CN113139241A - Automatic modeling method of car body structure conceptual model based on image - Google Patents
Automatic modeling method of car body structure conceptual model based on image Download PDFInfo
- Publication number
- CN113139241A CN113139241A CN202110521518.XA CN202110521518A CN113139241A CN 113139241 A CN113139241 A CN 113139241A CN 202110521518 A CN202110521518 A CN 202110521518A CN 113139241 A CN113139241 A CN 113139241A
- Authority
- CN
- China
- Prior art keywords
- model
- vehicle body
- hard points
- hard
- design
- 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 21
- 238000013461 design Methods 0.000 claims abstract description 55
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 18
- 230000003993 interaction Effects 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
An automatic modeling method of a conceptual model of a vehicle body structure based on images belongs to the field of vehicle body-in-white structure design. The method comprises the steps of automatically detecting hard points of a vehicle body in an image by utilizing a trained convolutional neural network model according to a two-dimensional design sketch of a certain vehicle type, wherein the image comprises a side view and a top view of the vehicle type, and then quickly establishing a three-dimensional structure conceptual model of the vehicle type. The invention integrates the artificial intelligence technology into the field of design of the car body structure, can quickly and intelligently establish the car body conceptual structure model in a three-dimensional CAD format according to the two-dimensional design sketch of the car body drawing, greatly shortens the modeling time of the car body structure in the car body conceptual design stage, improves the design efficiency of the model, and accelerates the progress of the car body conceptual design stage.
Description
Technical Field
The invention belongs to the field of automobile body-in-white structure design, integrates an artificial intelligence technology into the field, and particularly relates to a method for automatically completing the establishment of an automobile body three-dimensional conceptual model according to an automobile body two-dimensional design sketch. The method can be used in the design stage process of the vehicle body structure, and the automatic modeling method replaces manual modeling, so that the requirement on the modeling level of a designer is reduced, and meanwhile, the period of vehicle body structure modeling in the concept design stage of the vehicle body can be greatly shortened.
Background
The design of the automobile body is divided into two stages, namely a conceptual design stage and a detailed design stage according to the design process. The main task of the concept design stage is to determine the overall structure performance of the vehicle body, the vehicle body design at the stage needs to repeatedly simulate and check the mechanical performance of the overall model, the design cycle length of the vehicle and the repeated design quantity at the later stage are determined to a great extent, the development cost of the vehicle is directly related, if defects are left at the stage, a great deal of difficulty is faced in the further design at the later stage, and the errors at the early stage are difficult to make up at the later stage. Therefore, the achievement and period of the concept design play a crucial role in the design quality and period of the whole vehicle structure.
At present, a conceptual model of a vehicle body structure is established, and a conceptual design geometric model of the vehicle body is established on a CAD system by using a manual or template technology according to a detailed model of the vehicle body. Nowadays, artificial intelligence techniques represented by deep learning are widely applied to the fields of image recognition, voice recognition, unmanned driving and the like. The convolutional neural network is superior to the deep learning technology and has the characteristic of automatically extracting features. Therefore, if a method for automatically detecting hard points of the vehicle body according to a two-dimensional design sketch of the vehicle body and then quickly and automatically establishing a conceptual geometric model of the vehicle body according to the detected hard points can be designed by utilizing a deep learning technology, the method is a perfect combination of an artificial intelligence technology and the design field of the vehicle body structure, and has great significance for shortening the conceptual design period of the vehicle body and even the design period of the whole vehicle.
Disclosure of Invention
According to the method, a deep learning technology is applied to the design of the vehicle body structure, according to a two-dimensional design sketch of a certain vehicle type, images comprise side views and top views of the vehicle type, hard points of the vehicle body in the images are automatically detected by using a trained convolutional neural network model, and then a three-dimensional structure conceptual model of the vehicle type is quickly established.
The technical scheme of the invention is as follows:
a. firstly, training a convolutional neural network model with a function of detecting hard points of a vehicle body in an image, wherein the method comprises the following steps:
1) two-dimensional design sketches of different vehicle types are collected, the two-dimensional design sketches comprise a front view and a top view of the vehicle types, and points with adjustable positions are defined and are called hard points of a vehicle body. The main view comprises the position information of the hard points in the X and Z directions, and the top view comprises the position information of the hard points in the X and Y directions.
2) Hard points of the vehicle body on each two-dimensional design sketch are manually marked, and a set of all marked two-dimensional design sketches is called a data set.
3) A convolutional neural network model is built to train a data set, iteration and parameter optimization of the convolutional neural network model are performed through an Adam algorithm, and the finally obtained convolutional neural network model has the function of automatically detecting the hard points of the vehicle body in the image and has good generalization capability.
b. Based on the relative position information of the hard points in the X and Z directions in the main view and the relative position information of the hard points in the Y and Z directions in the top view detected by the convolutional neural network model, a local coordinate system is established to obtain the coordinate values of the hard points in the X, Y and Z directions in the three-dimensional space.
Further, the hard point determination principle is as follows:
1) each hard point is a parameterized point, and the position of the hard point in the space can be changed by changing coordinate values;
2) the basic structure and the shape of the vehicle can be determined through hard points;
3) for a certain type of motorcycle, the number of hard points is determined, and each hard point represents certain structural and geometric meanings.
4) Only the hard spots on one side and the middle of the vehicle body need to be determined.
c. And connecting a series of shape-adjustable curves corresponding to the beams in the conceptual design of the vehicle body structure based on the detected hard points, wherein the curves are parameterized, the head and the tail of two hard points are required to be connected for a straight line structure, and three or more hard points are required for a curve structure with a certain curvature.
d. And generating three-dimensional curved surfaces according to a series of closed-loop curves, wherein the curved surfaces correspond to the vehicle body plate surface in the concept design of the vehicle body structure.
e. And (d) after the steps a-d are completed, obtaining the three-dimensional geometric structure conceptual model of the vehicle type in the CAD format in the image.
Furthermore, the method can be realized by utilizing an image-based intelligent modeling module of the car body concept structure, wherein the image-based intelligent modeling module of the car body concept structure builds a graphical user interface by PyQt, takes OpenCASCADE as a geometric modeling engine, takes an electronic table containing parameters of hard points, beams, chassis and plate surfaces required by modeling as a database, and defines various data interaction interfaces, and in each step of model building operation, the data interaction interfaces can read parameter information in the database into the model, and after a user manually adjusts the model on an operation interface, the data interaction interfaces can automatically store modified data in the database, so that real-time updating of the data and the model in the database is realized.
The intelligent modeling module of the vehicle body concept structure based on the image comprises a convolutional neural network model for detecting key points of the vehicle body, a two-dimensional design sketch input interface of the vehicle body is arranged, the convolutional neural network model automatically finishes key point detection after reading the image, and automatically establishes three-dimensional coordinates of hard points according to key point information, then rapidly establishes a parameterized three-dimensional concept model through four modules of the hard points, beams, a chassis and a panel in sequence, and finally outputs a STEP-format vehicle body concept model and an electronic form containing all design parameters of the model, so that the synchronization of the model and the design parameters is ensured. Fig. 9 is the general architecture of the module.
The invention has the beneficial effects that: the artificial intelligence technology is integrated into the field of design of the automobile body structure, the automobile body conceptual structure model in the three-dimensional CAD format can be quickly established according to the two-dimensional design sketch of the automobile body drawing, the modeling time of the automobile body structure in the automobile body conceptual design stage is greatly shortened, the design efficiency of the model is improved, and the progress of the automobile body conceptual design stage is accelerated.
Drawings
FIG. 1 is a technical roadmap of the present invention.
FIG. 2 is a two-dimensional design sketch of a vehicle body. The upper part is a front view, and the lower part is a top view.
FIG. 3 is a schematic diagram of detected key points in an image. The upper part is a front view, and the lower part is a top view.
FIG. 4 generates a schematic of the hard spots of the vehicle body.
FIG. 5 generates a schematic view of the body frame structure.
Fig. 6 incorporates a schematic view of the chassis.
FIG. 7 is a schematic view of an add-on panel.
FIG. 8 conceptual model opens the effects graph in UG software.
FIG. 9 is an overall architecture of an image-based intelligent modeling module for a conceptual structure of a vehicle body.
FIG. 10 is a step of intelligent modeling module modeling of conceptual structure of a vehicle body based on images.
Detailed Description
The intelligent modeling module of the car body concept structure based on the image applies the modeling method of the invention, and the specific implementation process of the method is described below by taking a certain car model as an example and combining with the attached drawings.
The selection of the working catalog is mainly to store the finally generated conceptual model of the vehicle body structure and all design parameters of the model.
Step 2, importing images of a certain vehicle type
A two-dimensional design sketch of a certain vehicle type is imported into a model, wherein the side view and the top view of the vehicle type are included.
Step 3, detecting hard spots of the car body in the image
Because the convolutional neural network model trained before is embedded in the model, the hard points of the vehicle body in the image can be automatically identified, the side view identifies the position information of the hard points in the X and Z directions, and the top view identifies the information of the hard points in the X and Y directions.
Step 4, defining a local coordinate system
A local coordinate system is established on a hard point of a vehicle body, the F1 point is used as a coordinate origin, coordinate information of each hard point in the X, Y and Z directions can be obtained, and since the vehicle model size in an image is the scaling of the actual vehicle model size, a scaling coefficient is multiplied on the obtained hard point coordinates, and the obtained relative position information of the final hard point is more consistent with the actual vehicle body.
Step 5, displaying all hard points
This step is to display all the hard points on the model interface, as shown in fig. 4, to realize the transformation of the hard points from the two-dimensional design sketch to the three-dimensional geometry.
Step 6, adjusting hard points of the car body
All the established hard points can be finely adjusted in a mode of a manual operation interface, so that the positions of the hard points are more matched with the appearance of the vehicle body.
Step 7. Beam construction
By connecting all the hard points according to the rules, a wire frame model of the vehicle body can be obtained, as shown in fig. 5. Each line represents the beam structure of the actual car body, the straight line needs two hard points, the curves are B-spline curves, and three hard points are needed for determination.
Step 8, establishing a chassis structure
The chassis structure is automatically added according to a body wire frame model, as shown in fig. 6.
Step 9. creation of plate curved surface
Depending on the characteristics of the primary load bearing member in most automotive body structures, a front cowl, roof, front floor, and rear floor are created, as shown in fig. 7.
The conceptual model of the body structure obtained in the above STEPs is stored in STEP format, and fig. 8 shows the opening effect of the model in UG software.
The above-described embodiment is only one example of the present invention, and the present invention is not limited to the above-described embodiment, and any obvious modifications to the embodiment without departing from the principle of the present invention will fall within the spirit of the present invention and the scope of the appended claims.
Claims (2)
1. An automatic modeling method of a conceptual model of a vehicle body structure based on images is characterized by comprising the following steps:
a. training a convolutional neural network model with a function of detecting hard points of a vehicle body in an image, wherein the method comprises the following steps:
1) collecting two-dimensional design sketches of different vehicle types, wherein the two-dimensional design sketches comprise a front view and a top view of the vehicle types, and defining points with adjustable positions, namely hard points of a vehicle body; the main view comprises position information of hard points in X and Z directions, and the top view comprises position information of the hard points in X and Y directions;
2) respectively manually marking hard points of the vehicle body on each two-dimensional design sketch, wherein a set of all marked two-dimensional design sketches is called a data set;
3) a convolutional neural network model is built to train a data set, iteration and parameter optimization of the convolutional neural network model are performed through an Adam algorithm, and the finally obtained convolutional neural network model has the function of automatically detecting hard points of the vehicle body in an image and has good generalization capability;
b. establishing a local coordinate system based on the relative position information of the hard points X and Z in the main view and the relative position information of the hard points Y and Z in the top view detected by the convolutional neural network model, and obtaining the coordinate values of X, Y and Z of each hard point in a three-dimensional space;
the hard spot determination principle is as follows:
1) each hard point is a parameterized point, and the position of the hard point in the space can be changed by changing coordinate values;
2) the basic structure and the shape of the vehicle can be determined through hard points;
3) for a certain same type of vehicle, the number of hard points is determined, and each hard point represents certain structural and geometric meanings;
4) only hard points on one side and the middle part of the vehicle body need to be determined;
c. connecting a series of shape-adjustable curves corresponding to the beams in the conceptual design of the vehicle body structure based on the detected hard points, wherein the curves are parameterized, the head and the tail of two hard points are required to be connected for a linear structure, and three or more hard points are required for a curve structure with a certain curvature;
d. generating a plurality of three-dimensional curved surfaces according to a series of closed-loop curves, wherein the curved surfaces correspond to the vehicle body plate surface in the concept design of the vehicle body structure;
e. and (d) after the steps a-d are completed, obtaining the three-dimensional geometric structure conceptual model of the vehicle type in the CAD format in the image.
2. An image-based automatic modeling method of an outline body model according to claim 1, characterized in that the automatic modeling method of the image-based car body concept model is realized by using an intelligent modeling module of a car body concept structure based on images, the intelligent modeling module for the image-based car body concept structure is used for building a graphical user interface by PyQt, OpenCASCADE is used as a geometric modeling engine, an electronic form containing parameters of hard points, beams, chassis and board surfaces required by modeling is used as a database, various data interaction interfaces are defined, in each step of model creation, the data interaction interface reads the parameter information in the database into the model, when a user manually adjusts the model on the operation interface, the data interaction interface automatically stores the modified data in the database, so that the real-time update of the data and the model in the database is realized;
the intelligent modeling module of the vehicle body concept structure based on the image comprises a convolutional neural network model for detecting key points of the vehicle body, a two-dimensional design sketch input interface of the vehicle body is arranged, the convolutional neural network model automatically finishes key point detection after reading the image, and automatically establishes three-dimensional coordinates of hard points according to key point information, then rapidly establishes a parameterized three-dimensional concept model through four modules of the hard points, beams, a chassis and a panel in sequence, and finally outputs a STEP-format vehicle body concept model and an electronic form containing all design parameters of the model, so that the synchronization of the model and the design parameters is ensured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110521518.XA CN113139241B (en) | 2021-05-13 | 2021-05-13 | Automatic modeling method for conceptual model of vehicle body structure based on image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110521518.XA CN113139241B (en) | 2021-05-13 | 2021-05-13 | Automatic modeling method for conceptual model of vehicle body structure based on image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113139241A true CN113139241A (en) | 2021-07-20 |
| CN113139241B CN113139241B (en) | 2024-04-16 |
Family
ID=76817886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110521518.XA Active CN113139241B (en) | 2021-05-13 | 2021-05-13 | Automatic modeling method for conceptual model of vehicle body structure based on image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139241B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102023003193A1 (en) | 2022-08-19 | 2024-02-22 | Mercedes-Benz Group AG | System and method for the design of structural elements of a vehicle using generative adversarial networks |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851754A (en) * | 2006-06-02 | 2006-10-25 | 胡平 | Geometric model design method for rapid establishing car body concept |
| CN109033144A (en) * | 2018-06-11 | 2018-12-18 | 厦门大学 | Method for searching three-dimension model based on sketch |
-
2021
- 2021-05-13 CN CN202110521518.XA patent/CN113139241B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851754A (en) * | 2006-06-02 | 2006-10-25 | 胡平 | Geometric model design method for rapid establishing car body concept |
| CN109033144A (en) * | 2018-06-11 | 2018-12-18 | 厦门大学 | Method for searching three-dimension model based on sketch |
Non-Patent Citations (5)
| Title |
|---|
| SHIJIN LI 等: "Research on Fine-Grain Model Recognition Based on Branch Feedback Convolution Neural Network", THE 14TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION, 31 August 2019 (2019-08-31), pages 47 - 51, XP033619579, DOI: 10.1109/ICCSE.2019.8845061 * |
| XIN LUO等: "Fast Automatic Vehicle Detection in UAV Images Using Convolutional Neural Networks", REMOTE SENS., 31 December 1994 (1994-12-31), pages 1 - 15 * |
| 侯文彬等: "基于概念设计的客车车身结构设计与优化系统", 湖南大学学报（自然科学版）, vol. 40, no. 10, 31 October 2013 (2013-10-31), pages 58 - 63 * |
| 刘宝越等: "车身结构概念设计系统多目标优化模块设计", 农业机械学报, vol. 42, no. 4, 30 April 2011 (2011-04-30), pages 17 - 21 * |
| 韩景飞: "面向概念设计的车身结构智能建模方法的研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, 15 January 2022 (2022-01-15), pages 035 - 605 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102023003193A1 (en) | 2022-08-19 | 2024-02-22 | Mercedes-Benz Group AG | System and method for the design of structural elements of a vehicle using generative adversarial networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113139241B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491610B (en) | Car panel die intelligent design system and design method | |
| CN109664300B (en) | Robot multi-style calligraphy copying method based on force sense learning | |
| JP3441690B2 (en) | How to Recognize Physical Objects Using Templates | |
| CN109636905A (en) | Environment semanteme based on depth convolutional neural networks builds drawing method | |
| CN108595763A (en) | Die assembly design method based on model index technology | |
| CN109571480A (en) | A kind of automobile washing machine people Trajectory Planning System and method | |
| CN106156383A (en) | A kind of parametrization aerodynamic configuration digital-to-analogue and structured grid automatic generation method | |
| CN113139241B (en) | Automatic modeling method for conceptual model of vehicle body structure based on image | |
| CN109344497A (en) | A kind of design implementation method of mold foundation ontology | |
| CN106599810A (en) | Head pose estimation method based on stacked auto-encoding | |
| CN113409439A (en) | Unmanned aerial vehicle three-dimensional map modeling method | |
| CN112926207A (en) | Method and system for automatically constructing editable model of equal-geometry topological optimization result | |
| CN109255141A (en) | A kind of body of a motor car forward direction conceptual design cross sectional shape optimization method | |
| CN111859536B (en) | Integrity modeling method for mail wheel awning structure | |
| CN106294968B (en) | Tyre tread 3d designing system and its method based on Engineering Semantics interactive mode | |
| CN115270288A (en) | Product form generation design method based on deep learning and parametric modeling | |
| CN111583412A (en) | Method for constructing calligraphy relief deep learning network and method for constructing calligraphy relief | |
| CN106778579A (en) | A kind of head pose estimation method based on accumulative attribute | |
| CN113076571B (en) | Real-time simulation editing method and system for three-dimensional clothes | |
| CN112991744B (en) | Automatic driving decision-making method and system suitable for long-distance urban road | |
| CN110176074B (en) | Quick modeling method for bas-relief model based on isogeometric matching method | |
| CN113792362B (en) | Step-by-step recommendation method for mechanical design scheme | |
| Wu et al. | Application of Product Form Recognition Combined with Deep Learning Algorithm | |
| Saha et al. | Exploiting 3D variational autoencoders for interactive vehicle design | |
| CN116597149B (en) | Point cloud semantic segmentation system and method based on industrial production |
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 |