transparent a-pillar according to the present invention.
Detailed Description
In order to make the above objects, features and advantages of the present invention more comprehensible, embodiments accompanied with figures are described in detail below.
Embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Reference will now be made in detail to the preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.
Furthermore, although terms used in the present invention are selected from publicly known and commonly used terms, some terms mentioned in the present specification may be selected by the applicant at his or her discretion, the detailed meanings of which are described in relevant parts of the description herein.
Furthermore, it is required that the present invention is understood, not simply by the actual terms used but by the meaning of each term lying within.
Fig. 1 is a schematic diagram of the arrangement of discrete points in the complex space surface mapping method for transparent a-pillars according to the present invention. Fig. 2 is a schematic diagram of each coordinate point in the complex space curved surface mapping method for the transparent a-pillar according to the present invention.
As shown in fig. 1 and 2, the invention discloses a complex space curved surface mapping method for a transparent a column, which comprises the following steps:
step S 1 The 3D coordinates of a series of discrete sampling points are acquired on the depth image.
Said step S 1 And then further comprises: s is S 11 And filling the depth map of the discrete sampling points.
Preferably, the step S 11 Specifically comprises the following steps: calculating the depth of a cavity point by interpolating the existing depth information by adopting a nearest interpolation method;
step S 2 And (5) establishing a curved surface model.
Preferably, the method comprises the steps of,said step S 2 Comprises the following steps: establishing a curved surface model, and establishing a curved surface equation z=ax after removing square terms of Z by combining the randomness of the space model 2 +by 2 +cxy+ dxz + eyz +fx+gy+h. Step S 3 Adding regularization term.
Preferably, the step S 3 Comprises the following steps: adding regularization term, adding regularization term alpha (a) into model equation to ensure model convergence 2 +b 2 +c 2 +d 2 +e 2 +f 2 +g 2 +h 2 )。
Step S 4 And obtaining model parameters by adopting an LM optimization algorithm.
Preferably, the step S 4 Comprises the following steps: model parameters are obtained by adopting an LM optimization algorithm, and a final iteration model is that
Further, in said step S 4 The method further comprises the following steps:
step S 5 And under the calculation space coordinate system, the intersection points of the four corner points of the eyebrow coordinate 10 and the A column display screen 20 and the space curved surface equation form a space intersection point 30.
Further preferably, the step S 5 The method further comprises the following steps:
step S 6 And calculating the pixel point by the space intersection point through a projection equation.
Further, the step S 6 The method further comprises the following steps:
step S 7 The imaging area on the image plane 40 is deformed and then projected on the A-pillar display screen.
The invention relates to a complex space curved surface mapping method for a transparent A column, for example, aiming at a system mainly comprising a 3D camera and a personal computer, wherein the 3D camera is used for acquiring 3D coordinates (x, y, z) of a space object, and the 3D coordinates are shaped according to a quadric surface equation:
z＝ax 2 +by 2 +cxy+dxz+eyz+fx+gy+h。
introducing a function expression:
f(x,y,z)＝ax 2 +by 2 +cxy+dxz+eyz+fx+gy+h-z。
finally, the following optimization problem is converted:
since a, b, c, D, e, f, g, h and 8 parameters are required to be obtained, the equation can be obtained by using a minimum of 8 space 3D coordinates as known from the unknown number, and generally, in order to ensure the accuracy of the solution, the number of sampling points needs to be increased.
If the figure is in a certain density in space, the 3D coordinates of more than 8 discrete points can be obtained to fit a 3D curved surface equation. Due to the depth camera principle problem, certain discrete points have no depth problem, and the adjacent filling method is adopted for filling.
In addition, to prevent the curve shape from being over fitted, a regularization term is added, and the expression is converted into:
in summary, the complex space curved surface mapping method for the transparent A column has the following advantages:
1. a simple model is built, and a complex space is expressed;
2. the method of sampling in a large range is adopted, so that the fitting space range is increased;
3. adding a regularization method to prevent overfitting;
4. a filling method is adopted to prevent the influence of the cavity on the fitting result;
5. the model has wide application range, and is applicable to space planes, paraboloids, hyperboloids and the like;
6. the problem of holes can be solved, and the whole map can be increased in speed.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the invention, but such changes and modifications fall within the scope of the invention.

Claims (3)

1. The complex space curved surface mapping method for the transparent A column is characterized by comprising the following steps of:
S 1 acquiring 3D coordinates of a series of discrete sampling points on the depth image;
S 2 establishing a curved surface model;
S 3 adding a regularization term;
S 4 obtaining model parameters by adopting an LM optimization algorithm;
wherein,
said step S 2 Comprises the following steps: establishing a curved surface model, and establishing a curved surface equation after removing square terms of Z by combining the randomness of the space model
；
Said step S 3 Comprises the following steps: adding regularization term, adding regularization term into model equation to ensure model convergence；
Said step S 4 Comprises the following steps: model parameters are obtained by adopting an LM optimization algorithm, and a final iteration model is that
；
Said step S 4 And then further comprises:
S 5 under a calculated space coordinate system, an intersection point of four corner points of the eyebrow coordinate and the A column display screen and a space curved surface equation is formed;
said step S 5 And then further comprises:
S 6 calculating pixel points of the space intersection points through a projection equation;
said step S 6 And then further comprises:
S 7 and the imaging area on the image plane is deformed and then projected on the A-pillar display screen.
2. The complex space surface mapping method for transparent a-pillar according to claim 1, wherein the step S 1 And then further comprises:
S 11 and filling the depth map of the discrete sampling points.
3. The complex space curved surface mapping method for transparent A-pillar according to claim 2, wherein the step S 11 Specifically comprises the following steps: and calculating the depth of the cavity point by interpolating the existing depth information by adopting a nearest interpolation method.
CN202111342144.1A 2021-11-12 2021-11-12 Complex space curved surface mapping method for transparent A column Active CN113936116B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111342144.1A CN113936116B (en) 2021-11-12 2021-11-12 Complex space curved surface mapping method for transparent A column

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111342144.1A CN113936116B (en) 2021-11-12 2021-11-12 Complex space curved surface mapping method for transparent A column

Publications (2)

Publication Number Publication Date
CN113936116A CN113936116A (en) 2022-01-14
CN113936116B true CN113936116B (en) 2024-04-16

Family

ID=79286554

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111342144.1A Active CN113936116B (en) 2021-11-12 2021-11-12 Complex space curved surface mapping method for transparent A column

Country Status (1)

Country Link
CN (1) CN113936116B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106274686A (en) * 2016-08-05 2017-01-04 北京智芯微电子科技有限公司 A kind of vehicle blind zone rendering method and device
CN106791774A (en) * 2017-01-17 2017-05-31 湖南优象科技有限公司 Virtual visual point image generating method based on depth map
WO2018119771A1 (en) * 2016-12-28 2018-07-05 深圳大学 Efficient phase-three-dimensional mapping method and system based on fringe projection profilometry
CN108805977A (en) * 2018-06-06 2018-11-13 浙江大学 A kind of face three-dimensional rebuilding method based on end-to-end convolutional neural networks
CN110443883A (en) * 2019-07-08 2019-11-12 杭州电子科技大学 A kind of individual color image plane three-dimensional method for reconstructing based on dropblock
CN112288875A (en) * 2020-10-30 2021-01-29 中国有色金属长沙勘察设计研究院有限公司 Rapid three-dimensional reconstruction method for unmanned aerial vehicle mine inspection scene

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106274686A (en) * 2016-08-05 2017-01-04 北京智芯微电子科技有限公司 A kind of vehicle blind zone rendering method and device
WO2018119771A1 (en) * 2016-12-28 2018-07-05 深圳大学 Efficient phase-three-dimensional mapping method and system based on fringe projection profilometry
CN106791774A (en) * 2017-01-17 2017-05-31 湖南优象科技有限公司 Virtual visual point image generating method based on depth map
CN108805977A (en) * 2018-06-06 2018-11-13 浙江大学 A kind of face three-dimensional rebuilding method based on end-to-end convolutional neural networks
CN110443883A (en) * 2019-07-08 2019-11-12 杭州电子科技大学 A kind of individual color image plane three-dimensional method for reconstructing based on dropblock
CN112288875A (en) * 2020-10-30 2021-01-29 中国有色金属长沙勘察设计研究院有限公司 Rapid three-dimensional reconstruction method for unmanned aerial vehicle mine inspection scene

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
柱面基准下的深度图像建模研究;黄明等;测绘通报;20151031(10);全文 *

Also Published As

Publication number Publication date
CN113936116A (en) 2022-01-14

Similar Documents

Publication Publication Date Title
US10366534B2 (en) Selective surface mesh regeneration for 3-dimensional renderings
CN104794758B (en) A kind of method of cutting out of 3-D view
US8384716B2 (en) Image processing method
CN111553858B (en) Image restoration method and system based on generation countermeasure network and application thereof
CN109584327B (en) Face aging simulation method, device and equipment
CN106062824B (en) edge detecting device and edge detection method
WO2021142996A1 (en) Point cloud denoising method, system, and device employing image segmentation, and storage medium
CN113888689A (en) Image rendering model training method, image rendering method and image rendering device
EP3756163B1 (en) Methods, devices, and computer program products for gradient based depth reconstructions with robust statistics
EP3736776A1 (en) Apparatus, system and method for the generation of polygonal meshes
US20090309877A1 (en) Soft shadow rendering
CN113570658A (en) Monocular video depth estimation method based on depth convolutional network
CN113129352A (en) Sparse light field reconstruction method and device
CN107967675B (en) Structured point cloud denoising method based on adaptive projection moving least square
CN110706332B (en) Scene reconstruction method based on noise point cloud
CN114255285B (en) Video and urban information model three-dimensional scene fusion method, system and storage medium
CN108734772A (en) High accuracy depth image acquisition methods based on Kinect fusion
US11651533B2 (en) Method and apparatus for generating a floor plan
CN115375836A (en) Point cloud fusion three-dimensional reconstruction method and system based on multivariate confidence filtering
CN107590858A (en) Medical sample methods of exhibiting and computer equipment, storage medium based on AR technologies
CN111693729B (en) Particle image velocity measurement method and device based on global optimization
CN113936116B (en) Complex space curved surface mapping method for transparent A column
JP5230372B2 (en) Image processing apparatus and image processing method
CN116486015A (en) Automatic three-dimensional size detection and CAD digital-analog reconstruction method for check cabinet
US20180330514A1 (en) Selective 3d registration

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 314500 988 Tong Tong Road, Wu Tong Street, Tongxiang, Jiaxing, Zhejiang

Applicant after: United New Energy Automobile Co.,Ltd.

Address before: 314500 988 Tong Tong Road, Wu Tong Street, Tongxiang, Jiaxing, Zhejiang

Applicant before: Hezhong New Energy Vehicle Co.,Ltd.

GR01 Patent grant
GR01 Patent grant